Bayesian-Edge system for classification and segmentation of skin lesions in Internet of Medical Things.

BACKGROUND: Skin diseases are severe diseases. Identification of these severe diseases depends upon the abstraction of atypical skin regions. The segmentation of these skin diseases is essential to rheumatologists in risk impost and for valuable and vital decision-making. Skin lesion segmentation from images is a crucial step toward achieving this goal-timely exposure of malignancy in psoriasis expressively intensifies the persistence ratio. Defies occur when people presume skin diseases they have without accurately and precisely incepted. However, analyzing malignancy at runtime is a big challenge due to the truncated distinction of the visual similarity between malignance and non-malignance lesions. However, images' different shapes, contrast, and vibrations make skin lesion segmentation challenging. Recently, various researchers have explored the applicability of deep learning models to skin lesion segmentation. MATERIALS AND METHODS: This paper introduces a skin lesions segmentation model that integrates two intelligent methodologies: Bayesian inference and edge intelligence. In the segmentation model, we deal with edge intelligence to utilize the texture features for the segmentation of skin lesions. In contrast, Bayesian inference enhances skin lesion segmentation's accuracy and efficiency. RESULTS: We analyze our work along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules), and evaluation aspects (data annotation requirements and segmentation performance). We discuss these dimensions from seminal works and a systematic viewpoint and examine how these dimensions have influenced current trends. CONCLUSION: We summarize our work with previously used techniques in a comprehensive table to facilitate comparisons. Our experimental results show that Bayesian-Edge networks can boost the diagnostic performance of skin lesions by up to 87.80% without incurring additional parameters of heavy computation.

Formation mechanisms and degradation methods of polycyclic aromatic hydrocarbons in biochar: A review.

Biochar has been widely used in soil amendment and environmental remediation. Polycyclic aromatic hydrocarbons (PAHs) could be produced in preparation of biochar, which may pose potential risks to the environment and human health. At present, most studies focus on the ecotoxicity potential of biochar, while there are few systematic reviews on the formation mechanisms and mitigation strategies of PAHs in biochar. Therefore, a systematical understanding of the distribution, formation mechanisms, risk assessment, and degradation approaches of PAHs in biochar is highly needed. In this paper, the distribution and content of the total and bioavailable PAHs in biochar are reviewed. Then the formation mechanisms, influencing factors, and potential risk assessment of PAHs in biochar are systematically explored. After that, the effective strategies to alleviate PAHs in biochar are summarized. Finally, suggestions and perspectives for future studies are proposed. This review provides a guide for reducing the formation of biochar-associated PAHs and their toxicity, which is beneficial for the development and large-scale safe use of environmentally friendly biochar.

Multilayer cyberattacks identification and classification using machine learning in internet of blockchain (IoBC)-based energy networks.

The world's need for energy is rising due to factors like population growth, economic expansion, and technological breakthroughs. However, there are major consequences when gas and coal are burnt to meet this surge in energy needs. Although these fossil fuels are still essential for meeting energy demands, their combustion releases a large amount of carbon dioxide and other pollutants into the atmosphere. This significantly jeopardizes community health in addition to exacerbating climate change, thus it is essential need to move swiftly to incorporate renewable energy sources by employing advanced information and communication technologies. However, this change brings up several security issues emphasizing the need for innovative cyber threats detection and prevention solutions. Consequently, this study presents bigdata sets obtained from the solar and wind powered distributed energy systems through the blockchain-based energy networks in the smart grid (SG). A hybrid machine learning (HML) model that combines both the Deep Learning (DL) and Long-Short-Term-Memory (LSTM) models characteristics is developed and applied to identify the unique patterns of Denial of Service (DoS) and Distributed Denial of Service (DDoS) cyberattacks in the power generation, transmission, and distribution processes. The presented big datasets are essential and significantly helps in identifying and classifying cyberattacks, leading to predicting the accurate energy systems behavior in the SG.

An integrated in-silico approach for drug target identification in human pathogen Shigella dysenteriae.

