A Critical Cybersecurity Analysis and Future Research Directions for the Internet of Things: A Comprehensive Review.

The emergence of the Internet of Things (IoT) technology has brought about tremendous possibilities, but at the same time, it has opened up new vulnerabilities and attack vectors that could compromise the confidentiality, integrity, and availability of connected systems. Developing a secure IoT ecosystem is a daunting challenge that requires a systematic and holistic approach to identify and mitigate potential security threats. Cybersecurity research considerations play a critical role in this regard, as they provide the foundation for designing and implementing security measures that can address emerging risks. To achieve a secure IoT ecosystem, scientists and engineers must first define rigorous security specifications that serve as the foundation for developing secure devices, chipsets, and networks. Developing such specifications requires an interdisciplinary approach that involves multiple stakeholders, including cybersecurity experts, network architects, system designers, and domain experts. The primary challenge in IoT security is ensuring the system can defend against both known and unknown attacks. To date, the IoT research community has identified several key security concerns related to the architecture of IoT systems. These concerns include issues related to connectivity, communication, and management protocols. This research paper provides an all-inclusive and lucid review of the current state of anomalies and security concepts related to the IoT. We classify and analyze prevalent security distresses regarding IoT's layered architecture, including connectivity, communication, and management protocols. We establish the foundation of IoT security by examining the current attacks, threats, and cutting-edge solutions. Furthermore, we set security goals that will serve as the benchmark for assessing whether a solution satisfies the specific IoT use cases.

Improved Cognitive Vigilance Assessment after Artifact Reduction with Wavelet Independent Component Analysis.

Vigilance level assessment is of prime importance to avoid life-threatening human error. Critical working environments such as air traffic control, driving, or military surveillance require the operator to be alert the whole time. The electroencephalogram (EEG) is a very common modality that can be used in assessing vigilance. Unfortunately, EEG signals are prone to artifacts due to eye movement, muscle contraction, and electrical noise. Mitigating these artifacts is important for an accurate vigilance level assessment. Independent Component Analysis (ICA) is an effective method and has been extensively used in the suppression of EEG artifacts. However, in vigilance assessment applications, it was found to suffer from leakage of the cerebral activity into artifacts. In this work, we show that the wavelet ICA (wICA) method provides an alternative for artifact reduction, leading to improved vigilance level assessment results. We conducted an experiment in nine human subjects to induce two vigilance states, alert and vigilance decrement, while performing a Stroop Color-Word Test for approximately 45 min. We then compared the performance of the ICA and wICA preprocessing methods using five classifiers. Our classification results showed that in terms of features extraction, the wICA method outperformed the existing ICA method. In the delta, theta, and alpha bands, we obtained a mean classification accuracy of 84.66% using the ICA method, whereas the mean accuracy using the wICA methodwas 96.9%. However, no significant improvement was observed in the beta band. In addition, we compared the topographical map to show the changes in power spectral density across the brain regions for the two vigilance states. The proposed method showed that the frontal and central regions were most sensitive to vigilance decrement. However, in this application, the proposed wICA shows a marginal improvement compared to the Fast-ICA.

An Effective Self-Configurable Ransomware Prevention Technique for IoMT.

Remote healthcare systems and applications are being enabled via the Internet of Medical Things (IoMT), which is an automated system that facilitates the critical and emergency healthcare services in urban areas, in addition to, bridges the isolated rural communities for various healthcare services. Researchers and developers are, to date, considering the majority of the technological aspects and critical issues around the IoMT, e.g., security vulnerabilities and other cybercrimes. One of such major challenges IoMT has to face is widespread ransomware attacks; a malicious malware that encrypts the patients' critical data, restricts access to IoMT devices or entirely disable IoMT devices, or uses several combinations to compromise the overall system functionality, mainly for ransom. These ransomware attacks would have several devastating consequences, such as loss of life-threatening data and system functionality, ceasing emergency and life-saving services, wastage of several vital resources etc. This paper presents a ransomware analysis and identification architecture with the objective to detect and validate the ransomware attacks and to evaluate its accuracy using a comprehensive verification process. We first develop a comprehensive experimental environment, to simulate a real-time IoMT network, for experimenting various types of ransomware attacks. Following, we construct a comprehensive set of ransomware attacks and analyze their effects over an IoMT network devices. Furthermore, we develop an effective detection filter for detecting various ransomware attacks (e.g., static and dynamic attacks) and evaluate the degree of damages caused to the IoMT network devices. In addition, we develop a defense system to block the ransomware attacks and notify the backend control system. To evaluate the effectiveness of the proposed framework, we experimented our architecture with 194 various samples of malware and 46 variants, with a duration of sixty minutes for each sample, and thoroughly examined the network traffic data for malicious behaviors. The evaluation results show more than 95% of accuracy of detecting various ransomware attacks.

