Volume 12 | Issue 5 |

 Abstract

Advent of Internet of Things (IoT) technology has rised in various sectors, including agriculture, by introducing automated systems for efficient resource management. This case study presents an IoT-based automated irrigation system designed to optimize water usage in agriculture, ensuring both efficiency and sustainability. By integrating sensors to detect soil moisture levels, weather conditions, and plant requirements, the system intelligently controls irrigation processes. Real-time data analysis enables precise watering schedules tailored to the specific needs of crops, reducing water wastage and enhancing crop yield. Moreover, remote accessibility through mobile applications empowers farmers to detect and control irrigation activities from anywhere, fostering convenience and flexibility. This innovative approach not only conserves water resources but also promotes sustainable farming practices, contributing to environmental preservation and long-term agricultural viability.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IoT, automated irrigation, efficiency, sustainability, smart agriculture

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This report offers a thorough comparative analysis of three prominent machine learning models-- Naive Bayes, Gradient Boosting, and Ensemble Learning--in the domain of predicting the severity levels of lung cancer. Through meticulous data curation and preprocessing, a wide array of health parameters and lifestyle factors were incorporated to ensure the robustness of predictive modeling. The report delineates the rigorous methodologies employed in model training and evaluation, encompassing the utilization of diverse performance metrics to assess predictive efficacy comprehensively. By conducting extensive experimentation and comparative analysis, invaluable insights into the predictive capabilities and limitations of each model were garnered. These findings carry profound implications for healthcare professionals, furnishing them with evidence-based insights to facilitate early intervention and personalized treatment planning for patients at risk of lung cancer progression. Ultimately, this study endeavors to elevate clinical decision-making processes, fostering improved patient outcomes and more efficient allocation of healthcare resources in the management of lung cancer.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This study presents a comparative analysis of Naive Bayes, Random Forest, and Gradient Boosting algorithms for predicting the survival of lung cancer patients. As lung cancer continues to be one of the leading causes of cancer-related deaths globally, accurate prediction is essential for treatment planning and patient care. Here, these machine learning methods are used to create predictive models by utilizing a dataset that included clinical variables and patient outcomes. Each model's performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. Furthermore, a feature importance analysis was carried out to pinpoint the critical prognostic parameters affecting the prediction of survival. Our results demonstrate the effectiveness of Gradient Boosting in achieving the highest predictive performance, followed by Random Forest and Naive Bayes. Furthermore, the feature importance analysis revealed critical clinical variables contributing to survival prognosis, providing insights into the underlying factors influencing lung cancer patient outcomes. This study plays a pivotal role in advancing personalized medicine by enabling more precise survival prognoses for individuals diagnosed with lung cancer. Such insights empower clinicians to make well- informed decisions regarding treatment strategies, ultimately enhancing the quality of patient care.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Lung Cancer, Prediction, Ensemble learning, Voting Classifiers, Naive Bayes, Random Forest, Gradient Boosting, Accuracy, Precision, and F1- score.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The sense of sight is one of the most important senses for each human being. Regretfully, visual problems affect millions of individuals globally and provide serious obstacles to information access and communication. Their inability to maneuver safely and freely is frequently hampered by this battle. The suggested approach aims to convert the visual world into an aural one in order to remedy this problem. Using real-time object detection technology, this change will enable those with vision impairments to walk independently without the need for outside support. The program uses machine learning and image processing to quickly identify items using the camera in real time. It can also provide audio output to blind users so they can know where things are. This cutting-edge technology seeks to address the many issues caused by the incapacity to distinguish between items.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Object Detection, Android Application, YOLO, CNN (Convolutional Neural Network), Visually Impaired people, Computer Vision, Algorithms.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This comprehensive review examines recent advancements in agricultural research through a thorough analysis of four pivotal studies. Each paper contributes distinctive insights to the agricultural landscape, covering topics from integrating machine learning in seed testing to the adoption of natural farming practices, the implementation of smart farming technologies, and the development of an automatic system for crop pest and disease monitoring. The synthesis of these studies illuminates evolving strategies and technologies with the potential to enhance agricultural productivity, sustainability, and resilience.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Plant disease detection, Deep learning, Crop pest management, Knowledge graphs, Machine learning, Crop health, Early detection, Data integration, Remote sensing, Image processing

