TEP001
Data Mining Methods for Traffic Accident Severity Prediction
ABSTRACT - The growth of the population volume and the number
of vehicles on the road cause congestion (jam) in cities that is one of
the main transportation issues. Congestion can lead to negative
effects such as increasing accident risks due to the expansion in
transportation systems. The smart city concept provides opportunities
to handle urban problems, and also to improve the citizens’ living
environment. In recent years, road traffic accidents (RTAs) have
become one of the largest national health issues in the world. Many
factors (driver, environment, car, etc.) are related to traffic accidents,
some of those factors are more important in determining the accident
severity than others. The analytical data mining solutions can
significantly be employed to determine and predict such influential
factors among human, vehicle and environmental factors and thus to
explain RTAs severity. In this research, three classification
techniques were applied: Decision trees (Random Forest, Random
Tree, J48/C4.5, and CART), ANN (back-propagation), and SVM
(polynomial kernel) to detect the influential environmental features of
RTAs that can be used to build the prediction model. These
techniques were tested using a real dataset obtained from the
Department for Transport of the United Kingdom. The experimental
results showed that the highest accuracy value was 80.6% using
Random Forest followed by 61.4% using ANN then by 54.8% using
SVM. A decision system has been build using the model generated
by the Random Forest technique that will help decision makers to
enhance the decision making process by predicting the severity of the
accident. Contact: +91-9008001602 080-40969981
TEP002
Enhancing the Naive Bayes Spam Filter Through Intelligent Text Modification Detection
ABSTRACT - Spam emails have been a chronic issue in computer security. They are very costly economically and extremely dangerous for computers and networks. Despite of the emergence of social networks and other Internet based information exchange venues, dependence on email communication has increased over the years and this dependence has resulted in an urgent need to improve spam filters. Although many spam filters have been created to help prevent these spam emails from entering a user's inbox, there is a lack or research focusing on text modifications. Currently, Naive Bayes is one of the most popular methods of spam classification because of its simplicity and efficiency. Naive Bayes is also very accurate; however, it is unable to correctly classify emails when they contain leetspeak or diacritics. Thus, in this proposes, we implemented a novel algorithm for enhancing the accuracy of the Naive Bayes Spam Filter so that it can detect text modifications and correctly classify the email as spam or ham. Our Python algorithm combines semantic based, keyword based, and machine learning algorithms to increase the accuracy of Naive Bayes compared to Spamassassin by over two hundred percent. Additionally, we have discovered a relationship between the length of the email and the spam score, indicating that Bayesian Poisoning, a controversial topic, is actually a real phenomenon and utilized by spammers. Contact: +91-9008001602 080-40969981
TEP003
Job satisfaction and employee
turnover: A firm-level
perspective
ABSTRACT - how companies can use their personnel data and information from job
satisfaction surveys to predict employee quits. An important issue discussed at length in the
article is how employers can ensure the anonymity of employees in surveys used for management
and human resources (HR) analytics. I argue that a simple mechanism whereby the company
delegates the implementation of job satisfaction surveys to an external consulting company can
be optimal. In the subsequent empirical analysis, I use a unique combination of firm-level data
(personnel records) and information from job satisfaction surveys to assess the benefits for
companies using data in their decision-making. Moreover, I aim to show how companies can
move from a descriptive to a predictive approach.Contact: +91-9008001602 080-40969981
TEP004
Medical decision making diagnosis system integrating k-means and Naïve Bayes algorithms
ABSTRACT - Using data mining we can evaluate many patterns which will be use in future to make intelligent systems and decisions By data mining refers to various methods of identifying information or the adoption of solutions based on knowledge and data extraction of these data so that they can be used in various areas such as decision-making, the prediction value for the prediction and calculation. In our days the health industry has collected vast amounts of patient data, which, unfortunately, is not "produced" in order to give some hidden information, and thus to make effective decisions, which are connected with the base of the patient's data and are subject to data mining. This research work has developed a Decision Support in Heart Disease Prediction System (HDPS) using data mining modelling technique, namely, Naïve Bayes and K-means clustering algorithms that are one of the most popular clustering techniques; however, where the initial choice of the centroid strongly influences the final result. Using of medical data, such as age, sex, blood pressure and blood sugar levels, chest pain, electrocardiogram, analyzes of different study patient, etc. graphics can predict the likelihood of the patient. This paper shows the effectiveness of unsupervised learning techniques, which is a k-means clustering to improve teaching methods controlled, which is naive Bayes. It explores the integration of K-means clustering with naive Bayes in the diagnosis of disease patients. It also investigates different methods of initial centroid selection of the K-means clustering such as range, inlier, outlier, random attribute values, and random row methods in the diagnosis of heart disease patients. The results indicate that the integration of the K-means clustering with naïve Bayes with different initial centroid selecting naive Bayesian improve accuracy in diagnosis of the patient.Contact: +91-9008001602 080-40969981
TEP005
Information extraction methods for text documents in a Cognitive Integrated Management Information System
ABSTRACT - In contemporary companies unstructured knowledge is essential, mainly due to the possibility to obtain better flexibility and competitiveness of the organization. For example, on the basis of automatic analysis of the experts' opinions, the decision-makers are capable of taking decisions (for example decisions concerning investments). This paper presents issues related to developing and evaluating a methods of information extraction performed by cognitive agent running in integrated management information system. The main advantages of this approach are cognitive agents' ability of including a context of extracted information and its ability of automatic decision-making on the basis of extracted information Contact: +91-9008001602 080-40969981
TEP006
Techniques for sentiment analysis of Twitter data: A comprehensive survey
ABSTRACT - The World Wide Web has intensely evolved a novel way for people to express their views and opinions about different topics, trends and issues. The user-generated content present on different mediums such as internet forums, discussion groups, and blogs serves a concrete and substantial base for decision making in various fields such as advertising, political polls, scientific surveys, market prediction and business intelligence. Sentiment analysis relates to the problem of mining the sentiments from online available data and categorizing the opinion expressed by an author towards a particular entity into at most three preset categories: positive, negative and neutral. In this paper, firstly we present the sentiment analysis process to classify highly unstructured data on Twitter. Secondly, we discuss various techniques to carryout sentiment analysis on Twitter data in detail. Moreover, we present the parametric comparison of the discussed techniques based on our identified parameters. Contact: +91-9008001602 080-40969981
TEP007
Real-time vehicle detection and tracking
ABSTRACT - The rapid increase in the number of the automobiles on the highway and urban roads have created many challenges regarding the proper management and control of the traffic. Detection and tracking of vehicles using the traffic surveillance system gives more promising way to manage and control the road traffic. Vehicle surveillance represents a challenging task of moving object segmentation in complex environment. The detection ratio of such algorithms depends upon the quality of the generated foreground mask. Therefore, the aim of this paper is to present an efficient method for detection and tracking of vehicles which focuses on the trajectory of motion of the objects. The proposed method preserves the group of pixels in foreground which can be probable vehicles and discards the rest as noise. Therefore, it selectively rejects the objects which cannot be vehicles at the same time consolidate the candidate vehicles. Here, the foreground mask generation process is improved so that the quality of generated foreground mask better consequently increases the detection ratio. The performance of the proposed method is evaluated by comparing it with other standard methods qualitatively as well as quantitatively. The experimental results have established the superior performance of the proposed method. Contact: +91-9008001602 080-40969981
TEP008
A novelistic approach to analyse weather conditions and its prediction using deep learning techniques
ABSTRACT - To predict the weather conditions based on the features of the data collected over the past data and to design a model which can allow to predict the future occurence of the event and also gives the accuracy of the different models used.Contact: +91-9008001602 080-40969981