A Long Short-Term Memory Biomarker-Based Prediction Framework for Alzheimer's Disease.

The early prediction of Alzheimer's disease (AD) can be vital for the endurance of patients and establishes as an accommodating and facilitative factor for specialists. The proposed work presents a robotized predictive structure, dependent on machine learning (ML) methods for the forecast of AD. Neuropsychological measures (NM) and magnetic resonance imaging (MRI) biomarkers are deduced and passed on to a recurrent neural network (RNN). In the RNN, we have used long short-term memory (LSTM), and the proposed model will predict the biomarkers (feature vectors) of patients after 6, 12, 21 18, 24, and 36 months. These predicted biomarkers will go through fully connected neural network layers. The NN layers will then predict whether these RNN-predicted biomarkers belong to an AD patient or a patient with a mild cognitive impairment (MCI). The developed methodology has been tried on an openly available informational dataset (ADNI) and accomplished an accuracy of 88.24%, which is superior to the next-best available algorithms.

An Efficient Deep Learning Approach to Automatic Glaucoma Detection Using Optic Disc and Optic Cup Localization.

Glaucoma is an eye disease initiated due to excessive intraocular pressure inside it and caused complete sightlessness at its progressed stage. Whereas timely glaucoma screening-based treatment can save the patient from complete vision loss. Accurate screening procedures are dependent on the availability of human experts who performs the manual analysis of retinal samples to identify the glaucomatous-affected regions. However, due to complex glaucoma screening procedures and shortage of human resources, we often face delays which can increase the vision loss ratio around the globe. To cope with the challenges of manual systems, there is an urgent demand for designing an effective automated framework that can accurately identify the Optic Disc (OD) and Optic Cup (OC) lesions at the earliest stage. Efficient and effective identification and classification of glaucomatous regions is a complicated job due to the wide variations in the mass, shade, orientation, and shapes of lesions. Furthermore, the extensive similarity between the lesion and eye color further complicates the classification process. To overcome the aforementioned challenges, we have presented a Deep Learning (DL)-based approach namely EfficientDet-D0 with EfficientNet-B0 as the backbone. The presented framework comprises three steps for glaucoma localization and classification. Initially, the deep features from the suspected samples are computed with the EfficientNet-B0 feature extractor. Then, the Bi-directional Feature Pyramid Network (BiFPN) module of EfficientDet-D0 takes the computed features from the EfficientNet-B0 and performs the top-down and bottom-up keypoints fusion several times. In the last step, the resultant localized area containing glaucoma lesion with associated class is predicted. We have confirmed the robustness of our work by evaluating it on a challenging dataset namely an online retinal fundus image database for glaucoma analysis (ORIGA). Furthermore, we have performed cross-dataset validation on the High-Resolution Fundus (HRF), and Retinal Image database for Optic Nerve Evaluation (RIM ONE DL) datasets to show the generalization ability of our work. Both the numeric and visual evaluations confirm that EfficientDet-D0 outperforms the newest frameworks and is more proficient in glaucoma classification.

Multiclass Skin Lesion Classification Using Hybrid Deep Features Selection and Extreme Learning Machine.

