Archives | VDGOOD

Volume: 1- Issue: 1

impact of air pollution in the atmosphere with air measurement technologies and prevention methods

¹Ms.Anu Priya , ²Dr. V.Khanaa

¹Research Scholar, Computer Science, Bharath Institute of Higher Education and Research, India.
²Dean Info, Information Technology, Bharath Institute of Higher Education and Research, India.

Abstarct [+]

Air pollution can be described as an alternation of air quality that can be described by measurement of biological, chemical or physical pollutants in the air. So air pollution means the undesirable presence of impurities in the atmosphere. It can be categorized in two ways, visible and invisible air pollution. This paper focus review on what is the basic strategy for the causes of air pollution, and the factors can affect the purity of air with different levels. Environmental big data gained popularity that helps to identify environment trends and patterns. Air pollution is becoming an major issue that affecting human health. Dispersion of various air pollutants such as So2, No2, PM, SPM, RSPM, CO, Hydrocarbons. This paper audit the pollution detection, prevention and control, which thus reduces human and material resources. Therefore, it possesses greatly practical significance to the construction of smart city with IOT in future. The system can transfers data through the Internet, which also utilizes sensors, pH sensors to obtain environmental data and it transfers data through the Internet, which also utilizes, pH sensor and smoke sensor to obtain environmental data. To identify the levels of air quality and methods to prevent for Streaming data. Air Pollution, The Key to World-Wide Destruction.

| Download

intelligent mirror using raspberry pi and iot

¹Mr.Syed Mohamed Hadi Reza , ²R. Rohith Kumar , ³B. Tamil Selvan , ⁴P. Preethy Rebecca

¹Student , Computer Science and Engineering, St. Peter’s College of Engineering and Technology, , India.
²Student , Computer Science and Engineering, St. Peter’s College of Engineering and Technology, India.
³Student , Computer Science and Engineering, St. Peter’s College of Engineering and Technology, India.
⁴Student , Computer Science and Engineering, St. Peter’s College of Engineering and Technology, India.

Abstarct [+]

The Smart Mirror is based on general purpose household mirror. It belongs to home automation system to meet consumers needs towards modern and optimized life. It provides occupants with a series of intelligent experiences such as home appliance control, information acquisition, environmental monitoring, entertainment and remote operation. The intelligent home control platform. The Smart Mirror is designed to solve the problem of smart home communication and information integration in the family. Based on the development of Raspberry Pie, unidirectional mirror and the infrared frame and other hardware devices, the smart mirror, as a mirror display screen, offers a kind of safer, more comfortable, more conveniently, swift and open intelligent, information-based living space to household in the intellectual district. © 2020 VDGOOD Professional Association. All rights reserved

| Download

monitor mental health via ai powered chatbots

¹Dr.Balasubadra K , ²Ms. Nivedha VB , ³Ms. P.Pavani , ⁴Ms. A.Tejaswini

¹Head of Department , Information Technology , RMD Engineering College, India.
²Student, Information Technology , RMD Engineering College, India.
³Student, Information Technology , RMD Engineering College, India.
⁴Student, Information Technology , RMD Engineering College, India.

Abstarct [+]

The application provides a system/portal for assessing the mental wellbeing of an individual. The user could be able to easily use the application to check whether they are depressed or anxious. They need to provide all their basic details. All this data including their mental health report can go into a central database. It provides various features like Chatbot, calming exercises, music, etc to help the user to improve their mental health. The user can also get access to the nearby hospitals. The application also provides a feature to share the report of individual to their family and close friends. The main objective is to develop an application with AI powered chat bots, Psychological Questionnaires and Report Analysis. Thus it provides a self assessment which would also be a continuous evaluation of their mental health.

| Download

iot based smart parking using fastag

¹Ms.Harini S , ²Mr. Sabarish K , ³Mr. Nishanth K S , ⁴Mr. Nithish Kumar S

¹Assistant Professor, Electrical and Electronics Engineering, Adithya Institute of Technology, India.
²Researcher, Electrical and Electronics Engineering, Adithya Institute of Technology, India.
³Researcher, Electrical and Electronics Engineering, Adithya Institute of Technology, India.
⁴Researcher, Electrical and Electronics Engineering, Adithya Institute of Technology, India.

Abstarct [+]

In fast growing world the trends and technologies had been improved a lot. In that population also plays a important role, in this India is the second growing population in the world ranking status. In India one family requires two vehicles that had become a paramount of their life, here traffic congestion became major issue and so parking space are low and that has less requirement for the emptors. For this we consent an IoT, that every work today had been done through internet, so that only solution is the smart parking based IoT. Smart parking is a good idea of how the Internet-of-Things (IoT) will be pervasively deployed in our daily living environments to different users, hence the proposed idea is to make the parking easier by detecting and monitoring, security, locate and reserve parking lot using IoT then display the result. An Arduino Mega is based on the automatic control of parking system by using codes. The main aim is to reduce the traffic congestion and to make the parking easier with low and efficient technology. In order to focus on the parking by reducing traffic congestion with less time requirement. The proposal of the smart parking system is that gain information of parking area and book the parking lot and tag by using webpage. In that particular parking area, the sensor detects the vehicles the information given to the main gate of the parking lot and then display in the LCD and tag is read by RFID Tag reader. So that particular car is checked and parked in the particular lot. The Node MCU is used for the purpose to build an IoT product and allows the simple and powerful program in WIFI module with the Arduino IDE software. The main advantage is that reduces time for parking the vehicle, cost efficient and security control.

| Download

smart irrigation and animal monitoring system

¹Assoc_prof.Ananthi .S.N , ²K.Lavanya , ³N.Varsha

¹Associate Professor, Department of Computer Science and Engineering, S.A. Engineering College, India.
²Researcher, Department of Computer Science and Engineering, S.A engineering college, India.
³Researcher, Department of Computer Science and Engineering, S.A engineering college, India.

Abstarct [+]

Water is main resource for Agriculture. Irrigation is the main method to facilitate water but, in certain cases, there will be lot of water wastage. So, in this regard to save water and time we have proposed project titled smart irrigation and animal monitoring system using IoT. In this proposed system we are using various sensors which senses the various parameters of the soil and based on soil moisture value land gets automatically irrigated by ON/OFF the motor. This system is used to monitor the animal activities by restricting their entry to the agricultural land. To adapt to the changing needs and demands, we must modify the way we farm and safe guard the farm from the entry of animals. Keywords: Smart irrigation, sensor, relay driver, thingSpeak

| Download

automated vehicle entry and exit monitoring system using deep learning

¹Ms.Usha N.S , ²Mr. Mogeshwaran R , ³Mr. Udhayakumar S , ⁴Mr. Vigneshwaran B

¹Assistant Professor, Computer Science and Engineering, S.A Engineering College, India.
²Researcher, Computer Science and Engineering, S.A Engineering College, India.
³Researcher, Computer Science and Engineering, S.A Engineering College, India.
⁴Researcher, Computer Science and Engineering, S.A Engineering College, India.