Shigella dysenteriae, is a Gram-negative bacterium that emerged as the second most significant cause of bacillary dysentery. Antibiotic treatment is vital in lowering Shigella infection rates, yet the growing global resistance to broad-spectrum antibiotics poses a significant challenge. The persistent multidrug resistance of S. dysenteriae complicates its management and control. Hence, there is an urgent requirement to discover novel therapeutic targets and potent medications to prevent and treat this disease. Therefore, the integration of bioinformatics methods such as subtractive and comparative analysis provides a pathway to compute the pan-genome of S. dysenteriae. In our study, we analysed a dataset comprising 27 whole genomes. The S. dysenteriae strain SD197 was used as the reference for determining the core genome. Initially, our focus was directed towards the identification of the proteome of the core genome. Moreover, several filters were applied to the core genome, including assessments for non-host homology, protein essentiality, and virulence, in order to prioritize potential drug targets. Among these targets were Integration host factor subunit alpha and Tyrosine recombinase XerC. Furthermore, four drug-like compounds showing potential inhibitory effects against both target proteins were identified. Subsequently, molecular docking analysis was conducted involving these targets and the compounds. This initial study provides the list of novel targets against S. dysenteriae. Conclusively, future in vitro investigations could validate our in-silico findings and uncover potential therapeutic drugs for combating bacillary dysentery infection.

Dual-3DM3AD: Mixed Transformer Based Semantic Segmentation and Triplet Pre-Processing for Early Multi-Class Alzheimer's Diagnosis.

Alzheimer's Disease (AD) is a widespread, chronic, irreversible, and degenerative condition, and its early detection during the prodromal stage is of utmost importance. Typically, AD studies rely on single data modalities, such as MRI or PET, for making predictions. Nevertheless, combining metabolic and structural data can offer a comprehensive perspective on AD staging analysis. To address this goal, this paper introduces an innovative multi-modal fusion-based approach named as Dual-3DM3-AD. This model is proposed for an accurate and early Alzheimer's diagnosis by considering both MRI and PET image scans. Initially, we pre-process both images in terms of noise reduction, skull stripping and 3D image conversion using Quaternion Non-local Means Denoising Algorithm (QNLM), Morphology function and Block Divider Model (BDM), respectively, which enhances the image quality. Furthermore, we have adapted Mixed-transformer with Furthered U-Net for performing semantic segmentation and minimizing complexity. Dual-3DM3-AD model is consisted of multi-scale feature extraction module for extracting appropriate features from both segmented images. The extracted features are then aggregated using Densely Connected Feature Aggregator Module (DCFAM) to utilize both features. Finally, a multi-head attention mechanism is adapted for feature dimensionality reduction, and then the softmax layer is applied for multi-class Alzheimer's diagnosis. The proposed Dual-3DM3-AD model is compared with several baseline approaches with the help of several performance metrics. The final results unveil that the proposed work achieves 98% of accuracy, 97.8% of sensitivity, 97.5% of specificity, 98.2% of f-measure, and better ROC curves, which outperforms other existing models in multi-class Alzheimer's diagnosis.

Depression detection with machine learning of structural and non-structural dual languages.

Depression is a serious mental state that negatively impacts thoughts, feelings, and actions. Social media use is rapidly growing, with people expressing themselves in their regional languages. In Pakistan and India, many people use Roman Urdu on social media. This makes Roman Urdu important for predicting depression in these regions. However, previous studies show no significant contribution in predicting depression through Roman Urdu or in combination with structured languages like English. The study aims to create a Roman Urdu dataset to predict depression risk in dual languages [Roman Urdu (non-structural language) + English (structural language)]. Two datasets were used: Roman Urdu data manually converted from English on Facebook, and English comments from Kaggle. These datasets were merged for the research experiments. Machine learning models, including Support Vector Machine (SVM), Support Vector Machine Radial Basis Function (SVM-RBF), Random Forest (RF), and Bidirectional Encoder Representations from Transformers (BERT), were tested. Depression risk was classified into not depressed, moderate, and severe. Experimental studies show that the SVM achieved the best result with anaccuracy of 0.84% compared to existing models. The presented study refines thearea of depression to predict the depression in Asian countries.

Cyberattack patterns in blockchain-based communication networks for distributed renewable energy systems: A study on big datasets.