The variation in skin textures and injuries, as well as the detection and classification of skin cancer, is a difficult task. Manually detecting skin lesions from dermoscopy images is a difficult and time-consuming process. Recent advancements in the domains of the internet of things (IoT) and artificial intelligence for medical applications demonstrated improvements in both accuracy and computational time. In this paper, a new method for multiclass skin lesion classification using best deep learning feature fusion and an extreme learning machine is proposed. The proposed method includes five primary steps: image acquisition and contrast enhancement; deep learning feature extraction using transfer learning; best feature selection using hybrid whale optimization and entropy-mutual information (EMI) approach; fusion of selected features using a modified canonical correlation based approach; and, finally, extreme learning machine based classification. The feature selection step improves the system's computational efficiency and accuracy. The experiment is carried out on two publicly available datasets, HAM10000 and ISIC2018. The achieved accuracy on both datasets is 93.40 and 94.36 percent. When compared to state-of-the-art (SOTA) techniques, the proposed method's accuracy is improved. Furthermore, the proposed method is computationally efficient.

Tracking of a Fixed-Shape Moving Object Based on the Gradient Descent Method.

Tracking moving objects is one of the most promising yet the most challenging research areas pertaining to computer vision, pattern recognition and image processing. The challenges associated with object tracking range from problems pertaining to camera axis orientations to object occlusion. In addition, variations in remote scene environments add to the difficulties related to object tracking. All the mentioned challenges and problems pertaining to object tracking make the procedure computationally complex and time-consuming. In this paper, a stochastic gradient-based optimization technique has been used in conjunction with particle filters for object tracking. First, the object that needs to be tracked is detected using the Maximum Average Correlation Height (MACH) filter. The object of interest is detected based on the presence of a correlation peak and average similarity measure. The results of object detection are fed to the tracking routine. The gradient descent technique is employed for object tracking and is used to optimize the particle filters. The gradient descent technique allows particles to converge quickly, allowing less time for the object to be tracked. The results of the proposed algorithm are compared with similar state-of-the-art tracking algorithms on five datasets that include both artificial moving objects and humans to show that the gradient-based tracking algorithm provides better results, both in terms of accuracy and speed.

Breast Cancer Classification from Ultrasound Images Using Probability-Based Optimal Deep Learning Feature Fusion.

After lung cancer, breast cancer is the second leading cause of death in women. If breast cancer is detected early, mortality rates in women can be reduced. Because manual breast cancer diagnosis takes a long time, an automated system is required for early cancer detection. This paper proposes a new framework for breast cancer classification from ultrasound images that employs deep learning and the fusion of the best selected features. The proposed framework is divided into five major steps: (i) data augmentation is performed to increase the size of the original dataset for better learning of Convolutional Neural Network (CNN) models; (ii) a pre-trained DarkNet-53 model is considered and the output layer is modified based on the augmented dataset classes; (iii) the modified model is trained using transfer learning and features are extracted from the global average pooling layer; (iv) the best features are selected using two improved optimization algorithms known as reformed differential evaluation (RDE) and reformed gray wolf (RGW); and (v) the best selected features are fused using a new probability-based serial approach and classified using machine learning algorithms. The experiment was conducted on an augmented Breast Ultrasound Images (BUSI) dataset, and the best accuracy was 99.1%. When compared with recent techniques, the proposed framework outperforms them.

Gastroenterology Fellowship Applicants' Perspectives on GI Program Preferences.

Gastroenterology fellowship continues to be highly competitive among internal medicine subspecialties. Recruiting excellent applicants is also important for GI fellowship program directors. We aim to examine factors that influence GI fellowship applicants' perspectives about a fellowship program. The authors conducted an anonymous online survey of applicants focusing on program characteristics including location, faculty, research/clinical opportunities, website, and interview day experience. Anonymous survey responses were recorded regarding program characteristics, and subsequent candidate preferences were evaluated for factors influencing their decision. Candidates were also asked to evaluate their interview experience and share other comments about the program. Though GI fellowship applicants have varying preferences regarding the ideal training program, some opinions converged. The study of these trends can inform program directors regarding areas for improvement that in turn can help attract the best applicants.

COVID-19 Case Recognition from Chest CT Images by Deep Learning, Entropy-Controlled Firefly Optimization, and Parallel Feature Fusion.