Abstarct [+]

Automated vehicle number plate recognition is a tedious task with the existing monitoring systems. We can overcome this problem with the tools, methodologies and technologies provided by the deep learning techniques. Number Plates is the clearest indicator of a vehicle’s identity, still there is difficulties in precisely segmenting the number plates from the surveillance images with accuracy. In this paper a convolutional neural network (CNN) has been trained for the automated vehicle monitoring system (AVMS) that isolates the number plate from the vehicle for the purpose of segmentation. The YOLOv3 deep learning mechanism is used for isolating and segmenting the number plates from the images provided by the surveillance images. The convolutional neural network is trained accordingly with the datasets containing the images of Indian vehicles. YOLOv3 mechanism can only locate or annotate the number plate accuarately, it cannot recognize the specific characters in the number plates. Tesseract object character recognition(OCR) model is trained to detect the characters after preprocessing the images. The characters detected is stored in a separate field on an excel sheet which is done by tesseract. This entire processing is performed on a darknet framework. While experimenting the proposed system on several public sectors it is found to be better than the existing systems.

| Download

iot based vehicle traffic monitoring and license detection system

¹Mrs.Sudha .L , ²Swetha Sree MS , ³Santhiya V , ⁴Monica K

¹Researcher, Department of Computer Science and Engineering, S.A. Engineering College, India.
²Researcher, Department of Computer Science and Engineering, S.A engineering college, India.
³Researcher, Department of Computer Science and Engineering, S.A engineering college, India.
⁴Researcher, Department of Computer Science and Engineering, S.A engineering college, India.

Abstarct [+]

In today’s world, Traffic Jam during busy hours is one of the major concern. Traffic sign monitoring is one amongst a big deal since it has to be done on a regular basis. The next phase of it is with respect to the License monitoring system where the project focuses the monitoring and detection with the help of a person’s fingerprint using the sensor mechanism. Without being licensed and driving the vehicle is a major issue in many countries. Survey says that accidents have happened mostly by unlicensed drivers. So, a new system that has been proposed is Fingerprint Based License Detection System, that device will scan your fingerprint and check them with help of the database. The third module of the project deals with the accident detection system. As per the World Health Organisation (WHO), more than millions of individuals are meeting in accidents on account of vehicle mishaps. This issue is yet expanding because of rider’s poor activities, for example riding without rest and involved in drunk driving and so forth. This paper involves the automatic vehicle accident detection system involving the usage of Black Box and needed sensor mechanism. Keywords- RaspberryPI, FingerPrint Sensor, GSM, MEMS sensor.

| Download

internet of things principles, security and applications

¹Mr.Balasubramanian .M , ²Suryaprakash G , ³Karthikeyan K , ⁴Vignesh G

Abstarct [+]

The Internet of Things (IoT) is a succeeding big thing in the wireless revolution. It is a natural progression of the internet and, as the name suggests, goes beyond the connection of people to the internet by connecting things such as machines, sensors, and computers. A smart world is projected as an era in which things can automatically and intelligently collaboratively assist people. IoT permits objects to be detected and controlled remotely through an existing network, building opportunities for more incorporation of the physical world into computer-based systems, and result in better accuracy. IoT platform denotes those systems (software, hardware, and middleware) that enable IoT network devices, applications, and service management. This includes connectivity, device administration, identity management, authorizations control, data management. Keywords Internet of Things, wireless communication, Automation, Intelligence, Connecting people.

| Download

iot influenced automatic elephant repelling system for enhancing safety of public and plantations

¹Mr.Ritchie Pulikottil , ²Shihaan.W.S , ³Shafeeq Sadiq , ⁴M.Diviya

¹Student, Computer Science and Engineering, Rajalakshmi Engineering College, India.
²Student, Computer Science and Engineering, Rajalakshmi Engineering College, India.
³Student, Computer Science and Engineering, Rajalakshmi Engineering College, India.
⁴Assistant Professor, Computer Science and Engineering, Rajalakshmi Engineering College, India.

Abstarct [+]

Majority of the forest areas are getting destroyed, due to human population explosion and deforestation thereby causing Human-Animal Conflict. This has also resulted in tremendous agricultural losses. The proposed will be focusing mainly upon elephants rather than other animals in the wilderness. Currently Elephant identification are being done using CCTV, LVDT, etc. But these methods are very expensive and less accurate. The work in hand is an automated system for the identification of wild elephants and repel them back into their forest. The sensors are placed in two layers so as to track the presence of animals with greater accuracy. The first primary layer senses the movement of the animal in the vicinity. This is aided by InfraRed sensors/PIR sensors/ Sharp IR sensors. The next layer senses and confirms the vibrations of the elephant with the help of piezoelectric vibration sensor/seismic sensors and also helps in repelling the wild elephants back into the forest. As soon as the second layer confirms the intrusion of wild elephants, it sends alert signals to the base station using a GSM Module thereby alerting the concerned authorities to take necessary actions.

| Download

auditory access device for visually impaired using raspberry pi

¹Mr.Harish kumar R , ²Prem kumar. M , ³Dinesh. A

¹Student, Computer Science Engineering, Anna university, India.
²Student, Computer Science Engineering, Anna university, India.
³Student, Computer Science Engineering, Anna University, India.

Abstarct [+]

The blind and visually impaired people needs assistance in their day-to-day life, for navigation, detecting objects, text recognition etc., Computer vision based assistive device for the blind is promising and efficient technology but still, the area is still a developing one. Various assistive device exist today to assist the blind most of which are still in prototypical stages. Purpose of this paper is to apprise the research and scientific community about the progress of computer vision based assistive technology for blind.

| Download

business intelligence – an overview

¹Dr.Leelavathy S , ²Dr. R. Shobana , ³Dr. K. Shantha Shalini

¹Assistant Prof G-II, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology, India.
²Assistant Prof G-II, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology , Denmark.
³Assistant Professor, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology , India.

Abstarct [+]

BI decision-support environment is to provide cross-organizational business analysis capabilities to all business people and all departments in the organization. Business Intelligence involves a variety of new tasks, shifted roles and responsibilities, and a more hands-on business intelligence project planning and management approach. The implementation of Business intelligence in designing the data warehouse manages day to day activities of executives, managers, customers, suppliers, workers in a efficient way which includes OLAP that is not available in the current data warehouse. It is used for information consumers and information producers to extend and manage their organization in a efficient way .Proposed prototype can be applied in the business model for identification, comparison and evaluation of data’s.

| Download

artificial intelligence system for prediction and recommendation of diabetes

¹Mr.Deiva Nayagam R , ²Ms. Anusha R , ³Ms. Sangeetha M , ⁴Ms. Suryaselvi K

¹Assistant Professor, Electronics and Communication Engineering, Ramco Institute of Technology, India.
²Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
³Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
⁴Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.

Abstarct [+]

Diabetes is a metabolic disease affecting a people worldwide. Its incidence rates are increasing every year. Diabetes-related complications in many vital organs of the body may turn fatal. Early prediction of diabetes is very important for treatment which can stop the disease to such complications. Convolutional neural network (CNN) and its used for extracting complex temporal dynamic features of the input. We have obtained the performance improvement in CNN. We propose a strategy for the diagnosis of diabetes using convolutional neural network. The Pima Indian Diabetes (PID) data set is received from the UCI machine learning repository database. The results on PID dataset demonstrate that deep learning approach design an system for the prediction of diabetes. The result shows the decision tree algorithm and the highest precision of 82.0% and recall of 90.0%, respectively holds best for the analysis of diabetic data.

| Download

a survey on localization and tracking for women safety in iot

¹Ms.Vinodha D , ²Mr. P. Parthasarathi , ³Ms. R. Nikku Meena , ⁴Mr. J. Vignesh

¹Researcher, Computer Science & Engineering, S.A Engineering College, India.
²Researcher, Computer Science and Engineering, S.A Engineering College, India.
³Researcher, Computer Science and Engineering, S.A Engineering College, India.
⁴Researcher, Computer Science and Engineering, S.A Engineering College, India.

