VOLUME 9, ISSUE 6, JUNE 2020

Abstract: Web applications are programs that are available on the go. The increase in the number of customers accessing the web demands for technological complexity to manage the operation. The session established between the user and the server can be hijacked by an attacker by masquerading as an authorized user called Man-in-the-Middle (MITM). The target of the attacker is to have access to users’ confidential records in the server for their own financial gain. It was predicted by Juniper research that by 2023 over 146 billion records will be tampered with and also electronic commerce will progressively increase by 66% in 2024 as the number on online transaction reaches $18.7 trillion. The security of Web applications have been a great concern to many online services. The paper, therefore developed a web application for e-Commerce for the detection and prevention of session hijacking in order to protect individual records from unauthorized user.

Keywords: Session Hijacking, Security, Vulnerability, Authentication, HTTP, Web Application, MITM.

Abstract: A non-governmental organization is an organization with no self-profit, group based on the citizen that functions independently of government. Many Non-government organizations are working in the country. NGO activities include, but are not limited to, environmental, social, advocacy, and human rights work. They can work to promote social or political change on a broad scale or very locally. NGOs play a critical part in developing society, improving communities, and promoting citizen participation. There is a need to provide a platform to connect people to various NGOs based on their needs. This paper proposes WEB application that connects people directly to the relevant NGO. The information about various NGOs is given based on their field of operation. An individual or group requires the services of NGO, if wants to volunteer for some activity can do so after registering with this platform. Web application also provides chat-bot to directly communicate with NGOs and get the queries answered.

Keywords: NGO, Web Application, Register, Volunteer, Chatbot.

Abstract: In this project, we first survey the current situation of video processing on the edge for multimedia Internet-of-Things (M-IoT) systems in three typical scenarios, i.e., smart cities, satellite networks, and Internet-of-Vehicles. By summarizing a general model of the edge video processing, the importance of developing an edge computing platform is highlighted. Then, we give a method of implementing cooperative video processing on an edge computing platform based on light-weighted virtualization technologies. Performance evaluation is conducted and some insightful observations can be obtained. Moreover, we summarize challenges and opportunities of realizing effective edge video processing for M-IoT systems.

Keywords: M-IoT, SaW, MaaIP, SSCS.

Abstract: Creative Functionalized Bricks with Embedded Intelligence (FBEI), using custom-made LEGO-compatible bricks containing electronic circuits & sensors based on new micro & nano technologies, spark the interest of learners with different backgrounds and preparation levels from kindergarten to Ph.D. FBEI modules are based on a concept called TASEM (technology assisted science, engineering and mathematics) developed during 2000 - 2010. Doctoral students, involved in cutting-edge micro and nano research, interacted with K-12 students and teachers to develop TASEM. TASEM led to unique FBEIs covering a large number of learning areas including energy, power sources, math, Si crystals, computer switches, sensors and miniaturization, micro and nano concepts, technology assisted dancing, psychology, cognitive training, cancer education, microsystem fabrication, system integration, biomedical, and computer science. By allowing user-designs, FBEIs focus on research-oriented and entrepreneurial learning. Over 100 FBEI learning modules were developed benefiting over 2,500 learners nationally and globally.

Keywords: K-12 modules, micro and nano technologies, STEM education

Abstract: In response to COVID19 pandemic outbreak, there is a need for a temperature check-up of the visitors to detect fever before they enter the city via the airports, railway stations and even at the highway tolls. There is a need for thermal screening in shopping malls, multiplex, supermarket and various other places before granting access to the visitors.  There is a risk of cross infection in manual   testing.  The   MLX90614   is a high-performance   Infrared Temperature   Sensor that can be used to automatically make a temperature check-up and decide whether to grant the door access.  This paper is comprised of mainly the three subsystems: namely Human Presence Detection   System, Temperature Measurement System and automatic door access control with display.

Keywords: MLX90614, HC-SR04, microcontroller, I2C protocol, COVID19.

Abstract: Library Management System is a software which is developed to organize and maintain a library. A library contains a collection of books of vast categories and other important journals which helps the student gain knowledge. Every institution has a library that is needed to be organized. The integration of books from all departments within a library makes it difficult for a librarian to organize them. Moreover, there are many information that are to be recorded such as books details, the books issued, the books returned etc. which becomes a tedious job when done manually. Therefore, this software helps the users to make their work easy and proves to be convenient for both beginners as well as advanced users. It improves the ordinary library system to facilitate the staff or librarians in doing their work effectively by reducing the human efforts and maintaining the library in the best possible way.

Keywords: Library management system, Library, manual library system, automated library system, PyQT5 Designer, My SQL Workbench.

Abstract: Energy is essential for the economic growth and social development of any country. The world facing the problem of power generation. The fossil energy sources are limited and needed to use properly. This power generated increases the greenhouse effect. The used of the combined solar and wind power system can be more benefits in order to make useful throughout year. In this presented research the review is carried out on the different types of solar and wind associated hybrid system for developing the proposed research study.

Keywords: Solar, Wind turbine, Arduino UNO, LCD, Inverter.

