A comprehensive review of wind power integration and energy storage technologies for modern grid frequency regulation.

Integrating wind power with energy storage technologies is crucial for frequency regulation in modern power systems, ensuring the reliable and cost-effective operation of power systems while promoting the widespread adoption of renewable energy sources. Power systems are changing rapidly, with increased renewable energy integration and evolving system architectures. These transformations bring forth challenges like low inertia and unpredictable behavior of generation and load components. As a result, frequency regulation (FR) becomes increasingly important to ensure grid stability. Energy Storage Systems (ESS) with their adaptable capabilities offer valuable solutions to enhance the adaptability and controllability of power systems, especially within wind farms. This research provides an updated analysis of critical frequency stability challenges, examines state-of-the-art control techniques, and investigates the barriers that hinder wind power integration. Moreover, it introduces emerging ESS technologies and explores their potential applications in supporting wind power integration. Furthermore, this paper offers suggestions and future research directions for scientists exploring the utilization of storage technologies in frequency regulation within power systems characterized by significant penetration of wind power.

Intelligent decision making for energy efficient fog nodes selection and smart switching in the IOT: a machine learning approach.

With the emergence of Internet of Things (IoT) technology, a huge amount of data is generated, which is costly to transfer to the cloud data centers in terms of security, bandwidth, and latency. Fog computing is an efficient paradigm for locally processing and manipulating IoT-generated data. It is difficult to configure the fog nodes to provide all of the services required by the end devices because of the static configuration, poor processing, and storage capacities. To enhance fog nodes' capabilities, it is essential to reconfigure them to accommodate a broader range and variety of hosted services. In this study, we focus on the placement of fog services and their dynamic reconfiguration in response to the end-device requests. Due to its growing successes and popularity in the IoT era, the Decision Tree (DT) machine learning model is implemented to predict the occurrence of requests and events in advance. The DT model enables the fog nodes to predict requests for a specific service in advance and reconfigure the fog node accordingly. The performance of the proposed model is evaluated in terms of high throughput, minimized energy consumption, and dynamic fog node smart switching. The simulation results demonstrate a notable increase in the fog node hit ratios, scaling up to 99% for the majority of services concurrently with a substantial reduction in miss ratios. Furthermore, the energy consumption is greatly reduced by over 50% as compared to a static node.

A molecular dynamics simulations analysis of repurposing drugs for COVID-19 using bioinformatics methods.

A number of multidisciplinary methods have piqued the interest of researchers as means to accelerate and lower the cost of medication creation. The goal of this research was to find target proteins and then select a lead drug against SARS-CoV-2. The three-dimensional structure is taken from the RCSB PDB using its specific PDB ID 6lu7. Virtual screening based on pharmacophores is performed using Molecular Operating Environment software. We looked for a potent inhibitor in the FDA-approved database. For docking, AutoDock Vina uses Pyrx. The compound-target protein binding interactions were tested using BIOVIA Discovery Studio. The stability of protein and inhibitor complexes in a physiological setting was investigated using Desmond's Molecular Dynamics Simulation (MD simulation). According to our findings, we repurpose the FDA-approved drugs ZINC000169677008 and ZINC000169289767, which inhibit the activity of the virus's main protease (6lu7). The scientific community will gain from this finding, which might create new medicine. The novel repurposed chemicals were promising inhibitors with increased efficacy and fewer side effects.Communicated by Ramaswamy H. Sarma.

Identification of lead compound screened from the natural products atlas to treat renal inflammasomes using molecular docking and dynamics simulation.

