Abstract Energy consumption is a vital issue when optimum usage and carbon footprint are all considered in today’s Internet of Things (IoT) environments. Considering edge computing, that becomes too critical in terms of wireless devices with limited battery power. Especially in healthcare applications, the defined IoHT approach requires sustainability while future massive solutions may result negative outputs in terms of carbon footprint. So, optimum energy consumption seems positive in terms of multiple ways. In the literature, one trendy method is using clustering for lowering the energy consumption within the Internet of Healthcare Things (IoHT) environment on edge computing. In this study, optimization of energy consumption in IoHT was done via improved Genetic Electro-Search Optimization (GESO) algorithm. According to the obtained findings in the performed applications, GESO was effective enough in finding optimum conditions of energy consumption for an active IoHT setup.

Deep learning has a great impact on advanced real-world problem solving since it can deal with complex and big amount of data. One of the recent successful applications of deep learning is biomedical imaging and there is a remarkable research effort using medical image data (obtained via MR, tomography, X-Ray, pathology, microscopy, breast CAD, etc.) to perform especially diagnosis oriented studies considering vital diseases such as human brain disorders diseases (i.e., Alzheimer's, Parkinson, sleep disorders) or cancer (i.e., breast cancer, lung cancer, skin cancer). The literature often reports effective results, and thus the use of deep learning for biomedical imaging is a research hot topic. Deep learning is essentially a collection of advanced neural networks such as convolutional neural networks (CNN), deep belief networks (DBN), or auto-encoder neural networks. CNN is the most famous among them but all of these deep learning techniques can be successfully applied in biomedical imaging studies. In some cases, it has been also possible to combine them in hybrid-modelled solutions for improved results. Here, the key questions for understanding the performance of such deep neural networks could be (1) How effective can these neural networks detect a disease, via biomedical imaging? (2) How fast and early can they perform a diagnosis? (3) How can they accomplish the same performance for different types of diseases? (4) How can they contribute to the current and future of medicine?, by moving over the biomedical imaging? This special issue focuses on recent advances, challenges, and future perspectives about deep neural networks applied in biomedical studies in different domains of knowledge. From around 90 submitted articles to this particular section, six papers were selected based on the reviews. Each paper was reviewed by at least two reviewers and went through at least two rounds of reviews. The brief contributions of these papers are discussed below. In the first paper of this special issue, the authors (Shah et al., 2022) have used deep-convolutional generative adversarial networks algorithm to address which generates synthetic images for all the classes (Normal, Pneumonia and COVID-19). To validate whether the generated images are accurate, the k-mean clustering technique with three clusters (Normal, Pneumonia and COVID-19) have been used. The selected X-ray images classified in the correct clusters for training. In this way, a synthetic dataset with three classes has been formed. The generated dataset was then fed to The EfficientNetB4 for training and the experiments achieved promising results of 95% in terms of area under the curve (AUC). The authors (Yadav et al., 2022) propose an enhanced DL CNN model with the Leaky ReLU activation function. DermNet NZ's facial acne images dataset is used for the experiments. Three different techniques- K-Means, texture analysis and HSV model-based segmentation, are applied for image segmentation to extract the acne region from skin images. After applying all the above image segmentation methods five times for each method, output images from K-Means and HSV (5 + 5 images) are collected and combined with the dataset. Using that dataset, one SVM model using Scikit-learn and two CNN models- one with the ReLU activation function and another with the LeakyReLU activation function, is trained. Out of these three models, the proposed CNN (LeakyReLU) model achieved a 97.54% accuracy. In this paper by Loh et al. (2022), the short-time Fourier transform (STFT) is first applied to the EEG signals to obtain spectrogram images of MDD patients and healthy subjects. These spectrogram images are then fed to the CNN model for automated detection of MDD patients and healthy subjects. The EEG signals used in this study were obtained from public database with 34 MDD patients and 30 healthy subjects. The highest classification accuracy, precision, sensitivity, specificity and F1-score of 99.58%, 99.40%, 99.70%, 99.48% and 99.55%, respectively, were obtained with hold-out validation. The proposed MDD detection model is highly accurate and needs to be validated with more diverse MDD database before it can be used in clinical settings. In this research, the authors (Mallikarjuna et al., 2022) support deep neural network (DNN) analysis in healthcare and COVID-19 pandemic and gives the smart contract procedure, to identify the feature extracted data (FED) from the existing data. At the same time, the innovation will be useful to analyse future diseases. The proposed method also analyse the existing diseases which had been reported and it is extremely useful to guide physicians in providing appropriate treatment and save lives. To achieve this, the massive data is integrated using Python scripting language under various libraries to perform a wide range of medical and healthcare functions to infer knowledge that assists in the diagnosis of major diseases such as heart disease, blood cancer, gastric and COVID-19. The next paper by Mansour et al. (2022) presents a novel AI based fusion model for CRC disease diagnosis and classification, named AIFM-CRC. The presented AIFM-CRC model primarily undergoes Gaussian filtering based noise removal and contrast enhancement as a pre-processing stage. In addition, a fusion based feature extraction process takes place where the SIFT based handcrafted features and Inception v4 based deep features are fused together. Besides, whale optimization algorithm tuned deep support vector machine model is employed as a classification technique to determine the existence of CRC. In order to highlight the proficient results analysis of the AIFM-CRC model, a comprehensive simulation analysis takes place. The resultant experimental values pointed out the betterment of the AIFM-CRC model by accomplishing a maximum accuracy of 96.18%. The final article by Yuan et al. (2022) explores the adoption value of deep learning combined with computed tomography (CT) imaging omics in the prediction of metastatic lymph nodes of nasopharyngeal carcinoma (NPC). An end-to-end neural network architecture was designed based on the fully convolutional neural network (FCNN), which was applied to the CT image analysis of 52 patients with lymphatic metastasis and 36 patients without lymphatic metastasis. Patient's lymph node volume (V), the largest cross-sectional shortest diameter (d-value) and other macro characteristics were recorded. The microscopic features of its CT imaging omics were extracted. The results showed that the lymph node volume (4.37 ± 0.67) and the shortest diameter of the largest cross section (12.35 ± 2.31) of patients with lymph node metastasis were greatly larger than those without lymph node metastasis (1.84 ± 0.65, 7.98 ± 2.04) (p < 0.05). To conclude, this special issue publishes six papers out of a total of around 90 submitted papers. The guest editors hope that the research contributions and findings in this special issue would benefit the readers in enhancing their knowledge and encouraging them to work on various aspects of deep neural networks for biomedical data and imaging. We want to express our sincere thanks to the Editor-in-Chief and Special Issues & Reviews Editor for allowing us to organise this particular issue. The editorial office staffs are excellent, and thanks for their support. We are also thankful to all the authors who made this special issue possible, and to the reviewers for their thoughtful contributions.

