Data mining is a process that uses a combinational framework out of a supportable assessment and machine learning data collection development to eliminate hidden models from massive informative collections. Further, clinical data mining is a basic assessment field in light of its substance in the progression of numerous applications in the flourishing clinical benefits zone. However, considering the current occurrences around the globe, the coronary ailment radiates an impression of being the primary source. The ID of the probability of coronary disease in an individual is a tangled endeavor for clinical experts since it requires extended lengths of contribution and genuine clinical preliminaries to be considered. In this study, four data mining techniques for data collection, namely K-Nearest Neighbour, Random Forest, Decision Tree, Navie Bayes, are utilized to establish a figure model to evaluate and identify risk factors of coronary disease. primary goal of this preliminary inquiry is to determine the optimal representation count fitting for providing the highest level of precision when collecting data from regular and periodic individuals. With the assistance of the coronary disease benchmark dataset recovered from the UCI repository, an unstable setup was created for the evaluation of the show of counts. When compared to other estimations for coronary disease inference, Random Forest count achieves the highest accuracy with 90.16 %.

Accurate and effective mapping of soil properties is regarded as a critical task in environmental and agricultural management. The evaluation of properties of soil is a daunting task while monitoring and sensing the environment. Existing sampling methods is a time-consuming and laborious job and they are limited based on the regions. However, the need of soil analysis and its properties is essential at landscape level. In this paper, we use Recurrent Convolution Neural Network (RCNN) to assess the soil properties via its classification task. The model in turn is compared with conventional geostatistical spatial interpolation methods. The utilization of Recurrent Neural Network (RNN) aims at studying the spatial and temporal variability of the properties of soil that adopts Kriging interpolation technique. The simulation is conducted to study the efficacy of the model under different soil conditions and the efficacy of RCNN is reported. The results of simulation shows that the proposed method achieves higher rate of classification accuracy than other models.

Segmentation is an essential part of the detection and classification series. The best result of brain MRI detection was followed by the best segmentation process. Supporting brain MRI detection accurately, one of the ways could be used by increasing segmentation. This paper utilizes one of the segmentation methods which is called clustering. We propose a clustering approach using K-Means. K-Means has advantages easy to understand, fast process, and guarantees convergence. But it has drawbacks which are initialization cluster center randomly, sometimes it is given good results but sometimes it is not. Therefore, this research proposes to optimize the weak side of K-Means using a grey wolf optimizer. Initialization cluster center was chosen based on fitness value. The fitness value of this paper is Sum Square Error (SSE), we purpose to minimize the SSE of the population and searching new positions depend on Gray Wolf Optimization (GWO)’s rule. The final position of GWO would be initialized by K-Means. The series of our research steps are acquisition image, grayscaling, resizing, segmentation, and analysis performance based on MSE and PSNR. The best result of the purposed method is k=17 which PSNR (16.09) and MSE (15.99). GWO K-Means were given the best outcome segmentation brain MRI based on measuring error value and PSNR.

Student with special needs often encounter problems where they lack their basic needed skill. These kids face challenges in interacting with the society. These kids often have a low level of social communication. The purpose of this proposed research is to investigate the effectiveness of Multi-Sensory Storytelling (MSST) to improve the social communication of children with special needs/Multiple Disabilities (MD) using technically advanced Virtual Reality (VR) and Computational Intelligence tools. This proposed research work is mainly focusing on age group of 6-10 years old children with special needs. Their levels of communication and life skills have been assessed by standard pre assessment intervention. Based on that customized training strategies on MSST have been formulated using VR techniques and Artificial Intelligent Methods. The experimental sessions have been planned to conduct for a time period of 60mins session for alternate days for twelve weeks course of the duration. The progresses of the customized training programs have been validated through post assessment interventions. The result indicated that among the kids of 20% girls and 80% of boys and the outcomes found to have a gradual improvement (27%) in their social communication with advance technology supported multi-sensory storytelling method. This research work demonstrated by a controlled group of children with autism and their level of improvement has been witnessed. This research work makes the children who live in their own world to lead a normal child; it makes us to treat them both physically and mentally as normal kids to do their day-to-day activities

