According to the World Health Organization (WHO) breast cancer is the major reason of death among women and its impact on women is 2.1 million per year. Only in 2018 approximately 15% (62700) of women are died due to breast cancer. To detect this breast cancer oncologist rely on two methods i.e. early diagnosis and screening. To identify cancers before any symptoms appear screening plays an important role and in screening Mammography is heart of breast cancer detection. Apart from this Clinical Breast Exams, Breast Self-Exam and many other methodologies are used. Screening for breast cancer is too long and time consuming process if approach is manual analysis and its performed on medical images. Its also unfeasible for huge data sets. Thats the reason we required self-automated, efficient and more accurate machine to identify or capture the breast cancer as minimum as possible amount of time. We found the solution of this problem is Deep Learning Method. It provides the results in short period of time as compare to other techniques and giving the better accuracy for detection of Breast cancer. In this paper we focuses on, by using which methodology we got the more accurate results and how much amount of time is required to do this process. In this project we are going to deal with different classifiers like CNN, KNN, Inception V3, SVM and ANN. By using ANN we are going to detect the Breast Cancer. We are also going to compare the results of SVM with ANN Technique.

This paper is an attempt to understand various portals and mobile Apps available for the empowerment of rural folk in India. Digital India programme envisages a digital empowering of the citizens of India i.e. making them digitally literate so that they are enabled to seek better livelihood opportunities and become economically secure. The central and state governments, along with several private agencies are engaged in the digital empowerment of deprived groups. This article begins with the view of the government of India in digital transformation. The next section describes the unique methodology adopted for this study. The section that follows introduces some web portals and mobile applications designed and developed for the benefit of farmers, fishers and the tribes and for the general public and given thereafter is the conclusion

Let G= (V, E) be a graph with p vertices and q edges. A graph G={V, E} with p vertices and q edges is said to be a Permutation labelling graph if there exists a bijection function f from set of all vertices V G( ) to {1, 2,3... }p such that the induced edge labelling function h E G N : ( ) ? is defined as ( ) ( ) 1 2 1 ( 2 ) , f x h x x f x P = or ( ) 2 f x( 1 ) f x P according as f x f x ( 1 2 ) ( ) or f x f x ( 2 1 ) ( ) where P is the permutation of objects( representing the labels assigned to vertices). We in this paper have identified (m,n) Kite graph and attached an edge to form a join to the kite graph and proved that the joins of (m,n) kite graphs is permutation labelling graph and also have obtained some important results connecting the joins of a (m,n) kite graph.

In the present digital era massive amount of data is being continuously generated at exceptional and increasing scales. This data has become an important and indispensable part of every economy, industry, organization, business and individual. Further handling of these large datasets due to the heterogeneity in their formats is one of the major challenge. There is a need for efficient data processing techniques to handle the heterogeneous data and also to meet the computational requirements to process this huge volume of data. The objective of this paper is to review, describe and reflect on heterogeneous data with its complexity in processing, and also the use of machine learning algorithms which plays a major role in data analytics

Stock price forecasting is a popular and important topic in financial and academic studies. Share market is an volatile place for predicting since there are no significant rules to estimate or predict the price of a share in the share market. Many methods like technical analysis, fundamental analysis, time series analysis and statistical analysis etc. are used to predict the price in tie share market but none of these methods are proved as a consistently acceptable prediction tool. In this paper, we implemented a Random Forest approach to predict stock market prices. Random Forests are very effectively implemented in forecasting stock prices, returns, and stock modeling. We outline the design of the Random Forest with its salient features and customizable parameters. We focus on a certain group of parameters with a relatively significant impact on the share price of a company. With the help of sentiment analysis, we found the polarity score of the new article and that helped in forecasting accurate result. Although share market can never be predicted with hundred per-cent accuracy due to its vague domain, this paper aims at proving the efficiency of Random forest for forecasting the stock prices.

The race for urbanization and thirst for high living status leads to unhealthy life. As the result a rapid growth in number of diabetic patients in urban areas approaching to its deadline. In this situation it become a prime necessity for physicians and health workers to recognize accurate growth rate in number of diabetic patients. Artificial Neural Network is used as one of the artificial intelligent technique for forestalling growth rate of type II diabetic patients. Diabetes occurred due to increased level of glucose in blood. In this paper, an intense survey is done for the prediction of Type II diabetes using different Data Mining tools and Artificial Neural Network techniques, is presented. This survey is aimed to recognize and propose an effective technique for earlier prediction of the Type II diabetes. The data mining techniques like C4.5 Classifier, Support Vector Machine and K-Nearest Neighbour are compared for this work with Artificial Neural Network. As the results Artificial Neural Network found with a great accuracy of 89%.