In Medicine Deep Learning has become an essential tool to achieve outstanding diagnosis on image data. However, one critical problem is that Deep Learning comes with complicated, black-box models so it is not possible to analyze their trust level directly. So, Explainable Artificial Intelligence (XAI) methods are used to build additional interfaces for explaining how the model has reached the outputs by moving from the input data. Of course, that's again another competitive problem to analyze if such methods are successful according to the human view. So, this paper comes with two important research efforts: (1) to build an explainable deep learning model targeting medical image analysis, and (2) to evaluate the trust level of this model via several evaluation works including human contribution. The target problem was selected as the brain tumor classification, which is a remarkable, competitive medical image-based problem for Deep Learning. In the study, MR-based pre-processed brain images were received by the Subtractive Spatial Lightweight Convolutional Neural Network (SSLW-CNN) model, which includes additional operators to reduce the complexity of classification. In order to ensure the explainable background, the model also included Class Activation Mapping (CAM). It is important to evaluate the trust level of a successful model. So, numerical success rates of the SSLW-CNN were evaluated based on the peak signal-to-noise ratio (PSNR), computational time, computational overhead, and brain tumor classification accuracy. The objective of the proposed SSLW-CNN model is to obtain faster and good tumor classification with lesser time. The results illustrate that the SSLW-CNN model provides better performance of PSNR which is enhanced by 8%, classification accuracy is improved by 33%, computation time is reduced by 19%, computation overhead is decreased by 23%, and classification time is minimized by 13%, as compared to state-of-the-art works. Because the model provided good numerical results, it was then evaluated in terms of XAI perspective by including doctor-model based evaluations such as feedback CAM visualizations, usability, expert surveys, comparisons of CAM with other XAI methods, and manual diagnosis comparison. The results show that the SSLW-CNN provides good performance on brain tumor diagnosis and ensures a trustworthy solution for the doctors.

Abstract The facility layout problem (FLP) is a combinatorial optimization problem. The performance of the layout design is significantly impacted by diverse, multiple factors. The use of algorithmic or procedural design methodology in ranking and identification of efficient layout is ineffective. In this context, this study proposes a three‐stage methodology where data envelopment analysis (DEA) is augmented with unsupervised and supervised machine learning (ML). In stage 1, unsupervised ML is used for the clustering of the criteria in which the layouts need to be evaluated using homogeneity. Layouts are generated using simulated annealing, chaotic simulated annealing, and hybrid firefly algorithm/chaotic simulated annealing meta‐heuristics. In stage 2, the nonparametric DEA approach is used to identify efficient and inefficient layouts. Finally, supervised ML utilizes the performance frontiers from DEA (efficiency scores) to generate a trained model for getting the unique rankings and predicted efficiency scores of layouts. The proposed methodology overcomes the limitations associated with large datasets that contain many inputs / outputs from the conventional DEA and improves the prediction accuracy of layouts. A Gaussian distribution product demand dataset for time period T = 5 and facility size N = 12 is used to prove the effectiveness of the methodology.

Due to the absorption and scattering of light in underwater environment, underwater images have poor contrast and resolution. This situation generally causes to a color, which became more dominant than the other ones. Because of that, analyzing underwater images effectively and identifying any object under the water has become a difficult task. In this paper, an underwater enhancement approach by using differential evolution algorithm was proposed. In the approach, a contrast enhancement in the RGB space is done. By using the approach, both scattering and absorption effects are reduced.

In this paper, a software system, which employs an intelligent approach to adjust learning process more accurately by determining student's learning status, is described briefly. The system comes with an Artificial Neural Networks based infrastructure to evaluate students' learning styles or levels before feeding its interface with the related course contents. The Artificial Neural Networks structure is mainly fed with answers that were given for a specially designed Multiple Intelligences test and this data is also combined with some other ones like examination grades, or points given by the course teacher for each student. Eventually, the stored course contents are then viewed to the active student, according to his / her learning status determined by the system. The designed and developed software system has been tested during the "visual programming" course and obtained results have been also reported in this study.