Abstarct [+]

Nowadays, there are more news about women harassement, rape, than their achievements. Gender based violence become a major problem against women. This problem is in national countries as well as international countries. Eventhough there are more laws against domestic violence, sexual assault and other form of violence in every countries , there are more cases about women violence. We can provide safety for women by implementing devices by Internet of things (IoT). In IoT there are more sensors like temperature sensor, pulse rate sensor for detecting pulse rate, temperature, tracking the current location of the victim and also can send the alert message to the static mobile numbers. This paper reviews about how security is provided via IoT devices to women. This paper presents a survey on the existing systems about how the device provide security, what components are used in the devices and the competitive analysis.And this paper also discusses about the pros and cons of existing systems

| Download

a bridge dual-character time-perceptive traditionalized synergic ranking design for poi proposal

¹Mrs.Priya K.M , ²V.Gnanasekar , ³C.Suresh

¹Student, Computer Science and Engineering, Gojan School of Business and Technology, India.
²Head of the department, Computer Science and Engineering, Gojan School of Business and Technology, India.
³Assistant professor, Computer Science and Engineering, Gojan School of Business and Technology, India.

Abstarct [+]

Tourism has become an important domain for most of the economies, especially for non-industrialized countries where it represent the main source of income. Recommendation systems are the techniques which predict the rating of users interest with item based or society based entity. These items can be places, books, movies, restaurants and things on which individuals have different preferences. These preferences are analyzed and processed using two approaches first content-based filtering which involves distinctiveness of an item and second collaborative filtering approaches which takes into account user's precedent activities to make choice. Point of interest recommendation engine provides a feasible method for personalized recommendation of various places to its users.POI systems are generally more tedious in its operation comparatively to the already existing merchandise recommendation engines. The reason being the amount of time it takes for the services involved. When we consider the online services, designing a prominent approach for efficient and effective recommendation is very important. Generally, in the already existing services for searching and recommending the services are done by the keyword-based search which leads to the poor recommendation performance and leads to vast dependence on complex queries from the user. This proposal has advantage of functionality and competence, and thus possible for the realistic and good result with effective cost benefits.

| Download

an actualized suggestion system for forcasting of disease using big data logic

¹Mrs.Sandhya S , ²V.Gnanasekar , ³R.Kannan

Abstarct [+]

In restorative administrations system, using a Database is a striking methodology for securing information. In standard database structures, on occasion considering nearness of massive data it isn't possible to fulfill the customer's criteria and to outfit them with the right data required to choose a decision by them. In any case, the examination precision is decreased when the idea of remedial data is insufficient. Additionally, remarkable territories show intriguing characteristics of certain regional disorders, which may exploit the figure of disease scenes. With tremendous data improvement in biomedical and restorative administrations systems, precise examination of helpful data benefits early sickness area, getting thought, and system organizations. In huge data accumulate human administrations records from various source and using AI figuring’s for practical conjecture of ailments in illness visit systems.

| Download

a mobile based fleet management system

¹Dr.V.Geetha , ²Dr.C.K.Gomathy , ³Mr. M Pavan Manikanta Kiran , ⁴Mr. Rajesh Gandikota

¹Assistant professor, Computer Science and Engineering, SCSVMV, India.
²Assistant professor, Computer Science and Engineering, SCSVMV, India.
³UG Student, Computer Science and Engineering, SCSVMV, India.
⁴UG Student, Computer Science and Engineering, SCSVMV, India.

Abstarct [+]

Fleet management is a very important topic in analysis and development today. Companies, security, and emergency forces ought to keep track of their trucks and cars and recognize wherever a vehicle is at a flash in time, and when, wherever and for a way long a vehicle stopped. Our system includes two mobile applications one for organization head i.e., Smart Fleet and other for the driver of the vehicle (smart driver). This system enables the organization to keep track of their vehicles all the time. This is done by the geolocation of the mobile phone in which smart driver application is installed is shared to the mobile phone in which smart fleet application is installed. Organization head who is having our application installed is able to monitor the vehicles, updating the data.

| Download

to control toxic wasteby using wireless sensors, arduino and connecting chip

¹Mr.Himajasree R , ²Mr. P.Raja , ³Dr.N.Venkatachalapathi , ⁴Dr. M.Rudrakumar

¹Researcher, Computer Science and Engineering, Annamacharya institute of technology and sciences, India.
²Researcher, Computer Science and Engineering, Annamacharya institute of technology and sciences, India.
³Researcher, Computer Science and Engineering, Annamacharya institute of technology and sciences, India.
⁴Researcher, Computer Science and Engineering, Annamacharya institute of technology and sciences, India.

Abstarct [+]

The basic objective of this paper is to control thevehicle and the environment pollution and Industrial pollution effluents like carbon dioxide, sulphur dioxide, carbon monoxide, smoke detector that may cause damage to the ozonelayer, environment.We are also focusing to avoid harmful gases and disasters due to fire using proper sensors. Hence it will be useful for controlling environmental pollution in air in AP Transport control board to monitor the radiation streaming from vehicles.

| Download

cloud computing security – an overview

¹Dr.Shobana R , ²Dr. K. Shantha Shalini , ³Dr. S.Leelavathy

¹Assistant Prof G-II, Computer Science and Engineering, Aa Aarupadai Veedu Institute Of Technology, India.
²Assistant Professor, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology , India.
³Assistant Professor, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology , India.

Abstarct [+]

Cloud computing is one of today's most exciting technologies due to its ability to reduce costs associated with computing while increasing flexibility and scalability for computer processes. During the past few years, cloud computing has grown from being a promising business idea to one of the fastest growing parts of the IT industry. IT organizations have expresses concern about critical issues (such as security) that exist with the widespread implementation of cloud computing. These types of concerns originate from the fact that data is stored remotely from the customer's location; in fact, it can be stored at any location. Security, in particular, is one of the most argued-about issues in the cloud computing field; several enterprises look at cloud computing warily due to projected security risks. The risks of compromised security and privacy may be lower overall, however, with cloud computing than they would be if the data were to be stored on individual machines instead of in a socalled "cloud" (the network of computers used for remote storage and maintenance). Comparison of the benefits and risks of cloud computing with those of the status quo are necessary for a full evaluation of the viability of cloud computing. Consequently, some issues arise that clients need to consider as they contemplate moving to cloud computing for their businesses. In this paper I summarize reliability, availability, and security issues for cloud computing (RAS issues), and propose feasible and available solutions for some of them.

| Download

blockchain based user identity management: architecture, algorithms and applications

¹Mr.Pon Logesh P , ²Mr. Venkatraman S , ³Mr. Ajay S , ⁴Dr R Geetha

¹Researcher, Computer Science and Engineering, S.A Engineering College, India.
²Researcher, Computer Science and Engineering, S.A Engineering College, India.
³Researcher, Computer Science and Engineering, S.A Engineering College, India.
⁴Researcher, Computer Science and Engineering, S.A Engineering College, India.