The cloud computing platform has played significant role behind the exponential growth of modern IT industry. More and more organizations & individuals from various sectors of society are directory or indirectly consuming cloud computing platform. Such rising demand for cloud based computing resources has generated requirement of optimized resource management and load balancing. Extensive research work is taking place for efficient resource management and load balancing. A dynamic approach for virtual machine load balancing is presented here. The load balancing mechanism presented here offers better efficiency due to its multi-threaded approach.

The Archean Green Stone Belts (AGSB) having enormous metalliferous deposits like gold , copper, silver, iron and other precious gem stones which are also called as schist belts of Dharwar Craton. The study area Kempinakote lies in southern most part of Nuggihalli Schist Belt of Hassan district. The schist belt consists commonly two rock types Amphibolites and Ultramafics with their variants. Gold is occurring at or near the amphibolite-ultramafic contact. The Study area comes to Hassan district, Random samples were collected such as Gold bearing Amphibolite schist, Amphibolite, Diorite, Gabbro through GTC (Ground Truth Check). The study carried out by Geological, Petrological, Ore microscopic, SEM-EDX and Hyperspectral signatures using advent high-tech tools of Spectro- Radiometer (Spectral Evolution SR-3500) instrument, DARWin SP.V.1.3.0 and GIS softwares. The spectral signatures of the collected samples were derived in laboratory environment to achieve better accuracy. Hyperspectral (350-2500nm) were developed as works mainly on physicochemical and optical properties of the litho unit which help in mapping of gold mineralization at lithological contacts and mineralized zones of amphibolites and ultramafic rocks. The final results highlight the gold specks were noticed through ore microscopy and presence of gold is confirmed through SEM-EDX studies and also spectral characters of Gold bearing amphibolites schist and associated rocks for better mapping of Kempinakote area of Hassan district in Precambrian basement rocks and similar terrains of Dharwarcraton.

The Internet of Things is giving a bright future and with establishment and maturity of wireless sensor networks, it can be truly realised for the various purposes of human endeavour. The paper deals with challenge to integrate the data coming from heterogeneous sensor networks coming from various geographical locations. A Sensor Web Registry is proposed to achieve this task. The outcome of this effort is further realised by using Semantic Web Technologies like Ontologies, OWL, SPARQL and Python. The paper used all this practically using a Micaz Sensor Boards with Zigbee protocol in a lab setup

This paper presents the design of the low cost home automation system using the IoT(Internet of Things) technology along with the feature of speech recognition. The Internet of things (IoT) is the inter-networking of physical devices, vehicles, buildings, and other items embedded with electronics, software, sensors, actuators, and network connectivity that enable these objects to collect and exchange data. In this project IoT technology is used to control the home appliances wirelessly over the internet. The computing module used is a Raspberry pi development board. The project also aims to provide a speech control interface to the users to control the appliances. Speech recognition is provided using an online Speech-To-Text platform called wit. The home automation system listens for the user’s speech and whenever a defined phrase is identified it triggers corresponding action to switch appliances on or off. With speech recognition physically challenged people can control appliances with much more ease

In recent years, the use of online social networks (OSNs) such as Facebook, Twitter etc has tremendous increased. Users see these OSNs as a useful tool to find friends and interact with them. Moreover, OSNs allow their users to share photos, videos, and express their thoughts, views and feelings. However, users are usually concerned about their privacy when using OSNs. These OSNs not only offer smart resources for virtual social interfaces and sharing of data but also improve a number of security and privacy issues. While OSNs allow a single user to manage access to her/his data, those currently do not provide any mechanism to apply privacy concerns over data associated with multiple users, remaining privacy harms largely unresolved and leading to the potential confession of information that at least one user planned to keep private. This is because the unrestricted image of a subject can be affected by photos or comments posted on a social network. In this way, recent studies shows that users are demanding better mechanisms to protect their privacy. For this concern, we provide a systematic mechanism to identify and resolve privacy conflicts in online social networks (OSNs). The first computational tool to resolve conflicts for multiparty privacy management in social media. This makes it enable to adapt different situations by modelling the concessions that users make to reach a solution to the conflicts. Our conflict resolution specifies a tradeoff between privacy protection and data sharing by computing privacy risk and sharing loss

The aim of this paper is to apply the regularization functions namely TV norm, l1 norm and l0 norm and regularization parameters with these norms in image restoration. This class of problems results from combining a linear observation model with a non-quadratic regularizer. Improved Iterative Shrinkage Thresholding algorithm (IISTA) and Iterative Shrinkage Thresholding algorithm (ISTA) are employed for comparison. These algorithms are performed through a recursive application of two simple procedures such as linear filtering and soft thresholding