Blockchain-based reliable, resilient, and secure communication for Distributed Energy Resources (DERs) is essential in Smart Grid (SG). The Solana blockchain, due to its high stability, scalability, and throughput, along with low latency, is envisioned to enhance the reliability, resilience, and security of DERs in SGs. This paper presents big datasets focusing on SQL Injection, Spoofing, and Man-in-the-Middle (MitM) cyberattacks, which have been collected from Solana blockchain-based Industrial Wireless Sensor Networks (IWSNs) for events monitoring and control in DERs. The datasets provided include both raw (unprocessed) and refined (processed) data, which highlight distinct trends in cyberattacks in DERs. These distinctive patterns demonstrate problems like superfluous mass data generation, transmitting invalid packets, sending deceptive data packets, heavily using network bandwidth, rerouting, causing memory overflow, overheads, and creating high latency. These issues result in ineffective real-time events monitoring and control of DERs in SGs. The thorough nature of these datasets is expected to play a crucial role in identifying and mitigating a wide range of cyberattacks across different smart grid applications.

Super capacity of ligand-engineered biochar for sorption of malachite green dye: key role of functional moieties and mesoporous structure.

This study synthesized a new thiomalic acid-modified rice husk biochar (TMA-BC) as a versatile and eco-friendly sorbent. After undergoing chemical treatments, the mercerized rice husk biochar (NaOH-BC) and TMA-BC samples showed higher BET surface area values of 277.1 m2/g and 305.8 m2/g, respectively, compared to the pristine biochar (BC) sample, which had a surface area of 234.2 m2/g. In batch adsorption experiments, it was found that the highest removal efficiency for malachite green (MG) was achieved with TMA-BC, reaching 96.4%, while NaOH-BC and BC exhibited removal efficiencies of 38.6% and 27.9%, respectively, at pH 8. The engineered TMA-BC exhibited a super adsorption capacity of 104.17 mg/g for MG dye at pH 8.0 and 25 °C with a dosage of 2 g/L. The SEM, TEM, XPS, and FTIR spectroscopy analyses were performed to examine mesoporous features and successful TMA-BC carboxylic and thiol functional groups grafting on biochar. Electrostatic forces, such as π - π interactions, hydrogen bonding, and pore intrusion, were identified as key factors in the sorption of MG dye. As compared to single-solution adsorption experiments, the binary solution experiments performed at optimized dosages of undesired ions, such as humic acid, sodium dodecyl sulfate surfactant, NaCl, and NaSCN, reflected an increase in MG dye removal of 2.8%, 8.7%, 5.4%, and 12.7%, respectively, which was attributed to unique mesoporous features and grafted functional groups of TMA-BC. Furthermore, the TMA-BC showed promising reusability up to three cycles. Our study indicates that mediocre biochar modified with TMA can provide an eco-friendly and cost-effective alternative to commercially accessible adsorbents.

Designing a multi-epitope vaccine against Shigella dysenteriae using immuno-informatics approach.

Shigella dysenteriae has been recognized as the second most prevalent pathogen associated with diarrhea that contains blood, contributing to 12.9% of reported cases, and it is additionally responsible for approximately 200,000 deaths each year. Currently, there is no S. dysenteriae licensed vaccine. Multidrug resistance in all Shigella spp. is a growing concern. Current vaccines, such as O-polysaccharide (OPS) conjugates, are in clinical trials but are ineffective in children but protective in adults. Thus, innovative treatments and vaccines are needed to combat antibiotic resistance. In this study, we used immuno-informatics to design a new multiepitope vaccine and identified S. dysenteriae strain SD197's membrane protein targets using in-silico methods. The target protein was prioritized using membrane protein topology analysis to find membrane proteins. B and T-cell epitopes were predicted for vaccine formulation. The epitopes were shortlisted based on an IC50 value <50, antigenicity, allergenicity, and a toxicity analysis. In the final vaccine construct, a total of 8 B-cell epitopes, 12 MHC Class I epitopes, and 7 MHC Class II epitopes were identified for the Lipopolysaccharide export system permease protein LptF. Additionally, 17 MHC Class I epitopes and 14 MHC Class II epitopes were predicted for the Lipoprotein-releasing ABC transporter permease subunit LolE. These epitopes were selected and linked via KK, AAY, and GGGS linkers, respectively. To enhance the immunogenic response, RGD (arginine-glycine-aspartate) adjuvant was incorporated into the final vaccine construct. The refined vaccine structure exhibits a Ramachandran score of 91.5% and demonstrates stable interaction with TLR4. Normal Mode Analysis (NMA) reveals low eigenvalues (3.925996e-07), indicating steady and flexible molecular mobility of docked complexes. Codon optimization was carried out in an effective microbial expression system of the Escherichia coli K12 strain using the recombinant plasmid pET-28a (+). Finally, the entire in-silico analysis suggests that the suggested vaccine may induce a significant immune response against S. dysenteriae, making it a promising option for additional experimental trials.

