VOLUME 8, ISSUE 3, MARCH 2019

Abstract: In the current trends every organization manages work and its data online. Even though e-Commerce website maintaining data online in a distributed form. Online approach is very useful to collaborate with consumer and seller without any dependency of place and time. Every consumer can select product with any brand without wait for a time and produce the order for purchasing. Most of purchasing the product is done by using the website that produce some navigational or access pattern. This access pattern is utilized to produce some access rules. The projected Constraint based Closed Sequential Pattern Mining by using Self-Organizing Map Clustering (CBCSPMSC)approach principal comprises specific profile and GRC constraints for filtration of data among the duration and occurrence of article gap. Now applying closed pattern method for underrates the number of rules generation and execution time. At last SOM clustering method is implemented so that each item belongs the cluster for partial database scan not whole data with fewer execution time.

Keywords: Compactness, Data Stream, Data Mining, Web Usage Mining ,Gap, Personalization , Closed Pattern, Sequential Pattern Mining, NN-SOM Clustering

Abstract: Wireless communication plays a significant role in our life as it provides mobility and flexibility as well as scalability. Handoff delays make a serious problem. A lot of research has been done in last few years to reduce the handoff delays occur in the different levels of wireless communication. Due to the mobility of devices handoff is an important aspect in WLAN and cellular communications and in WLAN this aspect is much more important due to limited range of APs, WLAN also provides sufficient bandwidth for real time streaming services. In the literature a number of handoff schemes have been proposed to reduce the handoff latency and support fast handoff in IEEE 802.11 wireless networks. In this article, we review these fast handoff schemes and analyze their advantages and disadvantages qualitatively. Our aim is to make available groundwork for future research on reducing the handoff latency for Intelligent Transport Systems (ITS) in vehicular scenarios and give emphasis on requirement of fast handover for seamless connectivity. i comprise here various techniques to reduce handoff delays.

Keywords: Intelligent Transport Systems (ITS), Wireless Local Area Networks (WLANs), Internet Protocol (IP), Inter Access Point Protocol (IAPP)

Abstract: Online interpersonal organizations have now turned into the most famous stages for individuals to impart data to others. Alongside this, there is a genuine danger to people's security. One protection chance originates from the sharing of co-possessed information, i.e., when a client shares an information thing that includes numerous clients, a few clients' security might be imperiled, since various clients by and large have distinctive suppositions on who can get to the information. Step by step instructions to plan a shared administration component to manage such a security issue has as of late pulled in much consideration. In this paper, we propose a trust-based instrument to acknowledge community oriented security management. The trust esteems between clients are utilized to weight clients' feelings, and the qualities are refreshed by clients' protection misfortune. In addition, the client can make an exchange off between information sharing and security safeguarding by tuning the parameter of the proposed component. We define the choosing of the parameter as a multi-furnished desperado issue and apply the upper certainty bound arrangement to tackle the issue. Reenactment comes about exhibit that the trust-based instrument can urge the client to be thoughtful of others' protection, and the proposed crook approach can bring the client a high result.

Keywords: Protection, proposed, security, clients

Abstract: IoT refers to the infrastructure of connected physical devices which is growing at a rapid rate as huge number of devices and objects are getting associated to the Internet. Home security is a very useful application of IoT and we are using it to create an inexpensive security system for homes as well as industrial use. The system will inform the owner about any unauthorized entry or whenever the door is opened by sending a notification to the user. After the user gets the notification, he can take the necessary actions. The security system will use a microcontroller known as Arduino Uno to interface between the components, a magnetic Reed sensor to monitor the status, a buzzer for sounding the alarm, and a WiFi module, ESP8266 to connect and communicate using the Internet. The main advantages of such a system includes the ease of setting up, lower costs and low maintenance. 

