Search

Abstract Assisted living facilities cater to the demands of the elderly population, providing assistance and support with day-to-day activities. Fall detection is fundamental to ensuring their well-being and safety. Falls are frequent among older persons and might cause severe injuries and complications. Incorporating computer vision techniques into assisted living environments is revolutionary for these issues. By leveraging cameras and complicated approaches, a computer vision (CV) system can monitor residents’ movements continuously and identify any potential fall events in real time. CV, driven by deep learning (DL) techniques, allows continuous surveillance of people through cameras, investigating complicated visual information to detect potential fall risks or any instances of falls quickly. This system can learn from many visual data by leveraging DL, improving its capability to identify falls while minimalizing false alarms precisely. Incorporating CV and DL enhances the efficiency and reliability of fall detection and allows proactive intervention, considerably decreasing response times in emergencies. This study introduces a new Deep Feature Fusion with Computer Vision for Fall Detection and Classification (DFFCV-FDC) technique. The primary purpose of the DFFCV-FDC approach is to employ the CV concept for detecting fall events. Accordingly, the DFFCV-FDC approach uses the Gaussian filtering (GF) approach for noise eradication. Besides, a deep feature fusion process comprising MobileNet, DenseNet, and ResNet models is involved. To improve the performance of the DFFCV-FDC technique, improved pelican optimization algorithm (IPOA) based hyperparameter selection is performed. Finally, the detection of falls is identified using the denoising autoencoder (DAE) model. The performance analysis of the DFFCV-FDC methodology was examined on the benchmark fall database. A widespread comparative study reported the supremacy of the DFFCV-FDC approach with existing techniques.

Investigating Drug-Target Interactions (DTI) is crucial for drug repositioning and discovery tasks. However, discovering DTIs through experimental approaches is time-consuming and requires substantial financial resources. To address these challenges, machine learning-based methodologies have been adopted to reduce costs and save time. Unfortunately, the effectiveness of these methods has been limited due to the binary classification approach and the lack of empirically validated negative samples. The availability of abundant DTI datasets and protein structure data has enabled the development of new approaches, such as redefining the DTI problem as a regression task. Given this context, we propose an innovative deep-learning approach to predict binding affinities between drugs and targets. Our model, named the Convolution Self-Attention Network with Attention-based Bidirectional Long Short-Term Memory Network (CSAN-BiLSTM-Att), integrates convolutional neural network (CNN) blocks with self-attention mechanisms to create an attention-based bidirectional long short-term memory (BiLSTM) model, followed by fully connected layers. Due to the model's complexity, proper hyperparameter tuning is essential. To optimize this, we employ the Differential Evolution (DE) technique to select the most suitable hyperparameters. Experimental results demonstrate that the DE-based CSAN-BiLSTM-Att model outperforms previous approaches. Specifically, the model achieved a concordance index of 0.898 and a mean square error of 0.228 on the DAVIS dataset, and a concordance value of 0.971 with a mean square error of 0.014 on the KIBA dataset.

This study presents a Prairie Dog Optimization Algorithm with a Deep learning-assisted Aerial Image Classification Approach (PDODL-AICA) on UAV images. The PDODL-AICA technique exploits the optimal DL model for classifying aerial images into numerous classes. In the presented PDODL-AICA technique, the feature extraction procedure is executed using the EfficientNetB7 model. Besides, the hyperparameter tuning of the EfficientNetB7 technique uses the PDO model. The PDODL-AICA technique uses a convolutional variational autoencoder (CVAE) model to detect and classify aerial images. The performance study of the PDODL-AICA model is implemented on a benchmark UAV image dataset. The experimental values inferred the authority of the PDODL-AICA approach over recent models in terms of dissimilar measures.

The neurological ailment known as Parkinson’s disease (PD) affects people throughout the globe. The neurodegenerative PD-related disorder primarily affects people in middle to late life. Motor symptoms such as tremors, muscle rigidity, and sluggish, clumsy movement are common in patients with this disorder. Genetic and environmental variables play significant roles in the development of PD. Despite much investigation, the root cause of this neurodegenerative disease is still unidentified. Clinical diagnostics rely heavily on promptly detecting such irregularities to slow or stop the progression of illnesses successfully. Because of its direct correlation with brain activity, electroencephalography (EEG) is an essential PD diagnostic technique. Electroencephalography, or EEG, data are biomarkers of brain activity changes. However, these signals are non-linear, non-stationary, and complicated, making analysis difficult. One must often resort to a lengthy human labor process to accomplish results using traditional machine-learning approaches. The breakdown, feature extraction, and classification processes are typical examples of these stages. To overcome these obstacles, we present a novel deep-learning model for the automated identification of Parkinson’s disease (PD). The Gabor transform, a standard method in EEG signal processing, was used to turn the raw data from the EEG recordings into spectrograms. In this research, we propose densely linked bidirectional long short-term memory (DLBLSTM), which first represents each layer as the sum of its hidden state plus the hidden states of all layers above it, then recursively transmits that representation to all layers below it. This study’s suggested deep learning model was trained using these spectrograms as input data. Using a robust sixfold cross-validation method, the proposed model showed excellent accuracy with a classification accuracy of 99.6%. The results indicate that the suggested algorithm can automatically identify PD.

