Research & Review: Machine Learning and Cloud Computing(e-ISSN:2583-4835) 2023-09-11T13:25:00+0530 Open Journal Systems <p><strong>RRMLCC</strong> is a peer reviewed journal in the discipline of Computer Science published by the<br />MAT Journals Pvt. Ltd. It is a print and e-journal focused towards the rapid publication of<br />fundamental research papers on all areas of Artificial Intelligence. The Journal aims to<br />promote high quality empirical Research, Review articles, case studies and short<br />communications mainly focused on Machine Learning, Cloud Computing, Bayesian<br />Learning, Supervised Semi-Supervised and Unsupervised Learning, Decision Support<br />Systems, Human-Computer Interaction and Systems.</p> Evaluation of Soil Quality for Crop Prediction Based on Feature Selection in Machine Learning 2023-07-15T12:46:59+0530 Dr. Rasina Begum S Janarthanan B Naveen P Pandeeswaran <p><strong>Farmers can practice an effective understanding of the soil's idiosyncrasies allowing for more crops to be grown with fewer resources. Soil prediction relies heavily on calcium, phosphorus, pH, and soil organic carbon. These traits have a substantial impact on crop productivity. The method employs two independent machine learning models, Using KNN and random forest regression; specific soil parameters can be predicted. Crop productivity is boosted as a result of accurate crop prediction. This is where machine learning in the field of crop prediction comes into play. Crop forecast is influenced by geographic, meteorological, and soil characteristics. An integral aspect of the prediction process used by feature selection techniques is choosing the proper features for the right crop or crops. This paper uses categorization approaches to recommend the appropriate crop or crops for the area and conducts a comparative study of multiple wrapper feature selection methods. According to the experimental findings, the adaptive bagging classifier and recursive feature elimination approach surpass the competition. Based on the Africa soil property prediction dataset, the performance of these models is assessed. Knowing the characteristics of the soil in their particular terrain will be useful to the farmers. This study investigates how effectively various machine learning approaches can predict soil qualities crucial to agriculture using spectroscopic data. </strong></p> 2023-07-15T00:00:00+0530 Copyright (c) 2023 Research & Review: Machine Learning and Cloud Computing(e-ISSN:2583-4835) Exploring Machine Learning Techniques for Data Analysis in the RideSharing Industry 2023-07-26T11:40:53+0530 Rajendra Prasad R M.S. Shashidhara <p><strong>Uber, a popular ride-sharing platform, generates vast amounts of data that can be leveraged to gain valuable insights and optimize its operations. This research paper focuses on the application of machine learning techniques for data analysis in the context of Uber. The paper aims to provide a comprehensive overview of the existing literature and research on Uber-related data analysis using machine learning, covering various aspects such as demand forecasting, surge pricing optimization, rider behaviour analysis, driver allocation, and routing.</strong></p> <p><strong>In the domain of demand forecasting, researchers have explored time series analysis, regression, and deep learning models to accurately predict ride demand and optimize driver allocation. Surge pricing optimization has been addressed through reinforcement learning algorithms, dynamic pricing models, and approaches that consider user behaviour and market dynamics. Rider behaviour analysis has employed machine learning techniques for customer segmentation, churns prediction, and personalized recommendations. Driver allocation and routing have been optimized using machine learning algorithms to efficiently allocate available drivers based on factors like trip duration, driver availability, and traffic conditions.</strong></p> <p><strong>Additionally, privacy and security concerns associated with Uber data analysis have been addressed through privacy-preserving techniques and secure computation methods. The paper discusses the challenges faced in these areas and identifies potential future research directions.</strong></p> 2023-07-26T00:00:00+0530 Copyright (c) 2023 Research & Review: Machine Learning and Cloud Computing(e-ISSN:2583-4835) Detecting Persecution on Interactive Networks Using Machine Learning Methods 2023-07-27T12:45:42+0530 Sheela B V Rajesh N <p>Persecution on interactive networks, such as <br>social media platforms and online forums, <br>poses significant challenges to ensuring a safe <br>and inclusive digital environment. Detecting <br>and addressing instances of persecution is <br>crucial for safeguarding individuals' rights <br>and promoting online harmony. This research <br>paper presents a novel approach to detecting <br>persecution on interactive networks using <br>machine learning methods.<br>The proposed framework leverages the power <br>of machine learning algorithms to <br>automatically identify patterns and indicators <br>of persecution within user-generated content. <br>The process begins with the collection and <br>preprocessing of a large-scale dataset <br>comprising diverse interactions on interactive <br>networks. Various features, including textual, <br>contextual, and user-based attributes, are <br>extracted to capture the nuanced aspects of <br>persecution.<br>Next, a range of machine learning techniques, <br>such as natural language processing, <br>sentiment analysis, and social network <br>analysis, are employed to analyze the dataset. <br>Multiple classification models, such as <br>support vector machines, random forests, and <br>deep learning architectures, are trained and <br>evaluated to identify the most effective <br>approach for persecution detection.