Polycystic Ovary Syndrome Detection Based on Optimized Machine Learning Techniques
Machine Learning Framework for Water Contamination Detection using XGBoost and Naive Bayes Classifier
A Blockchain-Based Decentralized System for Secure, Transparent, and Fraud-Resistant Crowd Funding
Soil Analysis and Fertilizer Recommendation System using Machine Learning
A Research on Development of an Image Caption Generator using AI and Image Processing
Efficient Agent Based Priority Scheduling and LoadBalancing Using Fuzzy Logic in Grid Computing
A Survey of Various Task Scheduling Algorithms In Cloud Computing
Integrated Atlas Based Localisation Features in Lungs Images
A Computational Intelligence Technique for Effective Medical Diagnosis Using Decision Tree Algorithm
A Viable Solution to Prevent SQL Injection Attack Using SQL Injection
Research interest in using machine learning algorithms to develop models for detecting Polycystic Ovary Syndrome (PCOS) has increased significantly in recent years. This surge is understandable, as the condition mostly affects reproductive-age women and is a major cause of infertility. Consequently, researchers employ machine learning techniques to address this ailment. However, issues of accuracy and optimal results are still major issues to contend with using this technology owing to the complexity of the medical dataset. Therefore, this study proposes to detect PCOS using Support Vector Machine, Random Forest, and AdaBoost with the aid of optimized techniques such as the Red Deer Algorithm (RDA) and Firefly Optimization Algorithm. The optimization techniques and three machine learning models were used to optimize the 45 features of the PCOS dataset that was obtained from the Kaggle repository. The RDA + SVM achieved an accuracy of 88%, the RDA + RF achieved an accuracy of 82%, the RDA + AdaBoost achieved an accuracy of 85%, the FF + SVM achieved an accuracy of 89%, and the PSO + RF achieved an accuracy of 89%.
Water pollution occurs when harmful substances such as toxic chemicals, pathogenic microorganisms, or heavy metals contaminate freshwater sources, threatening both public health and ecosystem stability. Reliable monitoring of water quality is therefore essential for early detection and prevention of contamination. Conventional surveillance systems relying on large-scale Internet of Things (IoT) sensor networks are frequently costly to implement, complex to maintain, and may deliver inconsistent real-time data. This study presents a data-driven framework that combines IoT-enabled sensing with machine learning techniques to improve the accuracy and efficiency of water quality assessment. During preliminary testing, publicly available datasets are used to simulate sensor readings, reducing dependence on physical hardware and lowering operational costs. Two classification algorithms, Extreme Gradient Boosting (XGBoost) and Naïve Bayes (XGB-NB), are employed to categorize water samples as either potable or polluted. Using the pond_iot_2023 dataset, which contains diverse physicochemical parameters, the proposed system demonstrates a robust, scalable, and cost-effective approach to intelligent water contamination detection.
Crowdfunding is a widely used method to raise funds for startups, social initiatives, and creative study by collecting small contributions from a large number of people. Despite its popularity, traditional crowdfunding platforms suffer from issues such as high transaction fees, fraud risks, limited transparency, and lack of investor control. Blockchain technology offers a promising alternative by enabling secure, transparent, and decentralized management of funds without relying on intermediaries. This paper explores how blockchain can transform crowdfunding by improving trust, accountability, and efficiency. To address fraud-related challenges, the SMOTE Borderline technique is introduced as a machine learning method to balance datasets and improve the accuracy of fraud detection. The study also highlights ongoing issues such as scalability, regulatory uncertainties, and smart contract vulnerabilities, while pointing toward the future development of secure decentralized crowdfunding systems.
Agriculture is a growing field of research. In particular, crop prediction in agriculture is critical and is chiefly contingent upon soil and environmental conditions, including rainfall, humidity, and temperature. In the past, farmers were able to decide on the crop to be cultivated, monitor its growth, and determine when it could be harvested. Today, rapid changes in environmental conditions have made it difficult for the farming community to continue doing so. The existing system aims to investigate the use of machine learning techniques in crop prediction for agriculture, where environmental conditions play a critical role. Efficient feature selection methods are employed to preprocess raw data into a computable dataset, and only relevant features are included to ensure high precision and reduce redundancies. The proposed system aims to utilize a combination of machine learning algorithms to enhance crop prediction capabilities. The system employs a feed-forward backward propagation neural network to analyze soil data captured at different times, distances, and illumination levels, enabling precise assessment of soil conditions. Additionally, the system utilizes the k-nearest neighbor's algorithm to determine suitable fertilizers for various crops, ensuring optimal nutrient supply. Furthermore, the random forest algorithm is employed to predict crop yield based on a range of factors, facilitating accurate estimations for agricultural planning and decision-making. The integrated machine learning approach enhances crop yield prediction accuracy and increases productivity.
Image caption generation involves developing an appropriate textual description of an image through the combination of visual and textual information. Here, a deep learning pipeline with an encoder–decoder architecture is discussed, which uses a deep learning model, such as a convolutional neural network (for instance, ResNet50), to obtain feature representations from an image, and a sequence learning model that employs Long Short-Term Memory (LSTM) to generate the textual description of the image. Spatial attention is incorporated into the decoder to help generate more relevant and detailed captions by associating model attention across important image regions. The pipeline is evaluated using standard evaluation metrics such as BLEU, METEOR, and CIDEr, which provide scores showing how similar the newly generated captions are to human captions/annotations. Demonstrations on the standard Flickr8k dataset show that this approach produces fluent, accurate, and informative descriptions and discuss future applications of the approach, including accessibility, automated tagging, and human–computer interaction.