Core-shell niobium(v) oxide@molecularly imprinted polythiophene nanoreceptors for transformative, real-time creatinine analysis.

Creatinine, a byproduct of muscle metabolism, is typically filtered by the kidneys. Deviations from normal concentrations of creatinine in human saliva serve as a crucial biomarker for renal diseases. Monitoring these levels becomes particularly essential for individuals undergoing dialysis and those with kidney conditions. This study introduces an innovative disposable point-of-care (PoC) sensor device designed for the prompt detection and continuous monitoring of trace amounts of creatinine. The sensor employs a unique design, featuring a creatinine-imprinted polythiophene matrix combined with niobium oxide nanoparticles. These components are coated onto a screen-printed working electrode. Thorough assessments of creatinine concentrations, spanning from 0 to 1000 nM in a redox solution at pH 7.4 and room temperature, are conducted using cyclic voltammetry (CV), differential pulse voltammetry (DPV), and electrochemical impedance spectroscopy (EIS). The devised sensor exhibits a sensitivity of 4.614 µA cm-2 nM-1, an impressive trace level limit of detection at 34 pM, and remarkable selectivity for creatinine compared to other analytes found in human saliva, such as glucose, glutamine, urea, tyrosine, etc. Real saliva samples subjected to the sensor reveal a 100% recovery rate. This sensor, characterized by its high sensitivity, cost-effectiveness, selectivity, and reproducibility, holds significant promise for real-time applications in monitoring creatinine levels in individuals with kidney and muscle-related illnesses.

Autism spectrum disorder detection using facial images: A performance comparison of pretrained convolutional neural networks.

Autism spectrum disorder (ASD) is a complex psychological syndrome characterized by persistent difficulties in social interaction, restricted behaviours, speech, and nonverbal communication. The impacts of this disorder and the severity of symptoms vary from person to person. In most cases, symptoms of ASD appear at the age of 2 to 5 and continue throughout adolescence and into adulthood. While this disorder cannot be cured completely, studies have shown that early detection of this syndrome can assist in maintaining the behavioural and psychological development of children. Experts are currently studying various machine learning methods, particularly convolutional neural networks, to expedite the screening process. Convolutional neural networks are considered promising frameworks for the diagnosis of ASD. This study employs different pre-trained convolutional neural networks such as ResNet34, ResNet50, AlexNet, MobileNetV2, VGG16, and VGG19 to diagnose ASD and compared their performance. Transfer learning was applied to every model included in the study to achieve higher results than the initial models. The proposed ResNet50 model achieved the highest accuracy, 92%, compared to other transfer learning models. The proposed method also outperformed the state-of-the-art models in terms of accuracy and computational cost.

Highly Stretchable Polyurethane Porous Membranes with Adjustable Morphology for Advanced Lithium Metal Batteries.

