Search

Integrating cognitive radio into the current power grid is designed to enable smart communication and decisions within the grid. Communication within the grid is not feasible without channel(s) and most studies have emphasized the use of cellular spectrum. This study proposes a strategy that enables the use of television white space (TVWS) within the grid. To be specific, we propose using a next-generation utility network (Next-GUN), which leverages on the cognitive radio (CR) channel aggregation capability. This strategy enables the aggregation of idle TVWS into a usable channel, thus making the Next-GUN different from the traditional power network. Next-GUN differs in terms of security, reliability, self-awareness, and cross-layer compatibility to the interface, and conveys different traffic classes, thereby making it a hybrid system. It has no dedicated channel assigned to it, and hence, utilizes the idle TVWS opportunistically to transmit data. The proposed scheme was modelled as a Markovian process and analyzed using a continuous time Markov chain (CTMC). Extensive system simulations were performed to evaluate this proposed model and the corresponding comparison with the literature was done to see the improvement. The result of our comparisons shows that when channels are aggregated, more data/information are transmitted. In addition, the use of cognitive radios on a power network enables smart transaction because idle TVWS is utilized instead of congesting the GSM spectrum. Lastly, the power utility establishment can save the cost of paying for a licensed spectrum.

Distributed generators (DGs) are increasingly employed in radial distribution systems owing to their ability to reduce electrical energy losses, better voltage levels, and increased dependability of the power supply. This research paper deals with the utilization of a Particle Swarm Optimization algorithm by handling its random constraints to determine the most appropriate size and location of photovoltaic-based DG (PVDG) to keep the asymmetries of the phases minimal in the grid. It is thus expected that this algorithm will provide an efficient and consistent solution to improve the overall performance of the power system. The placement and sizing of the DG are done in a way that minimizes power losses, enhances the voltage profile, i.e., bringing symmetry in the voltage profile of the system, and provides maximum cost savings. The model has been tested on an IEEE 33-bus radial distribution system using MATLAB software, in both conditions, i.e., with and without PVDG. The simulation results were successful, indicating the viability of the proposed model. The proposed PSO-based PVDG model further reduced active power losses as compared to the models based on the teaching–learning artificial bee colony algorithm (TLABC), pathfinder algorithm (PFA), and ant lion optimization algorithm (ALOA). With the proposed model, active power losses have reduced to 17.50%, 17.48%, and 8.82% compared to the losses found in the case of TLABC, PFA, and ALOA, respectively. Similarly, the proposed solution lessens the reactive power losses compared to the losses found through existing TLABC, PFA, and ALOA techniques by an extent of 23.06%, 23%, and 23.08%, respectively. Moreover, this work shows cost saving of 15.21% and 6.70% more than TLABC and ALOA, respectively. Additionally, it improves the voltage profile by 3.48% of the power distribution system. [ABSTRACT FROM AUTHOR]

Wireless Sensor Network (WSN) technology has grown in importance in recent years. All WSN implementations need secure data transmission between sensor nodes and base stations. Sensor node attacks introduce new threats to the WSN. As a result, an appropriate Intrusion Detection System (IDS) is required in WSN for defending against security attacks and detecting attacks on sensor nodes. In this study, we use the Routing Protocol for Low Power and Lossy Networks (RPL) for addressing security services in WSN by identifying IDS with a network size of more or less 20 nodes and introducing 10% malicious nodes. The method described above is used on Cooja in the VMware virtual machine Workstation with the InstantContiki2.7 operating system. To track the movement of nodes, find network attacks, and spot dropped packets during IDS in WSN, an algorithm is implemented in the Network Simulator (NS2) using the Ad-hoc On-Demand Distance Vector (AODV) protocol in the Linux operating system. [ABSTRACT FROM AUTHOR]

Hepatitis B is a potentially deadly liver infection caused by the hepatitis B virus. It is a serious public health problem globally. Substantial efforts have been made to apply machine learning in detecting the virus. However, the application of model interpretability is limited in the existing literature. Model interpretability makes it easier for humans to understand and trust the machine-learning model. Therefore, in this study, we used SHapley Additive exPlanations (SHAP), a game-based theoretical approach to explain and visualize the predictions of machine learning models applied for hepatitis B diagnosis. The algorithms used in building the models include decision tree, logistic regression, support vector machines, random forest, adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost), and they achieved balanced accuracies of 75%, 82%, 75%, 86%, 92%, and 90%, respectively. Meanwhile, the SHAP values showed that bilirubin is the most significant feature contributing to a higher mortality rate. Consequently, older patients are more likely to die with elevated bilirubin levels. The outcome of this study can aid health practitioners and health policymakers in explaining the result of machine learning models for health-related problems. [ABSTRACT FROM AUTHOR]

The high prevalence of chronic kidney disease (CKD) is a significant public health concern globally. The condition has a high mortality rate, especially in developing countries. CKD often go undetected since there are no obvious early-stage symptoms. Meanwhile, early detection and on-time clinical intervention are necessary to reduce the disease progression. Machine learning (ML) models can provide an efficient and cost-effective computer-aided diagnosis to assist clinicians in achieving early CKD detection. This research proposed an approach to effectively detect CKD by combining the information-gain-based feature selection technique and a cost-sensitive adaptive boosting (AdaBoost) classifier. An approach like this could save CKD screening time and cost since only a few clinical test attributes would be needed for the diagnosis. The proposed approach was benchmarked against recently proposed CKD prediction methods and well-known classifiers. Among these classifiers, the proposed cost-sensitive AdaBoost trained with the reduced feature set achieved the best classification performance with an accuracy, sensitivity, and specificity of 99.8%, 100%, and 99.8%, respectively. Additionally, the experimental results show that the feature selection positively impacted the performance of the various classifiers. The proposed approach has produced an effective predictive model for CKD diagnosis and could be applied to more imbalanced medical datasets for effective disease detection. [ABSTRACT FROM AUTHOR]

A simple scheme was proposed by Knuth to generate binary balanced codewords from any information word. However, this method is limited in the sense that its redundancy is twice that of the full sets of balanced codes. The gap between Knuth's algorithm's redundancy and that of the full sets of balanced codes is significantly considerable. This paper attempts to reduce that gap. Furthermore, many constructions assume that a full balancing can be performed without showing the steps. A full balancing refers to the overall balancing of the encoded information together with the prefix. We propose an efficient way to perform a full balancing scheme that does not make use of lookup tables or enumerative coding. [ABSTRACT FROM AUTHOR]

In recent times, several machine learning models have been built to aid in the prediction of diverse diseases and to minimize diagnostic errors made by clinicians. However, since most medical datasets seem to be imbalanced, conventional machine learning algorithms tend to underperform when trained with such data, especially in the prediction of the minority class. To address this challenge and proffer a robust model for the prediction of diseases, this paper introduces an approach that comprises of feature learning and classification stages that integrate an enhanced sparse autoencoder (SAE) and Softmax regression, respectively. In the SAE network, sparsity is achieved by penalizing the weights of the network, unlike conventional SAEs that penalize the activations within the hidden layers. For the classification task, the Softmax classifier is further optimized to achieve excellent performance. Hence, the proposed approach has the advantage of effective feature learning and robust classification performance. When employed for the prediction of three diseases, the proposed method obtained test accuracies of 98%, 97%, and 91% for chronic kidney disease, cervical cancer, and heart disease, respectively, which shows superior performance compared to other machine learning algorithms. The proposed approach also achieves comparable performance with other methods available in the recent literature. [ABSTRACT FROM AUTHOR]