Phishing is one of the biggest crimes in the world and involves the theft of the user’s sensitive data. Usually, phishing websites target individuals’ websites, organizations, sites for cloud storage, and government websites. Most users, while surfing the internet, are unaware of phishing attacks. Many existing phishing approaches have failed in providing a useful way to the issues facing e-mails attacks. Currently, hardware-based phishing approaches are used to face software attacks. Due to the rise in these kinds of problems, the proposed work focused on a three-stage phishing series attack for precisely detecting the problems in a content-based manner as a phishing attack mechanism. There were three input values—uniform resource locators and traffic and web content based on features of a phishing attack and non-attack of phishing website technique features. To implement the proposed phishing attack mechanism, a dataset is collected from recent phishing cases. It was found that real phishing cases give a higher accuracy on both zero-day phishing attacks and in phishing attack detection. Three different classifiers were used to determine classification accuracy in detecting phishing, resulting in a classification accuracy of 95.18%, 85.45%, and 78.89%, for NN, SVM, and RF, respectively. The results suggest that a machine learning approach is best for detecting phishing.
1 October 2021 in Journal of Physics: Conference Series
Cancer is one of the main reason for loss of human life across the world. All the medical practitioners and researchers are dealing with the demanding situations to fight against cancer. Based on the report in 2019 from American Cancer Society, 96,480 deaths are anticipated due to skin cancers, 142,670 deaths are from lung cancers, 42,260 deaths are from breast cancers, 31,620 deaths are from prostate cancers, and 17,760 deaths are from mind cancers. Initial detection of most cancers has the pinnacle precedence for saving the lives. This paper proposed a lung cancer detection using Deep Learning based on VEE NET architecture. This was one of the famous models submitted to ILSVRC-2014. Visual checkup and manual practices are used on this venture for the various types of cancer diagnoses. This guide interpretation of scientific images that needs massive time intake and is notably susceptible to mistakes. Thus, in this project, we apply deep learning algorithms to identify lung cancer and its presence without the need for several consultations from different doctors. This leads to an earlier prediction of the presence of the disease and allows us to take prior actions immediately to avoid further consequences in an effective and cheap manner avoiding human error rate. In this project lung cancer and its presence is determined. A web application is developed as a hospital application where an input x-ray image is given to detect lung cancer.
The information regarding any abnormal behaviour in the physiological parameters of a patient should reach the remote healthcare personal immediately in real time, so as to take corrective action promptly and save the life. Biomedical wireless sensor network (BWSN) plays a vital role in this connection because it can be attached to the patient without causing any inconvenience to him/her and can communicate to any remote healthcare office without any delay. BWSN consists of individual nodes to collect the patient's information and communicate it to the remote health centre if the value of sensed signal is beyond normal range. The nodes deployed within the patients form a BWSN, and the network has to send the information from the source to the remote sink in an efficient way. The network should choose an optimized path for this communication, so that the node’s lifetime is increased. This paper presents a Q-learning-algorithm-based routing concept to route the sensed information if required from the individual node to the remote healthcare station. Simulations are made with a set of mobile biomedical wireless sensor nodes within an area of 100 m × 100 m flat space operating for 600 seconds of simulation time. Results show that the Q-learning-based approach requires less time to route the packet from the source node to the destination remote station.
26 March 2025 in Journal of Environmental Management
Although past studies and the performance of prior models have not been assessed, artificial intelligence models have shown great accuracy in distinguishing particular orthopedic implant types from imaging, which is an essential and time-consuming operation. To describe the breadth, approach, and effectiveness of artificial intelligence algorithms in categorizing orthopedic implant models, the authors carried out a comprehensive review. They used the search phrases “artificial intelligence,” “orthopedic,” “implant,” and “arthroplasty” to look at research published up to March 10, 2021 in PubMed, EMBASE, and the Cochrane Library. A modified version of the methodologic index for non-randomized studies was used to evaluate the studies. Area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were among the results that were reported. Eleven of the 2689 records found during the search were used in the analysis. Between 2 and 27 implant models were considered.
Fraudulent activities present significant challenges to organizations across various sectors, necessitating advanced techniques for detection and mitigation. Leveraging AI in BI offers promising solutions to enhance fraud detection capabilities and minimize risks effectively. It emphasizes importance of fraud detection and risk management strategies for safeguarding organizational assets, maintaining trust with stakeholders, The role of AI in BI focuses on machine learning techniques, deep learning approaches, and real-time fraud detection systems. Advanced techniques for fraud detection, including feature engineering, model evaluation, and explainable AI, and practical applications of AI-powered fraud detection and risk management in financial services, e-commerce, retail, and cybersecurity are illustrated through case studies. The chapter concludes by outlining future directions and emerging trends in AI, BI, and fraud detection, emphasizing importance of collaboration, ethical considerations, and knowledge sharing in addressing evolving challenges and opportunities.