Volume 8 Issue 4 2026

This review systematically examines recent advancements in AI-driven irrigation systems and their role in achieving sustainable water management under climate-resilient agricultural practices. By integrating machine learning algorithms, computer vision, and IoT-based sensors, these autonomous systems enable real-time soil–plant monitoring, adaptive water scheduling, and resource optimization across diverse agro-climatic contexts. Drawing upon a broad range of peer-reviewed experimental and modeling studies published between 2018 and 2025, the review highlights measurable improvements in water-use efficiency, energy savings, and crop productivity. Meta-analytical synthesis using random-effects models was employed to quantify water savings (30–50 %) and yield improvements (20–30 %), while subgroup analyses compared algorithmic performance (e. g., Random Forest, SVM, CNN) and irrigation methods. Moreover, the study discusses economic feasibility, system interoperability, sensor calibration protocols, and ethical considerations related to data governance. Findings reveal that AI-enabled irrigation offers scalable and cost-effective solutions for climate adaptation, especially in drought-prone and infrastructure-limited regions. Future research opportunities include standardization frameworks, cross-platform compatibility, and expanding validation across diverse crop types and regional settings. Eventually, this paper is keen on offering comprehensive background information about sensor-based irrigation systems and their undeniable ability to upgrade agricultural water management, preserve water resources, and be incorporated in food security issues for the sake of changing climate change.

The conservation of biodiversity within fruit crops is essential for sustaining both ecological and agricultural systems. Fruit crops, as integral components of nature's orchard, play a pivotal role in global food security and ecosystem health. India is one of the 12 mega biodiversity centers with 2 biodiversity hotspots, which are the reservoirs of plant genetic resources. India stands at 7th place in the global agricultural biodiversity status. Among fruit and nut crops, there are about 117 cultivated species with 175 wild relatives of which only 25 species have been domesticated. Genetic resources conservation of fruit trees is intricate and complex, as they belong to various genera and species which require specific climate. Hence, in situ and ex situ conservation can go simultaneously. The western ghat and North eastern India are centres of diversity for several important native fruits including Mango, Jackfruit and Citrus. Apart from the major fruit crops, India is home to several underutilized fruit crops. However, due to increased pressure on land use, several of the wild types, which are a great source of genes governing useful traits, are disappearing. Thus, there is an urgent need to conserve them in both in situ and ex situ conditions. The genetic diversity and modes of conservation of tropical fruits are discussed in this paper.

This research presents a conceptual study on artificial intelligence (AI), a concept increasingly discussed in the information age. The use of AI in education, in particular, has raised ethical concerns. The study aims to develop a general set of ethical principles by analyzing specific examples of AI and its use in Turkey and worldwide. Especially in recent years, AI has become accessible to all stakeholders in education through the ChatGPT software, offered free of charge to all users by Open AI. Its ease of use, simple interface, and most importantly, its purpose-driven nature have accelerated its adoption. This research will identify the ethical principles that should be applied to each case, based on national and international case studies, and aims to contribute to decisions made by both the Ministry of National Education (MEB) and the Council of Higher Education (YÖK) regarding the use of AI in education. It is believed that these principles will be beneficial not only for education but also for all other fields. The case studies will be analyzed objectively and subjectively. Case studies related to AI were gathered from news articles, social media, and academic studies. In this context, events covered in different media have been presented in chronological order. Specific news sources have not been used for general events, such as students, especially at the undergraduate level, having artificial intelligence complete their assignments and projects.

Nowadays, the use of microphone array beamformer has been widely commonly due to its convenience of steering the beampattern on the specified sound location and attenuating the background noise field. Microphone array beamforming own the capability of suppressing interference, third-party speakers and different adverse noise fields with high directivity index of extracting the clean speech data without speech distortion. Minimum Variance Distortionless Response beamformer bases on the constrained criteria of minimizing the total output noise power while saving the target talker by ensurign the beampattern equals one at certain direction. However, under realistic recording environments, due to the movement of speaker during conversations, the error of start time recording, the different sensitivities of microphones, the error of sampling frequency, the internal electrical acoustic equipments, the inaccurate distribution of microphones, the overall beamformer’s performance often degraded. The unacceptable surrounding noise level or speech distortion corrupt the speech intelligibility of output signal. In the article, the author proposed two-stage - based method for adaptively updating the smoothing parameters for increasing the beamformer’s evaluation in real-life scenarios. The numerical simulation has shown the improvement of reducing the speech distortion to 5 dB, removing the background noise level to 12.9 dB and increasing the speech quality in the term of signal-to-noise ratio from 5.3 to 8.8 dB.

