VOLUME 8, ISSUE 1, JANUARY 2019

Abstract: The semi-trusted servers in cloud environment may outsource the files of their clients to some low expensive servers to increase their profit. To some extent, such behavior may violate the wishes of cloud users and impair their legitimate rights and interests. In this paper, a probabilistic challenge-response scheme is proposed to prove that the clients’ files are available and stored in a specified cloud server. In order to resist the collusion of cloud servers, common cloud infrastructure with some reasonable limits, such as rational economic security model, semi-collusion security model and response time bound, are exploited. These limits guarantee that a malicious cloud server could not conduct a t-round communication in a finite time. So we proposed a system which will store data on cloud for specify time and then it will again restore automatically on the machine. The research reveals that the use of real time tracking technology in logistics is still at its infancy stage in UK, but with great potential to grow in the future[3]. We start analyzing motivations for cloud computing, providing also definitions and background for the following contributions. Then, we carefully analyze and discuss the properties of a monitoring system for the cloud. Cloud Computing has become an important aspect in today's world as technology has grown past all the boundaries and there is a need to connect resources and users without having physical connection. The high demand for data processing and leads to high computational requirement which is usually not available at the user's end.

Keywords: Pentium IV and Above, Lan, Hard Disk, Cloud Server, Compression, Decompression of a File, Compression Algorithms, Increasing Effective Data Density, Data Storage Space, Resource Usage or Transmission Capacity

Abstract: This Paper explained the performance evolution of ad-hoc routing protocols with shadow propagation i.e. AODV, AOMDV and DSDV in specific simulation situations and observing their conduct in phrases of 3 enormous parameters i.e. packet shipping fraction, and gen throughput in order to discover which one need to be preferred whilst the mobile ad hoc network needs to be set up for the precise duration underneath special situations. After implementing the three routing protocols under different propagation, the different conclusions have been drawn and results are optimized.

Keywords: AODV, AOMDV, NS2, DSDV, Routing

Abstract: In this paper the Application giving out outputs to the user for Nearest Available Car like AC and NON AC. The System is highly reliable as it uses Google map API which are very accurate for User Tracking and same goes for the User to travel his Ride.It also allows cities to develop fully integrated multimodal smart transportation systems. Owner will Display his car whenever he didn’t required to use as well as Track his car using GPS Tracking System. The User has options to select for the places he wants to visit for instance with all Details of Car; the system will ask whether he is searching for the current locality or some other place. The System is very flexible in changing places and makes use of Google maps to display places if the user wishes to within particular distance mentioned by the user considering a fence of geo locations.

Keywords: Smart car, GPS, GSM Module

Abstract: Water needs energy, energy needs water but human development needs both. Their intricate connectivity and dependencies revolve around many elemental issues. Present paper is focused towards deliberating updated overview on prospects of Information and Communication Technology (ICT) applications in water sector, seeing industrial, environmental, agricultural, municipal, domestic, recreational water utility segments. Portrayal of water communities, their existing challenges/risks, budding facets & applicability of ICTs (gadgets, information systems, big-data, models, smart water & energy systems) are deliberated with recently reviewed research results. Useful blend of information is offered on possible ICT amalgamations in water sector for transmuting ill water-systems into smart-water-systems, by achieving higher water productivities. Updated ICT oriented review is provided by uniting key challenges/risks of water applicability segments like transmission losses, leakage detections, energy reduction/recoveries in handling water, integrated water resource management for diverse stakeholders, climate-change, environment, irrigation, rainwater, water-quality, and sanitary aspects. Global initiatives (programs, consortiums, projects, collaborations) on ICTs in water sector are reviewed offering salient potential and forecasts of futuristic ICT based applications in such water segments. Pertinent food for thought is provided to pave road for smarter water management.

Keywords: Water-Security, ICT, Irrigation, Rainwater, Leakage-Control, Efficiency

Abstract: Today ICT era, computer plays a vital role in all organizations. Most of the organization makes computers as compulsory for all because using computing resources to perform a multitude of tasks, including work, research, teaching and learning. As computer system increasing so the amount of energy conservation and the carbon contents are increasing in atmosphere. Measure being taken to reduce the problem superficially called “green computing”. So the IT department uses the most of power which in turn is an excessive amount of overhead for a business as well as a source for toxic waste. Making IT “Green” can not only save money but help save our world by making it a better place through reducing and/or eliminating wasteful practices and using nontoxic materials. This study is briefly explain about Green which include what is Green Computing, Why Green Computing, How to make IT into Green and their approaches, and the implementation of Green computing.

