Volume 13 | Issue 4 |

 Abstract

Lung cancer is the most common and deadliest cancer worldwide, where early detection is essential in improving patient outcomes. Machine learning (ML) has emerged as a groundbreaking healthcare technology with enormous potential in optimizing the accuracy, efficiency, and accessibility of lung cancer diagnosis. This paper explores various ML algorithms for the early detection of lung cancer from clinical and medical imaging data. Different approaches, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and ensemble models, are assessed based on their capacity to classify and predict malignancy in lung nodules [1] to [5]. The work utilizes public datasets such as Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) for training and validation models [6], [7]. Data preprocessing tasks like noise removal, feature extraction, segmentation, and increasing the quality and pertinence of the input data are performed [8]. The feature selection methods use dimensionality reduction techniques to ensure efficient performance and minimal computational cost [9]. Research has demonstrated that CNNs are more sensitive and specific for the detection of cancerous lesions than traditional ML approaches [10]-[12]. Deep learning algorithms are also more capable of detecting subtle imaging features that may not be detectable by the naked eye, and this improves the reliability of diagnosis. The addition of clinical parameters such as age, smoking status, and genetic predispositions improves predictive ability [13], [14]. In conclusion, ML use in lung cancer detection is a significant step toward early diagnosis, with high potential for enhanced mortality rates and personalized treatment planning.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Lung cancer detection, Machine learning (ML), Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), Medical imaging, Lung nodules, Deep learning, Feature extraction ,Early diagnosis ,Predictive modeling

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

One potentially significant idea that contributes to achieving global sustainable development is green technology. A fresh, significant idea that would improve the environment is needed in the globe today. Realizing the need for creative green products in today's global market and attempting to determine the detrimental effects of non-green products are the study's main goals. A specific city (Coimbatore) has been chosen for the study, and the necessary data has been gathered from a variety of sources, examined using appropriate statistical techniques, and facts have been discovered. According to the study, so-called green or organic items benefit humanity more and aid in the eradication of some problems related to green technology. It contributes to sustainable growth. The study also sheds information on potential directions for future research.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Green technology, Sustainable, Environment, Organic, Eradicate, potential directions.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Increase in the number of potholes have serious impact on road safety and infrastructure, leading to increased costs for vehicle repairs and accidents. Why? Even with manual inspections and sensor-based systems, pothole detection is not an option. A real-time pothole detection system using deep learning techniques, built on the YOLO (You Only Look Once) ONNX model is presented in this article. This involves gathering data, generating model data and testing mobile and vehicle-mounted applications over the course of several months. It was 92% accurate in detection and had an adequate high confidence level estimate (ROC-AUC) score, while also maintaining proper balance between precision and recall. Other concerns we tackle include differences in environment between samples, inaccurate data detection systems, and hardware failures.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Road safety, object detection, YOLO, real-time, machine learning, image processing.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Androsace globifera contains significant phytochemicals such as saponins and is utilized for treating liver and kidney diseases, amenorrhea, skin allergies, leucorrhoea, and as an abortifacient. Morphological studies reveal that the leaves are diverse in shape, ranging from speculating to elliptical. Organoleptic analysis indicates an astringent taste, aromatic odor, and brittle fracture, with the stem being straight and colored brownish-green. The flowers are pink with 12-15 blooms, five petals, seven sepals, a 1.5 mm style, and a 3 mm capsule. The powdered leaves and roots are greenish and brown, respectively, with an astringent and aromatic odor, and a bitter and acrid taste. Microscopic and physicochemical studies identify vascular bundles and upper and lower epidermal cells. The moisture content of roots and leaves is 2.5% and 3%, respectively. The total ash content of roots and leaves is 25% and 22.5%, acid-insoluble ash is 12.5% and 9%, and water-soluble ash is 10% and 8.9%. The extractive values for roots and leaves are as follows: water (0.8% and 1%), ethanol (4% and 2.25%), chloroform (8% and 8.5%), ethyl acetate (9% and 7%), and methanol (11% and 13%). Leaf constants include a stomatal number of 5, a stomatal index of 2.5-7, a vein islet number of 11-17, a vein termination number of 9-12, and a palisade ratio of 2:6. Fluorescent studies show the leaves and roots as light brown and dark brown, respectively. Histochemical analysis reveals the presence of lignified cellulose and cuticular cell walls, aleurone grains, calcium oxalate, fatty acids, resins, inulin, mucilage, tannins, and hydroxyl anthraquinones.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Androsace globifera, Characteristics, Evaluation, Microscopy, Screening

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents the design and implementation of a versatile floor cleaning robot, controlled through an Android application. The robot integrates multiple cleaning functionalities--vacuuming, mopping, spraying, and drying--while ensuring effective navigation and obstacle avoidance. It is equipped with a modular cleaning platform, adjustable cleaning pads, and real-time resource and battery monitoring, all controlled through a user-friendly mobile interface. Building on previous research in smart home systems, intelligent path planning, and sensor fusion, the proposed system maximizes cleaning efficiency and adaptability, while significantly reducing user effort. The robot's ability to adapt to various floor types, optimize cleaning routes, and enable remote operation via mobile scheduling and monitoring is demonstrated through experimental tests. This work advances the development of energy-efficient cleaning devices and smart home automation.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Autonomous cleaning robot, Smart home, Obstacle detection, Android control, Vacuuming, mopping, Adaptive navigation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This report investigates the existing work on optimizing house price estimation with machine learning and deep learning techniques. Focusing on its base data types structured and then multi-modal (price, geospatial etc.) it runs through essential algorithms such as Linear Regression, XGBoost and Neural Network and compares their capabilities pros and cons. From the results, it emphasizes the ability of these methods to enhance predictive accuracy based on heterogeneous data sources, whilst challenges such as interpretability of models and integration of data persist. Promising future directions to move the field forward, such as hybrid models and multi-modal approaches, are discussed.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Deep learning, machine learning, house price prediction, multi-modal data, neural networks, regression analysis, feature engineering, hybrid models