Agriculture is the primary source of livelihood which forms the backbone of our country. Current challenges of water shortages, uncontrolled cost due to demand-supply, and weather uncertainty necessitate farmers to be equipped with smart farming. In particular, low yield of crops due to uncertain climatic changes, poor irrigation facilities, reduction in soil fertility and traditional farming techniques need to be addressed. Machine learning is one such technique employed to predict crop yield in agriculture. Various machine learning techniques such as prediction, classification, regression and clustering are utilized to forecast crop yield. Artificial neural networks, support vector machines, linear and logistic regression, decision trees, Naïve Bayes are some of the algorithms used to implement prediction. However, the selection of the appropriate algorithm from the pool of available algorithms imposes challenge to the researchers with respect to the chosen crop. In this paper, an investigation has been performed on how various machine learning algorithms are useful in prediction of crop yield. An approach has been proposed for prediction of crop yield using machine learning techniques in big data computing paradigm.

Building quality educational resources with new technologies requires offering learners and teachers a simple computing environment that would be adapted and would allow it to use its pedagogy in respondent contents of learners needs, in terms of adaptability, portability monitoring and evaluation. In this article, the focal point is reminding the architecture of our Dynamic Adaptive Hypermedia (DAH) system, we shall focus on these different elements namely, the model domain, the students model, teaching model, the courses generator, and the multimedia database. Then, we will detail the steps of the proposed approach to the development of educational content through this (DAH) system, dedicated to both teachers and learners. The purpose is to come up with a mechanism that can adapt the course to the learners profile, in a Computing Environment For Human Learning (CEHL). In this article, we are putting much importance on the various information stored in the models of our system, which would be useful to dynamically generate structured and comprehensive educational content according to cognitive status and the learners style. The aim is to try hard and to look for pedagogical contents, dealing with concepts of a particular field of knowledge that is adapted to a particular learner. In other words, we want to develop a generic model of interactive multimedia educational content and a learner model based on the integration of skills and knowledge.

Variation in the climatic conditions is the major hurdle in the Agriculture sector to attain high crop yield. The Crop simulation models portray the stage-wise growth of crop with the respective environment condition. The crop simulation models help the farmer to make better decisions for improving the crop yield. Artificial Intelligence, Data mining and Computational Intelligent are becoming more prominent in the agriculture field for decision making because of emerging technology such as GIS, Satellite data and remote sensing data in agriculture. This paper reviews information on crop simulation models using computational intelligence and their application. It also reviews the different types of crop simulation models and their limitation in Agriculture. It also discusses the different crop simulation models in details. Considering the emerging technology in the agriculture field we discussed the future trends of crop simulation models.

Distinguishing an individual with a picture has been advanced through the broad communications. Be that as it may, it is less powerful to unique finger impression or retina examining. This report depicts the face detection and recognition smaller than normal task attempted for the visual observation and self-governance module at Plymouth college. It reports the innovations accessible in the Open-Computer-Vision (OpenCV) library and technique to execute them utilizing Python. For face identification, Haar-Cascades were utilized and for face recognition Eigenfaces, Fisherfaces and Local double example histograms were utilized. The procedure is portrayed including stream diagrams for each phase of the framework. Next, the outcomes are indicated including plots and screen-shots pursued by an exchange of experienced difficulties. The report is finished up with the creators feeling on the venture and potential applications. This paper means to execute a face recognition programming code dependent on the strategy for Haar Cascade Classifiers and to effectively actualize this code on the Raspberry Pi stage for continuous recognition. In this paper, an endeavor to execute face acknowledgment calculation on an equipment stage, which is basic, yet productive in utilization is taken up . The product source codes for both detection and recognition of countenances are composed utilizing Opencv and Python.

Wireless network is an established connection for data transformation from one node to another node and the biggest issue in the data transformation is congestion and latency which destroys the transmitting function. In wireless sensor networks (WSNs), Shortest path routing can find multiple paths from source node to destination node for achieving high responsibility and high energy-efficiency. However, most of the existing Shortest path routing protocols in the literature construct multiple paths with long latency and high over head and it is a common issue. In this paper, a fiction Shortest path routing protocol in WSNs is proposed named LWSP [Shortest path without Latency], which can discover shortest paths with short latency and low command processing overhead time. Performance analyses and simulation results shows that our proposed protocol has much better performance than the existing ones in terms of both latency and command processing overhead time

The classification of data is an important field of data mining comes under supervised learning. In this approach classifier is trained on the pre-categorized data thereafter tested on unseen part called test data to evaluate it. The other related field clustering comes under unsupervised learning is used for categorizing data into different clusters or assigning labels to them which are previously unknown. In this article the classification of data is done and we are using artificial neural networks (ANN) for pre-processing i.e. removing noisy instances through novel clustering technique and then classifying pre-processed data through ANN. Both are exhaustive approaches. The data set used in this article is PIMA Indian diabetes data set available on UCI repository.