Keywords: Green IT, Green Computing, Recycling, Virtualization

Abstract: Developing countries like India need a significant improvement in infrastructure such as Roads or Highways. These highway constructions are very costly; therefore tolls are collected by citizens. Normally Public private partnerships are made to construct such a huge projects. The money spent on these projects can be regained by collecting toll from the passengers who use the roads. In India toll collection system has problem like escaping toll booths, long queues now only 100 vehicles per hour can pass through toll plaza, if more vehicles arrive it may occur traffic jams. To solve this we are developing geo-fences using GPS. By comparing the position of the vehicle and toll plaza, the owner of the vehicle can be charged from the account.

Keywords: Automated, QR-Code, GPS, Account

Abstract: The stock market has always been a promising avenue for lucrative investing, but most of the profit making depends on the analysis of the current and past market scenario followed by subsequent predictive actions. The currently overblown market economy has given rise to numerous variables which need to be considered before making a beneficial transaction in the stock market. Manually analysing all these variables and affecting factors is too cumbersome and error prone. Therefore, a Machine Learning approach is best suited for analysis of such a seemingly chaotic system. In this project we are using Machine learning, which give a prediction of various aspects of a particular stock or an index, such as future values of the opening price, closing price, index value etc. This will help investors and traders make better and faster decisions.

Keywords: Stock market; Prediction; Machine learning; Artificial neural network

Abstract: This Paper is review on Sentiment Analysis of Twitter data for examining the behaviour of people. Here, we focus on Twitter which is the most popular micro blogging platform. We collect tweets from the Twitter. These Tweets express emotions, feelings and point of view of people towards any particular type of subject. From the view of decision maker this collection of tweets provides Valuable source of information. Through this information we are able to examine the behaviour of people. This paper represents how we can examine the behaviour of people by performing Text Classification, Data mining, natural Language Processing and Sentiment Analysis.

Keywords: Data Mining, Sentiment Analysis, Text Classification, Natural Language Processing

Abstract: This research papers include the eye direction based safety automated navigation system that implemented for the elderly and physically challenged people. The purpose of this navigation system is to avoid the assist required for the physically challenged people. This systems control the motorized wheelchair navigation depends on the eye pupil detection. By the image processing technique (CNN), the sequential images have been capture via Bluetooth specs glass. The system navigate the user to desired directions such as move towards left, move towards right, move forward and stop. Additionally sensors are fixed in front of wheelchair to detect the objects to avoid the faulty navigation. A centralized wireless detector device is also made available in wheelchair for an emergency purpose. A raspberry pi model B is high speed detection kit controls the whole system. Another technique used in this navigation system speech to text conversion. Speech convert to text and then a connection established to raspberry pi model kit. So the system automatically moves by the users given the instruction.

Keywords: Bluetooth, Motorized Wheelchair, Eye Detection, Safety System, CNN

Abstract: The major role of this paper is inspection of fabrics. The fabric defect detection is carried out by manually in textile manufacturing industry .In manual work during which some of fabric defects are very small and undistinguishable. The important problems is inspection of fabric by human eye. Can be identified only monitoring by the skilled labour. The maximum number of the textile manufacturing industry in India performed the defect detection by many number of labour. To increase the fabric quality in industry to introduced the automated system. The automated fabric defect detection system detect defects definitely and identify them based on their physical appearance would naturally improve. To increase the customer satisfaction and reduce the costs associated with the quality. In recent periods many research are done on automated system to detect the fabric defect based on image processing techniques. These techniques takes much amount of time for processing the images to detect the fault. On this research, to overcome the above limitation, introduced the automated system based on deep learning algorithms to detect the defect. The proposed system efficiently detect the fabric defects with improved accuracy compared with other system.

Keywords: Fabric; Defect Detection; Automated; Manual; Textile

Abstract: The data size is growing day by day as it has large use in industrial applications. Due to various data sizes and type, it creates interrupt to find the exact results. The K Nearest neighbor search technique is widely used to find a similar type of data, but it will result in high computational time as the data size increases. In this research, the various widths clustering is introduced to efficiently find the K Nearest Neighbor (K-NN) for a query object from a given data set. This reduces clustering time in addition to balancing the number of producing clusters and their respective sizes.