Abstract: With the emergence of new technologies, new academic trends introduced into Educational system which results in large data which is unregulated and it is also challenge for students to prefer to those academic courses which are helpful in their industrial training and increases their career prospects. Another challenge is to convert the unregulated data into structured and meaningful information there is need of Data Mining Tools. Hadoop Distributed File System is used to hold large amount of data. The Files are stored in a redundant fashion across multiple machines which ensure their endurance to failure and parallel applications. Knowledge extracted using Map Reduce will be helpful indecision making for students to determine courses chosen for industrial trainings. In this research, we are deriving preferable courses for pursuing training for students based on course combinations. Here, using HDFS, tasks run over Map Reduce and output is obtained after aggregation of results.

Keywords: Distributed File System, data mining, educational data mining, Hadoop, MapReduce.

Abstract: Multi-Cloud Storage infers the utilization of various appropriated stockpiling organizations using a singular web interface rather than the defaults given by the circulated stockpiling shippers in a single heterogeneous plan. This Multi-Cloud accumulating model empowers customers to store cut mixed data in various cloud drives. Right now, offers assistance for various appropriated stockpiling organizations using the single interface as opposed to using single circulated stockpiling organizations. Cloud security objective basically focuses on issues that relate to information insurance and security parts of dispersed processing. Likewise, the data in clients' information can be spilled e.g., by methods for malignant insiders, indirect accesses, pay off and pressure. This latest data accumulating organization and data control model focus on vindictive insider's passageway on set aside data, affirmation from malignant archives, removal of united dissemination of data storing and clearing of out of date records or downloaded records once in a while. Data owner doesn't generally need to worry over the destiny of the data set aside in the Multi-Cloud server may be removed or ruined. The other is entrance control of data. The exploratory results exhibit that the suggested show is suitable for essential authority process for the data owners in the better choice of multi-disseminated capacity advantage for sharing their information securely.

Keywords: Multicloud storage, information leakage, system attack ability, remote synchronization, distribution and optimization  

Abstract: Internet plays a vital role in exchanging the information through e-mail, chat, etc. Users can get the information of advanced services through the creative use of the Information Technology. Regarding to this the patients who met with the accidents, sudden heart attacks or any snakebite to the persons, requires the first aid before reaching hospital for further treatment. For reaching hospital, they need the ambulance service, which provides first aid necessities to the patients. so whenever any problem occurs for persons, ambulance may reach the spot, is delayed in the first aid service, and reaches the hospital too late. Since there is late service given to the person who suffering from a lot without proper treatments. To get all the information at their fingertips to the publics, we have introduced our web application. Our manuscript called “First Aid Info App” is design for the use of patients. Through this, website patients get complete information about first aids that they needed through online. Here through the app patients get all the information regarding the first aids in video format, this app makes user friendly for the users to access the information at their fingertips quickly within time that shows the nearby list of hospital details, navigate to selected hospitals and videos helps to quick understanding and effective.

Keywords: Internet, Information Technology, First aid, video, navigation

Abstract: An AI bot to enhance the skills of the players in electronic sports. AI bot uses the algorithms Best First Search (BFS), A* with forward Search, and Almighty Move to automatically solve the classic snake game. Player can follow the simultaneously running AI bot to play the game effectively. To introduce the concept of AI Auto-Bot game solver, the work has been performed on the classic snake game which was first introduced in Nokia phones. The game is initiated with the snake of length one and the size of the snake increases by one, each time it eats a new fruit. Actions supported by the snake game simulates directions: ‘UP’, ‘DOWN’, ‘LEFT’, ‘RIGHT’. The snake moves with its head in the front direction followed by its body. The game terminates in two conditions they are, the head of the snake collides in its own body and the head collides to the walls of the game board.

Keywords: Best first search, A* search, A* with forward checking, Random move, Almighty move.

Abstract: Image compression is the technique used to reduce irrelevance and redundancy of the image data in order to be able to store as well as transmit data in an efficient form. Image compression techniques may be lossy or lossless. Among the various image compression techniques, BTC [Block Truncation Coding] belongs to lossy type of image compression technique especially for greyscale images. The procedure consists of steps which divides the original image into various blocks and then uses quantizers to reduce the number of grey levels in each block while maintaining the same mean and standard deviation. BTC technique is a quite old technique but a highly efficient compression technique. BTC suffers from certain key problems such as inherent artifacts, blocking effect and false contour. Through the proposed DDBTC method, namely Dot-Diffused BTC (DDBTC), we try to deal with those problems. The parallelism process of the dot diffusion is properly exploited to provide excellent processing efficiency. Similarly, excellent image quality is assured through co-optimizing the class matrix and diffused matrix of the dot diffusion. According to the experimental results using HVPSNR [Human-Visual Peak Signal-To-Noise Ratio], the proposed DDBTC is found to be superior to the original BTC techniques. Keywords: Image Compression, DDBTC, HVPSNR, Dot Diffused, False contour.