Keywords: Arduino Uno, ESP8266 (Wi-Fi Module), Reed Sensor Module, Bread board and Jump Wires

Keywords: Image processing, Machine learning, Recommendation system, Collaborative Filtering, Ingredients, CNN

Abstract: To improve network security different steps has been taken as size and importance of the network has increases day by day. At that point opportunity of a system attacks increases. Network is for the most part assaulted by intrusions that are distinguished by system intrusion recognition framework. This paper attempts to build up an intrusion location framework which uses the signature and identity of the intrusion for distinguishing various types of intrusions. Here random forest tree algorithm was used for finding the patterns in the input data. In this work use of Gini index was done for the decision tree construction in recursive manner. Experiment was done on NSL-KDD dataset which was real. Comparison was done with latest RNN (Recurrent Neural Network). Result obtained after analyzing this system improved precision value by 12.06%, while recall value by 1.15% and accuracy values were improved by 6.87%. Keywords: Clustering, Gini-Index, Intrusion Detection, Random Forest, Pattern generation

Abstract: Propose system tend to concentrate on modeling user-generated review and overall rating pairs and aim to spot linguistics aspects and aspect-level sentiments from review knowledge similarly on predict overall sentiments of reviews. We tend to propose a completely unique probabilistic Supervised Joint Side And Sentiment Model (SJASM) to upset the issues in one go underneath a unified framework. SJASM represents every review document within the style of opinion pairs, and might at the same time model side terms and corresponding opinion words of the review for hidden side and sentiment detection. It conjointly leverages sentimental overall ratings, which regularly comes with on-line reviews, as superintendence knowledge, and might infer the linguistics aspects and aspect-level sentiments that aren't solely purposeful however conjointly prognosticative of overall sentiments of reviews. Moreover, we tend to conjointly develop economical illation methodology for parameter estimation of SJASM supported folded Gibbs sampling. We tend to judge SJASM extensively on real-world review knowledge, and experimental results demonstrate that the planned model outperforms seven well-established baseline strategies for sentiment analysis tasks. We build social network web site on that user post with attaching files, thereon file topic name match with product name then suggest to user on e-commerce web site.

Keywords: Supervised Joint Side And Sentiment Model (SJASM), Gibbs Sampling, Sentiment Analysis, Aspect-Based Sentiment Analysis, Probabilistic Topic Model

Abstract: The whole project is based on the idea on length of time it takes a capacitor to charge, based on this charging time the distance and other related values and coordinates are measured and the motion path is calculated. The main objective of the project is Touchless 3D tracking, as the name suggests the project focuses on detection of 3D motion without any external touch and replicate the same motion on our computer screen. That is, the computer should be able to detect the entire motion path of the desired object. The Tracking takes place in 3 Dimensional field that is x,y and z, that is the depth is also taken into consideration. Each axis acts like a capacitor when the voltage is applied to it. As our hand approaches the plate our body electrically couples with the plate and changes its capacitance. The higher the capacitance the longer it will take for the capacitor to get fully charged. The software on the Arduino measures the time it takes to charge the plates. The change in the charge time corresponds to the hands distance from the plate. The Whole project is based on Arduino Micro-controller, which is an open source microcontroller. The project will be implemented on Arduino platform, which provides direct interaction with the Arduino micro-controller. The simplicity of this 3D tracking mechanism will show us, what all are the possibilities for future and what all can be achieved using some simple and logical techniques.

Keywords: Arduino, Touchless Interface, Micro Controller, Capacitive Sensing

Abstract: Regression Analysis one of the important techniques from data science, used for data analysis. In regression analysis the curve is designed so that the distance between curve and each point will be minimal. The association between or among dependent and independent variable is plotted with the help of this technique. Process is to observe the data, identify the relationship and trace the path for future so that the different values can use that path as a guideline. There are different types of regression based on number and nature of dependent and independent variable. This research article covers all mostly used Regression algorithm their properties usage; Based on the information about these algorithm, decision of selection of suitable algorithm can be made very easily. There different regression models are available, based on the applicability and frequency of use top 4 algorithms are considered for discussion. To support the research the mathematical equations and identity graphs are mentioned.