Abstarct [+]

Blockchain is one of the prominent technologies of the decade. It is a distributed, decentralized ledger based technology which allows us to perform transactions in a high secure manner. User identity data and related transactions associated with a blockchain network are stored in a data structure called blocks. These blocks are validated by the miner nodes of the network by using powerful consensus algorithms and added to the chain. Blockchain based solutions can be implemented in different identity based sectors such as Identity, Financial and asset Management etc. Blockchain based identity can also be integrated with other domains such as Artificial Intelligence and Cloud computing to ensure a high level security. This paper concentrates more on detailed architecture of blockchain based user identity management features, consensus algorithms, applications and some security threats associated with blockchain related to user identity.

| Download

conductor backed cpw fed bowtie slot antenna for breast cancer detection

¹Ms.Poonkodi S , ²Ms. Pramila R , ³Ms. Praveena S , ⁴Mrs.R.Ramalakshmi

¹Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
²Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
³Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
⁴Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.

Abstarct [+]

Microwave imaging is an efficient technique that can be used for the early detection of breast cancer. Breast imaging uses low power and longer wavelength signals to obtain information about breast. A flexible antenna with a simple structure and small size (30mm*20mm*1.6mm) designed for detecting breast cancer. The main objective of the proposed model is to design a flexible antenna to improve gain, efficiency, and directivity and reduces losses, backward radiation. The antenna consists of bowtie slot radiation elements fed by a coplanar waveguide structure and a floating ground and it operates at a frequency of ultra-band frequency. The antenna incorporates EBG-FSS in patch, which reduces the backward radiation, with reduced Specific Absorption Rate SAR. The antenna resonates at 8.40 GHz and has a peak gain of 6.91 dBi. The antenna is simulated by using CST Microwave Studio software. The analysis of the antenna is done by measuring the antenna parameters such as gain, bandwidth, efficiency, near and far-field radiation pattern.

| Download

after-deployment testing of applications: based on android

¹Mr.Satish J , ²Mr. Prince Babu. R , ³Mr. Rupesh Kumar V.N , ⁴Mr. Muthugurunathan. G

¹Researcher, Computer Science and Engineering, S.A Engineering College, India.
²Researcher, Computer Science and Engineering, S.A Engineering College, India.
³Researcher, Computer Science and Engineering, S.A Engineering College, India.
⁴Assistant Professor, Computer Science and Engineering, S.A Engineering College, India.

Abstarct [+]

Applications, during its life cycle, undergo several stages of development before getting deployed in the target device to fulfill the request. The final stages of the development cycle are the Testing process. The developed applications undergo various testing strategies to fix major error types, that are present in the application to check if the application runs fine, the requirements are met, and the result is optimal using minimal resources. But applications are certainly not free from errors entirely. Error confinement technologies have made sure to reduce the errors occurring in the application. Major advantage of using these confinement technologies is its automation. Integrated Development Environment (IDE) have inbuilt testing steps to ease the process of testing. But the errors that occur after installation are more severe and affects the market of that application. The idea aims at automating testing strategies in an after-deployed stage. Collection of test report is done from the application after installation process. The runtime is tested along with any abnormalities, so that it can be fixed in the next update. The test reports are collected in the cloud storage device and is then intimidated to the developer to fix that error.

| Download

design of multiband rectangular micro-strip patch antenna for 5g applications

¹Ms.Saraswathi M , ²Ms. Vigneshpriya K , ³Mr. Vivithaguru S , ⁴Mr.D.Gopinath

¹Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
²Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
³Student, Electronics and Communication Engineering, Ramco Institute of Technology, India.
⁴Assistant Professor, Electronics and Communication Engineering, Ramco Institute of Technology, India.

Abstarct [+]

In wireless communication antenna plays a major role. In order to obtain an efficient system an antenna is used at multiple frequencies called multiband antenna. There are various methods used to create multiband in Antenna like creating slots, Defective Ground Structure. In this Paper the effective method for getting multiband in antenna for 5G application is analyzed. The 5G frequency spectrum covers from 410MHz to 52.6GHz. This multiband antenna covers a mid-band frequency ranges from 6GHz to 17GHz which is a 5G frequency spectrum. Here, Ansys HFSS v13.0 software tool is used to simulate a antenna which operates at multiband.

| Download

design of planar inverted f antenna for wireless capsule endoscopy

¹Ms.UmaMaheswari G , ²Ms. K.UmaParameshwari , ³Ms. M.Vaishali

¹Researcher, Electronics and Communication Engineering, Ramco Institute of Technology, India.
²Researcher, Electronics and Communication Engineering, Ramco Institute of Technology, India.
³Researcher, Electronics and Communication Engineering, Ramco Institute of Technology, India.

Abstarct [+]

Wireless Capsule Endoscopy (WCE) is a procedure that uses a tiny wireless camera and antenna to detect the gastrointestinal tract(GI). The prominent concept of our paper is to design an Planar Inverted F Antenna for WCE which operates at an ISM band frequency of 2.4GHZ. A design of proposed PIFA antenna has been fabricated on polytetra fluro ethylene. The capsule has the overall size of 11×22mm. The performance metrics such as high return loss, radiation performance of the antenna, maximum gain with good directivity has been considered and fabrication

| Download

vehicle and license authentication using rfid and fingerprint

¹Mr.Muthupandi M , ²Mr. M. Sakthivel , ³Mr. M. Saravanan , ⁴Mrs. P. Hemalatha

¹Researcher, Computer Science and Engineering, Adhiyamaan College of Engineering, India.
²Researcher, Computer Science and Engineering, Adhiyamaan College of Engineering, India.
³Researcher, Computer Science and Engineering, Adhiyamaan College of Engineering, India.
⁴Researcher, Computer Science and Engineering, Adhiyamaan College of Engineering, India.

Abstarct [+]

A vehicle identification and drivers authentication system as a part of smart city development. The RFID tag is placed in a vehicle. The RFID tag reader is used to get the data from the RFID tags. For programming the RFID tags , the RFID tag writer is used. By reading the serial number in the RFID tag. Vehicle identification can be easily done. Driving license system is a huge task for the government to monitor. We can see many criminal activities from the traffic police while they are checking the documents. The crime will be done by both the side(people and police). To overcome that problem by implementing one more portable fingerprint sensor module that is given to the traffic police, Which is integrated with IOT where the person license information is stored. If the person places his finger on the sensor then the device will tell you whether they had a license or not. This can be done by interlinking the vehicle details with the IOT.

| Download

handwritten tamil character recognition using deep learning

¹Mr.Mathankumar M , ²Mr. M. Nithinmon , ³Mr. M. Sankara sabapathy , ⁴Mr. P. Balamurugan

Abstarct [+]

Character recognition is developed for various patterns of handwritten or optical characters to be recognized digitally. There are many Tamil literatures in undigitized form. Using deep learning the undigitized Tamil literatures can be converted into readable format. Many researches were carried on character recognition using deep learning for languages like Arabic, Devanagari, Telugu, etc… Due to the larger category set and confusion in similarities between handwritten characters Tamil character recognition is a challenge. In this paper, we propose a character recognition system for handwritten Tamil characters using deep learning. Here, CNN approach is carried out. The proposed work gives efficiency of 98% on our datasets.