Abstract: The efficient utilization of bandwidth in campus networks is a major traffic engineering issue. It requires a complete knowledge of the underlying physical network architecture as well a means to automate or reactively and proactively program the network. The static nature of traditional network creates a hurdle that must be overcome to achieve the above.  The Software Defined Network architecture proposes a novel way to automate, program and dynamically configure computer networks. This work uses the VMware virtualization software and the GNS3 network emulator to emulate a Software Defined-based campus network. A data plane made up software-based replicas of network devices is designed and configured to connect to a controller software. A network application scheme is implemented by leveraging the Hierarchical Token Bucket Queuing Discipline which automatically programs bandwidth allocation at the data plane through the controller based on traffic demands. The functionality of the architecture is tested by carrying out a number parallel-connections to simulate changing traffic patterns. This is done using the Iperf Application. The results show the conversion of a traditional campus network into a Software Defined-based campus network. It also depicts the complete emulation of the entire Software Defined-based campus network. At the data plane of the emulated network, devices are able to forward packets to one another with the most active port forwarding about 9,000 packets. The controller obtains a global view of all 11-network devices in the emulated network. The latency between the controller and the software defined switches at the data plane ranges between 50 and 62.5 milliseconds. The throughput between the controller and the software defined switches at the plane ranges between 2 and 9 Mbps. Application Plane to Control Plane communication in the emulated network is executed in an average of 30 milliseconds and bandwidth utilization occurs in a minimum of 11seconds and peaks at 27.5 seconds. It however becomes steady at 17 seconds as traffic patterns vary. Keywords: SDN, virtualization, GNS3, Hierarchical Token Bucket, automation.

Abstract: Heart Disease or Cardio Vascular Disease (CVD) is the key factor that leads to majority of deaths across the world from the past, therefore we require   accurate and appropriate treatment as well as diagnosis system, and already lot of machine learning techniques is applied on large data sets in medicine field to analyse the data. Many researchers also have been using various machine learning algorithms to help doctors and medical practitioners to Diagnose the Heart diseases. This paper gives the survey of various classification algorithms like Naive Bayes, Support Vector Machines (SVM), Decision Trees (DT), Random Forest (RF) and Logistic Regression (LR) and the execution of the heart data set is depicted using Weka tool.

Keywords: Decision Trees, Heart Disease, Logistic Regression, Random Forest, Support Vector Machines.

Abstract: Globally, ICT has emerged as a critical enabling-tool to achieve effective facilitation, monitoring and management of service delivery. As governments accept, adopt and move to invest in e-health implementation, there is need to evaluate and understand the state of adoption, the process and impacts at different stages of implementation. In Kenya, eHealth Policy (2016-2030) envisions progressive sustainable adoption, implementation and efficient use of eHealth products and services at all levels of healthcare delivery. The study explored e-health services availability by type and level of implementation to support service delivery at level 3 and 4 healthcare facilities. The presentation is based on data derived from literature review; triangulated with empirical data on e-Health implementation collected during a survey of three county referral hospitals, in western Kenya. The facilities lacked enough technologies in place; poor technological infrastructure, if not wholly lacking and low computer to task ratio. There were significant barriers to e-health implementation; notably, not enough skilled e-health practitioners to drive the implementation process. However, Kenyan government, through Health Policy and with the support of donor community partnership, seek to strengthen and accelerate integration of ICTs into healthcare system and health outcomes. Keywords: E-Health Services availability, Utilization, Level of Integration, Service Delivery.

Keywords: Deep learning, Machine learning, Artificial Intelligence and Image processing.

Abstract: A Wireless Sensor Networks (WSNs) are equipped with large number of sensor nodes that consists of several sensing elements distributed to achieve specific objective of environment. Sensor nodes can be used to solve many issues like air pollution, water pollution, wind speed and irrigation of agriculture. Energy is the most important factor in WSNs to enhance the sensor lifetime as well as the network lifetime due to all sensors is battery powered. Future research involves designs the routing protocols to utilize less energy during communication to extending the lifetime of network. In most of the applications, a replacement or rechargeable of energy is more expensive. An energy harvesting wireless sensor networks make use of nodes that are able to get energy from the environment. In this paper, we discuss and review wireless sensor network applications and energy optimization to minimize the e-waste to enrich for environmental. Keywords: Energy, E-Waste, WSN, Energy Harvesting

Abstract: These days, data privacy and secure data communication is one of the main concerns which led to design various techniques to encrypt the data and transmit it in a secure way. Steganography is the mechanism in which the secret message is transferred by hiding it in a covered file such as any media i.e., image, video, audio, etc. Various researches have been made in order to transmit the data in a secure way. Recently, to this end, the 2-1-4 LSB technique was used with RSA and SVD for color image. This approach was proved to be better, but after performing a literature survey, some pitfalls of this technique are observed. Thus, in this paper, a novel technique is proposed to perform secure steganography. In the projected approach, two novel techniques- Huffman Encoding and enhanced fuzzy controlled edge detection are introduced to encrypt the input data and extract hiding location respectively. Simulation is performed using MATLAB tool. Peak-to Signal Ratio, Mean-Square Error and embedding time are three parameters that are used to determine the performance of the proposed system. Comparative analysis of projected and existing techniques is performed which ensured the efficacy of the novel approach.  Keywords: Steganography, Advanced fuzzy edge detection technique, Huffman Encoding, PSNR, MSE, embedding time.

Abstract: The reliability and availability of network services is under threat as Denial-of-Service (DoS) attacks develop. It needs efficient mechanisms for detecting DoS attacks. Investigate and derive second- order information from traffic data found on the network. Such second-order statistics derived from the proposed approach to analysis may provide valuable correlative information that is concealed among the apps. Through using this secret information, the accuracy of detection can be significantly improved. Comparisons also show that our Cyber Crime based detection approach by Applying Data Mining techniques outperforms some other existing DoS attack detection work.

Keywords: Denial- of-Service (DoS), TCP & UDP, Local to User (R2L), Network Intrusion Detection Systems (NIDS).