Keywords: Regression Models, Types of Regression, Classification and Regression, Selection of Appropriate Regression Model

Abstract: If you aren’t aligned with the human need, you are just going to build a very powerful system to address a very small or perhaps nonexistent problem “. The vast amount of complex healthcare data yields many opportunities for us, and that can be achieved through effective analysis of data. More specifically, big data analytics has the potential to improve care, save lives, and lower costs by discovering associations and understanding patterns and trends within the data. Proposed system is an online consultation project in which symptoms of a disease are fed into the system, and it predicts the chances of having the disease by using machine learning. Thus, patients will get speedy diagnosis and quality of healthcare wills drastically improve.

Keywords: Healthcare, Machine Learning, Mobile Health, Cloud Computing

Abstract: One of the definition of blurring with respect to Laplacian is decrease in the variance. Blurring with respect to frequency domain means low frequency where high frequency represents edge. It occurs either because of motion or out of focus parameter. Blur is classified in two types (Local and Global Blur). In this research paper, both the blurred and unblurred images are passed through Fourier transform which calculates the high frequencies as well as low frequencies from the images. In other words, it transforms image from spatial domain to frequency domain. Labels for both blurred as well as unblurred images are chosen as the target i.e. 1 for blurred and 0 for unblurred. These set of images are trained using both support vector machine as well as logistic regression which are tested on the real time images which detects the blur from the images. Trained Model run over the real time image and captures the blur from it. Both state of art method i.e. support vector machine as well as logistic regression is compared in the terms of performance parameters and it is concluded from the results that later winds over the former in both accuracy as well as receiver operating characteristic curve.

Keywords: Support vector machine, Logistic regression, binary values, receiver operating characteristic curve

Keywords: Brain cancer, CNN ,OPENCV, Prevention, Classification, Care

Abstract: MPLS is the prime technology used in examine supplier Networks as quick pack forwarding mechanism. It is the tools used in service supplier networks to connect dissimilar remote sites. MPLS can be used to carry any kind of information whether it is layer 2 data such as frame relay, Ethernet, ATM data or layer 3 data such as IPV4, IPV6. MPLS creates two types of VPNs. One is Layer 3 MPLS VPN with Layer 2 MPLS VPN. In Layer 3 MPLS VPN, customer forms IP national distribute with Service Provider device. In Layer 3 VPN routing is performed between client edge device and Provider Edge device. Layer 2 VPNs behave like the consumer sites are connected using a Layer 2 Switch. Various L2 MPLS VPN techniques are Virtual Private LAN Service (VPLS), Virtual Private Wire Service (VPWS), and Ethernet VPN. This paper gives an indication of all these L2 and L3 MPLS VPN technologies.

Keywords: MPLS, VPLS, VPWS, Atom

Abstract: Today several organizations are in a process to adopt IPv6 addressing scheme. Since IPv6 is not backward compatible with IPv4, both IPv4 and IPv6 are going to work in parallel till IPv6 is fully deployed .Security in IPv6 is mandatory, but in IPv4 security scheme is optional. IPv6 packets are travelling through IPv4 network in transition mechanism. The IPv6 packet faces several security threats while it travels through IPv4 network. The transition remains an issue today for many enterprises which is a tedious and error prone task for network administrators. Routing protocols route the packet with their own metrics. The network administrator could not implement his own routing methodology in a routing process.In this project we are taking IPv6 network in GNS3 simulation tool and implement the IPSec scheme. Unauthorized routers are introduced in our network and we have to ensure that services for them are denied by our network routers. In the same network we are implementing the Policy Based Routing (PBR). Routers normally forward packet to destination addresses based on information in their routing tables. By using policy based routing we can implement policies that selectively cause packets to take different paths based on source address, protocol types or application types. Therefore PBR overrides the routers normal routing procedures. By implementing both the schemes in our IPv6 network, the IP packets are delivered safely and also take the path as desired by network administrator.