<br>The experimental results demonstrate the <br>effectiveness of the proposed methodology in <br>accurately detecting instances of persecution <br>on interactive networks. The trained models <br>achieve high precision and recall rates, <br>highlighting their ability to discern subtle <br>instances of persecution and distinguish them <br>from non-persecutory content. The findings of <br>this study contribute to the development of <br>automated tools that can aid in identifying <br>and mitigating persecution on interactive <br>networks, thereby fostering a safer and more <br>inclusive digital space.</p> 2023-07-27T00:00:00+0530 Copyright (c) 2023 Research & Review: Machine Learning and Cloud Computing(e-ISSN:2583-4835) A Review on Intelligent Malware Detection Using a Machine Learning Approach 2023-08-29T10:34:43+0530 Tiab Ali Pradeep Kumar <p>In the present period, cell phones are<br>becoming famous with different applications<br>(applications) to make our lives more<br>straightforward. A few versatile Working<br>Frameworks (operating systems) are<br>accessible in the market including iOS,<br>Android, BlackBerry and Windows<br>Telephone. Android is a broadly utilized<br>portable operating system with a piece of the<br>pie of over 85%. It depends on the Linux<br>piece explicitly worked for touchscreen<br>gadgets like tablets cell phones and so on. In<br>the on-going time, there is an expansion in the<br>use of cell phones for different purposes like<br>banking, virtual entertainment, training and<br>so on. The developing prominence of Android<br>applications has baited aggressors to make<br>pernicious applications that represent a few<br>dangers, for example, monetary misfortune,<br>data spillage and so on. These pernicious<br>applications are turning out to be more<br>complex and utilizing better approaches to<br>target cell phones. These can avoid location<br>and relief strategies that have previously been<br>created. The customary security frameworks<br>like interruption identification/counteraction<br>frameworks and Against Infection (AV)<br>programming depend on signature-based<br>techniques and accordingly can't recognize<br>new-age malware. Hence, there is a need to<br>plan methods for better malware<br>distinguishing proof and grouping. Besides, in<br>a true situation, the quantity of tests shifts<br>considerably among different malware<br>families. In this manner, it is vital to assemble<br>malware arrangement models that can deal<br>with imbalanced classes. Moreover, there is<br>an absence of sufficient exploration to break<br>down the dangers or hazards presented by<br>Android applications. The fundamental point<br>of this examination is to resolve these issues<br>and give powerful arrangements. AI (ML)<br>procedures have been utilized to distinguish<br>malware given characteristics mined utilizing<br>static and dynamic malware examination.<br>Through tests, it is seen that the two sorts of<br>malware examinations have their upsides and<br>downsides. The obscure malware utilizes<br>progressed muddling procedures to conceal<br>its presence, and it can distinguish the<br>sandbox climate where it is running.<br>Subsequently, the single methodology either<br>static or dynamic can't recognize and<br>characterize obscure malware. A coordinated<br>methodology (a blend of static and dynamic<br>ascribes) has been proposed in this work<br>which can break down, recognize and group<br>the malware</p> 2023-08-29T00:00:00+0530 Copyright (c) 2023 Research & Review: Machine Learning and Cloud Computing(e-ISSN:2583-4835) Advancements in Activity Recognition Technologies 2023-09-11T13:25:00+0530 Prathiksha S Raj R Ashok Kumar <p>In today's data-rich era, marked by the <br>widespread use of data collection tools like <br>smartphones and video cameras, Human <br>Activity Recognition (HAR) has become a <br>dynamic and versatile field with numerous <br>practical applications. The fusion of these<br>devices with artificial intelligence (AI) has <br>revolutionized our ability to detect and <br>understand human activities with <br>unparalleled precision, revealing hidden <br>insights.<br>The proliferation of electronic gadgets <br>equipped with sensors, cameras, <br>accelerometers, and gyroscopes has <br>significantly expanded the scope of HAR. <br>These devices serve as the bedrock for <br>collecting intricate data on human movements <br>and behaviours. Simultaneously, AI <br>advancements empower us to process and <br>interpret this data accurately, providing <br>profound insights into various human <br>activities.<br>HAR hinges on three interconnected pillars: <br>data acquisition devices, AI algorithms, and <br>diverse applications that leverage their <br>synergy. This paper conducts a <br>comprehensive exploration of these pillars, <br>drawing insights from extensive literature <br>and real-world datasets encompassing various <br>contexts and data sources.<br>Notably, neural networks play a pivotal role <br>in advancing HAR techniques. These AIdriven algorithms are the cornerstone of <br>precise activity recognition. The paper delves <br>into the intricacies of neural networks, <br>shedding light on their ability to reveal <br>concealed information and enable nuanced <br>activity interpretation.<br>Throughout our exploration, we confront the <br>challenges confronting HAR, including data <br>pre-processing, noise reduction, model <br>optimization, and generalization. Addressing <br>these challenges is essential for enhancing the <br>accuracy and applicability of HAR methods.</p> 2023-09-11T00:00:00+0530 Copyright (c) 2023 Research & Review: Machine Learning and Cloud Computing(e-ISSN:2583-4835)