Abstract: This Paper mainly focus on data mining techniques and methods as well as how these techniques are effectively used to generate business intelligence in different fields. Data mining can be classified as a process to extract information or knowledge pattern from massive amount of data using various operational sources such as data warehouse, databases and relational databases etc. The paper emphasizes various features of data mining. It also provides effectiveness of data mining in Business Intelligence (BI). Keywords: Data Mining, Business Intelligence, Operational Database, Business Analytics

Abstract: The nodes in networks are constrained with limited power for their vital operations since the connectivity of the network will go down as soon as node energy gets exhausted. Node failures due to power constraints cause system failures and hence minimize end-to-end connectivity in the network. And also  mobility  and  congestion  of  the nodes  lead  to  frequent  link  failures  and  packet  losses  affecting  the QoS  performance  of  the  protocol. In this work, we used an effective proposed scheme, named as Hybrid Optimization System (HOS), for efficient and routing and transmission for wireless networks. Our Hybrid scheme consist of many techniques such as, Dynamic Opportunistic Routing, Multipath Scheduling Scheme and Robust Transmission in networks to overcome above limitations in networks.  Hybrid K-means PSO clustering approach, ’KPSO’, that clusters the network into predefined number of clusters. K-means searches for the best number of clusters, and then groups the network into the selected clusters. PSO selects the best CH for each cluster. KPSO reduced the complexity on the way we are handling the problem and improved the network lifetime. It  provides  effective  load balancing  at  the  node  and  finds  a  stable  path  between  the  source and  destination  meeting  the  delay  requirement.  Simulation  results show  that  the  proposed  protocol  outperforms  in terms  of  packet  delivery ratio,  throughput,  routing  overhead  and average end to end delay.

Keywords: Wireless Network, Hybrid Optimization System (HOS), Internet of Things (IoT)

Abstract:  Automation nowadays has already entered human lives, but in designing a valuable, reliable and usable automatic system, there’s a need to conduct a critical investigation of the case studies in terms of functionality, information analysis, decision and action selection and action implementation. The complexity of automation design requires high logical process, related techniques and real execution. Every single part of the process should be clarified before starting. In this business competitive era, Information and Communication Technology is placed on a  platform  by  many  organizations  as  their  key  indicator for  success. Online data handling and automation service have been a major tool to provide better customers service. This research consists of an outline of the analysis and design process of booking of tickets for performances at the Aliero Community Theatre (ACT) and evaluation of the product deliverables.

Keywords: Software Engineering, Unified Modelling Language (UML), ACT, Ticket Booking, Theatre

Abstract: Nowadays, Cyber-attacks are occurring progressively. Along with this, diversity, size and density of the cyber-attacks are increasing.  When the logs of security devices are analyzed, massive amounts of attack signs are detained. Besides, it is also difficult for humans to evaluate the logs accurately. Therefore, the identification of key data, which can be used to distinguish an attack from this very large data set, is important for both rapid detection of attacks and rapid response of security devices. This study focuses on selection of appropriate features from logs via  machine  learning  and  determining the distinctive  attributes  specific  to  an attack in  the  selection  of  these  data. Based on the selected features, a classification methodology is proposed.

Keywords: Classifiers, Intrusion Detection System, Weka Tool

Abstract: This work gives an evaluation on photo fusion idea based totally on sensing images. The purpose of far flung sensing snap shots fusion is to produce a fused picture that contains extra clean, accurate and complete facts than any single image. A photo fusion set of rules incorporating gamma-corrected is proposed primarily based on Non-Sub sampled Contour let Transform (NSCT).  Firstly, the multispectral picture is converted to Intensity Hue-Saturation (IHS) system. Secondly, the panchromatic image and the aspect intensity of the multispectral image are decomposed. All simulations can be accomplished in MATLAB.

Keywords: Image Fusion, Optimization, Image Processing, Intensity Hue-Saturation (IHS),MATLAB

Abstract: The use of Cloud Computing Services offers significant cost advantages for both the enterprises and end-users. Particularly start-up companies benefit from these advantages; meanwhile often they do not operate an internal IT infrastructure. But are costs associated with cloud computing services are very high as most of them not used in an optimal way. So there is the need for the system/ tool that can give the solution for the most favourable usage of cloud resources to reduce the infrastructure cost on the private clouds like Amazon or Google as big companies are investing billions of money in buying cloud infrastructure. This paper gives a survey of different techniques used by the researchers for price reduction strategy and abstract view of the proposed system that we are going to implement to reduce the infrastructure cost of cloud usage and evaluate the performance of workloads on EC2 instances. 