One of the most prevalent ailments is kidney disease. Effective therapies for chronic renal disease are hard to come by. As a result, there is significant clinical and social interest to predict and develop novel compounds to treat renal disorders. So, specific natural products have been employed in this study because they have protective effects against kidney diseases. When taken orally, natural products can help protect against or lessen the severity of the kidney damage caused by high fructose intake, a high-fat diet, and both Type I and Type 2 diabetes. Reduced podocyte injury, a contributor to albuminuria in diabetic nephropathy, reduces renal endothelial barrier function disruption due to hyperglycemia, as well as urinary microalbumin excretion and glomerular hyperfiltration. Multiple natural products have been shown to protect the kidneys from nephrotoxic chemicals such as LPS, gentamycin, alcohol, nicotine, lead, and cadmium, all of which can persuade acute kidney injury (AKI) or chronic kidney disease (CKD). Natural compounds inhibit regulatory enzymes for controlling inflammation-related diseases. For this, use computational methods such as drug design to identify novel flavonoid compounds against kidney diseases. Drug design via computational methods gaining admiration as a swift and effective technique to identify lead compounds in a shorter time at a low cost. In this in-silico study, we screened The Natural Product Atlas based on a structure-based pharmacophore query. Top hits were analyzed for ADMET analysis followed by molecular docking and docking validation. Finally, the lead compound was simulated for a period of 200 ns and trajectories were studied for stability. We found that NPA024823 showed promising binding and stability with the AIM2. This research work aims to predict novel anti-inflammatory compounds against kidney diseases to inhibit kidney inflammasome by targeting the AIM2 protein. So, in initial preclinical research, there will be lower failure rates that demonstrate safety profiles against predicted compounds.Communicated by Ramaswamy H. Sarma.

AVPCD: a plant-derived medicine database of antiviral phytochemicals for cancer, Covid-19, malaria and HIV.

Serious illnesses caused by viruses are becoming the world's most critical public health issues and lead millions of deaths each year in the world. Thousands of studies confirmed that the plant-derived medicines could play positive therapeutic effects on the patients with viral diseases. Since thousands of antiviral phytochemicals have been identified as lifesaving drugs in medical research, a comprehensive database is highly desirable to integrate the medicinal plants with their different medicinal properties. Therefore, we provided a friendly antiviral phytochemical database AVPCD covering 2537 antiviral phytochemicals from 383 medicinal compounds and 319 different families with annotation of their scientific, family and common names, along with the parts used, disease information, active compounds, links of relevant articles for COVID-19, cancer, HIV and malaria. Furthermore, each compound in AVPCD was annotated with its 2D and 3D structure, molecular formula, molecular weight, isomeric SMILES, InChI, InChI Key and IUPAC name and 21 other properties. Each compound was annotated with more than 20 properties. Specifically, a scoring method was designed to measure the confidence of each phytochemical for the viral diseases. In addition, we constructed a user-friendly platform with several powerful modules for searching and browsing the details of all phytochemicals. We believe this database will facilitate global researchers, drug developers and health practitioners in obtaining useful information against viral diseases.

A computational approach to fighting type 1 diabetes by targeting 2C Coxsackie B virus protein with flavonoids.

Autoimmune diabetes, well-known as type 1 insulin-dependent diabetic mellitus (T1D). T1D is a prolonged condition marked by an inadequate supply of insulin. The lack is brought on by pancreatic cell death and results in hyperglycemia. The immune system, genetic predisposition, and environmental variables are just a few of the many elements that contribute significantly to the pathogenicity of T1D disease. In this study, we test flavonoids against Coxsackie virus protein to cope the type 1 diabetes. After protein target identification we perform molecular docking of flavonoids and selected target (1z8r). then performed the ADMET analysis and select the top compound the base of the docking score and the ADMET test analysis. Following that molecular dynamics simulation was performed up to 300 ns. Root means square deviation, root mean square fluctuation, secondary structure elements, and protein-ligand contacts were calculated as post-analysis of simulation. We further check the binding of the ligand with protein by performing MM-GBSA every 10 ns. Lead compound CID_5280445 was chosen as a possible medication based on analysis. The substance is non-toxic, meets the ADMET and BBB likeness requirements, and has the best interaction energy. This work will assist researchers in developing medicine and testing it as a treatment for Diabetes Mellitus Type 1 brought on by Coxsackie B4 viruses by giving them an understanding of chemicals against these viruses.

A Scalable Federated Learning Approach for Collaborative Smart Healthcare Systems with Intermittent Clients using Medical Imaging.