Automated rice variety detection and classification is a task that includes automatically categorizing and identifying varieties or different types of rice based on different characteristics namely grain texture, shape, color, and size. This process is essential for quality assessment, agricultural management, and research purposes. Deep learning (DL) is a subfield of machine leaching (ML) that focuses on training an artificial neural network (ANN) with multiple layers to learn hierarchical representations of data. Convolutional Neural Network (CNN) was widely applied in image-based tasks such as rice variety detection, as they could efficiently capture visual features and patterns. In this study, we propose an Automated Rice Variety Detection and Classification using Quantum Inspired Moth Flame Optimizer with Deep Learning (ARVDC-QIMFODL) technique. The presented ARVDC-QIMFODL technique focuses on the automated identification and classification of distinct kinds of rice varieties. To accomplish this, the ARVDC-QIMFODL technique uses the Median modified wiener filter (MMWF) technique for the noise removal process. Followed by, the feature extraction process takes place by an improved ShuffleNet model. For rice variety detection and classification, the long short-term memory (LSTM) approach was applied. At last, the QIMFO algorithm-based hyperparameter selection process is performed to optimize the detection results of the LSTM system. The simulation outcome of the ARVDC-QIMFODL method is tested on a rice image dataset. An extensive set of experiments showed the remarkable efficiency of the ARVDC-QIMFODL system over other models.

Biomedical image analysis has played a pivotal role in modern healthcare by facilitating automated analysis and interpretation of medical images. Biomedical image classification is the process of automatically labelling or categorizing medical images based on their content. In recent years, this field has received considerable attention because of the abundance of bio-medical image data and the potential for deep learning (DL) algorithms to assist medical staff in identifying diseases and making treatment decisions. DL methods are mostly convolutional neural networks (CNN) has illustrated outstanding performance in analyzing and classifying biomedical images. Therefore, this study presents a new Hybrid Metaheuristics with Deep Learning based Fusion Model Biomedical Image Analysis (HMDL-MFMBIA) technique. The HMDL-MFMBIA technique initially performs image pre-processing and Swin-UNet-based segmentation. Besides, a fusion of multiple DL-based feature extractors takes place using Xception and Residual Network (ResNet) model. Moreover, a hybrid salp swarm algorithm (HSSA) was employed for the optimal hyperparameter selection of the DL models. Finally, the gated recurrent unit (GRU) algorithm can be exploited for the detection and classification of bio-medical images. A widespread of simulated is conducted to establish the enhanced biomedical image classification results of the HMDL-MFMBIA method. The simulation outcomes inferred the greater outcome of the HMDL-MFMBIA algorithm over other DL models.

Bone cancer is treated as a severe health problem, and, in many cases, it causes patient death. Early detection of bone cancer is efficient in reducing the spread of malignant cells and decreasing mortality. Since the manual detection process is a laborious task, it is needed to design an automated system to classify and identify the cancerous bone and the healthy bone. Therefore, this article develops an Owl Search Algorithm with a Deep Learning-Driven Bone Cancer Detection and Classification (OSADL-BCDC) technique. The OSADL-BCDC algorithm follows the principle of transfer learning with a hyperparameter tuning strategy for bone cancer detection. The OSADL-BCDC model employs Inception v3 as a pretrained model for the feature extraction process which does not necessitate a manual segmentation of X-ray images. Besides, the OSA is applied as a hyperparameter optimizer for enhancing the efficacy of the Inception v3 method. Finally, the long short-term memory (LSTM) approach is used for identifying the presence of bone cancer. The proposed OSADL-BCDC technique reduces diagnosis time and achieves faster convergence. The experimental analysis of the OSADL-BCDC algorithm is tested using a set of medical images and the outcomes were measured under different aspects. The comparison study highlighted the improved performance of the OSADL-BCDC model over existing algorithms.