Keywords: Cloud Computing, Cloud Resource Optimizer, Cost Advantages, Private Clouds, Performance Evaluation, Price Reduction

Abstract: Education plays an important and critical role globally in developing a skilled workforce. For many decades, the use of textbooks has been the traditional method of instruction; however, the emergence and implementation of teaching effectiveness assessment techniques has discovered that most students do not absorb the course content up to the expected level. As a result, many researchers have focused on advancing and improving the existing learning methods, as well as introducing and experimenting with new teaching styles. Recommendations include empowering teachers through various innovative teaching methods (flipped classroom, Collaborative, Problem based Learning.)

Keywords: Innovation, Teaching Methods, Teaching Strategies, Teaching Techniques  

Abstract: Software defect prediction plays an important role in improving software quality and reducing time and cost for software testing. It is one of the most demanding activities of the testing phase of System Development Life Cycle (SDLC). It identifies defect prone modules that require extensive testing and utilizes testing resources effectively. In large software projects, prediction techniques will play a crucial role in aiding developers for speedy marketing of reliable software products. This survey introduces the common defect prediction process used in the literature, discusses methods to evaluate defect prediction performance and compares various defect prediction techniques that includes metrics, models, and algorithms.  It also deals applications involving defect prediction and other emerging topics. Finally, this survey assists to identify challenging issues that creep up during software defect prediction.

Keywords: Software defect, Clustering, Classification, Prediction

Abstract: The classical wireless networks based on TCP/IP protocols will provide better performance to the users when end to end connection is available. However, if the path is not available, then the TCP concept is not applicable. In such a case, Delay Tolerant Networks were applicable. DTN networks are also infrastructure-less wireless networks like Ad-hoc and Mobile Ad-hoc Networks (MANET), where the deployment is not depended on fixed infrastructure such as base station, router for successful data transmission. Messages are delivered from a source node to a destination node via a store-carry and forward based mechanism. In this article, we investigate the performance of two DTNs routing protocols such as Epidemic as well as Binary Spray and Wait (BSNW) together with two social-based routing protocols such as SCORP and dLife conducting Opportunistic Network Environment (ONE) simulator based on average latency by varying node density of every group and buffer size. Simulation result mention that, Binary Spray and Wait routing protocol performs excellent among the considered routing protocols as well as the simulation scenarios. Keywords: Delay-Tolerant Networks (DTN), Binary Spray and Wait (BSNW), Social-aware Content-Based Opportunistic Routing Protocol (SCORP), dLife, Ad-hoc and Mobile Ad-hoc Networks (MANET) Opportunistic Network Environment (ONE)

Abstract: Coronary Artery Disease is the most fatal of all diseases in human beings. The heart muscle, like every other part of the body, needs its own oxygen-rich blood supply. Arteries branch off the aorta and spread over the outside surface of the heart. The Right Coronary Artery (RCA) supplies the bottom part of the heart. The short Left Main (LM) artery branches into the Left Anterior Descending (LAD) artery that supplies the front of the heart and the Circumflex (Cx) artery that supplies the back of the heart. In this paper we start with data acquisition. Any acquired/ given data can be analysed and conclusions drawn accordingly. The acquired or given data usually exists in its crude or raw state. In our assignment, the acquired data consists of many physiological parameters which directly or indirectly lead to this disease. Data pre-processing helps to format the data into useful form by removing redundancy and noise, eliminating missing and non-numerical values, and also by normalization. Data analysis and visualization are carried out to improve the statistical analysis of given data. Logistic regression is carried out on the data since it contains lot of columns with categorical values. Accuracy, precision, and f1 score of the model have been measured. Various conclusions can be drawn from this interdependent data set and can be stored as historical data for future analysis. We then try out various other ML algorithms like Random Forest classifier, SVM and KNN algorithm. We then compare the models with Logistic Regression method.