Abstract: Somatization, depression, anxiety, fear, paranoid, interpersonal sensitivity and psychosis are some of the mental health problems that the college students are enduring from. These problems bring many negative effects to them. For analysis the relationship between these mental health problems from the dataset, many association rule mining algorithms are already used. These algorithms concentrate on positive rules and they don’t concentrate on negative rules. So this particular paper focuses to mine both negative and positive rules from the mental health dataset of college students. Here the mental health dataset of college students is considered and by using association rules, the correlation between different mental health problems is predicted using this dataset.

Keywords: Association Rule, Positive Rules, Negative Rules, Apiori Algorithm.

Abstract: The plant diseases are a main summon in the agriculture section and quick recognition of diseases in plant could help to develop an early treatment method and span the valuable reducing economic loss. In this work, the Apple Leaf Disease Dataset (ALDD) and Tomato Leaf Disease Dataset (TLDD), which is composed of laboratory images and complex images under real old conditions, is rapid storage technology constructed via data augmentation and image annotation technologies.  Based on this, a new apple leaf and tomato disease detection model that uses deep-CNN (Convolution Neural Network) is proposed by introducing the Google Net Inception structure and Rainbow concatenation. The novel INAR-SSD model provides a high-performance solution for the early diagnosis of apple and tomato leaf diseases that can perform real-time detection of these diseases with higher accuracy and faster detection speed than previous method.

Keywords: Deep Learning, Apple leaf diseases, Tomato leaf diseases, real-time detection, convolutional neural networks

Abstract: In the current era of technology, there has been an exponential increase in the cyber-attack. One of the most dangerous attacks in this cyber-attack is the ransomware attack which not only corrupt and encrypts the data but also steals the information from the system. Ransomware is a way of money extortion by cyber-attackers in which user’s files are encrypted and the decryption key is held by the attackers until a ransom amount is received from the victim. It is a highly advanced malware. The cyber-attackers behind the development of ransomware are constantly improving their attacking strategy by improving the malwares constantly. This is making it harder to develop effective long-lasting countermeasures to prevent such attacks. . In this paper, discuss the origin, evolution, and prevention techniques of ransomware. The various families of ransomware, their attacks, and prevention from these attacks have been presented.  

Keywords: Ransomware, Static, Dynamic, Information Security.

Abstract: As we accumulate more and more data of people who smoke, and improving the calculation, exact investigation leads to conceivable and quitting cigarettes. Be that as it may, supposedly, little examination is been frequently conducted on people who regularly burn cigarettes, for example, at what time will he/she smoke. The framework designed will depict a model which dependent over the AI calculation to foresee day by day smoking time. The recreation informational index of smoking time information was built up by utilizing the populace data of smokers for illness control and avoidance. So as to take care of the issue of too little component data, we propose an element data extraction module.

Keywords: Machine learning, Supervised Machine Learning, Naive Bayes, Classification Rules

Abstract: Days going on and the concept of e-learning enlarging in its details, tools, methods within the rapid development of cyberspace and its components, including the revolution in smartphones and requests for use it in learning and education. For that and more we need to put clear milestones, that can be traced to access available knowledge about e-learning, and use it in easier ways to understand the whole idea of e-learning in its components and how to interconnect between them. To remove the ambiguity and confusion that can arise when using various methods and tools in e-learning; thus, providing many people with a sense of comfort with the difficulty details of e-learning. This paper discusses the possibility of suggesting a roadmap that can be traced to access e-learning effectively, that by clarifying tangible foundations; which can be addressed and focus on when we want to use or design e-learning applications without going into variant ways may make it difficult. Especially in the basic concepts of e-learning and supporting infrastructure and the mechanism for the development of strategies, objectives, and tools. Taking in mind the effectiveness, assessing the quality, standards, and put all on a roadmap. Keywords: Computer, Internet, Education, Cyberspace, E-learning, E-teaching, e-education, roadmap, authoring tools, web, www, Information technology (IT).

Abstract: Phishing refers is the process whereby an attacker pretends to be a legitimate one for the purpose of getting vital information such as personal information, credit card details and confidential passwords from user. Phishing are usually done through websites Urls, emails, text messages and phone calls.  Once they successfully acquire user’s vital information, they used it in gaining access to the user’s account which can to financial theft and loss. This paper presents a model in detecting phishing websites using support vector classifier and a deep neural network algorithm. We used a urlset dataset which comprises of 48,009 legitimate website Urls and 48,009 phishing Urls making a total of 98,019 websites Urls. The dataset was pre-processed by removing all Nan and finite values therefore making it clean and fit for training. After processing, we used feature extraction in deducting the dataset dimension and some unwanted feature columns thereby reducing the dataset from 16 feature columns to 2 feature columns; with the domain feature column (this holds the domain name/website Urls) and the label feature column (this holds the binary values 0 and 1, where 0 represent a legitimate website Url and 1 represent a phishing website). We also used CountVectorizer in converting text documents (domain column) to a vector of term/token counts. CountVectorizer also enables the ​pre-processing of text data prior to generating the vector representation. After training, support vector classifier showed that the result of accuracy was 97.21% while our deep learning algorithm was 98.33% of the total 98,018 url dataset studied. Thereafter we saved and deployed both models to web using flask Keywords: Phishing, Support Vector Classifier, Deep Neural Network, Machine Learning

