Energy is a major driver of human activity. Demand response is of the utmost importance to maintain the efficient and reliable operation of smart grid systems. The short-term load forecasting (STLF) method is particularly significant for electric fields in the trade of energy. This model has several applications to everyday operations of electric utilities, namely load switching, energy-generation planning, contract evaluation, energy purchasing, and infrastructure maintenance. A considerable number of STLF algorithms have introduced a tradeoff between convergence rate and forecast accuracy. This study presents a new wild horse optimization method with a deep learning-based STLF scheme (WHODL-STLFS) for SGs. The presented WHODL-STLFS technique was initially used for the design of a WHO algorithm for the optimal selection of features from the electricity data. In addition, attention-based long short-term memory (ALSTM) was exploited for learning the energy consumption behaviors to forecast the load. Finally, an artificial algae optimization (AAO) algorithm was applied as the hyperparameter optimizer of the ALSTM model. The experimental validation process was carried out on an FE grid and a Dayton grid and the obtained results indicated that the WHODL-STLFS technique achieved accurate load-prediction performance in SGs.

The seamless operation of interconnected smart devices in wireless sensor networks (WSN) and the Internet of Things (IoT) needs continuously accessible end-to-end routes. However, the sensor node (SN) relies on a limited power source and tends to cause disconnection in multi-hop routes because of a power shortage in the WSN, eventually leading to the inefficiency of the total IoT network. Furthermore, the density of available SNs affects the existence of feasible routes and the level of path multiplicity in the WSN. Thus, an effective routing model is predictable to extend the lifetime of WSN by adaptively choosing the better route for the data transfers between interconnected IoT devices. This study develops a Hybrid Muddy Soil Fish Optimization-based Energy Aware Routing Scheme (HMSFO-EARS) for IoT-assisted WSN. The presented HMSFO-EARS technique majorly focuses on the identification of optimal routes for data transmission in the IoT-assisted WSN. To accomplish this, the presented HMSFO-EARS technique involves the integration of the MSFO algorithm with the Adaptive $\beta$-Hill Climbing (ABHC) concept. Moreover, the presented HMSFO-EARS technique derives a fitness function for maximizing the lifespan and minimizing energy consumption. To demonstrate the enhanced performance of the HMSFO-EARS technique, a series of experiments was performed. The simulation results indicate the better performance of the HMSFO-EARS algorithm over other recent approaches with reduced energy consumption, less delay, high throughput, and extended network lifetime.

Recently, facial expression-based emotion recognition techniques obtained excellent outcomes in several real-time applications such as healthcare, surveillance, etc. Machine-learning (ML) and deep-learning (DL) approaches can be widely employed for facial image analysis and emotion recognition problems. Therefore, this study develops a Transfer Learning Driven Facial Emotion Recognition for Advanced Driver Assistance System (TLDFER-ADAS) technique. The TLDFER-ADAS technique helps proper driving and determines the different types of drivers’ emotions. The TLDFER-ADAS technique initially performs contrast enhancement procedures to enhance image quality. In the TLDFER-ADAS technique, the Xception model was applied to derive feature vectors. For driver emotion classification, manta ray foraging optimization (MRFO) with the quantum dot neural network (QDNN) model was exploited in this work. The experimental result analysis of the TLDFER-ADAS technique was performed on FER-2013 and CK+ datasets. The comparison study demonstrated the promising performance of the proposed model, with maximum accuracy of 99.31% and 99.29% on FER-2013 and CK+ datasets, respectively.

Smart solutions for monitoring water pollution are becoming increasingly prominent nowadays with the advance in the Internet of Things (IoT), sensors, and communication technologies. IoT enables connections among different devices with the capability to gather and exchange information. Additionally, IoT extends its ability to address environmental issues along with the automation industry. As water is essential for human survival, it is necessary to integrate some mechanisms for monitoring water quality. Water quality monitoring (WQM) is an efficient and cost-effective system intended to monitor the quality of drinking water that exploits IoT techniques. Therefore, this study developed a new smart water quality prediction using atom search optimization with the fuzzy deep convolution network (WQP-ASOFDCN) technique in the IoT environment. The WQP-ASOFDCN technique seamlessly monitors the water quality parameters using IoT devices for data collection purposes. Data pre-processing is carried out at the initial stage to make the input data compatible for further processing. For water quality prediction, the F-DCN model was utilized in this study. Furthermore, the prediction performance of the F-DCN approach was improved by using the ASO algorithm for the optimal hyperparameter tuning process. A sequence of simulations was applied to validate the enhanced water quality prediction outcomes of the WQP-ASOFDCN method. The experimental values denote the better performance of the WQP-ASOFDCN approach over other approaches in terms of different measures.

Big Data analytics is a technique for researching huge and varied datasets and it is designed to uncover hidden patterns, trends, and correlations, and therefore, it can be applied for making superior decisions in healthcare. Drug–drug interactions (DDIs) are a main concern in drug discovery. The main role of precise forecasting of DDIs is to increase safety potential, particularly, in drug research when multiple drugs are co-prescribed. Prevailing conventional method machine learning (ML) approaches mainly depend on handcraft features and lack generalization. Today, deep learning (DL) techniques that automatically study drug features from drug-related networks or molecular graphs have enhanced the capability of computing approaches for forecasting unknown DDIs. Therefore, in this study, we develop a sparrow search optimization with deep learning-based DDI prediction (SSODL-DDIP) technique for healthcare decision making in big data environments. The presented SSODL-DDIP technique identifies the relationship and properties of the drugs from various sources to make predictions. In addition, a multilabel long short-term memory with an autoencoder (MLSTM-AE) model is employed for the DDI prediction process. Moreover, a lexicon-based approach is involved in determining the severity of interactions among the DDIs. To improve the prediction outcomes of the MLSTM-AE model, the SSO algorithm is adopted in this work. To assure better performance of the SSODL-DDIP technique, a wide range of simulations are performed. The experimental results show the promising performance of the SSODL-DDIP technique over recent state-of-the-art algorithms.

The electroencephalogram (EEG) signal is a key parameter used to identify the different sleep stages present in an overnight sleep recording. Sleep staging is crucial in the diagnosis of several sleep disorders; however, the manual annotation of the EEG signal is a costly and time-consuming process. Automatic sleep staging algorithms offer a practical and cost-effective alternative to manual sleep staging. However, due to the limited availability of EEG sleep datasets, the reliability of existing sleep staging algorithms is questionable. Furthermore, most reported experimental results have been obtained using adult EEG signals; the effectiveness of these algorithms using pediatric EEGs is unknown. In this paper, we conduct an intensive study of two state-of-the-art single-channel EEG-based sleep staging algorithms, namely DeepSleepNet and AttnSleep, using a recently released large-scale sleep dataset collected from 3984 patients, most of whom are children. The paper studies how the performance of these sleep staging algorithms varies when applied on different EEG channels and across different age groups. Furthermore, all results were analyzed within individual sleep stages to understand how each stage is affected by the choice of EEG channel and the participants’ age. The study concluded that the selection of the channel is crucial for the accuracy of the single-channel EEG-based automatic sleep staging methods. For instance, channels O1-M2 and O2-M1 performed consistently worse than other channels for both algorithms and through all age groups. The study also revealed the challenges in the automatic sleep staging of newborns and infants (1–52 weeks).