| Download

touchless heartbeat detection using artificial intelligence

¹Assoc_prof.Balasubramanian .C , ²Harini.M , ³Pavithra.K , ⁴Priya.D

Abstarct [+]

A system for touchless heartbeat detection using neural network analyser. Here, a system is used to detect the heart rate from a distance of 1m apart. The system shows the ability to disclose the heartbeat signals with the possibility of tuning frequency and power. Measurements are performed at different power levels. Based on measurements performed for both respiration and heartbeat, it describes the heartbeat activity. The heart beat and the variability are taking out from the modelling signal using wavelet and classic filters. Keywords- Neural network analyser, Heart beat signals, Cardiopulmonary activity, Wavelet, Classic filters.

| Download

conversational companion for mental health support using tensorflow

¹Ms.Keerthana Nithyakumar , ²Preetha Sridharan , ³Reshma Ramesh , ⁴S.Aarthi

¹Student, Computer Science Engineering, Meenakshi Sundararajan Engineering College, India.
²Student, Computer Science and Engineering, Meenakshi Sundararajan Engineering College, India.
³Student, Computer Science and Engineering, Meenakshi Sundararajan Engineering College, India.
⁴Senior Assistant Professor, Computer Science and Engineering, Meenakshi Sundararajan Engineering College, India.

Abstarct [+]

Depression and stress management have become inevitable buzz words in our hassle bound lives. According to World Health Organization, around 300 million people have been suffering from depression alone. Though counselling and psychiatric support groups are available, not everyone can afford to reap their benefits. As technology is reaching new heights every day, armed with Artificial Intelligence and Machine Learning, everything seems solvable and providing emotional assistance is no exception. Chatbots are becoming popular and gaining traction in almost every field due to its efficient and intelligent user interaction. This conversational service is powered with Natural Language Understanding (NLU) and the VOICE recognition works on the principle of Multi Nominal Naive Bayes Algorithm that captures the user’s voice using mike and converts into text. The chatbots response is refined by using training sets so as to make the user feel as if he is talking to a real person and not to a machine. This automation is accentuated with features such as sad or depressed or just feeling low. The subtle aim of the chatbot is to provide an adaptive and friendly platform for people seeking personal emotional assistance with less complexity and customizable features that continuously sharpens its emotional characters.

| Download

dynamic authentication key agreement scheme for effective path selection in iiot systems

¹Mr.Venkatesh M K , ²Mohamed Hussain A , ³Sukumar S , ⁴Dr R Geetha

Abstarct [+]

IoT is one of the one of the prominent technologies of the decade. Due to a rapid growth of Internet, the real time data that is distributed among different smart sensing devices can be accessed by the remote user in Industrial Internet of Things (IIoT) environment. There arise some major issues of privacy and security in the IIoT environment. To overcome this problem, we need a novel technology that safeguards all the illegal access of data in the IIoT environment. Therefore, a user authentication mechanism is one of the optimistic security solutions in the IIoT environment. So, we propose a new approach that is a Dynamic authentication key agreement scheme is used in which only legal users can access the data from the IoT sensing devices in the IIoT environment. In the proposed scheme, Dynamic Authentication key Agreement scheme (DAKAS) and Effective Path Selection and Security Control Logic scheme (EPSSCLS) are used for key verification and secure data communication. The proposed scheme supports addition of new nodes after the network pre-deployment phase, dynamic node IoT sensing device phase and path of transmission is revoked in case of any intrusion detection or data lost/stolen by an adversary. The formal security verification is done using Real or random (ROR) model and AVISPA (Automated Validation of Internet Security Protocols and Applications) tool and also informal security is carried out in the proposed scheme. A practical demonstration is carried out on the proposed scheme using the NS2 simulation. Keywords: Security, Privacy, DAKAS, Industrial Internet of things, EPSSCLS.

| Download

visible light communication for video transmissions

¹Mr.Sakthi Saravanan S , ²Santhosh kumar J , ³Santhosh kumar M , ⁴B.Saraswathy

¹Researcher, Electronics and Communication Engineering, Meenakshi Sundararajan Engineering College, India.
²Researcher, Electronics and Communication Engineering, Meenakshi Sundararajan Engineering College, India.
³Researcher, Electronics and Communication Engineering, Meenakshi Sundararajan Engineering College, India.
⁴Assistant Professor, Electronics and Communication Engineering , Meenakshi Sundararajan Engineering College, India.

Abstarct [+]

With the large technological advancements being made per annum, the requirement for better and faster data rates increases and improved security measures is being given high importance within the research community. The rationale for its high popularity is thanks to its ability to supply high data rates, high bandwidth and a really secure medium of transmission because it cannot penetrate walls. This paper investigates the impact of Visible Light Communication on video transmissions. A true experimental test-bed is setup to check the performance of video transmission over VLC under various conditions like distance from the source, interfering lighting etc.

| Download

food calories – based on food recognition system

¹Mr.Saravanan T.R , ²Balamurugan E , ³Gowtham S

¹Assistant Professor, Computer Science and Engineering, Jeppiaar SRR Engineering College, India.
²Student, Computer Science and Engineering, Jeppiaar SRR Engineering College, India.
³Student, Computer Science and Engineering, Jeppiaar SRR Engineering College, India.

Abstarct [+]

Measure the calories of food, which differ with each cooking time depending on its ingredients and length, it is important to measure the calories of the food before consumption. Based on knowledge of nutrition, naturally different calories have ingredients which are components of food. It proposes a method of estimating food calories based on ingredients, using knowledge and information about nutrition. First, an image of the food is recognized as a type of food, and ingredients of the recognized food are retrieved from the database with their knowledge of nutrition and brightness pattern and thermal images. At the same time, the picture is divided into ingredient boundaries All the boundaries are then grouped into neural networks ingredient.

| Download

challenges and issues of diabetes retinopathy without machine learning

¹Dr.Veena , ²R. Krupali , ³D .Mahalakshmi , ⁴B. Preetha

¹Researcher, Department of Computer Science and Engineering, S.A engineering college, India.
²Researcher, Department of Computer Science and Engineering, S.A engineering college, India.
³Researcher, Department of Computer Science and Engineering, S.A engineering college, India.
⁴Researcher, Department of Computer Science and Engineering, S.A engineering college, India.