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

For domestic, agricultural, and industrial purposes, groundwater is an essential supply of fresh water in India, particularly in regions with inadequate surface water infrastructure. Groundwater quality in Coimbatore, Tamil Nadu, a fast-growing metropolis renowned for its textile industries, is being weakened by pollution from sewage, automobile emissions, industrial discharges, and agricultural runoff. The physicochemical properties of borewell water from western Coimbatore's non-traffic and traffic-congested areas are compared in this study. To evaluate water quality and comprehend the impact of human activity, parameters including pH, TDS, hardness, chloride, and microbiological content were examined. The study emphasises the influence of urbanisation and traffic-related pollution on groundwater, pointing out notable variations in water quality between the two zones.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Groundwater quality, Borewell water, Physicochemical analysis, Urban pollution, Traffic areas, Coimbatore, Water contamination, Sustainable water management, Industrial effluents, Microbial content.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid advancement of Artificial Intelligence (AI) has introduced new complexities into the traditional framework of Intellectual Property Rights (IPRs). This research explores the legal challenges posed by AI-generated works in the Indian context, focusing on three primary domains of IP law--copyright, patents, and trademarks. It critically analyzes whether the existing legal structure, which assumes human authorship and inventorship, is equipped to handle autonomous or semi-autonomous outputs generated by AI systems. Drawing upon doctrinal research, comparative analysis with jurisdictions such as the United States, the European Union, and the United Kingdom, and policy reports by international organizations like WIPO, this paper reveals significant doctrinal and enforcement gaps in Indian IP law. It argues for the introduction of sui generis rights for AI-generated creations and recommends legislative amendments to accommodate AI's growing role in innovation and branding. By proposing a reform-oriented legal framework rooted in accountability, transparency, and global compatibility, the paper advocates for India to lead a proactive IP law transformation suitable for the AI era.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artificial Intelligence, Intellectual Property Rights, Copyright, Patents, Trademarks, India, Legal Reform, Sui Generis Rights, AI-Generated Works, Innovation Law Acknowledgement

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Agriculture forms the foundation of numerous nations, including India, sustaining millions by overcoming challenges like climate shifts and outbreaks of plant ailments. Innovative research has led to the creation of a web-based platform offering real-time guidance on optimal crop choices, considering points such as soil health, temperature, humidity, ph levels.This platform brings together advanced machine learning and deep learning techniques to address critical areas of precision agriculture. It comprises five key modules: Crop Recommendation, Yield Prediction, Plant Disease Detection, Smart Farming Guidance, and Weather Forecasting .The Crop Recommendation module suggests the most suitable crops for cultivation based on parameters such as soil type, pH, nutrient content, and regional agro-climatic conditions. This promotes sustainable crop planning and resource optimization. The Yield Prediction engine uses historical yield data, meteorological records, and agricultural inputs to forecast potential productivity, aiding in economic planning and supply chain management. Through the Plant Disease Detection module, farmers can identify diseases early by uploading images of affected crops, which are analyzed using convolutional neural networks to suggest accurate diagnoses and treatments. The Smart Farming Guidance system delivers dynamic recommendations for irrigation scheduling, nutrient management, and pest control tailored to current crop conditions. Additionally, the Weather Forecasting component offers hyper-local predictions, enabling timely interventions to mitigate climate-related risks. Collectively, AgriSense stands as a holistic advisory platform that empowers farmers, enhances crop productivity, and contributes to the advancement of smart and sustainable agriculture globally.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

crop recommendation, machine learning, plant disease identification, random forest, weather-forecast ,fertilizer recommendation.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper proposes a Smart Industrial Real-Time Water Quality Monitoring and Prediction System that integrates the Internet of Things (IoT) and machine learning to improve industrial water management and environmental safety. The system monitors key water parameters -Total Dissolved Solids (TDS), ammonia concentration, pH, turbidity, and temperature via dedicated sensors connected to an Arduino microcontroller, with data transmitted to the Thing-Speak cloud platform using an ESP8266 Wi-Fi module. Real-time alerts are facilitated through an on-site buzzer and a Telegram bot to notify users of abnormal conditions. For predictive analytics, the system employs machine learning algorithms such as Random Forest, Naive Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), XG-Boost, Logistic Regression, and Decision Tree to classify water quality status based on historical data. This unified framework provides a scalable and cost-effective solution for continuous monitoring, early warning, and data-driven decision-making across industries such as manufacturing, agriculture, and wastewater treatment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Water Quality Monitoring, Internet of Things (IoT), Machine Learning, Real-Time Prediction, Industrial Water Management, Environmental Safety.

  License

Creative Commons Attribution 4.0 and The Open Definition