Recently, the usage of remote sensing (RS) data attained from unmanned aerial vehicles (UAV) or satellite imagery has become increasingly popular for crop classification processes, namely soil classification, crop mapping, or yield prediction. Food crop classification using RS images (RSI) is a significant application of RS technology in agriculture. It involves the use of satellite or aerial imagery to identify and classify different types of food crops grown in a specific area. This information can be valuable for crop monitoring, yield estimation, and land management. Meeting the criteria for analyzing these data requires increasingly sophisticated methods and artificial intelligence (AI) technologies provide the necessary support. Due to the heterogeneity and fragmentation of crop planting, typical classification approaches have a lower classification performance. However, the DL technique can detect and categorize crop types effectively and has a stronger feature extraction capability. In this aspect, this study designed a new remote sensing imagery data analysis using the marine predators algorithm with deep learning for food crop classification (RSMPA-DLFCC) technique. The RSMPA-DLFCC technique mainly investigates the RS data and determines the variety of food crops. In the RSMPA-DLFCC technique, the SimAM-EfficientNet model is utilized for the feature extraction process. The MPA is applied for the optimal hyperparameter selection process in order to optimize the accuracy of SimAM-EfficientNet architecture. MPA, inspired by the foraging behaviors of marine predators, perceptively explores hyperparameter configurations to optimize the hyperparameters, thereby improving the classification accuracy and generalization capabilities. For crop type detection and classification, an extreme learning machine (ELM) model can be used. The simulation analysis of the RSMPA-DLFCC technique is performed on two benchmark datasets. The extensive analysis of the results portrayed the higher performance of the RSMPA-DLFCC approach over existing DL techniques.

Abstract Node failures are inevitable in wireless sensor networks (WSNs) because sensor nodes in WSNs are miniature and equipped with small and often irreplaceable batteries. Due to battery drainage, sensor nodes can fail at any instance. Moreover, WSNs operate in hostile environments and environmental factors may also contribute to nodes failure. Failure of nodes leads to disruption of inter-node connectivity and might also lead to network partitioning. Failure to communicate with each other and with the base station can compromise the basic operation of the sensor network. For restoration of connectivity, a robust recovery mechanism is required. The existing connectivity restoration mechanisms suffer from shortcomings because they do not focus on energy-efficient operation and coverage-aware mechanisms while performing connectivity restoration. As a result, most of these mechanisms lead to the excessive mobility of nodes, which itself causes the utilization of excessive battery. In this work, we propose a novel technique called smart node relocation (SNR). SNR is capable of detecting and restoring the connectivity caused by either single or multiple node failures. For achieving energy efficiency, SNR relies on transmitting a lesser number of control packets. For achieving the goal of being coverage-aware, it tries to relocate only essential nodes while trying to restore connectivity. By performing extensive simulations, we prove that SNR outperforms the existing approaches concerning multiple performance metrics including but not limited to the total number of packets transmitted, total distance moved for connectivity restoration, the percentage reduction in field coverage.

An Internet of Things (IoT)-assisted Wireless Sensor Network (WSNs) is a system where WSN nodes and IoT devices together work to share, collect, and process data. This incorporation aims to enhance the effectiveness and efficiency of data analysis and collection, resulting in automation and improved decision-making. Security in WSN-assisted IoT can be referred to as the measures initiated for protecting WSN linked to the IoT. This article presents a Binary Chimp Optimization Algorithm with Machine Learning based Intrusion Detection (BCOA-MLID) technique for secure IoT-WSN. The presented BCOA-MLID technique intends to effectively discriminate different types of attacks to secure the IoT-WSN. In the presented BCOA-MLID technique, data normalization is initially carried out. The BCOA is designed for the optimal selection of features to improve intrusion detection efficacy. To detect intrusions in the IoT-WSN, the BCOA-MLID technique employs a class-specific cost regulation extreme learning machine classification model with a sine cosine algorithm as a parameter optimization approach. The experimental result of the BCOA-MLID technique is tested on the Kaggle intrusion dataset, and the results showcase the significant outcomes of the BCOA-MLID technique with a maximum accuracy of 99.36%, whereas the XGBoost and KNN-AOA models obtained a reduced accuracy of 96.83% and 97.20%, respectively.

Wireless sensor networks (WSNs) are becoming a significant technology for ubiquitous living and continue to be involved in active research because of their varied applications. Energy awareness will be a critical design problem in WSNs. Clustering is a widespread energy-efficient method and grants several benefits such as scalability, energy efficiency, less delay, and lifetime, but it results in hotspot issues. To solve this, unequal clustering (UC) has been presented. In UC, the size of the cluster differs with the distance to the base station (BS). This paper devises an improved tuna-swarm-algorithm-based unequal clustering for hotspot elimination (ITSA-UCHSE) technique in an energy-aware WSN. The ITSA-UCHSE technique intends to resolve the hotspot problem and uneven energy dissipation in the WSN. In this study, the ITSA is derived from the use of a tent chaotic map with the traditional TSA. In addition, the ITSA-UCHSE technique computes a fitness value based on energy and distance metrics. Moreover, the cluster size determination via the ITSA-UCHSE technique helps to address the hotspot issue. To demonstrate the enhanced performance of the ITSA-UCHSE approach, a series of simulation analyses were conducted. The simulation values stated that the ITSA-UCHSE algorithm has reached improved results over other models.