Keywords: Coronary Artery Disease, Machine Learning, Data pre-processing, Logistic regression, accuracy, precision, and f1 score, data analysis and visualization, Random Forest classifier, SVM algorithm and KNN algorithm

Abstract: These days, heterogeneous networks are one of the most used networks. Customers are using these networks to access various services. However, Handover/Handoff (HO) is one of the major problems which are being faced in every network. Different criteria are used by the researchers in order to execute effective handoff in order to avoid disconnection and interruption in the call. When the ongoing call reaches beyond its base station, the call is needed to be transferred to other BS to maintain its continuity. Thus, HO is initiated and the call is transferred. It is important to perform this process seamlessly. Thus, neural networks are also introduced in this field to take HO decisions. HO decision relies on data rate; monetary cost, RSSI and speed of MS. Neural networks are proficient for this process as it involves deep analysis of the data HO parameters. In this paper, a novel technique is involved to make neural networks efficacious to take HO decision. The proposed model is the amalgamation of artificial neural network and Fuzzy logic which in turn resulted in ANFIS model. This model utilized four parameters namely, RSSI, cost, data rate and velocity as imperative factors to determine the supremacy of the designed model. Further, MATLAB is used to perform the simulation analysis. Eventually, obtained results are compared with existing techniques which ensures the efficacy of proposed model in terms of velocity and HO probability.

Keywords: Handover. fuzzy logic, Artificial neural network, ANFIS

Abstract: In this era of automation, vehicle cooperative driving is one of innovations in the automotive industry that aim to improve the safety, traffic flow efficiency, mileage and time of travel of vehicles while decreasing pollution and reducing stress for drivers. Having interconnected vehicles on road can to some extent reduce the accidents caused basically due to lack of human intervention on time. In this paper we discuss how we can make interconnected vehicle platooning a reality with Cooperative driving technology.

Keywords: Cooperative Adaptive Cruise Control, Dedicated Short Range Communication, Vehicle to Vehicle Communication, Visible Light Communication, ZigBee, Platooning

Abstract: Medical image segmentation is the task of classifying image components into relevant anatomical components or describing the structural and intensity changes in terms of the underlying functional process. This work provides a review on characterization of level set segmentation & Detection of Brain tumor image using energy optimization. For this, it uses an energy minimization approach to equalize the contrast of MR image. To enable the use of voxel gray values for interpretation of disease, it provides a new method, energy minimization with a spline model, to correct the severe intensity in homogeneity that arises from the surface coil array. Various automatic and semi-automatic methods have been developed for this purpose but with huge computational burden due to the enormous volume of data. All simulations can be accomplished in MATLAB.

Keywords: Image Processing, Brain Tumor, Energy Optimization

Abstract: Although (a) humans have been dealing with ‘what we call mind today’ for millions of years and (b) the first use of mind became obvious by works of Socrates (470 – 399 BC), a universal scientific definition/model of mind, that scientifically links mind to different parts in Central and Enteric Nervous Systems (CNS and ENS), has not been developed. In this paper, providing a scientific definition/model for the first time of mind and generation/emission of brainwaves, intriguing applications of scientific model of mind, as EEG-data-Based Algorithm across MGBA, are suggested for the first time.

Keywords: Electroencephalogram (EEG), MGBA, CNS, ENS

Abstract: Due to the lack of effective and coordinated disaster management system which consists of the stages like disaster mitigation, preparedness, response, and recovery has led to both the increase in the loss of both life and property. Disaster management deals with the issue of planing abstraction coordinative and communication, , The system proposes an effective disaster information system which uses the geofencing technique so as to detect the movement of users. This technique creates a geofence around the user and thus monitors the user’s entry and exit from the fence. For crowd disaster mitigation and real-time alert to avoid an occurrence of a stampede, this android application is an easily deployable context-awareness mobile Android Application Package. This application is very user friendly for user for accseing it properly .The application provides high accuracy when the user is in the fence. Disaster is a sudden event that suddenly occur in community and in a society. It is very important to people knowing the step to take during the disaster. Natural and Man-made disasters are proven to be devastating for both human life and property. The major cause is that neither the people were aware of it nor any effective measures were taken by them. Thus, there arises a need for proper mitigation and preparedness measures. And because of this need, a functional disaster information system is developed which will let people have prior knowledge in the times of disaster. This model aims at delivering risk information to the users directly in order to reduce the damage The system is proposed to be of a client-server. the client server architecture permits to use simultaneously by different user. While safety planning is familiar to schools, disaster planning is relatively new to the education sector. Such contingency planning may be seen as an extension of the risk assessment procedure.

