Search

The authors proposed a fusion protocol using multilevel clustering (FPMC), which is completely dependent on the increased coverage and wireless sensor network (WSN) reliability‐clustering framework to eliminate duplication. Therefore, a static sensor for a point of interest is allocated where possible so that the particular area can be protected. Furthermore, FPMC ensures that only one sensor node is allocated to cover a specific point of interest. The network coverage, energy usage, mean movement of WSNs nodes and sensor nodes are active in each loop due to which efficiency of the proposed protocol was assessed under various densities, and its performance was also analysed. Evaluations have shown that with restricted active nodes and sensor nodes, the FPMC can increase the networking coverage. The FPMC should be stressed as reducing the overlap level. The proposed protocol is based on the fusion protocol using multi‐level clustering for improving coverage and connectivity WSNs.

The polysomnography test (sleep study) is used to diagnose several sleeping disorders. Sleep study is used to detect sleep disorders such as Insomnia, REM Sleep Behavior, Insomnia, Restless Leg Movement Syndrome, and Sleep Apnea. It measures different parameters such as heart rate, level of oxygen in your blood, body position, brain waves (EEG), breathing rate, eye movement, and electrical activities of muscles. In the world, 700 million people suffer from sleeping disorders. A wide range of sensors was attached to the body of the patient to measure the value of different parameters. However, in 2020, due to the exponential spread of COVID-19 coronavirus disease, the sleep study centers were closed, and it was very difficult to perform sleep studies on patients. Therefore, we developed a hybrid model based on deep learning techniques like Convolutional Neural Network (CNN) and Deep Belief Network (DBN) architectures. Numerous cameras were mounted in rooms at certain angles, which provide live surveillance data and record a patient’s movements after a short periodic interval of time. This research paper concludes that non-contact-based hybrid models are highly accurate in detecting sleep disorders based on polysomnography tests.

In cloud computing environments, parallel processing is required for large.scale computing tasks. Two different tasks are taken, and these tasks are independent of each other. These tasks are independently applied to Virtual Machines (VM). We proposed Offbeat Load Balancing (LB) Machine Learning algorithm using a task scheduling algorithm in Cloud Computing (CC) environments to reduce execution time. In this paper, the proposed algorithm is based on the concept of Random Forest Classifier and Genetic Algorithm and K-Means clustering algorithm for optimized load. The proposed algorithm shows that the average execution time of 3.5104 seconds (20 jobs, 5 Machines) and 15.85 seconds (20 jobs, 10 machines) is based on a study of load balancing algorithms that needs less execution time than other algorithms.

The classic example of shared hidden data transformation is the Invisible Internet Protocol (I2P), which works with Tor web-net and make incognito relay confidential. The I2P offers an outstanding possibility for people seeking anonymity to circumvent authoritarian regimes. It can also be troublesome in corporate environments where I2P-routers over-use restricted web-net assets or provide a means for malware to exfiltrate information. In this research paper, the authors discussed the IDS possibility to track I2P web-net congestion and associate peers positively is done. Additionally, the authors given context details on the internal mechanisms of I2P, and showed the ways to recognize I2P routers throughout the bootstrapping process. The development and review of the new system is of the current state of the art. We intend to introduce Blockchain techniques for tracking Darkweb User Activities on a trust computational web-net to improve data protection in transparent blockchains (BC).

With the advancement of search engines, a major change has occurred in the way people are accessing data on the net. Search engines have made access to data efficient and easier as billions of pages on the net (or called big data) are suggested at once. The pages with the most significant rank generally have a higher visibility rate to people and hence every webmaster wants to push their page to higher rank. As a result, Search Engine Optimization (SEO) has become a massive business which strives in enhancing the ranking of clients’ webpage. But there are many myths and misconceptions about the ranking algorithms due to inadequate knowledge about SEO’s methods. Still there is a need to propose a verified algorithm that is efficient in retrieving pages from Google. The link analysis algorithm is in accordance with the link structure of any document as the page which has many links also has many connections to it and hence can increase retrieval capacity. There is another approach called the integrated ranking approach which comes under personalized web research. In the integrated ranking approach, both content and link are used as parameters to improve retrieval efficiency. This approach is used by Google using Deep Learning to increase retrieval efficiency of web pages as per the user’s requirement from the big data.