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

People can interact and exchange ideas and emotions through communication. The social contacts of the deaf community are hindered by multiple factors. The people converse with each other using sign language. A technology can translate sign languages into a form that is comprehensible in order to communicate with ordinary people. Developing a real- time text-to-Indian Sign Language (ISL) translation system is the aim of this project. For the most part, manual labor is used. In this paper, we describe a convolutional neural network-based deep learning method for classifying signs. We initially construct a classifier model using the numerical signs and the Python-based Keras convolutional neural network implementation. In phase two, a second real-time system was used to use skin segmentation to detect the Region of Interest in the frame that displays the bounding box. To forecast the sign, the segmented region is fed into the classifier model. The accuracy rating of the system for the same subject is 99.56% in poor light and 97.26% in high light. It was observed that the classifier improved with varying image capture angles and backgrounds. The RGB camera system is the main emphasis of our strategy.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Real-time systems, areas of interest, convolutional neural networks, and deep learning

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Facial expression detection is a critical component of the application designed to address mental health issues. By leveraging cutting-edge machine learning algorithms, system can analyse facial expressions to detect early signs of Facial , anxiety, and other mental health concerns. The approach involves gathering data from various sources, including social media networks, to train our models and improve their accuracy. System employs sophisticated techniques such as image and video processing to analyse facial gestures and expressions. Key facial characteristics including the lips, nose, hands, and eyes can help us recognize small clues that represent various emotional states. These cues include variations in muscle movements, changes in facial symmetry, and shifts in skin tone. Proposed approach makes use of an extensive emotion expression system that classifies facial expressions into several emotional states, such as neutral, happy, sad, and angry. By precisely recognizing these emotions, system can give clients bits of knowledge into their psychological prosperity and accommodate them with identifying possible problems early on. Through extensive analysis of facial expressions and behavioural patterns, the application can offer personalized recommendations and assistance to those dealing with problems related to mental health. By use of the identification and analysis of facial emotions, system empower the clients to proactively pursue improving their psychological well-being and seeking appropriate assistance when needed. In general, systems goal to enable early identification and analysis of mental health concerns is greatly aided by system's facial expression detection technology, which in turn helps people live longer, better lives.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Facial Emotion detection, Deep learning, Machine learning, Early detection, Real-time sensing, CNN, image processing, naive bias, medical science, supervised machine learning

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Farmers suffer economic losses due to agricultural dis eases. Routine disease detection and health monitoring in pomegranate crops is labor intensive, requires atte ntion and takes time. On the other hand, new advances in computer vision a nd imaging have made it possible to detect diseases in pomegranate plants. This study provides an overview of image processing techniques for detecting pomegran ate disease. This study provides an overview of image processing techniques for detecting pomegranate disea se. We also address the challenge of identifying disease s in images and demonstrate the possibility of accurate identification using deep learning.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CNN, Softmax layer, SVM (support vector machine), K-means, and pomegranate

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The development of a web application for training and placement cell management marks a significant stride towards automating manual and arduous tasks within the training and placement department. This platform serves as a centralized hub where students can input all requisite educational and personal information, aligning their profiles with the requirements of prospective companies. The primary objective of this initiative is to furnish a user-friendly login interface accessible to students, training and placement officers, and other pertinent employees. Students can effortlessly input necessary information into the system, streamlining the process, while training and placement officers can readily access pertinent student data. With the implementation of a fully automated system, the need for extensive manpower is diminished, resulting in substantial time savings for both students, training n placement officer. Moreover, this system serves as a centralized repository capable of controlling and processing all academic and personal student information. Additionally, the system facilitates various functionalities, including sending notices to students, generating lists of students based on company criteria, providing resumes of shortlisted students to HR companies, sending details of shortlisted students to companies, and managing student profiles and logins. By amalgamating these features into a cohesive platform, the web application enhances efficiency, transparency, and effectiveness within the training and placement process while alleviating the burden of manual labor and fostering seamless communication between stakeholders.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Web development, Admin, TPO, College, Authorization, Student, Portal.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

To secure deduplication plans we have proposed to spare the capacity space in the cloud firstly the AES encryption conspires which utilizes a message inferred key to scramble the message. Subsequently, indistinguishable plaintexts deliver the same cipher writings. Proposed AES, which subsumes concurrent encryption and gives nitty gritty security definitions. Moreover, we utilize an MD5 calculation (message-digest calculation) cryptographic strategy for advanced marks, substance confirmation, and message confirmation. Based on a hash calculation, MD5 checks that the record you send and the beneficiary both get the same record. Thus, cloud computing is the headway to the shared volume of data through the arrange. There are parts of procedures that are utilized to give security for information in the cloud. But current procedures are way better related to the cipher content. So here, we propose data gathering, sharing, and prohibitive dissemination arranged with multi-proprietor security protection in the cloud. Here, the information proprietor can give private data to gather clients through the cloud in a secure.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

MD-5 (Message-Digest Algorithm)

  License

Creative Commons Attribution 4.0 and The Open Definition