Keywords: Client server architecture, Geo-fence, Client activity, Notification alertness, disaster management.

Abstract: The most important and challenging research area in proactive and ubiquitous computing is Human activity recognition. Automatic classification of human activity milieu (from simple activities to more complex ones) are crucial for applications like monitoring elderly people in assisted living, activity aware media content delivery, designing smart homes and appliances, quantified self, smart health care etc. Physical activity recognition using wearable sensors is capable of providing priceless information regarding an individual’s degree of operative ability and lifestyle. During the old age periods, falls are a major problem.so they are forced to depend on others. To monitor the way of walking of elderly people development of a technology that analyzes the relationship between the possibility of fall with the fitness and the total number of daily living activities of the elderly person that looks for precursors to falls. As we are surrounded by a lot of IoT devices, and efficient communication between man and machine are important for the proper working of these devices. So, activity recognition can be used to make our life easier through these IoT devices. There are several models for recognizing activities that use different techniques. We aim to analyze various models of human activity recognition and to propose a model for secure activity monitoring.

Keywords: IoT, Automatic Classification, Ubiquitous Computing, Quantified Self

Abstract: The low awareness of sign language among the general public presents a hurdle in communication with the deaf and dumb communities and their integration within society. A sign language translator application can help reduce this communication gap. This paper presents a system developed to detect fingerspelling gestures from video and give their English equivalent letter using machine learning, with a focus towards developing a potential solution for everyday use. A classifier is trained on a dataset of 24 fingerspelling gestures using the bag of visual words approach, wherein features detected in the images are clustered to form a codebook, then each image is expressed as a histogram denoting the frequency of observed codewords in that image. The SURF and BRISK algorithms are explored for automatic feature detection. Four classification algorithms are evaluated, namely K-nearest neighbours, logistic regression, Naive Bayes and Support Vector Machine. The best performing model has been used to classify sign language gestures from video frames.

Keywords: Bag of visual words, codebook, descriptors, histogram of codewords, image processing, feature detection, machine learning, sign language, speeded up robust features

Abstract: The generation of natural language text from the given data has become common today. The text generation system find out the required information to must include in the output. The automatic text generation system has variety of applications. The researchers found that in the 192 countries in the private colleges and university college 56.7 million students are studying. The number of students in the world is increasing. And all students should have a proper Text Books. The number of Text Books production is limited and it is not sufficient to satisfy the student’s requirements. The text books as per the syllabus make students to learn easy. Here we are attempt to develop a Text Book generator software. The software is to get a pdf formatted Text Book as per their syllabus. In which the syllabus of our subjects are given as the input to the system, and generate a text document by collecting the information using web crawling method from the trusted educational websites. The generated text document is summarized to get a precise and crisp summary with the required data.

Keywords: Educational Websites, Summary, Text Book Generator, Web Crawling

Abstract: Day by day the number of accidents is increasing at very high rates. In India, more than 150,000 people killed each year in traffic accidents. The large majority of accidents are occurred due to the unconscious states of the driver. Only few of the accidents occurred in a conscious state. There are many victims of the accidents other than drivers. It is very challenging to develop an accurate system to prevent accidents. An efficient system should consist of the mechanisms for drowsiness detection, alcoholic detection and accident detection. After detecting the condition the system itself should take the appropriate measure. The main aim should be the safety of drivers. In this paper we are presenting a brief overview of different methods to prevent and detect accidents. Drowsiness can be detected by using IR sensor or camera. Alcoholic rate can be detected by using sensors like MQ-3. The accidents are detected by using accelerometer sensors. After detecting the unconscious state the system will alert the driver. Even after alerting, if the driver continues in the unconscious state due to drowsiness or drunken the system will stop the vehicle and inform the relatives or helpline numbers. If the system is implemented in all cars the number of accidents can be reduced.