Abstract: Oral health is a part of general health. Oral health also influences the quality of life. Dental caries and periodontal diseases are the common diseases in populations. These diseases are highly irreversible, once occur and also have complex etiology. Although primary preventive techniques exist to total protection. A Descriptive study to access the awareness regarding oral hygiene and prevalence of oral problems among school children at selected school, Mohali, Punjab. Assess the awareness regarding oral hygiene, describe prevalence of oral problems, determine the association between awareness regarding oral hygiene and prevalence of oral problems, find out the association between awareness and prevalence with selected sociodemographic variable. Qualitative approach and descriptive research design is adopted in this study. The study was conducted at BSF, Arya Senior Secondary School, Sohana, Mohali (Punjab). Target population was school children. Study was conducted on 150 school children; sampling technique adapted to this study is purposive sampling technique. Structured questioner and check list were prepared. Tools were validated by various concerned experts before application. The result was interpreted as follows. According to sociodemographic  variable  the age of 12 years 20% (30) 13 years 44 % (66) 14 years 36% (54), class 7^th 20% (30), 8^th class 44% (66) 9^th 36% (54) sex of the child male 100% female 0%,  education of father, illiterate 0%, middle 8%  (12), Matric 41% (62), Senior Secondary 41% (62) graduate and above 9% (14). In the present study 150 students participated. The findings of the study revealed that majority of school children show moderate level of awareness about oral hygiene and prevalence of oral problems.  

Keywords: Assess, Awareness, Prevalence, Dental Problems, Oral Hygiene

Abstract: Accidents remain a major health problem for children of all ages, in spite of attempts at prevention by industry, health workers, educators, and legislation. In order of decreasing frequency, serious pediatric accidents include moving- vehicle accidents, water-related accidents, burns, poisonings, and falls. Their cause, severity, and prevention will be considered, with future challenge. WHO: Shape healthy environments for children-the feature of life WHO Health Day -7 April 2003. One study that deals with the reported and observed practices of mothers of children 0 to 3 years old [n = 357] in relation to injury prevention. Prevention practices for falls, poisonings, burns, suffocation, electrocution, and drowning and car safety were studied following a developmental approach. At both ages unsafe behavior conducive to suffocation, scalds and car safety were reported in relatively higher frequency than for other causes of injury. A Study to assess the effectiveness of structured teaching program regarding knowledge and practice of mothers on prevention of accidents among toddlers in selected urban community area Bangalore. Assess the knowledge and practices of mothers regarding prevention of accidents among toddlers, find out the effectiveness of structured teaching program regarding knowledge and practice of mothers on prevention of accidents among toddlers, determine the association between the selected demographic variables with knowledge and practice score of mothers regarding prevention of accidents among toddlers. Evaluative approach and one group pre test post test pre experimental design was selected for the study. The study was conducted in Rupena Agrahara Area, Bommanahalli, in Bangalore. The population of the study was mothers of toddlers in selected urban community area at Bangalore. Content validity of the tool was obtained from seven experts and the reliability of the tool was r=0.92. A stratified random sampling technique was used to select 40 mothers of toddlers. A structured interview schedule was used to know the knowledge of mothers regarding prevention of accidents. The data obtained were analyzed and interpreted in terms of objectives and hypotheses of the study by using descriptive and inferential statistics in term of frequencies, percentage, mean, standard deviation and chi-square test. The study findings revealed that in the pre test score the mothers have less knowledge score in all aspects the mean percentage in the pre test score is 31.67% with S.D. 2.6.  in the post test score the mothers gained knowledge with the mean percentage of 73.33% with S.D. 2.6. The study revealed that there was an enhancement of the knowledge score in the post test. This indicates that the structured teaching program is effective in enhancing the knowledge and practice of the mothers regarding prevention of accidents among toddlers. On the basis of findings, it is recommended that a similar study may be replicated issuing a large number of respondents. It is also recommended that the other methods of teaching with frequent reinforcement be implemented for improving the knowledge and practice of mothers regarding prevention of accidents among toddlers and well-educated mothers could be expected to reduce the mortality and morbidity among toddlers.  

Keywords: Effectiveness, Structured Teaching Program, Knowledge, practice, prevention, accidents, toddlers.

Abstract: The MRI and mammogram texture analysis matrix itself does not directly provide a single feature that may be used for texture discrimination. Instead, the matrix can be used as a representation scheme for the texture image and the features are computed. Feature selection is focused on many areas, especially in artificial intelligence, medical image processing, Data Mining [Dom et al.] and pattern recognition. Classification of objects is an important area of research and of practical applications in a variety of fields, including pattern recognition, artificial intelligence and vision analysis. Classifier design can be performed with labelled or unlabelled data. 

Keywords: Magnetic Resonance Imaging (MRI), Surrounding Region Dependency Matrix, Spatial Gray Level Dependency Matrix, Feature Selection.