The healthcare industry is one of the most vulnerable to cybercrime and privacy violations because health data is very sensitive and spread out in many places. Recent confidentiality trends and a rising number of infringements in different sectors make it crucial to implement new methods that protect data privacy while maintaining accuracy and sustainability. Moreover, the intermittent nature of remote clients with imbalanced datasets poses a significant obstacle for decentralized healthcare systems. Federated learning (FL) is a decentralized and privacy-protecting approach to deep learning and machine learning models. In this paper, we implement a scalable FL framework for interactive smart healthcare systems with intermittent clients using chest X-ray images. Remote hospitals may have imbalanced datasets with intermittent clients communicating with the FL global server. The data augmentation method is used to balance datasets for local model training. In practice, some clients may leave the training process while others join due to technical or connectivity issues. The proposed method is tested with five to eighteen clients and different testing data sizes to evaluate performance in various situations. The experiments show that the proposed FL approach produces competitive results when dealing with two distinct problems, such as intermittent clients and imbalanced data. These findings would encourage medical institutions to collaborate and use rich private data to quickly develop a powerful patient diagnostic model.

Community-Acquired Skin and Soft Tissue Infections: Epidemiology and Management in Patients Presenting to the Emergency Department of a Tertiary Care Hospital.

BACKGROUND: Skin and soft tissue infections are one of the most common diseases presenting to the emergency department (ED). There is no study available on the management of Community-Acquired Skin and Soft Tissue Infections (CA-SSTIs) in our population recently. This study aims to describe the frequency and distribution of CA-SSTIs as well as their medical and surgical management among patients presenting to our ED. METHODS: We conducted a descriptive cross-sectional study on patients presenting with CA-SSTIs to the ED of a tertiary care hospital in Peshawar, Pakistan. The primary objective was to estimate the frequency of common CA-SSTIs presenting to the ED and to assess the management of these infections in terms of diagnostic workup and treatment modalities used. The secondary objectives were to study the association of different baseline variables, diagnostic modalities, treatment modalities, and improvement with the surgical procedure performance for these infections. Descriptive statistics were obtained for quantitative variables like age. Frequencies and percentages were derived for categorical variables. The chi-square test was used to compare different CA-SSTIs in terms of categorical variables like diagnostic and treatment modalities. We divided the data into two groups based on the surgical procedure. A chi-square analysis was conducted to compare these two groups in terms of categorical variables. RESULTS: Out of the 241 patients, 51.9% were males and the mean age was 34.2 years. The most common CA-SSTIs were abscesses, infected ulcers, and cellulitis. Antibiotics were prescribed to 84.2% of patients. Amoxicillin + Clavulanate was the most frequently prescribed antibiotic. Out of the total, 128 (53.11%) patients received some type of surgical intervention. Surgical procedures were significantly associated with diabetes mellitus, heart disease, limitation of mobility, or recent antibiotic use. There was a significantly higher rate of prescription of any antibiotic and anti-methicillin-resistant Staphylococcus aureus (anti-MRSA) agents in the surgical procedure group. This group also saw a higher rate of oral antibiotics prescription, hospitalization, wound culture, and complete blood count. CONCLUSION: This study shows a higher frequency of purulent infections in our ED. Antibiotics were prescribed more frequently for all infections. Surgical procedures like incision and drainage were much lower even in purulent infections. Furthermore, beta-lactam antibiotics like Amoxicillin-Clavulanate were commonly prescribed. Linezolid was the only systemic anti-MRSA agent prescribed. We suggest physicians should prescribe antibiotics appropriate to the local antibiograms and the latest guidelines.

A Novel Framework for Melanoma Lesion Segmentation Using Multiparallel Depthwise Separable and Dilated Convolutions with Swish Activations.