Keywords: Clustering, K-nearest neighbor, Various widths clustering, high dimensional

Abstract: Rural library information is maintained manually using hard bounded records which were replaced by software that stored records in form of database. It is also enabled with a wide variety of resources such as E-books, PDF and much more using the Internet. The objective of the proposed system is to provide an interactive system that could be incorporated with voice interaction. The voice interaction is carried out with a help of a tool that could build natural voice experiences and offer users a more intuitive way to interact to get their work done. The Voice User Interface models the real human assistant strategy by incorporating artificial intelligence techniques. In specific, Artificial Intelligence makes the library management system more realistic which can adapt to the scalable requirements of a learner. The proposed system is an interactive library system that uses Amazon’s Echo device, which can help users with the regular operation of new book entry, new user entry, issue and return of books and to query for books on specific inputs such as title, author, publisher etc. through voice interaction without any manual assistance. The system’s specific application is the prediction of books matching the combinations of user requirements. The natural language processing is used to provide support to the user and the artificial intelligence uses an algorithm that can help to suggest or to predict the resource available based on the user’s choice.

Keywords: Artificial Intelligence, Alexa Skills set, Human-Computer Interaction, Lambda function, Natural Language Processing

Abstract: A large number of studies have been executed for classifying plant types and identifying diseases of various crops particularly using images. The plant type identification problem is further complicated by common object recognition difficulties mainly due to light, pose and orientation. The present study was undertaken to distinguish the four different Indian rice varieties by utilizing the respective collected features and applying machine learning methods. There are various methods available from simple to complex model. However, the study was carried out with simple models like Linear Discriminant Analysis, Logistic Regression, K-Nearest Neighbours and Naïve-Bayes method. K-NN out performed over the other methods with an Accuracy and Precision of 99.16% and 99% respectively.

Keywords: Distinctness, Rice Varieties, Machine Learning, K-NN

Abstract: This paper entitled “Mobile distribution for personal security” is an application that is used to store data about an individual like Body Mass Index (BMI), personal information and relative information which is secured by high level of authentication that consists of three levels. The user has to cross three levels of authentication levels in order to get access to the application. Even if one of authentication fails the user cannot enter. After successful login the user is taken to the dashboard where he/she can select and use any of the three modules BMI, Personal information and Relative information. 

Keywords: Mobile distribution, Body Mass Index (BMI), Personal Information and Relative Information

Abstract: Diet problem is about finding the best proportion of food ingredients which could cover all daily nutrient needs with affordable cost. So in this paper to recommend the quantity of every ingredients food for a normal human or specific diet patient.to sense blood pressure, sugar level, heart rate, temperature. In order to obtain relevant information on food intake this system will check the data sensed by sensors and if any improvement is required in diet then accordingly the diet will get ordered from a smartphone application. All these techniques are non – invasive meaning the usage doesn’t depend on taking out blood from the body but uses sensors to compute all the 4 parameters.

Keywords: Health Monitoring, Smart Phone, Diet Plan

Abstract: In current scenario due to increase in kidnapping of kids and road accidents, Parents feel much worried about the safety of their children. They always seek a solution to track the presence of their kid once they depart from home to school.  Thus, we propose a SMS based solution to help parents to know their children arrival and time of departure during their school days. Accident detection sensors are implanted on the front surface of the school bus to detect collision with another vehicle on the road. Each student is tagged with a unique code. The code will be recognized by the RFID system. If  the  bus  journey  is  not harmful  from  the  source  to destination, the  GSM  will  send  an  SMS  to  the   management and parents to  inform  its  departure  and  arrival  status of  the

Keywords: Bus Safety System, RFID (Radio Frequency Identification), GSM modem, GPS

Abstract: An increasing number of organizations maintain collections of data about individuals. Hospitals keep medical records of their patients, commerce companies collect information of their clients and web service companies keep track of the preferences of their users. Publication of these data can be useful for research, epidemic studies, commerce development, statistical analysis, etc. It is difficult to keep all the data open on internet, in some cases, to keep confidence and in safe manner where it contains some important or sensitive details.  The removal of directly identifying information (such as Name, Disease) from the published records is not enough to guarantee individuals privacy. The personal data can be misused, for a variety of purposes. Maintaining the privacy for high dimensional database has become difficult. A potential attacker could infer a record’s identity by linking public external information sources (voters registration lists, phone number catalogues, etc.) with a combination of other attributes, like age, gender and postal code, which are not generally unique per person. The main goal is to focus on Privacy and utility of the shared data. l - Diversity is one of the methods to preserve the data which is very sensitive and confidential. Keeping more sensitive data in dataset helps us to preserve the database more safe and secure manner. The advantage of using l-diversity provides a greater distribution of sensitive attributes within the group, thus increasing data protection. This method protects against attribute disclosure, which is an enhancement of k-anonymity technique. 

