Abstract : The Degradation process model was found to be appropriate and fixed over the two bio-object frameworks: (i) Comparison among Low and High BMI, WC, OC consumption levels of Parous and Nulliparous women (ii) Profile of 17β-estradiol and progesterone against upper, middle and lower tertile. The author verified the results provided by the medical field and found that there is no significant connection between performance of Reliability function of Degradation process fixed for 17β-estradiol and progesterone and parity of the women. The monotonically increasing curves depicts that the Reliability function of Degradation process fixed for 17β-estradiol and progesterone over parous, nulliparous women have maximum performances over the women having high BMI (>25 Kg/m2) and who were consuming oral contraceptives more than 3 years. But interestingly we observed the inverted results over daily salivary observation against lower, middle and upper tertile as lower tertile with less than 10 ten years interval serves upper bound and upper tertile with 13.5 years’ time interval serves lower bound of middle tertile with interval 10 – 13.5 years..
Full article

Abstract : Over the last couple of decades, virtual and augmented reality technologies have been widely used to minimize the problems affecting public safety and emergency services. The paper outlines a technology that would let first responders navigate their route through built environments by using AR devices attached to their helmets and visors, which would be helpful during natural disasters and severe fires. This development has enabled the capability to see and hear through smoke, fire, debris, adverse weather, and other obscuring materials; navigation; real-time sensor data related to the environment and dangerous situations; and the ability to see through smoke. It may also provide users with audio and visual commands in a disaster, information on the availability of shelter, ways of evacuation, and what to do in an emergency using head-mounted displays and personal digital assistants [2]. Deep learning approaches, such as CNNs and SLAM techniques, are crucial in improving the graphics generated by augmented reality systems, thereby enhancing the end-user experiences. The SLAM technique tracks the positions and orientations of views in an artificial environment and supplies the geometric position for the augmented reality system. It, therefore, allows the system to draw the surroundings three-dimensionally. The CNN algorithm detects and perceives the objects within an environment..
Full article

Abstract : "Mind Harbor: Navigating Wellness Together - with AI integration" is a research initiative aimed to propose an application to address mental health challenges faced by university students in Oman. This study recognizes the complex elements influencing students' mental health and focuses on those who are experiencing anxiety and depression. Sometimes social situations, insecurity, shyness or awkwardness make students reluctant to talk about their mental health problems. This may lead to significant mental and physical health issues, as well as negatively impact academic performances which is a major concern for university, parents and the society. Through this suggested application's user-friendly interface, students will be able to express their concerns in a safe and non-judgmental environment. The inputs collected through the interface will then be sent to an AI-powered LLM that is intended to offer customized recommendations and solutions to assist students in overcoming obstacles. This research aims to provide a comprehensive and easily accessible support system for managing mental health challenges of students by combining the capabilities of artificial intelligence with human-computer interaction. The research aims to create a customized interface to be integrated with Large Language Model (LLM) which will provide recommendations and interventions depending on the particular requirements and circumstances of every learner. The core of the application lies in its user-friendly interface, designed to facilitate easy and confidential communication between students and the system. Students can input their concerns, which are then processed by an AI-powered Large Language Model (LLM). This research intends to improve the delivery of mental health support in learning environments by merging technology with human-centered design concepts that are sympathetic. Students can access a virtual harbor called Mind Harbor, where their voices are heard, their problems are validated, and solutions provided..
Full article

Abstract : This study aims to assess the reliability of crop production under diverse environmental conditions and utilizes regression modeling for Foxtail millets growth prediction, a focal point of this investigation. Machine learning is an emerging field in agricultural research, particularly in the analysis and forecasting of Foxtail millets growth yields. The process of crop production is impacted by a multitude of factors such as the number of days to flowering, maturity period, plant height, and fodder yield, among others. In this research, machine learning techniques, particularly linear regression, have been employed to forecast Foxtail millets yield. Linear regression was chosen due to its effectiveness as a predictive model, demonstrating a notably higher accuracy for this dataset in comparison to alternative models. Complex datasets that pose challenges for conventional analysis methods can be effectively decoded using machine learning strategies, uncovering valuable underlying patterns automatically. This enables informed decision-making processes by revealing unseen knowledge and patterns related to various agricultural challenges. Furthermore, machine learning facilitates the prediction of future events. During the growing season, farmers are keen on estimating their expected yield. With the continuous increase in agricultural data volume globally, this paper focuses on predicting crop yields using collected agricultural datasets. The research employs a regression analysis model to evaluate the accuracy and efficacy of predicting Foxtail millets crop yields in India. Linear regression is utilized to establish correlations between mean, variance and Foxtail millets yield. Assessing the potential millet production rate is crucial for farmers to benefit from predictive outcomes and mitigate financial losses. The research findings highlight the accuracy of Foxtail millets yield predictions using the regression model..
Full article

Abstract : Channel estimation is a pivotal component in determining the performance of wireless networks. Recent advancements in deep learning have significantly enhanced communication reliability and reduced computational complexity in 5G and future wireless networks. While least squares (LS) estimation remains widely used due to its simplicity and lack of requirement for prior statistical knowledge about the channel, it often suffers from relatively high estimation errors in digital communication. This paper introduces a novel channel estimation framework that leverages deep learning hybrid models to enhance the accuracy of channel estimates traditionally obtained through the least squares (LS) method. Our approach is validated using a Multiple-Input Multiple-Output (MIMO) system, incorporating a multi-path channel profile, and simulating scenarios in 5G and beyond networks under various mobility conditions characterized by Doppler effects. The system model is designed to accommodate any number of transceiver antennas, and the machine learning component is versatile, allowing the use of various neural network architectures. Numerical results show that the proposed deep learning-based channel estimation structure outperforms traditional methods commonly used in previous studies. Furthermore, our analysis indicates that bidirectional long short-term memory (LSTM) networks achieve the maximum channel estimation accuracy and the lowest bit error rate among the evaluated artificial neural network architectures..
Full article