Skin cancer remains one of the deadliest kinds of cancer, with a survival rate of about 18-20%. Early diagnosis and segmentation of the most lethal kind of cancer, melanoma, is a challenging and critical task. To diagnose medicinal conditions of melanoma lesions, different researchers proposed automatic and traditional approaches to accurately segment the lesions. However, visual similarity among lesions and intraclass differences are very high, which leads to low-performance accuracy. Furthermore, traditional segmentation algorithms often require human inputs and cannot be utilized in automated systems. To address all of these issues, we provide an improved segmentation model based on depthwise separable convolutions that act on each spatial dimension of the image to segment the lesions. The fundamental idea behind these convolutions is to divide the feature learning steps into two simpler parts that are spatial learning of features and a step for channel combination. Besides this, we employ parallel multidilated filters to encode multiple parallel features and broaden the view of filters with dilations. Moreover, for performance evaluation, the proposed approach is evaluated on three different datasets including DermIS, DermQuest, and ISIC2016. The finding indicates that the suggested segmentation model has achieved the Dice score of 97% for DermIS and DermQuest and 94.7% for the ISBI2016 dataset, respectively.

Sex-Linked Differences in Pulmonary Functions of COVID-19 Patients After a Six-Minute Walk Test.

Coronavirus disease 2019 (COVID-19) predominantly impacts the respiratory system. Historically, numerous lung diseases have shown sex-related differences throughout their progression. This study aimed to identify sex-linked disparities in pulmonary function tests (PFTs) among individuals who have recovered from COVID-19 when subjected to a six-minute walk test (6MWT). In this observational cross-sectional study, we analyzed 61 participants, consisting of 39 (64%) males and 22 (36%) females, all of whom previously contracted COVID-19 three months or more prior. We measured vitals such as blood pressure, pulse, oxygen saturation, and PFT values before and after the 6MWT. The post-6MWT evaluation revealed notable mean differences between males and females in parameters systolic blood pressure (SBP) (p = 0.003), diastolic blood pressure (DBP) (p = 0.026), forced expiratory volume in the first second (FEV1) (p = 0.038), forced vital capacity (FVC) (p = 0.041), and maximum voluntary ventilation (MVV) index (p = 0.011). PFT outcomes indicated sex-based variations among post-COVID-19 subjects. Specifically, post-stress values for FEV1, FVC, MVV index, SBP, and DBP were more elevated in males than in females. However, females presented with higher oxygen saturation levels post-COVID-19 compared to males. Using multiple linear regression modeling, sex was not found to be a strong predictor of PFT results. However, individual regression analyses for FEV1, FVC, and MVV index consistently showcased higher values in males. In conclusion, significant PFT differences exist between males and females after recovery from COVID-19 when exposed to stress induction via the 6MWT.

Diagnosis and Treatment of Liver Disease: Current Trends and Future Directions.

This narrative review delves into the intricate landscape of liver diseases, providing a comprehensive background of the diverse conditions that afflict this vital organ. Liver diseases, ranging from viral hepatitis and non-alcoholic fatty liver disease (NAFLD) to cirrhosis and hepatocellular carcinoma (HCC), pose significant global health challenges. Understanding these diseases' multifaceted origins and progression is pivotal for developing effective diagnostic and therapeutic strategies. The epidemiology and etiology of liver diseases emphasize the global impact of viral hepatitis, with hepatitis B and C as significant contributors. Concurrently, the rising prevalence of NAFLD, linked to lifestyle factors and metabolic syndrome, underscores the intricate relationship between modern living and liver health. Chronic liver diseases often evolve insidiously, progressing from inflammation to fibrosis and, ultimately, to cirrhosis - a stage characterized by irreversible scarring and compromised function. The heightened risk of HCC in advanced liver disease stages further underscores the urgency of effective diagnostic and therapeutic interventions. The evolving landscape of non-invasive diagnostic tools is explored for their role in enabling early detection and accurate staging of liver diseases. In the realm of treatment, there is a continuous transition toward personalized medicine, customized to suit the unique profiles of individual patients. This shift encompasses a broad spectrum, ranging from personalized pharmacological interventions to lifestyle modifications and surgical options. Delving into innovative therapies, such as gene editing and immunomodulation, offers a glimpse into the promising future directions that have the potential to redefine the landscape of liver disease diagnosis and treatment.

Neurological Manifestations of Infectious Diseases: Insights From Recent Cases.