Keywords: Sensitive Attribute, Privacy Preserving Data, Adult Dataset, l-Diversity Model, Quasi Identifier, Utility, Sensitive Value

Abstract: This system provides data-driven therapy recommendation for the patients. Therapy will be recommended to a patient by analysing the response from previous records which are similar to the given patient’s record. Two methods for therapy recommendation, namely, Collaborative Recommender and Demographic-based Recommender, were proposed. Both algorithms aim to predict the individual response to different therapy options using diverse patient data and recommend the therapy which is assumed to provide the best outcome for a specific patient and time, that is, consultation. Both methods are evaluated using a clinical database incorporating patients suffering from the autoimmune skin disease psoriasis. The Collaborative Recommender proves to generate both better outcome predictions and recommendation quality. However, due to sparsity in the data, this approach cannot provide recommendations for the entire database. In contrast, the Demographic-based Recommender performs worse on average but covers more consultations. Consequently, both methods profit from a combination into an overall recommender system. In addition to the above proposed system, new Model-based Recommender is proposed and it is compared with the above system to check its efficiency. Model-based Recommender is also proposed to enhance the efficiency of recommendation. Data mining brings the concept of artificial intelligence, data structures, statistics, and database together. It is a high demand area because many organizations and businesses can benefit from it. The large volume of daily captured data in healthcare institutions and out-of-hospital settings opens up new perspectives for Data Mining in healthcare. Due to the amount of the data, its high dimensionality and complex interdependencies within the data, an efficient integration of the available information is only possible using technical aids. So, data-driven Clinical Decision Support Systems (CDSS) are designated to assist physicians or other health professionals during clinical decision-making.

Keywords: Therapy Recommendation, Hybrid Recommender System, Collaborative Filtering, Demography Based Filtering, Model Based Recommender, Clinical Decision Support System

Abstract: Mortality rate increases all over the world on daily basis. The reasons for this could be increase in the numbers of patient with cardiovascular disease. When considering death rates and large number of people who suffers from heart disease, it is revealed how important early diagnosis of heart disease. Traditional way of predicting Heart disease is doctor’s examination or number of medical tests such as ECG, Stress Test, and Heart MRI etc. Nowadays, Health care industry contains huge amount of heath care data, which contains hidden information. This hidden information is useful for making effective decisions. Computer based information along with advanced Data mining techniques are used for appropriate results. Neural network is widely used tool for predicting Heart disease diagnosis. In this paper, a heart disease prediction system which uses artificial neural network backpropagation algorithm is proposed. 13 clinical features were used as input for the neural network and then the neural network was trained with backpropagation algorithm to predict absence or presence of heart disease with accuracy of 95%.

Keywords: Heart Disease; Artificial Neural Network; Cleveland Database; Data Mining and Machine Learning

Abstract: In world of automation every individual needs an instant result of any query. As result of which different applications and software are coming into existence. The information is the major aspect of human life. The information is available as documents, database, multimedia resources, etc. Through this project we are extracting appropriate keyword from several documents input. Extracted keywords are matched with available documents. Finally, we recommend appropriate documents to the participants for reference. In document clustering, hundreds of thousands of files are usually examined. Much of the data in those files consists of unstructured text, whose analysis by computer examiners is difficult to be performed. In this context, automated methods of analysis are of great interest. Algorithms for clustering documents can facilitate the discovery of new and useful knowledge from the documents under analysis. We have proposed a more efficient document clustering algorithm. This will enhance the searching and analysis of the document and the best suitable results related to the query loaded will be recommended. In this software, we can add any number of documents. After that we can see all the documents, then after tokenization and clustering, we gain the extracted keywords and their frequency (count of the words) and then recommend the data sets generated to the user. Due to it the computation process of finding the data will be reduced in amount of time and efforts.

Keywords: Keyword Extraction, Stop-Words Analysis and Removal, Stemming of Clusters, Data Clustering Techniques and Document Recommendation

Abstract: Secured data storage and transmission has become an important issue in the digital world due to the increased use of Internet for communication purposes. Information security is becoming more important as the amount of sensitive data being exchanged on the Internet increases. The services like confidentiality and data integrity are required to protect data against unauthorized usage and modification. Visual systems help humans to understand the scenario and improve the understanding capacity. Secure sharing of images helps not only to prevent leakage of data, but also makes it difficult to retrieve the original image in case of the image falling into the wrong hands. In this paper, the cipher feedback mode with hash function has been utilized to encrypt digital images. The proposed method is experimented, tested against security attacks and the obtained results are compared with the existing methods.