Abstarct [+]

Nowadays, a major problem faced by many people is diabetics. Diabetics is the chronic metabolic disorder it is the state caused by an abnormal increase in the glucose level in the blood and which causes the damage to the blood vessels. The tiny blood vessels that nourish the retina are damaged by the increase glucose level in the blood. The retina is the only part of the human body where the blood circulation can be observed directly. Retinal image analysis is one of the active research areas with the goal of providing computer- aided methods to help the qualification, measurement and visualization. Even though they are various methods of detecting diabetics like fasting blood sugar (FBS),A1C test, Oral glucose tolerance test (OGTT), proper eye test etc. We can provide easy way for detecting diabetics for human without usage of blood test and eye drops. This can be done by implementing devices by internet of things (IoT).In IoT there are more sensors ,NIOR infrared camera system to detect pupil dilation, constriction and saccades of the eye. These parameters are tracked using IR illuminators. This paper reviews about how diabetic is detected via IoT devices for humans. This paper presents a survey on challenges and issues in diabetics and how the device provide easy detection of diabetic, what components are used in the devices and the competitive analysis. And this paper also discusses about the technology, pros and cons of existing systems. Index Terms : Infrared, Camera, pupil, dilation, Raspberry Pi NoIR , saccades, Raspberry Pi 2, Diabetic Autonomic Neuropathy.

| Download

modern workspace policy management with ai based record management

¹Ms.Pavithra U , ²Priyavarsha R , ³Rupika Devi K K , ⁴Sharmasth Vali Y , ⁵Shakkeera L

¹Student, Computer Science and Engineering, Dhanalakshmi College of Engineering, India.
²Student, Computer Science and Engineering, Dhanalakshmi College of Engineering, India.
³Student, Computer Science and Engineering, Dhanalakshmi College of Engineering, India.
⁴Assistant Professor, Computer Science and Engineering, Dhanalakshmi College of Engineering, India.
⁵Assistant Professor, Information Technology, BSA Crescent Institute of Science and Technology, India.

Abstarct [+]

The project is to create a Modern workspace-based policy management with multiple level authoring and approval with both publishing and consumption views, in order to overcome the inefficient and complex methods of maintaining and managing documents across the organization. This system has multi-level approval workflow, AI based records management and use of Microsoft Office 365 Graph APIs to take care of regulatory functions based on certain business criterion

| Download

protected banking verification system using pixel comparison

¹Mr.Harshith S P , ²Jeevanandam M , ³Mr. Rajesh Kambattan K , ⁴Kumaran V

¹Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

E-Banking may be a course of movement of agencies given by employing a gathering of sorted out bank places of labor. Through web user can access their account from anywhere within the world. Recognition of valid client may be a major problem in E-banking. The safety issue arises thanks to unavoidable hacking of banking web. Duplicate websites may be a quite online data misrepresentation that expects to require confidential data, like keeping cash passwords and cash transaction data from user. OTP based verification may be a standout amongst the foremost broadly utilized techniques to verify a client before allowing guests to anchored sites. This sort of verification is straightforward for hacking. Hence we propose a framework having figure pixel comparison for user validation supported blocking chain process. In proposed system for each currency surrendered by the client we produce an ID for every money, when the any sum of amount is transferred the ID of the currencies will only be transferred so we will track the way of the cash going around. The expansion of internet storing money and web based business frameworks has prompted a big increment within the quantity of usernames and passwords oversaw by singular clients and therefore the Text based password uses username and password. So recalling of password is important which can be a difficult one and straightforward for hacking. Graphical passwords are generally easier to be remembered than text; user can set images as their password. Therefore graphical password has been proposed by many researchers as an alternate to text based password. Implementation of Link chain graphical password which uses circular tolerance makes the system more secured than existing.

| Download

wearable band for patient health monitoring using k-means clustering algorithm

¹Ms.Arthi K , ²Hema Priya N , ³Nivetha T , ⁴Sridevi S

¹Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

Internet of Things (IoT) is another innovative technology that can associate things from different fields through the Internet. The wireless body area network (WBAN) is gaining popularity as wearable device spring into the market. This paper proposes a wearable sensor node that enables the implementation of an autonomous biomedical monitoring system. Various sensor nodes can be placed on various parts of the body to measure the person’s body temperature and heartbeat. Recent years, the number of applications for wearable technologies grows rapidly. Usually, these applications are focused on sensing human body and continuous monitoring of physiologic and acceleration parameters which are extremely useful in wearable ubiquitous healthcare application. The existing medical device which is used for sensing and monitoring of human body are invasive and it is uncomfortable to wear. This paper aims to present a wearable device which is non-invasive, comfortable, and continuous. This means that patient may not feel the existence of the wearable devices when they are attached on patient’s body.

| Download

voice based chatbot for student assistance system

¹Mr.Sanjai Kumar R , ²Sabarinathan N , ³Raghul K , ⁴Mrs. Rajalakshmi S

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

A chatbot is a computer program that simulates human communicate to the system by voice or text chats or both. Chatbot are short with man made artificial intelligence feature that can be embedded and used through any major messaging application. A chatbot is interact with customers like a human. Chatbot is a technology that makes communication between man and machines using NLP. Chatbot can give different responses from the same input by using speech recognition. Rich Site Summary(RSS) feeds and expert content processing systems to web users. We cannot translate from one language to another language. Web bots were created as text based web friends for a user. Speech Recognition for application voice message is done by using the HMM algorithm. Exactness of speech Recognition systems differ in vocabulary size. The Voice based chatbots was developed by using Android Application on the basis of HMM algorithm. Android application was developed to process many government based projects using various algorithms. Dragon Speech is a Naturally Speaking Language. As user dictates the words it’ll converts it into text and it displays. HMM algorithm converts speech into a set of words. Speaker dependence vs independence modality of speech.

| Download

tutor alert in e-learning environment using support vector machine algorithm

¹Ms.Priyadharsini S , ²Revathy S , ³Lydia S , ⁴Vijayalakshmi K

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Professor , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

User-friendly E-Learning platform which enhances students’ involvement with the course. In the present system, there is no proper guidance for clarifying students’ queries. The discussion forum present in e- learning environment is not well organised, queries posted are not clarified at the right time. Involvement of the student with the course is reduced in such cases. The proposed system uses Support Vector Machine algorithm which works relatively well when there is clear margin of separation between classes. The proposed system provides an interactive platform for discussion and clarification of various queries. Sentimental analysis is done to find out positive and negative comments which is then used by SVM algorithm for further process. Support-vector machine are supervised learning models which separates queries into two categories such as positive and negative comments. Analysis of negative queries is done to find out the parts of the course where students are facing difficulties. Analyzed results are sent as a report to the tutor through mail so that particular lessons are retaught which helps students to have a better understanding of the lesson.

| Download

traffic monitoring using convolutional neural network

¹Ms.Devi K , ²Bhuvanesh J , ³Madhu Krishna V , ⁴Murali Kashya B

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

The exponential increase in the accidents on the road, fatal rate has become a global problem at this point in time. The project embarks on monitoring the accident prone zone with the help of the neural networks developed with help of Keras and TensorFlow. The proposed implementation increases the survival rate by meagre percent. For this, we go with a simple convolutional neural network with an optimizer function and a loss function (minimizes the loss in accuracy of the model), and categorize them into Mild, Severe and Normal. Efficient computation occurs when the algorithm utilizes the maximum GPU and the right activation function. This is an example of supervised learning where the machine is labelled with features and labels for the input and output layer. Convolution Neural Network is the first layer to extract features from an input image. Convolution possess the relationship between the pixels by learning image features using small squares of input data. Pooling is also introduced to reduce the number of parameters when the images of the Dataset is too large. Once, the process of flattening is done and it is fed to a fully connected layer the output (Category) is provided with the aid of an Activation Function (ReLU). Overall, the application induces the uses of Mailing Feature and Geo-Location to achieve the objective of the project. However, the key feature would be the use of Convolutional Neural Network (CNN). The model summarizes by manual collection of datasets, training, validating and testing the dataset for proper categorical results.