Crime Prediction is an effort of determining future crime with the intention of diminishing them. Post-analysis of the data from past events, Crime prediction forecasts the future crime on the basis of time and location. In recent decades, the rapidly increasing series of criminal cases make accurate future crime prediction a difficult task. For crime trend prediction, a Prophet Model and Keras stateful LSTM has utilized in a recent study, in which missing value imputation and feature selection has carried out by simple computation as regards the enhancement of dataset quality and crime prediction. Though this method is simple to be applied, yet it has the inadequacy to prove its prediction accuracy. Because the sequence form of the input existed in LSTM maximizes the complexity while estimating the impact of each variable. For confronting these challenges, this study proposes a novel approach explicitly for crime trends prediction. In this model, the missing values have replaced by first Predictive Mean Matching method in the dataset. In addition, an improved bat optimization (IBAT) takes place to extract highly subjective features from the dataset, concerning the performance enhancement of trends forecasting and reduction of time computation. Ultimately, the convolution neural network algorithm has further involved predicting the crimes trends in order to reduce future crime.

ICTACT Journals are peer reviewed International Journals published quarterly. With the objective of creating Indian-based Journals of International quality and to build up local research content, ICTACT Journals exists for the purpose of providing a quality peer-reviewed platform for Scientists, Researchers, Academicians and Engineers who carry out their original research. The Journals will highlight the continued growth and new challenges in both basic research and application development.

Opinion Mining and Sentiment Analysis in Natural Language Processing (NLP) are challenging, as they require deep understanding. Understanding involves methods that could differentiate between the facts of explicit and implicit, regular and irregular, syntactical and semantic language rules. Researches oriented towards Natural Language Processing and Sentiment Analysis have many unresolved problems like co-reference resolution, negation handling, anaphora resolution, named-entity recognition, and word-sense disambiguation. This paper is proposed to develop an Optimized Partial Ancestral Graph (O-PAG) which is capable of mining patterns in human interactions and compare it with an existing tree based pattern mining approach. The experimental results are exposed to number of frequent interactions made and execution time. Results indicate that the overall performance can reach considerable improvements on using O-PAG approach.

An attempt has been made to evaluate the feedbacks of library users of four different libraries by using neural network based data mining techniques. This paper presents the results of a survey of users’ satisfactory level on four different libraries. The survey has been conducted among the users of four libraries of educational institutions of Kovai Medical Center Research and Educational Trust. Data were collected through questionnaires. Artificial neural network based data mining techniques are proposed and applied to assess the libraries in terms of level of satisfaction of users. In order to assess the users’ satisfaction level, two neural network techniques: Modified Multilayer Perceptron Network-Supervised and Modified Multilayer Perceptron Network-Unsupervised are proposed. The proposed techniques are compared with the conventional classification algorithm Multilayer Perceptron Neural Network and found better in overall performance. It is found that the quality of service provided by the libraries is highly good and users are highly satisfied with various aspects of library service. The Arts and Science College Library secured the maximum percent in terms of user satisfaction. This shows that the users’ satisfaction of ASCL is better than the other libraries. This study provides an insight into the actual quality and satisfactory level of users of libraries after proper assessment. It is strongly expected that the results will help library authorities to enhance services and quality in the near future.

Missing values are a widespread problem in data analysis. The purpose of this paper is to design a model to handle the missing values in predicting financial health of companies. Forecasting business failure is an important and challenge task for both academic researchers and business practitioners. In this study, we compare the classification of accuracy in decision tree methods (REP tree, C4.5) and with ANN method (K*) to handle the missing values.

In recent trends, the mobile devices play a very vital role in day to day activities of human beings. Google Android OS appeared lately i.e., in September 2008 in mobile market and gains more popularity. Google Android OS offers more flexibility for the users by offering N number of free downloadable applications to the users, which in turn gets changed as the superlative target for the attackers . As a result, many android applications that may contain the malware applications which are capable of stealing privacy information of users are available in market as a (.apk) file. The attackers started to target uneducated people and started stealing the information using applications. These applications request user to allow set of permissions during installation. For a new user it is difficult to identify the set of permissions that are harmful. This could be an advantage for malware intruders to access the data or infect the mobile device by introducing malware applications. Therefore, android malware detection various algorithms algorithm and Machine learning approaches is proposed to classify malware and goodware applications by analyzing the permission features.