Data Mining and Knowledge Engineering https://www.i-scholar.in/index.php/CiiTDMKE <p>The aim of Journal Data Mining Knowledge Engineering focuses on theoretical and practical research development on knowledge engineering and data mining.</p><p><br />        The scope of the journal includes developing technologies in Data Analysis, Data cleaning and pre-processing, Data engineering, Data extraction and reporting, Data mining algorithms and processes, Data mining techniques, tools and applications, Decision analysis, Knowledge-based/rule-based/case based/expert system design, Knowledge acquisition, dissemination, discovery methodologies and technologies, Database design and architecture, Intelligent system design, Data integration and exchange, Data security and data integrity, Database administration and maintenance issues.</p> Coimbatore Institute of Information Technology en-US Data Mining and Knowledge Engineering 0974–9683 Design and Implementation of Final Year Project Management System https://www.i-scholar.in/index.php/CiiTDMKE/article/view/216082 Final year project is one of the requirements for undergraduate degree program in higher institutions. Every student must complete and submit his/her project before graduating. The process entails the coordinator to group the final year students and then assign them to supervisor and then the student meets their respective supervisor and agree on project topic for approval. It has been established that students are unable to complete their projects on scheduled due to manual documentation with supervisor and their geographical locations thereby making monitoring very difficult. To ameliorate these challenges, a web based final year project management system was designed and developed. Agile methodology approach was adopted while JavaScript, Hypertext Markup Language (HTML), and Cascade Style Sheet (CSS) was used for the frontend, PHP for the backend and MySQL as the database. The project supervisor will be able to use the system to monitor the progress of the projects and the online collaboration. Both the students and supervisor will benefit from this feature as there is no need to interact physically. The system also provides features that facilitate effective communication among group members. J. V. Joshua O. D. Alao T. S. Nwachukwu 2021-06-01 2021-06-01 13 A Survey on ML Models of Wind Energy Forecasting https://www.i-scholar.in/index.php/CiiTDMKE/article/view/216083 Given the intermittent nature of the wind, accurate wind energy forecasting is significant to the proper utilization of renewable energy sources. Various types of data processing methods are successfully applied to assist these models and further improve forecasting performance. Comprehensive research of their methodologies is called on for a thorough understanding of current challenges that affect model accuracy and efficiency. An overall analysis of their intentions, positions, characteristics, and implementation details is provided. A general evaluation is carried out from different perspectives including accuracy improvement, usage frequency, consuming time, robustness to parameters, maturity, and implementation difficulty. Among the existing data processing methods, outlier detection and filter-based correction are relatively less used. Their potential can be better explored in the future. Furthermore, some possible research directions and challenges of data processing in wind energy forecasting are provided, in order to encourage subsequent research. T. M. Angelin Monisha Sharean S Sanjana 2021-06-01 2021-06-01 13 Human Pose Estimation Benchmarking And Action Recognition https://www.i-scholar.in/index.php/CiiTDMKE/article/view/216103 Existing frameworks for video-based posture assessment and following battle to perform well on reasonable recordings with various individuals and regularly neglect to yield body-present directions steady over the long haul. To address this inadequacy this paper presents Pose Track which is another huge scope benchmark for video-based human posture assessment and verbalized following. Our new benchmark includes three assignments zeroing in on I) single-outline multi-individual posture assessment, ii) multi-individual posture assessment in recordings, and iii) multi-individual enunciated following. To set up the benchmark, we gather, explain and discharge another dataset that highlights recordings with various individuals marked with individual tracks and verbalized posture. A public brought together assessment worker is given to permit the examination local area to assess on a held-out test set. Moreover, we lead a broad trial concentrate on ongoing methodologies to explained present following and give examination of the qualities and shortcomings of the cutting edge. We imagine that the proposed benchmark will invigorate useful examination both by giving a huge and agent preparing dataset just as giving a stage to impartially assess and think about the proposed strategies Vineethapodila 2021-06-01 2021-06-01 13 Sentiment Analysis using SVM Machine Learning Techniques on Social Media https://www.i-scholar.in/index.php/CiiTDMKE/article/view/216104 Sentiment analysis is a branch of Natural Language Processing (NLP) and machine learning in which text is classified into two categories: positive and negative. Because the use of the internet and social media is growing at a rapid pace, the products created by these two are receiving far more client input than in the past. Text generated by social media, blogs, posts, and product reviews, among other places, has become the best-suited examples for consumer sentiment, delivering the best-suited notion for that particular product. As a result, the hybrid feature selection proposed in this paper is a combination of particle swarm optimization (PSO) and cuckoo search. The hybrid feature selection technique surpasses the standard technique due to the subjective nature of social media reviews. Support Vector Machine (SVM) classifier was used to examine performance criteria such as f-measure, recall, precision, and accuracy on the Twitter dataset, and it was compared to a convolution neural network. The proposed work outperforms the existing work, according to the findings of this paper's experiments based on various factors. R Gunavathi N Saranya 2021-06-01 2021-06-01 13