Healthcare institutions around the world become an organised and user-centred structures. Managing vast volumes of data, such as IoT device data or medical records of each person, however, contributes to an increase in human resources and security threats. To solve these challenges, healthcare IoT increases the quality of patient care and lowers costs by efficiently allocating medical services. Via blockchain technology, we have a safety mechanism for healthcare data through creating the SHA256 hash algorithm of each data such that every modification or alteration of data confirmed with improved simulation results that due to blockchain methodology give the security. Our proposed algorithm based on SHA256 hash algorithm to every block which are verified by every node, data cannot be altered by nefarious source. In this research work, we proposed a blockchain-based model with consensus protocol and SHA256 hash algorithm related to the priorities of the verifiability, suitability, extensiveness, uniqueness, sturdiness, and coercion resistance.

The Internet of Things (IoT) idea has arisen as interconnected components of the healthcare tracking facilities of smart linked healthcare networks. Hard sensor-based data aggregation with the help of devices in the form of wearables or intrusive samples attached with the acquisition of soft sensors like crowd sensor results in the aggregated sensor data being concealed in patterns. This problem is tackled through several secret stages of interpretation of deep learning techniques. In this research work, we proposed hybrid deep learning (HDL) techniques to develop estimation and enhance quality of smart health services on health monitoring data. We also showed a detailed comparison of methods on the basis of health surveillance types. Hence, our proposed models work for risk detection in health information which will help us to increase the efficiency of existing healthcare industry.

Depression is a common disease occurring in every human at least once in his or her lifetime. Patients were analyzed based upon their text information, audio, video and image (IOT-based data) recording. The most effective techniques available in the deep learning models are being obtained and combined together to form the hybrid fusion model that how various types of fusion techniques. The fusion-based deep learning (FBDL) model was found to have a more accurate result along with the early fusion techniques, which also provided a good result. This technique is also being used in various IoT-based data applications to detect the depression of a person based upon their messages. The prevention of depression can be done using robotics which contains FBDL models. Several robots were used in the form of social animals or humanoids to minimize the effect of depression in elderly people. Thus deep learning models and robotics domain can be used to detect and cure the symptoms of depression in elderly people.

Robots are ideal replacements for trained staff in repeatable, general, and strategically significant roles, but they are not always practicable as replacements. In spite of growth and advancement in the automation industry, several sectors historically have been robot-reluctant, because they require large or unique quantities and nonserialized properties. The present chapter introduces a newer approach to advanced Productivity and Product Quality, integrating control and robotics’ repeatability with human versatility. The strategy suggested is focused on interactive and symbiotic partnerships between human staff and robots which give the historically manual, robot-reluctant industries a secure and dynamic solution. The proposed architecture contains components for the power, protection, and interface for the current production phase. The results demonstrate that machines, robots, and humans can occupy the field at the same time comfortably without physical separation, delivering advantageous symbiotic cooperation and dramatically reducing time, risk, and expense, with increased efficiency and product consistency over manual service.

Sleep apnea is a syndrome that repetitively starts breathing ans stops. It causes a major issue in terms of quality of sleep and affects daily activities. It can be treated by laboratory tests or imaging on diagnosed with sleep apnea disorder. Numerous researchers have proposed and implemented automatic scoring processes to address these issues, based on fewer sensors and automatic classification algorithms. The proposed work develops an optimized CNN and LSTM smart deep learning model that classified the data set based on physical contact and without physical contact from patients for analysis and detects the OSA condition of the patient. We proposed a deep learning model for detecting torso and head by various sleep patterns. We achieved 93.02%, 94.50%, and 98.30% accuracy on frames using conversional CNN model, and received accuracy as 92.1%, 90.2%, 80.50% and 89.6% using CNN-LSTM architecture.

Sleep Apnea is due to a respiratory condition, which is linked to a sleep issue that often contributes to reduction in airflow and often sometimes fully prevents airflow. In addition, this issue needs the individual to be checked overnight to determine the amount of oxygen in the blood. Several experiments carried out on animals like-mice the research reveals that sleep apnea can also contribute to cancer. The findings suggest that the development of cancer cells is advancing rapidly as mice is put in low- oxygen conditions. In this paper a deep learning algorithm for evaluating different variables including throat muscles, it usually collapses whilst a sleep, triggering both gasping and snoring as body searches for oxygen. This paper provides a description of the apnea deep learning paradigm related to dynamic cancer impermanence. Deep Learning (DL) technology, primarily the modified Fusion Convolution Neural Network (MFCNN), is used as a function detector to learn the features of the high-order association between observable data and associated marks. Preparing and segmenting the data model is a critical move toward training into deep learning. During the last stage of the MFCNN, a completely linked layer is attached to the output layer and builds the required number of outputs for sleep apnea occurrences during investigate the ECG data, data section whether apnea happens or not and challenges associated with complex impermanence from cancer.