The rapid expansion of the e-commerce industry, accelerated by the COVID-19 pandemic, has led to a significant increase in digital fraud and associated financial losses. To maintain a healthy e-commerce ecosystem, robust cybersecurity and anti- fraud measures are essential. However, research on fraud detection systems has struggled to keep pace due to limited real- world datasets. Advances in artificial intelligence (AI), machine learning (ML), and cloud computing have revitalized research and applications in this domain. While ML and data mining techniques are popular in fraud detection, specific reviews focusing on their application in e-commerce platforms like eBay and Facebook are lacking depth. Existing reviews provide broad overviews but fail to grasp the intricacies of ML algorithms in the e-commerce context. To bridge this gap, our study conducts a systematic literature review using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA)

Generative AI—especially ChatGPT—has shown great promise in tourism, particularly as an itinerary planner. A recent study compared three-day itineraries created by ChatGPT for Vienna, Plovdiv, and Spetses against those designed by tourism While ChatGPT excelled in crafting clear and accessible plans that are ideal for initial travel inspiration, it often fell short in accuracy and specificity when weighed against expert-curated itineraries. Across 11 quality criteria, findings showed that ChatGPT-based itineraries consistently included only permanent attractions such as museums and landmarks, frequently neglecting critical logistical elements like time schedules, transport routes, meal suggestions, and local insights . Another drawback stems from the AI’s static dataset cutoff; although ChatGPT may appear up-to-date, it can present outdated or incomplete information (e.g., closed attractions or changed schedules), which can mislead non-expert travelers

India is an agrarian nation and its economy is for the foremost portion based upon trim efficiency and precipitation. For analyzing the trim capability, precipitation want is require and vital to all agriculturists. Precipitation Want is the application of science and progression to anticipate the state of the climate. It is essential to completely select the precipitation for compelling utilize of water assets, trim viability and pre organizing of water structures. Utilizing unmistakable information mining procedures it can foresee precipitation. Information mining techniques are utilized to overview the precipitation numerically. This paper centers a number of of the transcendent information mining calculations for precipitation want. Credulous Bayes, K-Nearest Neighbor calculation, Choice Tree, Neural Organize and padded premise are numerous of the calculations compared in this paper. From that comparison, it can analyze which strategy gives superior exactness for

A machine learning technique called "few-shot learning" enables artificial neural networks to learn and generate accurate predictions using just a few number of labelled instances. Due to the scarcity of labelled information in the medical field, few-shot medical picture classification is a difficult task. MedOptNet is a deep learning-based optimisation system designed especially for applications in medical imaging. It is specifically made to improve the performance and quality of magnetic resonance imaging (MRI). It reduces the time and resources needed for scanning while improving the presentation of medical images by using a neural network to solve issues like photo reconstruction and denoising. To overcome this difficulty, the MedOptNet system employs curvature-based optimisation and meta-learning, which produces better results than conventional techniques. The goal of this initiative is to improve the model's feature extraction and classification accuracy by addin

Early disclosure of diabetes is crucial to evade veritable complications in patients. The reason of this work is to recognize and classify sort 2 diabetes in patients utilizing machine learning (ML) models, and to choose the primary idealize outline to anticipate the hazard of diabetes. In this paper, five ML models, counting K-nearest neighbor (K-NN), Bernoulli Naïve Bayes (BNB), choice tree (DT), calculated backslide (LR), and back vector machine (SVM), are reviewed to anticipate diabetic patients. A Kaggle-hosted Pima Indian dataset containing 768 patients with and without diabetes was utilized, checking components such as number of pregnancies the tireless has had, blood glucose concentration, diastolic blood weight, skinfold thickness, body assault levels, body mass record (BMI), intrinsic foundation, diabetes interior the family tree, age, and result (with/without diabetes). The comes around appear up that the K-NN and BNB models beat the other models. The K-N

We need effective and scalable webbased systems to monitor data in real-time for IoT, healthcare, and industrial applications. In this study, a web server for embedded monitoring systems that can dynamically display real-time sensor data is conceived and built. Data collecting, processing, and visualization are all made easy by the system's integration of embedded hardware and lightweight web technologies. The web interface makes use of HTML, JavaScript, and AJAX to allow for constant updates with less server load, which improves responsiveness, adaptability across numerous applications is ensured by the system design and supports diverse sensor inputs and network protocols. Evaluations of performance shows that this technology is useful for remote embedded system monitoring because to its low-latency transmission, accurate representation of real-time data, and efficient utilization of resources.