Keywords: Policy Based Routing (PBR), IPv4 network, IPv6 network, Quality of Service (QoS)                                                                                                                                                          

Abstract: Traffic Engineering is a topic which ensures the best possible use of the resources. Now to support traffic engineering in our today’s network, Multi Protocol Label Switching (MPLS) is being used which is very helpful for reliable packet delivery in an ongoing Internet service. During the delivery of packets from one location to another, it ensures high transmission speed, efficient use of bandwidth and lower delays. MPLS is a process which depends on Label Switching for taking forwarding decisions. Label is created for every route in the routing table. This paper presents a general idea of the MPLS technology and how it is faster and better than traditional IP routing.

Keywords: Multi Protocol Label Switching (MPLS), Internet Service Providers (ISP), IGP, RSPV, OSPF

Abstract: MPLS technology is being widely adopted by service providers worldwide to implement VPNs to connect geographically separated customer sites i.e., Inter-provider VPN network. In this project we first briefly describe VPNs which are behind the scope of secure private MPLS connections such as several VPN deployments emerged from the sudden growth of requirements. We then discuss about the requirements of interconnections from customer end to service provider in one's perspective. We then propose and discuss the methods used for deployment options from service providers point of view. The usage of peer-to-peer model had overcome the drawbacks of the Overlay model and paved way for optimal data transport via the Service Provider backbone.  Hence, the Service Providers would actively participate in customer Layer 3 routing. Customer Layer 3 routing information is carried between routers in the provider network and customer network. Layer 3 VPNs implemented on MPLS backbone of service providers are referred as “MPLS L3 VPNs” In this paper we present a novel method of communication among branches or partner branches of an organization each of them situated at distinct geographical areas with absence of the same ISP in every area. We came up with an idea of designing an Inter-provider network i.e., connecting multiple ISPs with the private network mechanism which provides global reach ability. It deals with the security issues confidently and provides the replacement of Internet in Private/Public organization

Keywords: Multi Protocol Label switching (MPLS), Digital Subscriber Line (DSL), Virtual Private Network (VPN)

Abstract: Salesforce is a CRM Platform provides various software solutions and help administrators and designers to improve and hand out routine software. Salesforce.com is based on multi-tenant architecture. This means that several clients part common technology and all run on the latest release. We don’t have to worry about the application or infrastructure upgrades – they happen automatically. This helps your institute emphasis on modernization rather than managing technology.  In this project we are Building a app that lets conference attendees to view the session schedule, and absorb more about conferences and speakers. we are Creating a data model for a conference management application using Apex classes and work with the Sales force Object Query Language (SOQL) to implement the business logic of the  application, such as making sure speakers are not double-booked.

Keywords: Salesforce Object Query Language (SOQL), National Institute of Standards and Technology (NIST)

Keywords: Routing Information Protocol (RIP), Routing Protocol, GNS 3 software tool, Open Short Path First(OSPF), Enhanced Interior Gateway Routing Protocol (EIGRP)

Abstract: A vast amount of data is generated in the fields of healthcare and diagnostics, doctors have to make a direct contact with patients to determine the wounds, injuries and diseases by which the patient is affected. This paper highlights the application of classifying and predicting a specific disease by implementing the operations on medical data generated in the field of medical and healthcare. The proposed system can solve difficult queries for detecting a particular disease and also can assist medical practitioners to make smart clinical decisions which traditional decision support systems were not able to. The decisions taken by medical practitioners with the help of technology can result in effective and low cost treatments. In this paper, data mining methods namely, Naive Bayes and J48 algorithms are compared for testing their accuracy and performance on the training medical datasets. 

