Sajal Halder

Smart CDSS: integration of Social Media and Interaction Engine (SMIE) in healthcare for chronic disease patients

Chronic disease may lead to life threatening health complications like heart disease, stroke, and diabetes that diminish the quality of life. CDSS (Clinical Decision Support System) helps physician in effective utilization of patient’s clinical information at the time of diagnosis and medication. This paper points out the importance of social media and interaction integration in existing Smart CDSS for chronic diseases. The proposed system monitors health conditions, emotions and interests of patients from patients’ tweets, trajectory and email analysis. We extract keywords, concepts and sentiments from patient’s tweets data. Trajectory analysis identifies the focused activities after considering imperative location and semantic tags. Email analysis finds interesting patterns and communication trends from daily routine of patient. All these outputs are supplied to Smart CDSS into vMR (virtual Medical Record) format through social media adapter. This helps the health practitioners to understand the behavior and lifestyle of patients for better decision making about treatment. Consequently, patients can get continuous relevant recommendations from Smart CDSS based on their personalized profile. To verify and validate the working of proposed methodology, we have implemented a proof of concept prototype that reflects its complete working with potential outcomes.

Movie swarm: Information mining technique for movie recommendation system

Huge amount of movies are available over the world, all of those are impossible to see for one user and all of them are not interesting. Movie recommendation systems filter out irrelevant movies and suggest the relevant movies those would be interesting for users. Traditional system can not recommend new users and new items efficiently. In collaborative filtering recommendation is based on users activities and products features hence when new users enter the system and new items added, it can not recommend. In content based recommend can recommend new items based on items features but unable to recommend new users. Therefor, We have proposed an information mining tool that collect all important information which is needed in movie recommendation system. In our proposed system, we have generated movie swarm which is very useful for movie producers and can solve new items problem. Also finds out which genres of movie should be recommended among followers, that solves new users recommendation problem. Experimental studies on the real data demonstrate the encourages and effectiveness of our methods.

Supergraph based periodic pattern mining in dynamic social networks

In dynamic networks, periodically occurring interactions express especially significant meaning. However, these patterns also could occur infrequently, which is why it is difficult to detect while working with mass data. To identify such periodic patterns in dynamic networks, we propose single pass supergraph based periodic pattern mining SPPMiner technique that is polynomial unlike most graph mining problems. The proposed technique stores all entities in dynamic networks only once and calculate common sub-patterns once at each timestamps. In this way, it works faster. The performance study shows that SPPMiner method is time and memory efficient compared to others. In fact, the memory efficiency of our approach does not depend on dynamic network’s lifetime. By studying the growth of periodic patterns in social networks, the proposed research has potential implications for behavior prediction of intellectual communities.

Movie Recommendation System Based on Movie Swarm

A movie recommendation is important in our social life due to its strength in providing enhanced entertainment. Such a system can suggest a set of movies to users based on their interest, or the popularities of the movies. Although, a set of movie recommendation systems have been proposed, most of these either cannot recommend a movie to the existing users efficiently or to a new user by any means. In this paper we propose a movie recommendation system that has the ability to recommend movies to a new user as well as the others. It mines movie databases to collect all the important information, such as, popularity and attractiveness, required for recommendation. It generates movie swarms not only convenient for movie producer to plan a new movie but also useful for movie recommendation. Experimental studies on the real data reveal the efficiency and effectiveness of the proposed system.

Efficient Mining Frequently Correlated, Associated-Correlated and Independent Patterns Synchronously by Removing Null Transactions

Market basket analysis techniques are useful for extracting customer’s purchase behaviors or rules by discovering what items they buy together using the association rules and correlation. Associated and correlated items are placed in the neighboring shelf to raise their purchasing probability in a super shop. Therefore, the mining combined association rules with correlation can discover frequently correlated, associated, associated-correlated and independent patterns synchronously, that are extraordinarily useful for making everyday’s business decisions. Since, the existing algorithms for mining correlated patterns did not consider the overhead of ‘null transactions’ during the mining operations; these algorithms fail to provide faster retrieval of useful patterns and besides, memory usages also increase exponentially. In this paper, we proposed an efficient approach for mining above mentioned four kinds of patterns by removing so called ‘null transactions’; by which not only possible to save precious computation time but also speeds up the overall mining process. Comprehensive experimental results show that the technique developed in this paper are feasible for mining large transactional databases in terms of time, memory usages, and scalability.

Predicting students yearly performance using neural network: A case study of BSMRSTU

Students academic performance is the reflection of both academic background and family support. This performance record is critical for the educational institution because they can learn from this to improve their quality. Educational data mining helps to analyze these data and extract information from it. We can determine the status of learners academic performance. For achieving this we can use techniques like decision tree, neural network, classification, data clustering, support vector machine and so on. In this paper, we will predict students yearly performance in the form of Cumulative Grade Point Average (CGPA) using neural network and compare that with real CGPA. In this regard, a real dataset would be of great importance. We used real dataset from Bangabandhu Sheikh Mujibur Rahman Science and Technology University (BSMRSTU) to perform the prediction.

An Efficient Sentiment Mining Approach on Social Media Networks

In today’s competitive environment, there is an essential need to collect and analyze data from social media, news, and other data streams that concern processing of huge amounts of data. A large number of posts, news, and blogs include opinions about product, service, and different issues. To accomplish an upper advantage, it is regularly important to listen and comprehend what individuals are saying in regard to contenders’ item, benefit, and distinctive issues. We proposed a sentiment mining technique for social media analytics to identify influential opinions. Our aim to mine and to compress every one of the people surveys of an item as well as the polarity of subjective topics which isn’t determine combined with opinion mining previously. Proposed task is performed in three steps: Firstly, mining item includes that have been remarked on by clients; secondly, recognize the supposition sentences in each survey and choosing whether every opinion sentence positive or negative or neutral; and finally, we summarize the results based on real datasets.

Novel recommendation systems in social networks

Absence of the user based recommendation system is a prevalent problem in a social network. In this paper, our work tends to model distance based group and probability based group in terms deciding recommendation dynamics. Here, we want to identify the best user who appears to be the innocent audience. In this regard, the effect of network density and preference homogeneity according to the user have been calculated. We have also used the probability function to evaluate the group of user that could be recommended.

An efficient approach of identifying tourist by call detail record analysis

Tourist identification with a lower effort can be highly demandable for the tourism department and related organizations of a country. Nowadays, most of the people including tourists use cell phones to keep communication resulting in corresponding data for every transaction (call, SMS, MMS, mobile data) named call detail record. This kind of data is usually collected and stored by telecom operators mainly for billing reasons. Call detail record (CDR) can be mined to get the approximate location of cellular mobile phones. This article describes a framework that identifies tourists among total population by analyzing cellular phone location data from call detail record. The framework also includes an efficient yet effective data scan method from huge CDR database of the total cell phone users.