Browse
Recent Submissions
Item TRAINING ON LINUX AND AWS(2019-08-28T06:24:07Z) SABIR HUSSAINAmazon Web Services is a cloud service from Amazon, which provides services in the form of building blocks, these building blocks can be used to create and deploy any type of application in the cloud. These services or building blocks are designed to work with each other, and result in applications which are sophisticated and highly scalable. Cloud computing is the on-demand delivery of compute power, database storage, applications, and other IT resources through a cloud services platform via the internet with pay-as- you-go pricing. Whether you are running applications that share photos to millions of mobile users or you’re supporting the critical operations of your business, a cloud services platform provides rapid access to flexible and low-cost IT resources. With cloud computing, you don’t need to make large upfront investments in hardware and spend a lot of time on the heavy lifting of managing that hardware. Instead, you can provision exactly the right type and size of computing resources you need to power your newest bright idea or operate your IT department. You can access as many resources as you need, almost instantly, and only pay for what you use. simple way to access servers, storage, databases and a broad set of application services over the Internet. A Cloud services platform such as Amazon Web Services owns and maintains the network- connected hardware required for these application services, to retrieve all data from the aws through the command line argument, In Aws only linux and linux’s distributors is available while launching the instance you have to select the os.Item PYTHON LEARNING (SENTIMENT ANALYSIS)(2019-08-28T06:21:00Z) JAYANTH JSentiment analysis is an application of natural language processing integrated with machine learning. In order to classify the reviews on a website as positive or negative, we use bag of words and term frequency and inverse document frequency. The text classification includes importing dataset, text pre-processing, conversion from text to numbers, split data into training and testing sets, predict the text classification model for new data and finally produce a classification report along with the confusion matrix. The final output will be gaining the maximum accuracy in predicting the test data output. Natural language processing is one of the widely studied areas of research as the language used by humans need to be understood by the computers. The communication can be textual or visual. For example, face-to-face conversations, speech recognition, voice recognition, SMS messages, spam emails etc. NLP is very important for machines to understand as it can be viewed as a source of huge chunks of data which can be intelligently processed. It also provides a better communication between machines and humans. Sentiment analysis has proved to be useful to predict the reviews on a particular item, movie, product etc. In order to predict the outcome, data needs to gathered, cleaned and processed. After data processing, a model needs to be chosen and trained in order to allow further predictions. Finally the model will be evaluated and tested for its accuracy in prediction.Item INTELLIGENT VOICE ASSISTANT(2019-06-22T09:35:48Z) SANJANA ANANDThis project aims to provide the services of voice-controlled automation with a personalized, cross-platform touch. The application can manipulate the system and perform basic tasks through speech recognition. In today’s world of increasing demand for personal assistants, this project offers a solution that simplifies the functionality of present-day assistants. This project is a standalone application that can be used by anyone who doesn’t know about the workings of a system. It can perform tasks such as opening another application (like settings or calculator), opening the clock or alarms, responding to user greetings, controlling volume or brightness, etc.Item IMAGE RESOLUTION USING DEEP LEARNING(2019-06-22T09:34:07Z) RASHMI N GONDThe term resolution is often considered equivalent to pixel count in digital imaging, Though international standards in the digital camera field specify it should instead be Called & quot; Number of Total Pixels & quot; in relation to image sensors, and as " Number of Recorded Pixels" for what is fully captured. The "Number of Effective Pixels" that an image sensor or digital camera has is the count of pixel sensors that contribute to the final image (including pixels not in said image but nevertheless support the image filtering process), as opposed to the number of total pixels, which includes unused or light-shielded pixels around the edges. An image of N pixels height by M pixels wide can have any resolution less than N Lines per picture height. But when the pixel counts are referred to as " resolution", the convention is to describe the pixel resolution with the set of two positive integer numbers, where the first number is the number of pixel columns (Width) and the second is the number of pixel rows (height), for example as 7680 × 6876.Item