Traditional livestock farming in rural parts of India and developing countries still depends on human observation and experiential decision-making in the process of monitoring the health of animals, diagnosing diseases, and conducting various farm activities. The problem is that the aforementioned practice tends to cause delays in detecting illnesses among livestock, resulting in unnecessary deaths of cattle and economic losses for farmers without any access to a veterinarian at all times. However, existing applications and platforms used for farm management purposes are either prohibitively costly, lack stable internet connection, or cannot be employed to solve problems peculiar to resource-poor areas. Therefore, this paper describes a Machine Learning-Based Smart Livestock Management System, which is a sophisticated, yet inexpensive, solution developed specifically for low-resource regions. The presented product incorporates various IoT devices and can monitor key physiological parameters such as body temperature, heart rate, level of activity, and eating habits of individual animals. The trained machine learning model analyzes the live data from sensors to identify anomalies, predict early signs of diseases like Foot-and-Mouth Disease and Mastitis, and create automatic alerts about the health status of the animal to the farmers through an easy-to-use mobile application without requiring cloud storage or broadband connection. This system uses a Random Forest classifier model trained on a livestock health data set consisting of more than 12,000 labeled data samples, providing an accuracy of disease prediction as high as 94.3% with a maximum error rate of less than 3%. Classification of behavioral patterns with respect to normal grazing, resting, and distressed states with 91.7% accuracy is done by analyzing the data collected from accelerometers. An easy-to-use Android app helps farmers to monitor the health status, schedule feed, and get expert advice in English and Tamil languages.

The resurgence of great power competition has seen the emergence of the "Gray Zone," a strategic space where state actors employ coercive measures below the threshold of conventional war. This paper investigates the application of cyber statecraft by the Russian Federation, utilizing Social Network Analysis (SNA) to deconstruct information operations targeting Ukraine and NATO. By mapping the relationships between state media, proxy bot networks, and online amplifiers, the study identifies the structural mechanisms that facilitate narrative diffusion. The analysis reveals that Russian campaigns are highly decentralized yet tightly coordinated around specific themes designed to exacerbate societal fractures. Specifically, the findings illustrate how these networks bridge the gap between the tactical theater in Ukraine and the strategic information environment of NATO, aiming to erode alliance cohesion. The study underscores that the efficacy of these operations lies not just in the volume of content, but in the strategic positioning of nodes within the digital ecosystem. Ultimately, this research argues that countering such threats requires a shift in focus from simple fact-checking to the disruption of network architecture. It recommends that NATO enhances its strategic resilience by developing comprehensive counter-disinformation frameworks that identify and isolate key influence vectors.

The most important culture being followed in India since ancient times is agriculture. The crops were cultivated by the people in ancient times within their own land areas such that they could fulfill their own requirements. India is a farming nation. Crop production analysis is one of the applications of prediction analysis. This study is related to paddy production. To improve accuracy of the paddy production, the hybrid classifier will be designed based on k mean clustering and Naive Bayes classifier. The presented and earlier algorithms will be applied in python and it is expected that accuracy will be improved with reduction in execution time. The performance of SVM, KNN and Naïve Bayes is compared for the wheat production prediction. Naive Bayes is the best classifier for the wheat production prediction as per the obtained analytic results.

Small-scale industries play very important role in the economic development of any less developed or under-developed country. These industries meet the twin needs viz. solution of unemployment problem and checking the economic concentration in the hands of a few. These industries encourage self-sufficiency, self reliance and co-ordination. They provide beneficial re-allocation of available resources and their proper utilisation. They help to eradicate poverty in the rural sector. These industries entail equitable distribution of national income and ensure a harmoniously balanced, integrated and egalitarian socio-economic order in the country. The government of India has implemented different policies for the growth and development of smallscale industries. Different measures have been taken by the government through different five year plans to develop and strengthen the small scale industries.

Objectives:This paper aims at the study of the customer satisfaction towards Eshopping using the Technology Acceptance Model Approach in which we study that how new trend of online shopping is being adopted by the customers and how much they are satisfied with it. Methods/Statistical analysis: Research has been done by filling the online google form from the customers having the demographic parameter of age, gender. Questionnaire focus on the preference of online website, frequency of doing online shopping, mode of payment, monthly expenditure on the online shopping. Questionnaires have been filled and analyzed and interpreted using the hypothesis and SPSS. Graph, tables and diagrams have been used to interpret or to show the results. Findings: According to the findings age group between 20-29 prefer online shopping and women prefer more online shopping than men. Amazon is preferred more than any other site and customers prefer to buy clothes than any other commodity from these online websites.

The VANET simulation is a completely subset of MANETs simulation, but completely different from MANETs communication, VANET environment impose new issues and requirements, like constrained road topology, multi-path fading and roadside communication, traffic lights, traffic jam, traffic flow models, trip models, different vehicular speed, drivers’ activity, location etc. Now, there are VANET mobility provided, network simulators, and VANET simulators. This paper presents a comprehensive study and comparisons of the varied publicly available VANET simulation applications and their components. Especially, we contrast their applications characteristics, graphical interface (GUI), popularity, simple use, input requirements, output visualization capability, accuracy of simulation, etc. Finally, while each of the calculated simulators provides an direct simulation environment for VANETs, clarification and further contributions are require before they will be commonly employed by the research group. This framework makes use of the open source applications called “Simulation of Urban Mobility”(sumo) and the “input trajectory files” feature of Opnet Modeler. The OpenStreetMap is made of everyone who takes part in it, and hearing each other’s voices during a coordinated way, on a regular basis, will help prioritize where work is required and what actions to pursue. It ensures a standard thanks to engage. Surveying can help set up mechanisms to route issues to the correct place, share pathways for OpenStreetMap members to contribute and address problems, and identify where the project as an entire needs more help to return up with answers. We will identify people and topics for more in depth follow up. This may only work and be useful if there's actual follow through and transparency on what we hear through surveys