Abstract: Poultry is a supplementary service to agriculture. It helps the farmer in balancing their financial status during the time of non harvest. The proposed poultry management system aims in monitoring and controlling the environmental conditions like temperature & Moisture and parametric considerations like food & water quantity assessment in the poultry farm. They are the most important constraints responsible for the improvement in productivity output. Feed proportion maintenance, environmental parameter maintenance and providing healthy, risk free & low cost Equipments are the key aspects considered in design and development of our poultry management system. The inputs are sensors like HX711 Load cell amplifier module, LM35, FC28 and HC-SR04 for measuring weight, temperature, moisture and water level respectively. The processing is done with the help of Arduino Uno board. The output is displayed with the help of 16x2 LCD Display and the user is intimated with LED and Buzzers. This provides smart assistance for farmers to get alerted. Comparing to the conventional poultry farm, the proposed system has a better monitoring, profit, production and also reduces human intervention. It is cost effective and less complex system. The evaluation of efficiency and deviation in performance of sensors are studied and tabulated. Keywords: Arduino Uno Board, Efficiency, Deviation, Poultry Management System (PMS), Sensors and Smart Systems.

Abstract: Electronic nose applications in environmental monitoring are nowadays of great interest, because of the instruments’ proven capability of recognizing and discriminating between a variety of different gases and odours using just a small number of sensors. Such applications in the environmental field include analysis of parameters relating to environmental quality, process control, and verification of efficiency of odour control systems. This article reviews the findings of recent scientific studies in this field, with particular focus on the abovementioned applications. In general, these studies prove that electronic noses are mostly suitable for the different applications reported, especially if the instruments are specifically developed and fine-tuned. As a general rule, literature studies also discuss the critical aspects connected with the different possible uses, as well as research regarding the development of effective solutions. However, currently the main limit to the diffusion of electronic noses as environmental monitoring tools is their complexity and the lack of specific regulation for their standardization, as their use entails a large number of degrees of freedom, regarding for instance the training and the data processing procedures. Emissions of many air pollutants have been shown to have a variety of negative effects on public health and the natural environment. With the ever increasing population and the need for automobiles for transportation, the number of vehicles have increased considerably which has lead to increase in the emission of air pollutants such a CO, CO2, Hydrocarbons, SO2, etc., which may cause grievous problems to living beings and environment. One solution to this problem is frequent monitoring of the gases in the environment. In India, the present emission monitoring system is available only at emission testing centres located either in petrol bunks or few other places. The model we have designed can be handed over to the traffic police for continuous and instant monitoring of emission levels of vehicles. The present standard device is not portable and involves wired connections unlike our design which is portable, rechargeable and wireless. These features make our design easier to use than the traditional device. Also, our new model is comparatively cheaper than the existing device with the same level of accuracy.

Keywords: Electronic nose, CO, CO2, Hydrocarbons, SO2, Emission testing, continuous and instant monitoring of emission levels of vehicles, only at emission testing centres, comparatively cheaper, COPD and environmental quality.

Abstract: Accidents are among the crucial problems the world is facing nowadays as they cause many demises, bruises, and mortalities as well as consistent loss of the economy. Exact frameworks to say the extremity in the accident is a crucial work to vehicular systems. This analysis work initiates representation in choosing many important parameters and to put up a framework for grouping the extremity of injuries. These frameworks are prepared by many machine ML techniques. Supervised learning techniques and unsupervised ML techniques are executed on set traffic accident values. The important point is to find the correlation among various types of the accidents with the type of the bruises. The survey of this study points out that unsupervised learning techniques could be a favorable aid to know the extremity and severity caused in an accident injury.

Keywords: Machine Learning, Traffic Accident, Unsupervised Learning, Eclat Algorithm, Injuries.

Abstract: Metaphoric expressions are regular in ordinary language. Metaphor identification is important in natural language processing since it comes in several common tasks. Conventional methodologies, like phrase-level metaphor identification, identify metaphors with word pairs, where an objective word whose metaphoricity is to be distinguished is given ahead of time. However, such objective words are not featured in genuine content information; a more up-to-date approach is sequential metaphor identification. Also, most of the conventional methodologies use restricted linguistic context to identify metaphors like by considering a single verbs argument or the sentence containing a phrase. Since context has an inevitable role in identifying metaphors, the wider context is critical in metaphor identification tasks. In this work, a novel neural sequential metaphor identification system, constrained to semantically correct input and considers a wider context area, has been proposed. The system is tested on two widely used metaphor datasets: VUA and MOH-X and outperforms the previous approaches. Keywords: BERT, BiLSTM, Context- dependent, Metaphor.

Abstract: Pattern identification in texts refers to the identification of repeating texts from set of sentences. Patterns are automatic discovery of regularities present in data through the use of computer algorithms. There is limited research carried out for such identification of patterns. The input to the system is first gathered and is then cleaned to remove the noisy elements present in the data. After cleaning the data, the similarity of the elements present in data is identified. The similar elements are grouped into segments and these segments are then analyzed to check whether repeating elements are present in the data. From this data, the necessary repeating insights are extracted which are the resulting pattern. The detection of patterns of any real world entity or substances of text or any other source is a difficult task for humans as well as for machines. It may be a time-consuming task if the detection of such patterns are done by the human. Also, human supervision is unable to deal with large quantities of data as there will be 'n' number of patterns. Therefore, automatic identification of such repeating texts has become an urgent need. For identifying patterns, context of text accompanying repeating sentences is very useful. In this work, pattern identification of text in semantics level is addressed by using ontology. After identifying similar sentences, the Sequence-to-sequence model is developed to identify patterns present from set of sentences given as input to the system.

Keywords: Pattern, Seq2seq, Ontology, Domain-Specific Words.