PREDICTION OF MALNOURISHMENT IN INFANTS(2019-06-22T08:47:16Z) RAHUL PREMA condition which results from eating a diet in which one or more nutrients are either not sufficient or are too much such that the diet causes health problems is called Malnutrition. Not sufficient nutrients is called undernutrition or undernourishment while too much is called overnutrition. If undernutrition occurs during pregnancy or before two years of age, it may result in permanent problems with respect to physical and mental development. Undernourishment usually occurs when the child does not have sufficient nutrition intake in the food he/she eats. This maybe due to factors such as poverty or insufficient breastfeeding for infants. There are primarily two types of undernutrition: proteinenergy malnutrition and dietary deficiencies. Two severe forms of Protein-energy malnutrition are marasmus (caused due to lack of protein and calories) and kwashiorkor (caused due to lack of just protein. Due to the body's increased needs, deficiencies seldom become more common during pregnancy. Overnutrition is prevalent in some developing countries in the form of obesity. Failure in identifying and diagnosing malnourishment at any early age is the root cause for many physical and mental problems and undergrowth, thus hampering the progress of the country. This project aims to predict whether the child is malnourished very early on so that he/she can be given proper and immediate medical attention, thereby eradicating malnourishment and facilitating in smooth progress of the nation as a whole.Item TV AD RECOMMENDATION BASED ON DATA ANALYSIS(2019-06-22T08:45:36Z) PRASHANT MEHTAWith broadcast Television (TV) going digital, the number of channels and the programs aired have increased tremendously. Millions of audiences of various categories such as adults, children, youth and families watch these programs. Advertisements (ads) aired during these programs are targeted to reach these varied audiences and are the main revenue earners for TV broadcasters. While TV broadcasters have the task of scheduling hundreds of ads during the various ad breaks of programs, it is important that the ads shown during any ad break have a good impact on the viewers. An intelligent ad recommendation system that takes into account various factors such as ad/program content, viewers, interests, sponsors, preferences, program timing, program popularity and the available ad slot that help increasing the ad revenue would be useful for sponsors and broadcasters.Item CUSTOMER CHURN ANALYSIS(2019-06-22T08:43:10Z) PRANITA D BIRADARCustomer churn is one of the fundamental issues in the broadcast communications industry. A few examinations have demonstrated that drawing in new clients is substantially costlier than holding existing ones. In this way, organizations are concentrating on creating precise and dependable prescient models to recognize potential clients that will agitate sooner rather than later. The point of this paper is examining the primary explanations behind beat in media transmission area in Macedonia. The proposed strategy for examination of beat expectation covers a few stages: understanding the business; determination, investigation and information preparing; executing different calculations for characterization; assessment of the classifiers and picking the best one for forecast. The acquired outcomes for the information from a media transmission organization in Macedonia, ought to be of extraordinary incentive for the board and showcasing branches of other telecom organizations in the nation and more extensive.Item MINIMIZING COMMERCIAL AVIATION DISASTERS(2019-06-22T08:40:57Z) PRANAV MA majority of civil aviation disasters over the past few decades (58%) has been attributed to ‘Pilot Error’ - a phrase generally used to describe wrong decisions, actions or even inaction by a pilot of an airplane, which is determined to be a major contributing factor in accidents involving the deaths of many passengers. It includes lapses in judgment due to fatigue, extreme habits, oversights and failure to follow correct protocol. This paper demonstrates how we can use pilots’ real-time physiological metrics to determine and predict their various cognitive states, thereby developing a model that can be installed in warning systems to ensure they are fully focused on to the task at hand.Item CUSTOMER CHURN ANALYSIS(2019-06-22T08:37:34Z) PARAMARTHA ROYCustomer churn is one of the fundamental issues in the broadcast communications industry. A few examinations have demonstrated that drawing in new clients is substantially costlier than holding existing ones. In this way, organizations are concentrating on creating precise and dependable prescient models to recognize potential clients that will agitate sooner rather than later. The point of this paper is examining the primary explanations behind beat in media transmission area in Macedonia. The proposed strategy for examination of beat expectation covers a few stages: understanding the business; determination, investigation and information preparing; executing different