Search

The journal retracts the article “Continual Learning Approach for Continuous Data Stream Analysis in Dynamic Environments” [...]

Continuous data stream analysis primarily focuses on the unanticipated changes in the transmission of data distribution over time. Conceptual change is defined as the signal distribution changes over the transmission of continuous data streams. A drift detection scenario is set forth to develop methods and strategies for detecting, interpreting, and adapting to conceptual changes over data streams. Machine learning approaches can produce poor learning outcomes in the conceptual change environment if the sudden change is not addressed. Furthermore, due to developments in concept drift, learning methodologies have been significantly systematic in recent years. The research introduces a novel approach using the fully connected committee machine (FCM) and different activation functions to address conceptual changes in continuous data streams. It explores scenarios of continual learning and investigates the effects of over-learning and weight decay on concept drift. The findings demonstrate the effectiveness of the FCM framework and provide insights into improving machine learning approaches for continuous data stream analysis. We used a layered neural network framework to experiment with different scenarios of continual learning on continuous data streams in the presence of change in the data distribution using a fully connected committee machine (FCM). In this research, we conduct experiments in various scenarios using a layered neural network framework, specifically the fully connected committee machine (FCM), to address conceptual changes in continuous data streams for continual learning under a conceptual change in the data distribution. Sigmoidal and ReLU (Rectified Linear Unit) activation functions are considered for learning regression in layered neural networks. When the layered framework is trained from the input data stream, the regression scheme changes consciously in all scenarios. A fully connected committee machine (FCM) is trained to perform the tasks described in continual learning with M hidden units on dynamically generated inputs. In this method, we run Monte Carlo simulations with the same number of units on both sides, K and M, to define the advancement of intersections between several hidden units and the calculation of generalization error. This is applied to over-learnability as a method of over-forgetting, integrating weight decay, and examining its effects when a concept drift is presented.

Healthcare comprises the largest revenue and data boom markets. Sharing knowledge about healthcare is crucial for research that can help healthcare providers and patients. Several cloud-based applications have been suggested for data sharing in healthcare. However, the trustworthiness of third-party cloud providers remains unclear. The third-party dependency problem was resolved using blockchain technology. The primary objective of this growth was to replace the distributed system with a centralized one. Therefore, security is a critical requirement for protecting health records. Efforts have been made to implement blockchain technology to improve the security of this sensitive material. However, existing methods depend primarily on information obtained from medical examinations. Furthermore, they are ineffective for sharing continuously produced data streams from sensors and other monitoring devices. We propose a trustworthy access control system that uses smart contracts to achieve greater security while sharing electronic health records among various patients and healthcare providers. Our concept offers an active resolution for secure data sharing in mobility computing while protecting personal health information from potential risks. In assessing existing data sharing models, the framework valuation and protection approach recognizes increases in the practicality of lightweight access control architecture, low network expectancy, and significant levels of security and data concealment.

Wireless sensor networks (WSNs) are used for recording the information from the physical surroundings and transmitting the gathered records to a principal location via extensively disbursed sensor nodes. The proliferation of sensor devices and advances in size, deployment costs, and user-friendly interfaces have spawned numerous WSN applications. The WSN should use a routing protocol to send information to the sink over a low-cost link. One of the foremost vital problems is the restricted energy of the sensing element and, therefore, the high energy is consumed throughout the time. An energy-efficient routing may increase the lifetime by consuming less energy. Taking this into consideration, this paper provides a multi-criteria clustering and optimal bio-inspired routing algorithmic rule to reinforce network lifetime, to increase the operational time of WSN-based applications and make robust clusters. Clustering is a good methodology of information aggregation that increases the lifetime by group formation. Multi-criteria clustering is used to select the optimal cluster head (CH). After proper selection of the CH, moth flame and salp swarm optimization algorithms are combined to analyze the quality route for transmitting information from the CH to the sink and expand the steadiness of the network. The proposed method is analyzed and contrasted with previous techniques, with parameters such as energy consumption, throughput, end-to-end delay, latency, lifetime, and packet delivery rate. Consumption of energy is minimized by up to 18.6% and network life is increased up to 6% longer compared to other routing protocols.

The goal of today’s technological era is to make every item smart. Internet of Things (IoT) is a model shift that gives a whole new dimension to the common items and things. Wireless sensor networks, particularly Low-Power and Lossy Networks (LLNs), are essential components of IoT that has a significant influence on daily living. Routing Protocol for Low Power and Lossy Networks (RPL) has become the standard protocol for IoT and LLNs. It is not only used widely but also researched by various groups of people. The extensive use of RPL and its customization has led to demanding research and improvements. There are certain issues in the current RPL mechanism, such as an energy hole, which is a huge issue in the context of IoT. By the initiation of Grid formation across the sensor nodes, which can simplify the cluster formation, the Cluster Head (CH) selection is accomplished using fish swarm optimization (FSO). The performance of the Graph-Grid-based Convolution clustered neural network with fish swarm optimization (GG-Conv_Clus-FSO) in energy optimization of the network is compared with existing state-of-the-art protocols, and GG-Conv_Clus-FSO outperforms the existing approaches, whereby the packet delivery ratio (PDR) is enhanced by 95.14%.