This narrative review examines the complex connection between infectious diseases and their neurological effects. It provides a detailed analysis of recent instances and insights derived from various pathogens. As we explore the realm of infectious agents, including viruses, bacteria, parasites, and fungi, a thorough and diverse analysis reveals the intricacies of neurological problems. The review begins by examining viral infections, specifically focusing on how viruses invade the neurological system and its subsequent effects. Significant instances from recent widespread disease outbreaks function as instructive benchmarks, highlighting the progressing comprehension of these ever-changing interconnections. The article examines the complex pathophysiology of neurological problems caused by bacterial infections. It presents current cases that illustrate the various ways these complications might manifest and the difficulties faced in their therapeutic management. Parasitic and fungal infections, which are typically overlooked, are being carefully examined to emphasize their distinct role in causing neurological complications. The mentioned cases highlight the importance of being thoroughly aware of these less-explored areas ranging from protozoan parasites to opportunistic fungal infections. In addition to the immediate effects caused by infectious agents, the review investigates autoimmune responses activated by infections. It provides a detailed examination of specific instances that shed light on the complex relationship between viral triggers and future neurological problems. This text elaborates on the intricacy of autoimmune-related neurological issues, highlighting the necessity for a comprehensive approach to diagnosing and treating them. The narrative next redirects its attention to the diagnostic difficulties that arise when interpreting the neurological symptoms of viral disorders. This article provides a thorough examination of existing diagnostic tools, along with an investigation into new technologies that have the potential to improve our capacity to identify and comprehend complex presentations. This debate connects to the following examination of treatment methods, where current cases that showcase successful interventions are carefully examined to extract valuable insights into good clinical management. The discussion focuses on the public health implications of preventive efforts against infectious infections, including their neurological consequences. The story emphasizes the link between infectious diseases and overall societal health, advocating for a proactive strategy to reduce the impact of neurological complications. The abstract concludes by providing a prospective viewpoint, highlighting areas of research that still need to be addressed, and suggesting potential future avenues. This narrative review seeks to provide a comprehensive resource for physicians, researchers, and public health professionals dealing with the complex field of neurological manifestations in infectious diseases. It combines recent examples, synthesizes current information, and offers a holistic perspective.

Cardio-Oncology: Managing Cardiovascular Complications of Cancer Therapies.

This narrative review explores the complex relationship between cancer medicines and cardiovascular health in the junction of oncology and cardiology, known as cardio-oncology. The study examines the historical development of cancer treatments and highlights the growing importance of cardiovascular problems in patient care. This text delves into the topic of cardiotoxicity, examining both conventional chemotherapeutic drugs like anthracyclines and more recent tyrosine kinase and immune checkpoint inhibitors. The complex molecular and cellular mechanisms that control cardiovascular problems are explained, including an understanding of how genetic predisposition influences an individual's sensitivity. The narrative expands into the crucial realm of risk stratification and evaluation, revealing advanced instruments for identifying cardiovascular risk in cancer patients. The importance of non-invasive imaging methods and biomarkers in early detection and continuous monitoring is emphasized. The prioritization of preventive tactics emphasizes the need to take proactive measures incorporating therapies to protect the heart throughout cancer treatment. It also highlights the significance of making lifestyle improvements to reduce risk factors. The narrative emphasizes the changing collaborative treatment environment, advocating for merging oncologists and cardiologists in a coordinated endeavor to maximize patient outcomes. In addition to clinical factors, the review explores the critical domain of patient education and support, acknowledging its crucial role in promoting informed decision-making and improving overall patient well-being. The latter portions of the text anticipate and consider upcoming treatments and existing research efforts that offer the potential for the future of cardio-oncology. This review seeks to provide a detailed viewpoint on the intricate connection between cancer treatments and cardiovascular well-being. Its objective is to encourage a more profound comprehension of the subject and prompt careful contemplation regarding the comprehensive care of cancer patients who confront the intricate difficulties presented by their treatment plans.

Successful Repair of a Complete Tracheobronchial Tear Two Months After the Injury.