calculations for characterization; assessment of the classifiers and picking the best one for forecast. The acquired outcomes for the information from a media transmission organization in Macedonia, ought to be of extraordinary incentive for the board and showcasing branches of other telecom organizations in the nation and more extensive.Item CABREC(2019-06-22T08:34:28Z) PABITRA BORAHUtilizing large-scale GPS data to improve CAB services has become a popular research problem in the areas of data mining, intelligent transportation, geographical information systems, and the Internet of Things. In this paper, we utilize a large-scale GPS data set generated by over 7,000 CABs in a period of one month in Nanjing, China, and propose CABREC: a framework for evaluating and discovering the passenger finding potentials of road clusters, which is incorporated into a recommender system for CAB drivers to seek passengers. In CABREC, the underlying road network is first segmented into a number of road clusters, a set of features for each road cluster is extracted from real-life data sets, and then a ranking-based extreme learning machine (ELM) model is proposed to evaluate the passenger-finding potential of each road cluster. In addition, CABREC can use this model with a training cluster selection algorithm to provide road cluster recommendations when CAB trajectory data is incomplete or unavailable. Experimental results demonstrate the feasibility and effectiveness of CABREC.Item CHATBOT USING DIALOGFLOW(2019-06-22T08:32:36Z) NISSI THOMASMany people now a days look for assistance for the products which they usually buy from different e-retail shops. Now I am building a software using machine learning and Artificial intelligence, that can by which user needs to provide their order id, so the verification of the product will be done earlier. So to ensure that the customer needs the help for the product ,actually belongs or bought from that company or e-commerce site. After verification, my system will ask them their order id,by which my system will fetch all the details of the customer and will be able to book an appointment for either repair or intsall. User have to choose a date and time, on the basis of user data my system will check that the date and time of the user is matching with other customer or not. If not then it will generate a ticket(unique) number and thus the appointment will be booked. After that is customer wants to reschedule it or delete the appointment, my system will do that also, but it will ask for the ticket number that gets generated when the appointment is booked. For the conversation and the integration I am using “DialogFlow”.Item PERSONALIZED MOBILE SEARCH ENGINE(2019-06-22T08:30:27Z) MAHESH BABU MWe propose a personalized mobile search engine, PMSE, that captures the users’ preferences in the form of concepts by mining their clickthrough data. Due to the importance of location information in mobile search, PMSE classifies these concepts into content concepts and location concepts. In addition, users’ locations (positioned by GPS) are used to supplement the location concepts in PMSE. The user preferences are organized in an ontology-based, multi-facet user profile, which are used to adapt a personalized ranking function for rank adaptation of future search results. To characterize the diversity of the concepts associated with a query and their relevance’s to the users need, four entropies are introduced to balance the weights between the content and location facets. Based on the client-server model, we also present a detailed architecture and design for implementation of PMSE. In our design, the client collects and stores locally the clickthrough data to protect privacy, whereas heavy tasks such as concept extraction, training and re-ranking are performed at the PMSE server. Moreover, we address the privacy issue by restricting the information in the user profile exposed to the PMSE server with two privacy parameters. We prototype the PMSE on the Google Android platform. Experimental results show the PMSE significantly improves the precision comparing to the baseline.Item “CREDIT CARD FRAUD DETECTION USING ADABOOST AND MAJORITY VOTING(2019-06-22T08:28:05Z) MANTOSH PRASAD SAHCredit card fraud is a serious problem in financial services. Billions of dollars are lost due to credit card fraud every year. There is a lack of research studies on analyzing real-world credit card data owing to confidentiality issues. In this project, machine learning algorithms are used to detect credit card fraud. Standard models are firstly used. Then, hybrid methods which use AdaBoost and majority voting methods are applied. To evaluate the model efficacy, a publicly available credit card data set is used. Then, a realworld credit card data set from a financial institution is analyzed. In addition, noise is added to the data samples to further assess the robustness of the algorithms. The experimental results positively indicate that the majority voting method achieves good accuracy rates in detecting fraud cases in credit cards.Item SECURE: SELF