Keywords: Alcohol, Sensor, Accident, Drowsiness, Detection, Unconscious, Vehicle

Abstract: We introduce a low cost, easily, scalable system for assisting customers in shopping. Most of the supermarkets use the barcode based product scanning technique which requires additional time and manpower. The RFID technology enhances the overall shopping experiences due to its significant advantages over existing barcode system. The RFID reader is attached with the trolley so that the customer can scan each item and can access the product information, product features, and discounts. The system provides location of particular item, if the user unable to find the location. The system detects the expiry date of the product and alerts the user. It also provides product suggestions based on the customer’s previous purchase and also popup the current offers. The customer can pay the bill using pre-recharged card or net banking.

Keywords: Machine Learning, RFID Reader, RFID Tag, Recommendation System

Abstract: The objective of the study presented in this paper, is to determine the potential effects that serious games can have on the learning of primary school students.  This study concentrated on learning mathematics especially mental calculation, a subject that is often regarded as complicated by students of all ages in schools. An experiment was carried out to investigate how the serious games affect arithmetic learning. Two groups were assigned, a control and experimental group. Controlled students have learned mental calculation by traditional teaching method and the experimental group used our Serious Games.  A t-test using  SPSS   statistical  software  was  carried  out  to  test  the  existence  of  significant  change  in  students’  performance  based  on  the  marks  they  scored  on  a  test  for  a  mental calculation before  and  after  the  introduction of serious games in students learning process.. Based on the analysis carried out, results show that the students in the experimental group performed better when using serious games than the control group with traditional teaching method. And those serious games positively influence the motivation of learners.

Keywords: Serious Games, Mental calculation, Primary school, Mathematics, Motivation.  

Abstract: Celebrity endorsement is one of the important key marketing strategies used by marketers or companies in current scenario. Marketers are using this key of endorsement as a promotional tool for their respective brand or product. 15% and above advertisements shown on TV are endorse by famous celebrities either from sports or cinemas. The purpose of this study was to explore the impact of celebrity endorsement on customer perception with respect to cosmetic products. 4 factors were found; motivation, goodwill, brand value and physical appearance. 150 female respondents; married and unmarried both have taken as a sample size. Study shows that customer perception about cosmetic products were more influenced by celebrity endorsement and they get motivation from endorse advertisements and this feeling create more strong goodwill of brand and value. Study also shows that marital status and price of the product cannot change the perception of customers on the basis of celebrity endorsement. People are more positive to purchase the product after watching endorse advertisements, so with the help of this study marketer could better understand the use of celebrity endorsement and with the help endorsement of celebrity with right marketing strategies they could change the perception of customers with respect to their product or brand on positive direction

Keywords: Celebrity Endorsement, Customer Perception, Advertisement, product perception.

Abstract: As organizations increasingly migrate their operations to cloud environments, ensuring the security of data and applications becomes paramount. This paper explores the intricate landscape of cloud computing security, delving into the challenges, measures, and emerging trends that shape the safeguarding of digital assets in the cloud. The paper begins with addressing common security challenges associated with cloud computing, including data breaches, unauthorized access, and the complexities introduced by multi-tenancy. It outlines comprehensive security measures and best practices, spanning encryption, access controls, identity management, and regular audits, aiming to equip readers with a robust understanding of proactive security strategies. Furthermore, the paper explores the intricate balance of shared responsibility between cloud service providers and customers, emphasizing the need for a collaborative approach to security. It discusses compliance and regulatory considerations, shedding light on the evolving landscape of industry standards. The importance of incident response and disaster recovery planning within the context of cloud environments is also explored, offering insights into strategies for effective mitigation and recovery. The paper delves into emerging technologies and trends shaping the future of cloud computing security, with a focus on innovations like zero-trust security, edge computing, and AI-driven solutions. Real-world case studies underscore the practical application of security principles, providing tangible examples of successful implementations. In conclusion, this paper paints a comprehensive picture of the current state of cloud computing security while emphasizing the dynamic nature of the field. As organizations navigate an ever-evolving threat landscape, a continuous commitment to robust security measures and a forward-looking approach are crucial to realizing the full potential of cloud computing while safeguarding digital assets.

Keywords: Cloud Computing Security Data Encryption in the Cloud, Identity and Access Management (IAM), Virtualization Security, Compliance and Regulations in Cloud Security, Incident Response in Cloud Environments, Disaster Recovery Planning.