Search

Studies indicate cardiac arrhythmia is one of the leading causes of death in the world. The risk of a stroke may be reduced when an irregular and fast heart rate is diagnosed. Since it is non-invasive, electrocardiograms are often used to detect arrhythmias. Human data input may be error-prone and time-consuming because of these limitations. For early detection of heart rhythm problems, it is best to use deep learning models. In this paper, a hybrid bio-inspired algorithm has been proposed by combining whale optimization (WOA) with adaptive particle swarm optimization (APSO). The WOA is a recently developed meta-heuristic algorithm. APSO is used to increase convergence speed. When compared to conventional optimization methods, the two techniques work better together. MIT-BIH dataset has been utilized for training, testing and validating this model. The recall, accuracy, and specificity are used to measure efficiency of the proposed method. The efficiency of the proposed method is compared with state-of-art methods and produced 98.25 % of accuracy. [ABSTRACT FROM AUTHOR]

Data security is critical in wireless sensor networks (WSNs) because communication signals are highly available due to data transmission in free space. Attacks ranging from passive eavesdropping to active snooping are more common on these networks. This paper proposes secure data transfer using data encryption based on the improved Rivest–Shamir–Adleman (RSA) with Diffie–Hellman (DH) key exchange algorithm (IRSA-DH). For this purpose, the adaptive distance-based agglomerative hierarchical (ADAH)-based clustering method is used. Then the cluster head (CH) is selected using the improved weight-based rain optimization (IWRO) to improve the network's lifespan. This study aims to design a secure group communication method for WSNs. In order to generate and distribute the key to the group, the RSA and DH and key exchange algorithm had been hybridized with the Key Management Center (KMC). For safe communication between users, the key exchange technique is investigated. The performance measures such as throughput, packet loss ratio (PLR), packet delivery ratio (PDR), latency, energy consumption, end-to-end delay (EED) and network lifetime are analyzed and compared with the existing approaches. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) is generated, when the DNA in breast cells mutate or alter, impairing critical processes, which govern cell growth and division. In many situations, these mutant cells die or are targeted by the immune system. But some cells escape the immune system and proliferate uncontrolled, producing a tumour in the breast. Age, smoking, sun exposure, exposure to radiation, chemicals, and other substances, some viruses and bacteria, certain hormones, personal history of cancer, alcohol, poor diet, lack of physical activity, or obesity are the most common risk factors for breast cancer. Sorting through MRIs, Artificial Intelligence (AI) can establish a patient’s breast cancer diagnosis. With artificial intelligence technologies, medical practitioners can rapidly and reliably sift through breast MRIs in patients with dense breast tissue to remove those without malignancy. The suggested approach BC-AI is utilized to determine the prediction of breast cancer using computer vision. AI can regulate the use of chemotherapy medications and forecast the tolerance of chemotherapy drugs to optimize the chemotherapy regimen. AI can assist physicians in making proper treatment choices, avoid unnecessary procedures, and help oncologists enhance patients’ cancer treatment programs. Medical AI applications are designed to examine links between patient outcomes and preventative or therapeutic tactics. It is possible to apply AI for cancer screening in various methods, including pre-screening to identify individuals at low risk, replacing radiologist readers, or assisting radiologists in making diagnostic decisions. Image-recognition tasks have been a massive success for artificial intelligence systems, intensive learning. Automatic detection of complex patterns in imaging data and providing quantitative rather than qualitative judgements of radiographic quality are among the strengths of AI-assisted techniques. The AI program detects and shows problematic elements in the picture and forecasts the possibility of cancer to facilitate clinical diagnosis. AI programs are used for diagnostic processes, treatment protocol creation, medication research, customized medicine, and patient monitoring and care. [ABSTRACT FROM AUTHOR]

Online advertisement plays an important role in human society and is used to influence customers to buy a product or service. But these advertisements are not user-preferred. Sometimes unwanted and malware advertisements appear on the page and make them uncomfortable. Therefore, advertisement classification and displaying the userpreferred advertisement is an important concept in the modern era. For this, in this paper, a hybrid deep learning-based framework is implemented for advertisement classification and user-preferred advertisement. Initially, the Densenet121-based system is implemented. To extract the features like texts and objects from the input advertisement image, Densenet-121’s convolution and pooling layers are used, and then average pooling and softmax layers of Densenet121 are used for classifying the advertisement into four categories such as automobiles, clothes, foods, and cosmetics. Then, the DNN (deep neural network) technique is implemented to recommend the advertisement based on user preference. Gather the information of the user from user profiles and then process the collected data, if the information is matched with any advertisement then it will show the advertisement as recommended to the user. To evaluate the performance of the proposed approach manually collected data will be used with the accuracy, F1-score, recall, and precision metrics. The proposed models achieve a high accuracy of 99.93%. Furthermore, the outcomes show good precision for various advertisement categories. [ABSTRACT FROM AUTHOR]