PROTECTION APPROACH IN CLOUD RESOURCE MANAGEMENT(2019-06-22T08:16:25Z) M.RAMYAIn the current scenario of cloud computing, heterogeneous resources are located in various geographical locations requiring security-aware resource management to handle security threats. However, existing techniques are unable to protect systems from security attacks. To provide a secure cloud service, a security-based resource management technique is required that manages cloud resources automatically and delivers secure cloud services. In this paper, we propose a self-protection approach in cloud resource management called SECURE, which offers self-protection against security attacks and ensures continued availability of services to authorized users. The performance of SECURE has been evaluated using SNORT. The experimental results demonstrate that SECURE performs effectively in terms of both the intrusion detection rate and false positive rate. Further, the impact of security on quality of service (QoS) has been analyzed.Item VCM- FETCH DATA FASTER(2019-06-22T08:08:06Z) MADHUMITHA SVarious caching techniques have been deployed to increase the performance of multi-tier web-based applications in response to the ever-increasing scale of the Internet. Such applications typically achieve a measure of scalability with application servers running on multiple (relatively cheaper) systems connecting to a single database system. This, however, does not solve the scalability problem for backend database servers. One way to address this problem is middle-tier database caching which is deployed in the middle. Cache mechanism is a time-honoured method for improving the performance of an application. In place of constantly creating and destroying objects as needed, a cache holds on to them and reuses them when appropriate. A cache is a group of temporary data elements that either duplicates data located elsewhere or is the result of a computation. Data’s that are already in the cache can be repeatedly accessed without hitting the database and with minimal costs in terms of time and resources. A database cache is placed in place of the primary database by removing unnecessary pressure on it, typically in the form of frequently accessed read data. The cache itself can live in multiple numbers of areas including the database, application or as a standalone layer.Item CUSTOMER CHURN ANALYSIS(2019-06-22T08:05:48Z) M MADHURICustomer loss is very closely related with customer loyalty. Today’s economic trend dictates that price cuts are not the only way to build customer loyalty. The main goal of customer lost study is to figure out a customer who will likely be lost and is to calculate cost of obtaining those customers back again. The purpose of the project is to predict the customer churn that is happening across different networks and the reasons for why there is churn happening around them. If the profile of churner customers can be identified, specific campaigns can be created to keep the target groups. Analysis shows that subscribers who are not have discounted package, have very high tendency to churn. This project demonstrates models for predicting churner customer behaviour, to improve customer relationship management, and to develop various campaigns and marketing strategies for customer retention and loyalty. After eliminating non-related data and preparing stages, SQL server management and reporting are applied for determining the reasons for customer churn. Graph have displayed according to the feedback and result of the SSRS dashboard. According to graph of reporting system we can analyze the customer churn from one company to another company.Item TRAFFIC SIGNAL OPTIMIZATION(2019-06-22T08:04:04Z) LIKHITA SURESHIndian urban cities today are facing the biggest problem yet – traffic. A word that is mentioned by every commuter at least ten times a day is – traffic. Urban commuters see the worse side of the traffic almost every day and are all equally a victim and a cause. The government has tried several ways to alleviate the condition. The various fundamental solutions to avoid unnecessary danger on the road are traffic signals, fly-overs, magic boxes and express highways. The more recent methods implemented are Odd-Even rule, and public transport commute compulsion. The government strongly urge the Delhi residents to follow the Odd-Even policy on planned days. Other states are working on bettering the public transport conditions. Bengaluru is seeing massive Namma Metro constructions to help the city be more connected. Traffic signals, when used correctly, can create a huge positive impact on the population. Whereas, if used wrongly, can create an outburst in traffic densities throughout the city. The smart traffic signals are operated using IoT and optimization can help assuage the traffic densities further. This application aims at optimizing the inner workings of the current traffic lights used widely throughout the country, with the city of Bengaluru being the main interest. It will use a traffic density as the main input parameter and automatically adjust the traffic signal