In healthcare, a multitude of data is collected from medical sensors and devices, such as X-ray machines, magnetic resonance imaging, computed tomography (CT), and so on, that can be analyzed by artificial intelligence methods for early diagnosis of diseases. Recently, the outbreak of the COVID-19 disease caused many deaths. Computer vision researchers support medical doctors by employing deep learning techniques on medical images to diagnose COVID-19 patients. Various methods were proposed for COVID-19 case classification. A new automated technique is proposed using parallel fusion and optimization of deep learning models. The proposed technique starts with a contrast enhancement using a combination of top-hat and Wiener filters. Two pre-trained deep learning models (AlexNet and VGG16) are employed and fine-tuned according to target classes (COVID-19 and healthy). Features are extracted and fused using a parallel fusion approach-parallel positive correlation. Optimal features are selected using the entropy-controlled firefly optimization method. The selected features are classified using machine learning classifiers such as multiclass support vector machine (MC-SVM). Experiments were carried out using the Radiopaedia database and achieved an accuracy of 98%. Moreover, a detailed analysis is conducted and shows the improved performance of the proposed scheme.

Human Action Recognition: A Paradigm of Best Deep Learning Features Selection and Serial Based Extended Fusion.

Human action recognition (HAR) has gained significant attention recently as it can be adopted for a smart surveillance system in Multimedia. However, HAR is a challenging task because of the variety of human actions in daily life. Various solutions based on computer vision (CV) have been proposed in the literature which did not prove to be successful due to large video sequences which need to be processed in surveillance systems. The problem exacerbates in the presence of multi-view cameras. Recently, the development of deep learning (DL)-based systems has shown significant success for HAR even for multi-view camera systems. In this research work, a DL-based design is proposed for HAR. The proposed design consists of multiple steps including feature mapping, feature fusion and feature selection. For the initial feature mapping step, two pre-trained models are considered, such as DenseNet201 and InceptionV3. Later, the extracted deep features are fused using the Serial based Extended (SbE) approach. Later on, the best features are selected using Kurtosis-controlled Weighted KNN. The selected features are classified using several supervised learning algorithms. To show the efficacy of the proposed design, we used several datasets, such as KTH, IXMAS, WVU, and Hollywood. Experimental results showed that the proposed design achieved accuracies of 99.3%, 97.4%, 99.8%, and 99.9%, respectively, on these datasets. Furthermore, the feature selection step performed better in terms of computational time compared with the state-of-the-art.

A Review on Mental Stress Assessment Methods Using EEG Signals.

Mental stress is one of the serious factors that lead to many health problems. Scientists and physicians have developed various tools to assess the level of mental stress in its early stages. Several neuroimaging tools have been proposed in the literature to assess mental stress in the workplace. Electroencephalogram (EEG) signal is one important candidate because it contains rich information about mental states and condition. In this paper, we review the existing EEG signal analysis methods on the assessment of mental stress. The review highlights the critical differences between the research findings and argues that variations of the data analysis methods contribute to several contradictory results. The variations in results could be due to various factors including lack of standardized protocol, the brain region of interest, stressor type, experiment duration, proper EEG processing, feature extraction mechanism, and type of classifier. Therefore, the significant part related to mental stress recognition is choosing the most appropriate features. In particular, a complex and diverse range of EEG features, including time-varying, functional, and dynamic brain connections, requires integration of various methods to understand their associations with mental stress. Accordingly, the review suggests fusing the cortical activations with the connectivity network measures and deep learning approaches to improve the accuracy of mental stress level assessment.

Human Gait Recognition: A Single Stream Optimal Deep Learning Features Fusion.

Human Gait Recognition (HGR) is a biometric technique that has been utilized for security purposes for the last decade. The performance of gait recognition can be influenced by various factors such as wearing clothes, carrying a bag, and the walking surfaces. Furthermore, identification from differing views is a significant difficulty in HGR. Many techniques have been introduced in the literature for HGR using conventional and deep learning techniques. However, the traditional methods are not suitable for large datasets. Therefore, a new framework is proposed for human gait recognition using deep learning and best feature selection. The proposed framework includes data augmentation, feature extraction, feature selection, feature fusion, and classification. In the augmentation step, three flip operations were used. In the feature extraction step, two pre-trained models were employed, Inception-ResNet-V2 and NASNet Mobile. Both models were fine-tuned and trained using transfer learning on the CASIA B gait dataset. The features of the selected deep models were optimized using a modified three-step whale optimization algorithm and the best features were chosen. The selected best features were fused using the modified mean absolute deviation extended serial fusion (MDeSF) approach. Then, the final classification was performed using several classification algorithms. The experimental process was conducted on the entire CASIA B dataset and achieved an average accuracy of 89.0. Comparison with existing techniques showed an improvement in accuracy, recall rate, and computational time.