Tracheobronchial injury (TBI) is a rare but potentially life-threatening tear of the lower airway that can result from iatrogenic or accidental trauma. We present a case of a young male who suffered from acute TBI following blunt trauma to the chest. The patient was managed conservatively with intubation and oxygen support initially. The condition improved and the patient was discharged. However, he developed chest pain two months later and was diagnosed with a complete TBI on the right side. He subsequently underwent open surgical repair of the tear with end-to-end anastomosis, which led to a full recovery.

A malware detection system using a hybrid approach of multi-heads attention-based control flow traces and image visualization.

Android is the most widely used mobile platform, making it a prime target for malicious attacks. Therefore, it is imperative to effectively circumvent these attacks. Recently, machine learning has been a promising solution for malware detection, which relies on distinguishing features. While machine learning-based malware scanners have a large number of features, adversaries can avoid detection by using feature-related expertise. Therefore, one of the main tasks of the Android security industry is to consistently propose cutting-edge features that can detect suspicious activity. This study presents a novel feature representation approach for malware detection that combines API-Call Graphs (ACGs) with byte-level image representation. First, the reverse engineering procedure is used to obtain the Java programming codes and Dalvik Executable (DEX) file from Android Package Kit (APK). Second, to depict Android apps with high-level features, we develop ACGs by mining API-Calls and API sequences from Control Flow Graph (CFG). The ACGs can act as a digital fingerprint of the actions taken by Android apps. Next, the multi-head attention-based transfer learning method is used to extract trained features vector from ACGs. Third, the DEX file is converted to a malware image, and the texture features are extracted and highlighted using a combination of FAST (Features from Accelerated Segment Test) and BRIEF (Binary Robust Independent Elementary Features). Finally, the ACGs and texture features are combined for effective malware detection and classification. The proposed method uses a customized dataset prepared from the CIC-InvesAndMal2019 dataset and outperforms state-of-the-art methods with 99.27% accuracy.

A Rare Case of Asymptomatic Massive Colonic Lithobezoar in a Young Child.

Colonic bezoar is a rare condition of accumulation of foreign bodies or non-nutritious material in the large intestine, usually presenting with symptoms of obstruction. Colonic lithobezoar is an even more rare type of condition with only 12 cases reported in the literature to date. We present a case of a young, intellectually disabled kid, who was diagnosed incidentally with lithobezoar after a road traffic accident. The first-line treatment for uncomplicated non-obstructed bezoar is a medical treatment with laxatives and fluids. For acutely obstructed bezoars, the treatment of choice is evacuation under general anesthesia. Surgical evacuation may be considered a last resort in complicated or refractory cases. Moreover, regardless of obstruction, all cases must be treated as inpatients and must receive a psychiatric and hematologic evaluation.

Explainable Malware Detection System Using Transformers-Based Transfer Learning and Multi-Model Visual Representation.

Android has become the leading mobile ecosystem because of its accessibility and adaptability. It has also become the primary target of widespread malicious apps. This situation needs the immediate implementation of an effective malware detection system. In this study, an explainable malware detection system was proposed using transfer learning and malware visual features. For effective malware detection, our technique leverages both textual and visual features. First, a pre-trained model called the Bidirectional Encoder Representations from Transformers (BERT) model was designed to extract the trained textual features. Second, the malware-to-image conversion algorithm was proposed to transform the network byte streams into a visual representation. In addition, the FAST (Features from Accelerated Segment Test) extractor and BRIEF (Binary Robust Independent Elementary Features) descriptor were used to efficiently extract and mark important features. Third, the trained and texture features were combined and balanced using the Synthetic Minority Over-Sampling (SMOTE) method; then, the CNN network was used to mine the deep features. The balanced features were then input into the ensemble model for efficient malware classification and detection. The proposed method was analyzed extensively using two public datasets, CICMalDroid 2020 and CIC-InvesAndMal2019. To explain and validate the proposed methodology, an interpretable artificial intelligence (AI) experiment was conducted.

Cyber-Threat Detection System Using a Hybrid Approach of Transfer Learning and Multi-Model Image Representation.