Keywords: Image Encryption, Random Number, Modes of operation, Hash Function

Abstract: Sentiment analysis is field of research that can have significant impact on today’s environment. Using social media, such as Twitter, Facebook, and etc. user share their views, feelings in a suitable way, where millions of people express their views in their daily interaction, which can be their sentiments and opinions about particular thing.  Different areas of sentiment approaches do it will be mentioned. This paper is focused on feature based sentiment analysis in which not the sentiment of the whole opinion is analyzed but how particular features of opinion’s subject are seen. Sentiment analysis is the task of identifying Sad and happy emotions, and evaluations.

Keywords: Speaker recognition, Vocal emotion recognition, Sentimental analysis, Emotion prediction, Text mining

Abstract: This app is especially made to ease out waiter’s job in a restaurant. Customers would get in a restaurant, get a table, and then download and open the application, log in/sign up and unlock the menu. The customers will have an option to order any dish of any quantity they want from the menu on their mobile and Bid for it. A special notes section would be in the app for special requirements of the customer. Hence, leaving only one job for waiters that is to only serve food.

Keywords: Menu Card, Digitalization, Food Bidding, Cloud Database

Abstract: Now-a-days, in many cities/towns, we see that the garbage bins are filled with lot of waste which won’t take care by municipal people due to lack of information about it. In this paper, we present a solution for garbage monitoring system using Raspberry Pi and Ultrasonic sensor. A central system made up of Raspberry pi which monitors the garbage bins frequently and collects information about the amount of waste present in the garbage bins with help of ultrasonic sensor placed over it. The collected data will be updated to the municipal officer or to a user who is accessing it via an application in the form of GUI. This system monitors the garbage bins and informs about the level of garbage collected in the garbage bins in a web page or an application. Based on the information collected, the bins which have waste above some prescribed level will be cleaned up.  This solution helps us to keep our city clean as well as to reduce traffic that occurs due to unnecessary travelling of municipal vehicles in the city/town.

Keywords: Smart Dust Bin, Smart Garbage Monitoring System, Internet of Things, Ultrasonic sensor, Raspberry Pi, PHP

Abstract: In this paper, Analysis of Railway Track Crack Detection System is done. The development board has been interfaced to the stepper, servo & dc motors such that the anthropomorphic like structure can be controlled from the buttons at the base of the structure (robotic arm). When signal come to robotic arm, it will activated and then it searching for the code object in storage area when it get confirmation of availability thus it call rover to collect and dispatch that object to its destination of call at the instant of getting signal inbuilt program in arduino controller activate and check signal status incoming signal on terminal via Node MCU module thus programmed the DC motor with fixed degree which have been place in programming for particular objects , end effecter as a claw made up of servo geared motor and spar gear assembly with L293d motor driver.

Keywords: Railway Track; Crack Detection System; Robotic Arm; MPU; Automatic

Abstract: Sentiment analysis (SA) is the automated process of detecting and understanding the emotions conveyed through written text. Over the past decade, SA has gained significant popularity in the field of Natural Language Processing (NLP). With the widespread use of social media and online platforms, SA has become crucial for companies to gather customer feedback and shape their marketing strategies. Additionally, researchers rely on SA to analyze public sentiment on various topics. In this particular research study, a comprehensive survey was conducted to explore the latest trends and techniques in SA. The survey encompassed a wide range of methods, including lexicon-based, graph-based, network-based, machine learning, deep learning, ensemble-based, rule-based, and hybrid techniques. The paper also addresses the challenges and opportunities in SA, such as dealing with sarcasm and irony, analyzing multi-lingual data, and addressing ethical concerns. To provide a practical case study, Twitter was chosen as one of the largest online social media platforms. Furthermore, the researchers shed light on the diverse application areas of SA, including social media, healthcare, marketing, finance, and politics. The paper also presents a comparative and comprehensive analysis of existing trends and techniques, datasets, and evaluation metrics. The ultimate goal is to offer researchers and practitioners a systematic review of SA techniques, identify existing gaps, and suggest possible improvements. This study aims to enhance the efficiency and accuracy of SA processes, leading to smoother and error-free outcomes.

Keywords: Sentiment Analysis, Natural Language Processing Mining, Emotion Classification, Ethical Considerations