| Download

stable - study on trusted authentication scheme using m-rsa based blockchain technique for legacy environment-a novel method to enhance cloud security

¹Ms.Janani A , ²Lavanya A , ³Mahima Thankam Eapen , ⁴Ms. Julia Faith S

Abstarct [+]

Cloud computing is an important way to drive the IT industry, but security is a key factor in the handling of cloud data. The accuracy of the cloud data is jeopardized. Although cloud-related infrastructures are much more powerful and reliable than computer equipment, they continue to face the wide range of internal and external data integrity threats. In this paper, we propose a secure cloud storage system that supports the protection of privacy. Through this scheme, the data owner uploads the data in the cloud (implemented with Google Drive) and they are allowed to modify the data using the private key. For the protection of cloud computing environments, RSA based Technique uses a newly developed security algorithm based on Encrypted User End Generated (EUEG), which decreases the role of the third party and enhances security testing with an automated logging of malicious devices to produce keycode using System motherboard numbers, System disk number and user password

| Download

securing digitized bank documents using hybrid advanced encryption standard- twofish techniques

¹Ms.Anusha V , ²Nithanyaa V L , ³Vaishali T M , ⁴Dr. Jayalakshmi S L

¹Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

Data Security is a major issue in cloud computing, because it is essential to ensure that only authorized access is permitted. Security issues such as data breach and modification of messages in cloud make the bank’s sensitive data vulnerable to hackers. In existing work, Selective Encryption (SE) technique is used to encrypt a subset of the original data with DWT algorithm and hence it leads to loss of data at the time of decryption. This problem is solved by using the proposed hybrid encryption technique to encrypt the complete original data. In the proposed work, the user’s text or multimedia files are uploaded through the cloud environment. The uploaded user file is accessed only by authorized user based on request and response. The uploaded original data is encrypted completely and stored in public cloud. For encrypting text files, AES-Twofish algorithm is used and for Multimedia files AES-RSA algorithm is used. The user can access the uploaded file by sending request to the file owner. At the time of file download, the file owner shares the random key to the authorized user for decrypting the requested file. This method ensures data security for sensitive bank documents and prevents from security attacks.

| Download

real time online auction application using truthful incentive mechanism

¹Ms.Archana R , ²Kiruthiga R , ³Nandhini S , ⁴Mrs. Vijayalakshmid K

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

Online auction is that the best way to notice and bid in auctions regionally and from afar. it's a really giant potential market of sellers and consumers. In existing system, the net auction method is applicable for restricted product solely that the different product don't seem to be enclosed within the auction method. The projected system involves the look and implementation of an internet auction system with several classes of product. This presents an internet show of class wised product they need to sell or bid. The projected system includes Truthful Incentive Mechanism (TIM) to scale back the biding traffic. The properties of TIM also are analyzed in terms of process potency, individual rationality. After the registration method, the vendor will transfer their product details. Admin will approve product by the classes and conjointly decides the date and time of auction .Then the merchandise data is distributed as a notification to the registered users. The user will participate within the auction method at intervals the point in time, the merchandise is given to the customer with best biding quantity. Conjointly this projected system includes the analysis supported date-wise categorization of product they won within the auction

| Download

human eye blinking detection and fatigue tracking

¹Mr.Adithya M M , ²Chakravarthy J T , ³Shiva Shanmugam V , ⁴Vijayalakshmi M

¹Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

The increasing addiction and time spent with back-lit screen devices has aroused a new issue of eye health. Modern research shows that a preliminary cause of this as heavily decreased rate of blinking while watching screens. No applications of the image processing subdomains are developed yet. Using frame differencing subtraction algorithm, each and every frame is studied to identify any differences. Detection of moving object from a sequence of frames captured from a static camera is widely performed by frame difference method. The frame difference method is the common method of motion detection. This method adopts pixel-based difference to find the moving object. The program compares the difference the eye region of interests in subsequent frames. Any pixels that are different can plotted on a separate image. The landmarks are detected precisely and a single scalar quantity EAR is derived. The EAR (Eye Aspect Ratio) scalar magnitude derived by Dlib's facial recognition Java library is used as the differencing parameter to detect the blinking of eyes. The Eye Aspect Ratio is a constant value when the eye set to understand where certain points exist on facial structures. Then the program plots the same points on region of interests in other images. A notification of sufficiency of blinking reminds the user to blink. The blink count, blink rate, average blink duration, viewing distance is open, but rapidly falls to 0 when the eye is closed. The program uses a facial training is observed and used as parameters to mathematically assess the eye fatigue levels. Detailed reports and graphical representation of blinking behavior is provided at the end of a session.

| Download

handwriting synthesizing and generation using deep recurrent neural network

¹Mr.Durairaj S , ²Samuel J John , ³Santhosh M , ⁴Dr. Chakaravarthi S

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
², , , .
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

Children learn writing by practicing repeatedly to master their own writing styles. This process is similar for any human being to learn any activity. Even with advanced Deep Learning algorithms, computers are still incapable to learn a task. Trying to solve simple problems like handwriting may lead to a better understanding of how humans think, and can further develop better algorithms for computers. It should be mentioned as generating sequences, rather than generating handwriting. This is how Alex Graves achieved the solution from his research. The model should also learn to imitate the particular style of the generated handwriting. The objective of the project is to develop an application which transforms the input text into handwritten script. The regular practice involves only the process of handwriting generation, whereas this project recognizes and generates the Handwriting. The problem with the Residual Network is Skip Connections. It will skip between multiple layers in the process. So, it cannot produce an accurate result. The Existing solution comprises only of Handwriting Recognition using Residual Networks and position embedding of characters. The network predictions are based only on the last few inputs, and these inputs were predicted by the network. It has few opportunities to imitate the handwriting. This reduces the performance accuracy of native handwriting and also increases the conversion time. The Proposed model is made by using Long Short-term Memory recurrent neural networks to generate complex sequences with long-range structure simply by predicting single data point at a time.

| Download

detection of reliable and unreliable sensor nodes in wsn using pra

¹Ms.Usha N S , ²Harishkumar V , ³Karthik S , ⁴Ramaswamy M

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

The use of wireless sensor networks is getting improved the importance as this kind of networks are becoming the communication base for many cyber-physical systems. Such systems depend on sensor data correctness to make results. Thus, duplicate data can lead such systems to take false actions. Errors can be generated by sensor’s hardware failures or bugs and also from the intentional interference in intruders. The path that connect such WSN to the Internet are natural intruders targets as they usually ran over conventional operating systems and communication protocols. These work proposes a confidence attribution scheme, based on lightweight predictors running on the sensors. The solution also proposes a parameterizable formula, in order to stamp every value sent by a sensor with a confidence level, calculated upon the values of a subset of correlated sensors. This work also gives an algorithm that can identify a defective sensor into its subset. The use of predictors is confidence attribution are proposed as the basis of a mechanism that increases the WSN resilience against sensor failure or bad data injection by intruders. Several simulations were performed in evaluating the detection efficiency against different types of sensor errors. This work also analyses mechanisms to deal with concept work in the WSN lifetime.