Currently, Android apps are easily targeted by malicious network traffic because of their constant network access. These threats have the potential to steal vital information and disrupt the commerce, social system, and banking markets. In this paper, we present a malware detection system based on word2vec-based transfer learning and multi-model image representation. The proposed method combines the textual and texture features of network traffic to leverage the advantages of both types. Initially, the transfer learning method is used to extract trained vocab from network traffic. Then, the malware-to-image algorithm visualizes network bytes for visual analysis of data traffic. Next, the texture features are extracted from malware images using a combination of scale-invariant feature transforms (SIFTs) and oriented fast and rotated brief transforms (ORBs). Moreover, a convolutional neural network (CNN) is designed to extract deep features from a set of trained vocab and texture features. Finally, an ensemble model is designed to classify and detect malware based on the combination of textual and texture features. The proposed method is tested using two standard datasets, CIC-AAGM2017 and CICMalDroid 2020, which comprise a total of 10.2K malware and 3.2K benign samples. Furthermore, an explainable AI experiment is performed to interpret the proposed approach.

Explainable Artificial Intelligence-Based IoT Device Malware Detection Mechanism Using Image Visualization and Fine-Tuned CNN-Based Transfer Learning Model.

Automated malware detection is a prominent issue in the world of network security because of the rising number and complexity of malware threats. It is time-consuming and resource intensive to manually analyze all malware files in an application using traditional malware detection methods. Polymorphism and code obfuscation were created by malware authors to bypass the standard signature-based detection methods used by antivirus vendors. Malware detection using deep learning (DL) approaches has recently been implemented in an effort to address this problem. This study compares the detection of IoT device malware using three current state-of-the-art CNN models that have been pretrained. Large-scale learning performance using GNB, SVM, DT, LR, K-NN, and ensemble classifiers with CNN models is also included in the results. In light of the findings, a pretrained Inception-v3 CNN-based transfer learned model with fine-tuned strategy is proposed to identify IoT device malware by utilizing color image malware display of android Dalvik Executable File (DEX). Inception-v3 retrieves the malware's most important features. After that, a global max-pooling layer is applied, and a SoftMax classifier is used to classify the features. Finally, gradient-weighted class activation mapping (Grad-CAM) along the t-distributed stochastic neighbor embedding (t-SNE) is used to understand the overall performance of the proposed method. The proposed method achieved an accuracy of 98.5% and 91%, respectively, in the binary and multiclass prediction of malware images from IoT devices, exceeding the comparison methods in different evaluation parameters.

Explainable artificial intelligence approach in combating real-time surveillance of COVID19 pandemic from CT scan and X-ray images using ensemble model.

Population size has made disease monitoring a major concern in the healthcare system, due to which auto-detection has become a top priority. Intelligent disease detection frameworks enable doctors to recognize illnesses, provide stable and accurate results, and lower mortality rates. An acute and severe disease known as Coronavirus (COVID19) has suddenly become a global health crisis. The fastest way to avoid the spreading of Covid19 is to implement an automated detection approach. In this study, an explainable COVID19 detection in CT scan and chest X-ray is established using a combination of deep learning and machine learning classification algorithms. A Convolutional Neural Network (CNN) collects deep features from collected images, and these features are then fed into a machine learning ensemble for COVID19 assessment. To identify COVID19 disease from images, an ensemble model is developed which includes, Gaussian Naive Bayes (GNB), Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), K-Nearest Neighbor (KNN), and Random Forest (RF). The overall performance of the proposed method is interpreted using Gradient-weighted Class Activation Mapping (Grad-CAM), and t-distributed Stochastic Neighbor Embedding (t-SNE). The proposed method is evaluated using two datasets containing 1,646 and 2,481 CT scan images gathered from COVID19 patients, respectively. Various performance comparisons with state-of-the-art approaches were also shown. The proposed approach beats existing models, with scores of 98.5% accuracy, 99% precision, and 99% recall, respectively. Further, the t-SNE and explainable Artificial Intelligence (AI) experiments are conducted to validate the proposed approach.