A highly flexible, tunable morphology membrane with excellent thermal stability and ionic conductivity can endow lithium metal batteries with high power density and reduced dendrite growth. Herein, a porous Polyurethane (PU) membrane with an adjustable morphology was prepared by a simple nonsolvent-induced phase separation technique. The precise control of the final morphology of PU membranes can be achieved through appropriate selection of a nonsolvent, resulting a range of pore structures that vary from finger-like voids to sponge-like pores. The implementation of combinatorial DFT and experimental analysis has revealed that spongy PU porous membranes, especially PU-EtOH, show superior electrolyte wettability (472%), high porosity (75%), good mechanical flexibility, robust thermal dimensional stability (above 170 °C), and elevated ionic conductivity (1.38 mS cm-1) in comparison to the polypropylene (PP) separator. The use of PU-EtOH in Li//Li symmetric cell results in a prolonged lifespan of 800 h, surpasing the longevity of PU or PP cells. Moreover, when subjected to a high rate of 5 C, the LiFePO4/Li half-cell with a PU-EtOH porous membrane displayed better cycling performance (115.4 mAh g-1) compared to the PP separator (104.4 mAh g-1). Finally, the prepared PU porous membrane exhibits significant potential for improving the efficiency and safety of LMBs.

Reverse Vaccinology Approach to Identify Novel and Immunogenic Targets against Streptococcus gordonii.

Streptococcus gordonii is a gram-positive, mutualistic bacterium found in the human body. It is found in the oral cavity, upper respiratory tract, and intestines, and presents a serious clinical problem because it can lead to opportunistic infections in individuals with weakened immune systems. Streptococci are the most prevalent inhabitants of oral microbial communities, and are typical oral commensals found in the human oral cavity. These streptococci, along with many other oral microbes, produce multispecies biofilms that can attach to salivary pellicle components and other oral bacteria via adhesin proteins expressed on the cell surface. Antibiotics are effective against this bacterium, but resistance against antibodies is increasing. Therefore, a more effective treatment is needed. Vaccines offer a promising method for preventing this issue. This study generated a multi-epitope vaccine against Streptococcus gordonii by targeting the completely sequenced proteomes of five strains. The vaccine targets are identified using a pangenome and subtractive proteomic approach. In the present study, 13 complete strains out of 91 strains of S. gordonii are selected. The pangenomics results revealed that out of 2835 pan genes, 1225 are core genes. Out of these 1225 core genes, 643 identified as non-homologous proteins by subtractive proteomics. A total of 20 essential proteins are predicted from non-homologous proteins. Among these 20 essential proteins, only five are identified as surface proteins. The vaccine construct is designed based on selected B- and T-cell epitopes of the antigenic proteins with the help of linkers and adjuvants. The designed vaccine is docked against TLR2. The expression of the protein is determined using in silico gene cloning. Findings concluded that Vaccine I with adjuvant shows higher interactions with TLR2, suggesting that the vaccine has the ability to induce a humoral and cell-mediated response to treat and prevent infection; this makes it promising as a vaccine against infectious diseases caused by S. gordonii. Furthermore, validation of the vaccine construct is required by in vitro and in vivo trials to check its actual potency and safety for use to prevent infectious diseases caused by S. gordonii.

Comparison Of Hemodynamic Effect Caused By Intrathecal Low Dose Administration Of 0.5% Against 0.75% Hyperbaric Bupivacaine In Patients Undergoing Lower Limb Surgery Under Unilateral Spinal Anaesthesia.

BACKGROUND: Spinal anaesthesia has its unique place in modern anaesthetic practice. In past, most of the surgeries, irrespective of the site of surgery, were performed in general anaesthesia but now in the modern anaesthetic field, spinal anaesthesia has markedly replaced general anaesthesia, specifically in obstetrics, lower limbs, and abdominal surgeries. METHODS: A total of 100 patients fit to undergo lower limb surgery between the ages of 20 to 70 years were included in the study. 50 patients were in 0.5% hyperbaric bupivacaine (Group A) while 50 patients were in the 0.75% hyperbaric bupivacaine group (Group B). Patients with a history of allergies to local anaesthetics, ischemic heart disease and contraindications to spinal anaesthesia were excluded. At the end of the injection, the patient was immediately laid down and tilted to 30 degrees lateral on the operative side for unilateral anaesthesia. Mean arterial pressure at baseline, 15, 30, 45 and 60 minutes was recorded by trainee anaesthesia. A baseline was taken of mean arterial pressure measured 15 minutes before induction of spinal anaesthesia in a lying position. RESULTS: The mean baseline arterial pressure of patients in group A was 88.72±1.71 mmHg and in group B was 88.94±1.95 mmHg. Mean arterial pressure MAP at 15, 30, 45 and 60 minutes in both groups was as follows; 86.22±2.55 vs 81.78±1.52 mmHg, 83.72±3.36 vs 75.84±1.34 mmHg, 80.02±3.40 vs 70.90±0.97 mmHg and 77.14±4.24 vs 66.06±1.62 mmHg respectively (p-value <0.05). CONCLUSIONS: This study concluded that the hemodynamic parameters in terms of mean arterial pressure remained more stable by deviating less from the baseline value with the use of a low dose of 0.5% hyperbaric bupivacaine instead of 0.75% hyperbaric bupivacaine in patients undergoing lower limb surgery under unilateral spinal anaesthesia.