Abstract: In social media platforms like Twitter, You Tube etc. generates huge amount of user contents daily. In order to detect the user behaviour and interests keyphrases plays a crucial role. Keyphrases are short text pieces that can quickly express the key idea of source post. In case of extracting the main points from articles or documents the keyphrase generation is also important. Here proposes a methodology by generating keyphrases from the users post with the help of neural network representations and also generates the missing keyphrases which is the drawback of the previous systems. That is key phrase generation aims at predicting both present and absent keyphrases for user’s posts. The proposed method is a sequence to-sequence (seq2seq) based neural keyphrase generation frame work. Also, this model is topic- aware for avoiding sparsity in social media languages. Here also discussing about key phrase generation using BERT which is a latest technology in today’s world.

Keywords: Keyphrase, Seq2seq, Bert, Topic-Aware.

Abstract: Data, is the statistics and facts collected together for reference or analysis. The available data forms like numbers or text, and as facts stored in an individual's mind, or as bits stored in electronic system. Text is the most the basic portrayal of information. Natural Language processing is the emerging field in computer science and text classification is the process of assigning tag or label to the text. It is one of the fundamental task in NLP with many applications such as topic detection, intent detection, sentiment analysis, etc. Text classification can be done based on the different aspects, on which different works have been done. In this work, a novel context aware text classification system has been proposed which is built using a keyword extractor. The keyword extraction is the process of extracting relevant words or phrases from the text. Keyword extraction helps to find out the sense of the important words present in the text, and which subjects are being discussed. The extraction of the keyword is based on semantic knowledge which is available in taxonomies. These keywords are used for classification which is built using deep learning. The results show that the generated result is meaningful and context dependant in most of the cases.

Keywords: Keywords, Taxonomy, Pagerank.

Abstract: Today’s modern life is completely based on Internet. Now a day’s people cannot imagine life without Internet. From last few years people share their views, ideas, information with each other using social networking sites. Such interchanges might include diverse sorts of substance such as text, image, audio and video data. One fundamental issue in today On-line Social Networks (OSNs) is to give users the ability to control the messages posted on their own private space to avoid that unwanted content is displayed. Up to now OSNs provide little support to this requirement. Hence Online Social Networks should be extremely secure and should protect the individual’s privacy. The Online Social Network provides the security measures but they were limited. While Socializing the user can access the profile of other members which are involved in social sites and even share data such as images, text, videos etc. One critical issue in user wall is to give users the capability to control the messages posted on their own personal space in order to avoid unwanted content to be displayed on their wall. To overcome this problem, we propose a system allowing OSN users to have a direct control on the messages posted on their walls. This is achieved through a flexible rule-based system, that allows users to customize the filtering criteria to be matter-of-fact to their walls, and a Machine Learning based soft classifier automatically labelling messages in content-based filtering. Keywords: On-line Social Networks (OSNs), Machine learning, short Text Classifier, content-based-filtering

Abstract: In agricultural field the crop yield prediction is significant and also a challenging task. Earlier, yield prediction was performed by considering farmer's experience on particular field and crop. This always requires involvement of farmer in prediction of crop yield which is not possible always. To overcome this challenge automated way to predict the yield of crop is proposed. In this work comparative analysis of crop yield prediction model using Machine learning techniques for the selected region i.e. district of Tamil Nadu in India. The machine learning algorithms like K-Nearest Neighbour, Decision Tree (Regression), Support Vector Regression were implemented and the performance of crop prediction model was analysed. The experimental analysis suggested that the performance for Support Vector Regression is better than K-Nearest Neighbour, Decision Tree, Support Vector Regression models.

Keywords: Machine Learning, K-Nearest Neighbour, Decision Tree, Support Vector Regression, Crop Yield Prediction.

Abstract: The human blood consists of the RBCs, WBCs, Platelets and Plasma. Blood is a health indicator therefore segmentation and identification of blood cells is very important. Complete blood count (CBC) includes counting of all the cells which determines persons health. The RBC and WBC counts very important to diagnose various diseases such as anemia, leukemia, tissue damage etc. Old conventional method used in the hospital laboratory involves manual counting of blood cells using device called hemocytometer and microscope. But this method extremely monotonous, laborious , time consuming and leads to the inaccurate results due to human error. Also there are some expensive machines like analyzer, which are not affordable by every laboratory. The objective of this paper is to produce a survey on an image processing based system that can automatically detect and count the no of RBCs and WBCs in the blood sample image. Image acquisition, pre-processing,  Image enhancement, image segmentation, Image post-processing and counting algorithm these are six steps involved in an image processing algorithm.    

Abstract: Over the past years, automation gets involved in various industrial operations and in decision making too. Some industries take steps to implement full automation over the manufacturing, process and control plants. This paper aims to present the various emerging technologies are adopting and using for the industrial automation. Nowadays, engineering fields are equipped with advanced sensors, machine vision, robotic platform and innovative instruments for fully automated systems. According to Industrial Trade Administration (ITA) reported that the annual global automation expenditure is expected to increase to over $300 billion by 2020. Furthermore, the spend is expected to increase to over $600 billion in the coming years as automation systems become more interconnected within process operations. This paper explores the availability and presence of technology globally in various sectors Keywords: Industrial Automation, IoT, Robotic Platform, Multi touch technology, Virtualization.