Deep Learning-Based COVID-19 Detection Using CT and X-Ray Images: Current Analytics and Comparisons.

Currently, the world faces a novel coronavirus disease 2019 (COVID-19) challenge and infected cases are increasing exponentially. COVID-19 is a disease that has been reported by the WHO in March 2020, caused by a virus called the SARS-CoV-2. As of 10 March 2021, more than 150 million people were infected and 3v million died. Researchers strive to find out about the virus and recommend effective actions. An unprecedented increase in pathogens is happening and a major attempt is being made to tackle the epidemic. This article presents deep learning-based COVID-19 detection using CT and X-ray images and data analytics on its spread worldwide. This article's research structure builds on a recent analysis of the COVID-19 data and prospective research to systematize current resources, help the researchers, practitioners by using in-depth learning methodologies to build solutions for the COVID-19 pandemic.

Real-Time Diagnosis System of COVID-19 Using X-Ray Images and Deep Learning.

The novel coronavirus named COVID-19 has quickly spread among humans worldwide, and the situation remains hazardous to the health system. The existence of this virus in the human body is identified through sputum or blood samples. Furthermore, computed tomography (CT) or X-ray has become a significant tool for quick diagnoses. Thus, it is essential to develop an online and real-time computer-aided diagnosis (CAD) approach to support physicians and avoid further spreading of the disease. In this research, a convolutional neural network (CNN) -based Residual neural network (ResNet50) has been employed to detect COVID-19 through chest X-ray images and achieved 98% accuracy. The proposed CAD system will receive the X-ray images from the remote hospitals/healthcare centers and perform diagnostic processes. Furthermore, the proposed CAD system uses advanced load balancer and resilience features to achieve fault tolerance with zero delays and perceives more infected cases during this pandemic.

Heavy metal accumulation imparts structural differences in fragrant Rosa species irrigated with marginal quality water.

Wastewater is an alternative to traditional sources of renewable irrigation water in agriculture, particularly in water-scarce regions. However, the possible risks due to heavy metals accumulation in plant tissues are often overlooked by producers. The present study aimed to identify heavy metals-induced structural modifications to roots of scented Rosa species that were irrigated with water of marginal quality. The chemical and mineral contents from the experimental irrigation canal water (control) and treated wastewater were below the limits recommended by the Pakistan Environmental Protection Agency (Pak-EPA) for medicinal plants. The experimentally untreated wastewater contained electrical conductivity (EC), chemical oxygen demand (COD), biological oxygen demand (BOD), and heavy metals (Co, Cu, Cd, Pb) that were above the recommended limits. The responses by wastewater-treated Rosa species (Rosa damascena, R. bourboniana, R. Gruss-an-Teplitz, and R. centifolia) were evaluated. The experimental data revealed that treated wastewater significantly increased the thickness of collenchyma (cortex and pith) and parenchyma tissues (vascular bundle, xylem, and phloem) of R. Gruss-an-Teplitz. Root dermal tissues (epidermis) of R. bourboniana also responded to treated wastewater. R. damascena and R. centifolia were the least affected species, under the experimental irrigation conditions. Collenchyma and dermal tissues were thicker in R. damascena and R. Gruss-an-Teplitz under untreated wastewater conditions. In parenchyma tissues, vascular bundles were thicker in R. damascena in untreated wastewater conditions, while the xylem and phloem of R. Gruss-an-Teplitz were thicker where treated wastewater was applied. In tissues other than the vascular bundle, the differences in anatomical metrics due to the experimental irrigation treatments were greater during the second year of the experiment than in the first year. The contents of metals other than chromium in the roots and stems of roses were below the WHO limits, under all of the experimental irrigation conditions. Rosa centifolia contained higher heavy metals content than the other experimental species, and heavy metals content was associated with anatomical changes due to the treatments. We conclude that, under conditions of wastewater irrigation, R. Gruss-an-Teplitz was highly resistant; R. damascena was moderately resistant while R. bourboniana and R. centifolia were the most susceptible to irrigation with marginal quality water. This is the first report of plant tissue responses to wastewater irrigation by the experimental species. Regarding the accumulation of heavy metals in rose plant tissues, the results confirm that untreated wastewater must be treated to grow Rosa species where water is scarce.