Keywords: Prediction, Classification, KNN, Naïve Bayes, J48, neural network

Abstract: Internet of Things which is a network of physical objects plays a vital role in the near future. The idea behind Internet of Things is that Things instead of humans can make use of Internet to communicate. IoT can be used to ease the life style of people with better facilities such as smart cities, homes, hospitals that give a better service than the traditional one. Analysis of applications that use IoT is very much needed  to improve the quality of life style of people. Keywords: Internet of Things, Motes, WSN Nodes, Smart Cities, Smart Homes, Smart Hospitals, Ontology

Abstract: Over the last few years, there has been the remarkable improvement of wireless network systems (WENS), IT systems and sensor networks. Solid bulk data transfer is a WENS modular construction imperative that supports various applications, such as remote software update, video properties. Current reviews regularly develop the facilities to improve the multi-hop pipeline network with the time spread of open data. In any case, the transmission system created protocols and structure less along these lines initially received, posed enormous difficulties for the productive diffusion of organized data. In this study, we explore the problem of mass dispersion of organized mass data. Specifically, we propose reliable transmission outside of the application and encode impulsive tools to transmit packets however many as it would be wise in any space transmission. Consequently, the resulting transmission protocol can fully utilize any transmission aperture and proliferate on-line information as fast as it would be cautious. Performance is achieved by both tested and recreational tests show that, contrary to the state of the art protocols, ULTRA can significantly improve the performance of slower dispersion delay dispersion in 34.8%. Keywords: High­ Performance, Embedded Systems, Multiple Processors, progress, programming, Digital Signal Processors, DSPs, memory design, architecture, memory, information, improvement, DMA, technology

Abstract: Data mining could be a method of extracting desired and helpful data from the pool of information. Cluster in data processing is that the grouping of information points with some common similarity. Cluster is a vital aspect of information mining. It simply clusters the information sets into given no. of clusters. Various no. of ways are used for the information cluster among that K- suggests that is that the most generally used cluster formula. During this paper we've briefed within the kind of a review work done by completely different researcher’s victimization K-means cluster formula. As a partition primarily based cluster algorithmic program, K-Means is wide employed in several areas for the options of its efficiency and simply understood. However, it's documented that the K-Means algorithmic program could get suboptimal solutions, looking on the selection of the initial cluster centers. During this paper, they propose a projection-based K-Means low-level formatting formula. The planned formula initial use standard mathematician kernel density estimation technique to search out the extremely density information areas in one dimension. Then the projection step is to iteratively use density estimation from the lower variance dimensions to the upper variance ones till all the scale square measure computed. Experiments on actual datasets show that our technique will get similar results compared with different standard ways with fewer computation tasks.

Keywords: Data Mining, Data Sets, Clustering, Clustering Method, K-means Clustering, Unsupervised Learning

Abstract: Nowadays petrol pump are operated manually. we required more man power and it is time consuming process. So we implemented automatic fuel filling system by using GSM and AT mega 328. This system can improve the fuelling process in order to make it easier, reliable and secure.  This system aims at safe and secure fuel delivery, ensuring that the customer gets the equivalent amount of fuel for what he/she is paying, hence successfully eliminating any sorts of malpractices that might occur at a various fuel stations. In this paper, we developed an automated fuel station management system which can overcome the disadvantages of present system. The result of this methodology places cashless transactions and authenticated system . It will also help to prevent corruption at fuel stations and can help fuel stations to become faster and less time consuming.   Normally in petrol bunks there is a Human to Human interaction. Our project is to overcome this phenomenon by bringing the interaction between Human and Software. By following mechanism we can avoid all the errors that a human does and also avoid the cheating activities.

Keywords: RFID, Raspberry Pi, GSM and AT mega 328

Abstract: The occurrence of the natural disaster is a big lose for human life and property. Here we introduce a embedded system using ATmega 328 called black box which have water level sensor that helps in the rescue mission. If any disaster like flood occurs sensor senses the water level, whenever it exceeds  the threshold value the black box system gets ON  and further the alert message is send to the authority. The system is provided with a mobile charger ,light and a hooter. Black box system is powered with solar panel. This project is used for real time purpose for saving lives and property. A GSM wireless communication technology is used in the system thus no network issues arise. 

Keywords: Embedded System, Microcontroller ATmega328, GSM, Data Modem, Flood, Rescue

Abstract: This paper is focused on the protection of crops from the wild animals which often damages the crops by self- feeding or simply by running over the field and crushing the crops. In this paper, Raspberry Pi is used to detect and track the motion of the animals. Using image processing techniques the animal is detected precisely and a tranquilizer gun is used with sedatives to control the animals. Also the information would be passed on to the nearest forest officers and villagers selectively, thereby reducing the crop damages and also efficiently conserve the wildlife which often gets affected from the existing methods like electric fences or other human weapons. 