Atorvastatin as an Antihypertensive Agent: A Pilot Study.

Objective Hypertension (HTN) is among the most common causes of chronic disease burden, along with dyslipidemia. It is a prominent risk factor for cardiovascular and cerebrovascular morbidity and mortality. More often than not, HTN coexists with dyslipidemia. This study aimed to see the antihypertensive effect of statins (atorvastatin), as certain animal models have shown that statins have a voltage-gated calcium channel-blocking effect. Material and methods This was a randomized controlled trial done at the Ayub Hospital Complex in Abbottabad, Pakistan. After ethical approval, 120 patients with newly diagnosed hypertension belonging to either gender and aged 35 and above were enrolled in the trial. They were randomly divided into two groups, with each group comprising 60 patients. One group was administered amlodipine 5 mg per oral (PO) once a day, while the other group was given 5 mg of amlodipine PO plus 10 mg of atorvastatin PO. The patients were examined on a follow-up visit 14 days later, and blood pressure was recorded as per protocols. Results A total of 120 newly diagnosed patients were studied in this trial. The mean age was 51.07 years, with a standard deviation of ±6.15 years and a range of 41-60 years. There were 64 (53.3%) males and 56 (46.7%) females in the study. The mean systolic blood pressures (SBPs) and diastolic blood pressures (DBPs) in Group 2 (amlodipine 5 mg + atorvastatin 10 mg) were significantly lower than the patients in Group 1 (only amlodipine 5 mg) in the follow-up visit, which was 14 days after starting the medication (p≤0.05). Conclusion The addition of a lipid-lowering drug to an antihypertensive regimen results in a better lowering of blood pressure in hypertensive individuals.

Effect Of Perineural Administration Of Dexmedetomidine With Bupivacaine Versus Bupivacaine Alone In Ultrasound Guided Supraclavicular Block For Upper Extremity Orthopaedic Operations.

BACKGROUND: During procedures on the upper limbs, the brachial plexus block is usually advised. To increase the length of the block, many medicines have been utilized as adjuvants. The purpose of this study was to compare the effects of dexmedetomidine plus bupivacaine against bupivacaine alone on the onset and duration of the sensory and motor block and the duration of analgesia in the supraclavicular block during upper extremity orthopaedic surgery. METHODS: Sixty individuals qualified for orthopaedic operations on the upper extremities, ranging in age from 20 to 60 years, participated in this prospective, randomized investigation. The modified Bromage scale and the pinprick method were used to assess the sensory and motor block. Using a visual analogue pain scale, the postoperative pain was evaluated at 0, 6, 12 and 24 hours after surgery. RESULTS: In patients receiving only bupivacaine, the mean onset time of sensory and motor block was 32.84 minutes and 26.67 minutes respectively; while in those receiving bupivacaine along with dexmedetomidine, it was 23.38 minutes and 14.81 minutes (p<0.005). In the intervention group (bupivacaine and dexmedetomidine), the period between the first request for analgesia and the duration period of sensory and motor block were both longer (p<0.005). The intervention group experienced less postoperative discomfort for 24 hours (p<0.05). CONCLUSIONS: Dexmedetomidine added to bupivacaine perineurally prolonged both numbness and immobility while shortening the time it took for sensory and motor blocks to begin. Moreover, dexmedetomidine considerably decreased postoperative pain when combined with bupivacaine for supraclavicular blocks.