timer accordingly in a more efficient way.Item TEXT SUMMARIZER(2019-06-22T08:00:58Z) KABIRAJ MAHATO NUNIYASummarization is the way of abstracting important information from one or more sources. It increases the likelihood of finding the points of texts, so the user will spend less time on reading whole documents. Text summarization is one among the typical tasks of text mining. The World Wide Web provide a huge information available to users and users are overloaded with lengthy text document where smaller version would do. Some people make decisions on the basis of reviews they have seen and with summaries they can make effective decision in less time. With increasing volume of information summarization play a very important role in terms of time saving. Text summarization is a difficult task which preferably involves deep natural language processing capacities and in order to simplify the issue current research is focused on extractive summary generation. Summary can be generated through either extractive or Abstractive summarization technique. Sentence based extractive summarization techniques are commonly used in automatic text generation. Summarization task can be either supervised or unsupervised.in supervised learning training data is needed for selecting main content from the documents. Large amount of annotated or labeled data is needed for learning techniques. These systems are addressed at sentence level as two-class classification problem in which sentences belonging to the summary are termed as positive samples and sentences not present in the summary are named as negative samples. Some of the classification methods used in machine learning is Support Vector Machine (SVM) and neural networks. Unsupervised systems do not need any training data. They generate the summary by retrieving only the target documents. Therefore, they are appropriate for newly observed data without any advanced modifications.Item LUNGS CANCER DETECTION USING IMAGE PROCESSING(2019-06-22T07:57:28Z) ISHAN GYAWALIA Recommendation System is a sub class of information filtering system that tries to predict the preference of a user on a particular item. Recommender systems play a major role in today's ecommerce industry. Grocery Recommendation System as the name states will recommend grocery items to the users. This system helps the users to get personalized recommendations, helps users to take correct decisions in their online transactions, increase sales and redefine the users browsing experience, retain the customers, enhance their shopping experience. It provides related content out of relevant and irrelevant collection of items to users. Grocery Recommendation System is a web application. In order to recommend items to users, first the user behavior should be analyzed. We need to first study the past order history of the users in order to recommend them products. So, in order to recommend products, we will study the similar types of users with regards to target user. The similarity is calculated using cosine similarity and then we will find out the top N products of those similar users. After that recommendation is made based on the purchase history of similar users. Such type of recommendation is both beneficial to customers as well as the vendors because customers can easily and more conveniently find the products they are interested and in turn it will boost up the sales from which vendors can take advantage. As 35% of Amazon’s revenue is generated from its recommendation engine, it is a very profitable feature that each and every ecommerce application can benefit from.Item DEEP LEARNING-BASED DOCUMENT MODELLING FOR PERSONALITY DETECTION FROM TEXT(2019-06-22T07:48:40Z) BIMAL BHATTARAIPsychological stress is threatening people’s health. It is non-trivial to detect stress timely for proactive care. With the popularity of social media, people are used to sharing their daily activities and interacting with friends on social media platforms, making it feasible to leverage online social network data for stress detection. In this paper, we find that users stress state is closely related to that of his/her friends in social media, and we employ a large-scale dataset from real-world social platforms to systematically study the correlation of users’ stress states and social interactions. We first define a set of stress-related textual, visual, and social attributes from various aspects, and then propose a novel hybrid model-factor graph model combined with Convolutional Neural Network to leverage tweet content and social interaction information for stress detection. Experimental results show that the proposed model can improve the detection performance by 6-9% in F1-score. By further analysing the social interaction data, we also discover several intriguing phenomena, i.e. the number of social structures of sparse connections (i.e. with no delta connections) of stressed users is around 14% higher than that of non-stressed users, indicating that the social structure of stressed users’ friends tend to be less connected and less complicated than that of non-stressed users.