| Download

digital twin – lifetime performance of the assets and live diagnosis

¹Mr.Mohamed Sulaiman M , ²Mohammed Durvesh M , ³Dr Pritto Paul P , ⁴Dr Usha M

¹Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

The curiosity about the future goes beyond its saturation by humans. We are quite curious about the future than the present. Though we can’t predict the future for humans, when it comes to machines, it will play a vital role in industries. In India, Road accidents are the biggest threat, claim about 1.5 lakhs of death this year. This paper provides the status of the asset’s current condition through the dashboard and also predicts its lifetime to the user for clarification. This paper is based on lifetime Prediction of an asset in the automobile industries. With the help of Matlab, CAD models, and simulation techniques, we create a virtual replica of the asset. It also predicts whether it is safe to drive with the current condition. If any fault occurs while driving, it will immediately alert the user and sent a request message to the manufacturing unit for its replacement. This paper concluded to reduce two-third of the death population and pave a way for the healthy life across the globe.

| Download

drowsiness detection using viola jones algorithm

¹Dr.Smitha P. S , ²Pugazhendhi D , ³Nivas M , ⁴Shiril Vijai R

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

In India major accidents are caused due to drowsiness. Around 20% of vehicle crashes have been caused by drowsy drivers. Image processing has applied to process images in medical stream, in cooperating drowsiness detection using various algorithms. In Traditional System there were Monitors which could predict the drowsiness based on the eyes but they required more time & also they got poor result. So, to overcome that problem, we designed a new system called Drowsiness Detection System (DDS) which will give better result in less time. The system uses DIP and analyzing techniques to identify such status of eyes. DDS increases accuracy of such observations of eyes. With the help of DDS system, we can detect the drowsiness in its early stage hence the cost can be reduced for the further treatment. As the drowsiness is detected in the early stage so the diagnosis becomes easy for the prevention of accidents. DDS applies digital image processing techniques on input as face image to find the certain features in the eyes and mouth using MATLAB Software.

| Download

ecommerce warehousing management system using logistic regression

¹Ms.Abinaya C , ²Priyadharshini B , ³Sumathi Y , ⁴Dr. Ramya Devi R

Abstarct [+]

Data Analytics with business intelligence is used to make great business decisions. These have greatly influenced the market place with highly illustrative charts. Data Analysis using Logistic Regression for inventory management with precision, Constrained Linear Regression for sales Summary and Novel Hybrid Algorithm for data integration can be a great approach to deliver a highly recommended system. Data visualization using d3.js and Angular 8 along with cloud/MYSQL could provide a great solution to the existing scenario. The Existing solutions are based on columnar database e.g. Software – Net suite, Zoho Inventory, Fish Bowl. The Proposed System is Logistic Regression Algorithm over the stocks, Constrained Linear Regression for sales and Novel Hybrid Algorithm for integrating the basic returns and investments of the warehouse. The peculiar trace line for each attribute is marked on a linear scale. ETL – Extract Transform Load is the data extraction process that is used to configure data and use for integration. The data is fed into the software in the form of JSON for Data security and Object mapping. Data Security is achieved through Linked Hashing technique. © 2020 VDGOOD Professional Association. All rights reserved

| Download

elite book reader using iot and neural network

¹Ms.Asmitha S , ²Monisha D , ³Niveditha K , ⁴Keerthivasan R

¹Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
²Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

Our focus is on enhancing the capabilities of blind people by providing them with a solution through which the information can be fed to them in the form of a speech. Our project develops a model which uses the optical character recognition(OCR) technology for the identification of the printed characters using image sensing devices and computer programming. It is then processed by text-to-speech conversion software and the output is sent to the speaker via Bluetooth.

| Download

securing the cloud access using outsourced decentralized multi-authority attribute based signature

¹Mr.Hirrangandhi D , ²Prasanna V , ³Suryaprabhaharan M , ⁴Sundar K

Abstarct [+]

The advent of cloud computing, data owners are moti-vated to outsource their complex data management systems from local sites to commercial public cloud for great flexibility and economic savings. Attribute based signature (ABS), which utilizes the signer’s attributes to generate private keys, plays a competent role in data authentication and identity privacy preservation. In ABS, there are multiple authorities that issue different private keys for signers based on their various attrib-utes, and a central authority is usually established to manage all these attribute authorities. However, one security concern is that if the central authority is com-promised, the whole system will be broken. So, Out-sourced Decentralized Multi-Authority Attribute Based Signature (ODMAABS) Scheme is used. The proposed ODMA-ABS achieves attribute privacy and stronger authority-corruption resistance than existing multi-authority attribute based signature schemes can achieve. By this scheme, when a user wants to access a file that is been stored in the cloud, the user has to send a request to the data owner. When the data owner ac-cepts the request, an One Time Password (OTP) will be generated and sent to the user’s e- mail. Using that the user can access the file he/she has been requested. By this, we can protect the privacy of the data and secure the cloud access, so that unauthorized entity will not be able to access the data.

| Download

fire detection in unpredictable environment using convolutional neural network

¹Ms.Hemalatha B , ²Reshma D , ³Pallavi Priyadarshini J , ⁴Hemalatha V

¹Assistant Professor, Computer Science and Engineering, Velammal Engineering College, Chennai, India.
², , , .
³Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.
⁴Student , Computer Science and Engineering, Velammal Engineering College, Chennai, India.

Abstarct [+]

Most of the disasters are either due to human mistakes or system failure which endangers human lives and properties, especially fire disaster can occur anywhere or at anytime even in inaccessible areas. Fire detection and instant reporting of such disaster in surveillance is very necessary for quick actions. Traditional methods involve fire detection by color and motion characteristics but they showed high rate of false alarm, less accuracy and early stages of fire couldn’t be detected. These methods fails to detect fire in unpredictable environment like smoke, fog and snow. Present fire detection methods like thermal detectors, smoke detectors and flame detectors are not very reliable for fire detection. In this work, an efficient CNN based system for fire detection using surveillance videos even in unpredictable scenarios is presented. This approach uses pre- trained model called FireNet for training augmented video datasets making it computationally easier for feature extraction and training. CNN based classifier is built with FireNet architecture to which surveillance videos is given as input. The classifier detects whether fire is present in the video frames and classifies as Fire or Clear. If fire detected, an alarm notification message is sent to user using Firebase through smart phones which are synchronized with Firebase.

| Download

cloud computing- an overview

¹Dr.Shantha Shalini K , ²Dr. S.Leelavathy , ³Dr. R.Shobana

¹Assistant Prof G-II, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology , India.
²Assistant Prof G-II, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology , India.
³Assistant Professor, Computer Science and Engineering, Aarupadai Veedu Institute Of Technology , India.

Abstarct [+]

Cloud computing is a type of Internet-based computing that provides shared computer processing resources and data to computers and other devices on demand.Cloud technology is widely adopted by healthcare organizations worldwide. During the past few years, healthcare industries have realized the potential of cloud computing and how it can help them give quality services to patients. The cloud technology has accelerated the way healthcare industry can use or share information across a network.This paper is designed to eliminate the need to transfer data between different data centers. It eliminates paper work. The information becomes available in the “cloud” from where it can be processed by expert systems and/or distributed to medical staff.

| Download

Sign In

Reset My Password

VDGOOD Journal of Computer Science Engineering

Volume: 1- Issue: 1