Keywords: Raspberry Pi, Wild Animals, Image Processing, Tranquilizer Gun

Abstract: Big data is growing exponentially, and along with that is the technology and new algorithms being developed. With the accumulation of big data, Machine learning and Artificial Intelligence are getting implemented into newer spheres. One of the fields in the sphere is Healthcare and Biomedical. Early disease prediction, patient care, and community services can be made possible using this accumulation of big data, with the help of Machine Learning. Though predicting diseases using Machine Learning can be implemented, but the accuracy of prediction is reduced due to incomplete medical data. Moreover different regions have different chronic diseases depending on the geographical conditions and community, an outbreak of disease. To overcome the problem of incomplete data, an approach of the latent factor model is used to reconstruct the missing data. In this paper, we propose a new Convolutional Neural Network which is based on Multimodal Disease Risk Prediction algorithm (CNN-MDRP) with the help of structured and unstructured data directly from hospital and research institutes. None of the existing work is focused on both data types in the field of medical big data analytics. Compared to several previous prediction algorithms, our prediction algorithm has the prediction accuracy of approximately 95% and speed faster than that of CNN-UDRP, a Uni modal Disease Risk Prediction based prediction algorithm.

Keywords: CNN-MDRP, Big Data, healthcare, Naive Bayes Algorithm, Decision Tree algorithm, K-nearest neighbor Algorithm

Abstract: The Indian Penal Code (IPC) is the main criminal code of India. It is a comprehensive code intended to cover all substantive aspects of criminal law. Majority of people are unaware of the legal systems prevailing in the country and also of their constitutional rights. Even though people are aware of it, they are not in a situation to afford because of their economic and social backwardness. They are in a helpless situation to engage the services of legal counsel, which has become a costly affair. This project intends to overcome all these problems. Through this we can improves the people’s awareness about the Indian law’s as well as this system act as a mediator between the clients and the lawyers. This also provides online support during the emergency situations like police checking, petty cases, warrant issue, etc. People and lawyer can add quotes as well as anyone can react to the quotes. Legal documents and judgments (past case histories) from different courts are available for the lawyers which would be helpful for lawyers for practicing and this facility is implemented using data mining technology. 

Keywords: Data Mining, Information Extraction, Data Base Searching, Video Call

Abstract: In this paper, pick and place robotic arm is designed and implemented. This robotic arm is based on android application controlled for remote operation. In this paper, commands are sent to the receiver to control the movement of the robot either to move forward, backward and left or right etc using android application device. Four motors are interfaced to the microcontroller where two motors are used for arm and gripper movement of the robot while the other two motors are used for the body movement. The android application device transmitter acts as a remote control that has the advantage of adequate range, while the receiver end Bluetooth device is fed to the microcontroller to drive DC motors via motor driver IC for necessary work. Remote operation is achieved by any smart-phone/Tablet etc., with Android OS; upon a GUI based touch screen operation. This system can be enhanced by interfacing it with a wireless camera so that the person controlling it can view operation of the arm and gripper remotely.

Keywords: Robotic Arm, DC Motor, Wirelessly Controlled Robotic Arm, Android Application Device

Abstract: Image resampling detection is a key strategy in the blind image forgery detection and has been developed a lot in a previous couple of years. This paper surveys the picture resampling detection techniques proposed in the latest years, give comprehensive differences in their performance and uncovers the principle difficulties brought up in a few significant issues, for example, detection of rotating image, reducing noise in the resampled image and improving productivity. Moreover, this paper examines the current expariments and brings up potential hotspots in this field. We accept this review can give some direction for researchers from significant research zones, offering them a general and novel view.

Keywords: Image Resampling, Interpolation, Bicubic, Bilinear, Nearest Neighbor.