The Facilitator's Role in London's Air Ambulance's simulation "moulage" training.

OBJECTIVE: This research focused on the facilitator's role in the simulated patient training "moulages" used by London's Air Ambulance (LAA) for their team training. Facilitators are chosen based on their experience and expertise in the field. The aim of this research was to gain insight into the role of moulage facilitator. METHODS: An ethnographic approach was employed, using the notion of "progressive focusing." Overt observational fieldwork was performed, with the resulting field notes evaluated by content analysis. Semistructured interviews were then conducted with 8 facilitators selected by convenience sampling in order to gain an understanding of the role according to their perspective. RESULTS: The research revealed the role of the facilitator to be challenging and multifaceted. The moulage process appeared appropriate to its function, and the facilitation methods were largely in accordance with recommended practice outlined in educational literature. CONCLUSIONS: The London's Air Ambulance moulage facilitators have to prepare trainees for an intense and emotionally demanding job. Their methods are derived from experience, often with a subconscious application of sound educational practice. This research may help the team identify certain areas with scope for further refinement including feedback methods, fidelity, and reducing the burden of multitasking.

Combatting ransomware in ZephyrOS-activated industrial IoT environments.

The rapid growth of the Industrial Internet of Things (IIoT) has opened up new avenues for cyber threats, with ransomware being a primary area of concern. In response to this, proposed study introduces an innovative approach that combines the strength of the Gradient Boosting Machine (GBM) and the precision of Lasso Regression to effectively identify ransomware threats in IIoT settings. Functioning on the Zephyr operating system, the GBM's ability to handle large-scale datasets and traverse complex data dimensions is complemented by Lasso Regression's skill in curbing overfitting and extracting critical features. This combined ML technique is specifically designed to address the diverse data challenges of IIoT, providing a solid line of defense. Comprehensive tests on updated ransomware tools and the established RanSAP & IoT-23 datasets validated our model's capabilities, achieving an impressive 92 percent detection rate while keeping false positives to a minimum. When compared to existing strategies, projected solution showcased superior performance, highlighting its pivotal role in bolstering IIoT security against ransomware attacks. These results shed light on the next steps for ensuring a safer IIoT landscape, emphasizing the need for advanced, flexible cybersecurity measures in our ever-evolving industrial ecosystem.

Experimental, Computational, and Machine Learning Methods for Prediction of Residual Stresses in Laser Additive Manufacturing: A Critical Review.

In recent decades, laser additive manufacturing has seen rapid development and has been applied to various fields, including the aerospace, automotive, and biomedical industries. However, the residual stresses that form during the manufacturing process can lead to defects in the printed parts, such as distortion and cracking. Therefore, accurately predicting residual stresses is crucial for preventing part failure and ensuring product quality. This critical review covers the fundamental aspects and formation mechanisms of residual stresses. It also extensively discusses the prediction of residual stresses utilizing experimental, computational, and machine learning methods. Finally, the review addresses the challenges and future directions in predicting residual stresses in laser additive manufacturing.

Effect of Pre-Heating on Residual Stresses and Deformation in Laser-Based Directed Energy Deposition Repair: A Comparative Analysis.

Laser-directed energy deposition (DED), a metal additive manufacturing method, is renowned for its role in repairing parts, particularly when replacement costs are prohibitive. Ensuring that repaired parts avoid residual stresses and deformation is crucial for maintaining functional integrity. This study conducts experimental and numerical analyses on trapezoidal shape repairs, validating both the thermal and mechanical models with experimental results. Additionally, the study presents a methodology for creating a toolpath applicable to both the DED process and Abaqus CAE software. The findings indicate that employing a pre-heating strategy can reduce residual stresses by over 70% compared to no pre-heating. However, pre-heating may not substantially reduce final distortion. Notably, final distortion can be significantly mitigated by pre-heating and subsequently cooling to higher temperatures, thereby reducing the cooling rate. These insights contribute to optimizing DED repair processes for enhanced part functionality and longevity.