Abstract: RFID is a versatile and trending technology which is used in many real time applications. In this proposed work, RFID system is a microcontroller-based system that reduces the man power and dispenses the accurate amount of fuel. Also, if the customer tries to swipe the unauthorized card, the RFID system rejects the card. In this way, the system is very secured. For the RFID operation, the frequency of the reader ranges from 125 KHz to 2.4 GHz.

Keywords: RFID, Microcontroller, Dispensing system, Automated Petrol Pump system.

Abstract: Grammatical Error Correction (GEC) in English language is a challenging topic among the emerging works. GEC is a process of converting the erroneous sentences to a corrected sentence by using Sequence2Sequence (Seq2Seq) method. Usually the system focused on correcting the grammars based on the 20 rules in English language and it includes punctuation, grammatical and word choice errors. Deep learning method is used to work behind the system. Long Short-Term Memory (LSTM) Encoder - Decoder model is used in the conversion of incorrect sentence to a grammatically corrected sentence. This is a supervised learning system which includes incorrect and corrected sentences in the GEC dataset and thus gives better results.

Keywords: GEC, Deep Learning, seq2seq, LSTM.

Abstract: Social media platforms are globally connected inter network through which users can interact with each others. Twitter is one of such social media platform. Because of the globally connected nature of social media platforms, once a user post something on social media it may reach out to everywhere around the world. This is the advantage and disadvantage of social media platforms. Some people use this feature to promote their products and needs, the legitimate users. Some of them use for spreading unwanted and illegitimate contents, the spam users. This project aims for detecting and classifying legitimate and illegitimate accounts on Twitter based on different user activities. The user activities include tweets of a user, friends count of user, followers count of user, list count of user etc. To build the model data of users is collected from Twitter API. And to label the dataset collected from twitter unsupervised machine learning algorithm like k-mean clustering technique is used for this project. And for the detection and classification of spam users this project use a machine learning model and this model performs better than other machine learning algorithms such as Random Forest, Decision Tree and Multinomial NB. And this work also capable to work on real time twitter data so that users can easily identify the spam users on real time.

Keywords: Machine Learning, Twitter API, Labelling, Classification

Abstract: This document gives formatting instructions for authors preparing papers for publication in the Proceedings of an International Journal. The authors must follow the instructions given in the document for the papers to be published. You can use this document as both an instruction set and as a template into which you can type your own text.

Keywords: Arduino Uno, temperature Sensor, pulse sensor, Accelerometer, piezo electric sensor, node mcu, gps, gsm.

Abstract: Agriculture is one of the major sources of income in India. Agriculture faces lots of challenges, farmer needs to handle all the challenges. For example, farm maintenance, different diseases on crop and infelicitous management of pesticides. Diseases in plants results in reducing of yield in the plant. Hence detection and identification of diseased plant are important task with continuous monitoring of the crop and apply appropriate pesticides for the better yield of the crop. Generally, whenever a plant(s) is infected with mosaic virus, its symptoms are usually seen on leaves like dark spots, black traces, etc. The amount of infection affected to the plant can be approximated by analyzing the infection symptoms on leaves. To address this problem, there is a need to develop a system which continuously monitors the crop and detects the diseased plants and take appropriate action automatically. Hence, we proposed an automated system called “Spray-Robo” which detects and reacts for the diseased plants using image processing technique and robotic mechanism. Spray-Robo will be able to spray pesticides for the diseased plants with appropriate quantities.

Keywords: Spary-Robo, Image Processing, Identification of Diseased Plant, Spray Pesticide

Abstract: Twitter is a social networking and microblogging service on which users interact with messages. It is one of the best examples of microblogging and has a 280-character limit for a tweet. Registered users on twitter can post, like, and retweet tweets, but unregistered users can only read them. It is used not only to communicate with friends but also to share real-world events. Event detection is a major research area in text mining. Social media data (specifically, twitter data) is easily available. Twitter is a major source of information about real-world events. In twitter hashtags and word limit ensures the concise representation of real-world events. In this work, a segmentation based model is used to detect real-world events. Hashtags are the most important segment in the event detection process. The method of event detection is to split each tweet and hashtags into segments. From these segments extract the bursty segments. Then bursty segments are clustered based on the similarity measures. Finally, these clusters are summarized to produce final event. The key features of the event detection system are hashtags, retweet count, user popularity, and follower count. Here hashtags are more important and giving more weight to improve the performance of the model. The event detection system uses a Wikipedia title file for indexing the segments. Events2012 dataset is used for event detection. The results show the events are real-world in most of the cases.

Keywords: Microblogging, Hashtags, Natural language processing, Segmentation.

Abstract: Smartphones have become a part of our daily lives. Thus, they have become a big target for attacks such as malware. While smartphone malware is very popular in their search community, charging attack are often ignored by the literature. As public charging stations are common, the charging attacks will become a big concern and be used to compromise user’s privacy. Vulnerability of smartphone charging and introduce juice filming attacks that can steal sensitive information by recording screen activities during charging. The display of smartphones can be leaked through a standard micro USB connector using the Mobile High-Definition Link (MHL) standard or the iPhones' lightning connector, making our attack feasible in both Android OS and iOS. Furthermore, the implementation of prototype called Juice Caster, which can automate the whole adversary procedure including video-capturing user’s inputs, dividing videos into images extracting texts from images with OCR (Optical Character Recognition) technology.

Keywords: Mobile security and vulnerabilities, Android and iOS security, Video recording, charging attacks.