Quality and antioxidant potential of goat's milk paneer prepared from different citrus juices and its whey

The experiments reported in this research paper aimed to evaluate the physico-chemical and sensory characteristics, microbial quality and antioxidant potential of goat's milk paneer during storage (0-12 d, 4 ± 1°C). The juices from five different citrus fruits were used as coagulant (treatments) to make goat's milk paneer. The pH of all paneer samples decreased during storage whereas titratable acidity increased. Ash (%) fat (%) and protein (%) of paneer increased slightly during storage, whereas sensory perception decreased. The juices from all the citrus fruit varieties showed high contents of total phenolics and total flavonoids which ultimately influenced ferric reducing antioxidant power, total antioxidant capacity and radical scavenging activities. As the contents of different juices were also retained in the paneer matrix, so paneer coagulated with citrus juices also showed encouraging results in terms of total phenolic and flavonoid contents, ferric reducing antioxidant power and radical scavenging activities. Amongst all the paneers, the most promising was that coagulated by kinnow juice. In addition, the whey obtained from paneer coagulated by citrus juices also showed appreciable quantities of total phenolic and flavonoid contents, thereby beneficially influencing ferric reducing antioxidant power andradical scavenging activities. It is concluded that citrus juices improve the sensorial quality and antioxidant potential of goat's milk paneer and its whey.

Internet of medical things and blockchain-enabled patient-centric agent through SDN for remote patient monitoring in 5G network

During the COVID-19 pandemic, there has been a significant increase in the use of internet resources for accessing medical care, resulting in the development and advancement of the Internet of Medical Things (IoMT). This technology utilizes a range of medical equipment and testing software to broadcast patient results over the internet, hence enabling the provision of remote healthcare services. Nevertheless, the preservation of privacy and security in the realm of online communication continues to provide a significant and pressing obstacle. Blockchain technology has shown the potential to mitigate security apprehensions across several sectors, such as the healthcare industry. Recent advancements in research have included intelligent agents in patient monitoring systems by integrating blockchain technology. However, the conventional network configuration of the agent and blockchain introduces a level of complexity. In order to address this disparity, we present a proposed architectural framework that combines software defined networking (SDN) with Blockchain technology. This framework is specially tailored for the purpose of facilitating remote patient monitoring systems within the context of a 5G environment. The architectural design contains a patient-centric agent (PCA) inside the SDN control plane for the purpose of managing user data on behalf of the patients. The appropriate handling of patient data is ensured by the PCA via the provision of essential instructions to the forwarding devices. The suggested model is assessed using hyperledger fabric on docker-engine, and its performance is compared to that of current models in fifth generation (5G) networks. The performance of our suggested model surpasses current methodologies, as shown by our extensive study including factors such as throughput, dependability, communication overhead, and packet error rate.

4SQR-Code: A 4-state QR code generation model for increasing data storing capacity in the Digital Twin framework

INTRODUCTION

The usage of Quick Response (QR) Codes has become widely popular in recent years, primarily for immense electronic transactions and industry uses. The structural flexibility of QR Code architecture opens many more possibilities for researchers in the domain of the Industrial Internet of Things (IIoT). However, the limited storage capacity of the traditional QR Codes still fails to stretch the data capacity limits. The researchers of this domain have already introduced different kinds of techniques, including data hiding, multiplexing, data compression, color QR Codes, and so on. However, the research on increasing the data storage capacity of the QR Codes is very limited and still operational.

OBJECTIVES

The main objective of this work is to increase the data storage capacity of QR Codes in the IIoT domain.

METHODS

In the first part, we have introduced a 4-State-Pattern-based encoding technique to generate the proposed 4-State QR (4SQR) Code where actual data are encoded into a 4SQR Code image which increases the data storage capacity more than the traditional 2-State QR Code. The proposed 4SQR Code consists of four types of patterns, including Black Square Box (BSB), White Square Box (WSB), Triangle, and Circle, whereas the traditional 2-State QR Codes consist of BSB and WSB. In the second part, the 4SQR Code decoding module has been introduced using the adaptive YOLO V5 algorithm where the proposed 4SQR Code image is decoded into the actual data.

RESULTS

The proposed model is tested in a Digital Twin (DT) framework using randomly generated 3000 testing samples for the encoding module that converts into 4SQR Code images successfully and similarly for the decoding module that decodes the 4SQR Code images into the actual data.

CONCLUSION

Experimental results show that this proposed technique offers increased data storage capacity two times than traditional 2-State QR Codes.

A Novel Deep Learning-Based Classification Framework for COVID-19 Assisted with Weighted Average Ensemble Modeling

COVID-19 is an infectious disease caused by the deadly virus SARS-CoV-2 that affects the lung of the patient. Different symptoms, including fever, muscle pain and respiratory syndrome, can be identified in COVID-19-affected patients. The disease needs to be diagnosed in a timely manner, otherwise the lung infection can turn into a severe form and the patient's life may be in danger. In this work, an ensemble deep learning-based technique is proposed for COVID-19 detection that can classify the disease with high accuracy, efficiency, and reliability. A weighted average ensemble (WAE) prediction was performed by combining three CNN models, namely Xception, VGG19 and ResNet50V2, where 97.25% and 94.10% accuracy was achieved for binary and multiclass classification, respectively. To accurately detect the disease, different test methods have been proposed and developed, some of which are even being used in real-time situations. RT-PCR is one of the most successful COVID-19 detection methods, and is being used worldwide with high accuracy and sensitivity. However, complexity and time-consuming manual processes are limitations of this method. To make the detection process automated, researchers across the world have started to use deep learning to detect COVID-19 applied on medical imaging. Although most of the existing systems offer high accuracy, different limitations, including high variance, overfitting and generalization errors, can be found that can degrade the system performance. Some of the reasons behind those limitations are a lack of reliable data resources, missing preprocessing techniques, a lack of proper model selection, etc., which eventually create reliability issues. Reliability is an important factor for any healthcare system. Here, transfer learning with better preprocessing techniques applied on two benchmark datasets makes the work more reliable. The weighted average ensemble technique with hyperparameter tuning ensures better accuracy than using a randomly selected single CNN model.

Metal organic framework derived NiO x nanoparticles for application as a hole transport layer in perovskite solar cells

NiO _x as a hole transport layer (HTL) has gained a lot of research interest in perovskite solar cells (PSCs), owing to its high optical transmittance, high power conversion efficiency, wide band-gap and ease of fabrication. In this work, four different nickel based-metal organic frameworks (MOFs) using 1,3,5-benzenetricarboxylic acid (BTC), terephthalic acid (TPA), 2-aminoterephthalic acid (ATPA), and 2,5-dihydroxyterephthalic acid (DHTPA) ligands respectively, have been employed as precursors to synthesize NiO _x NPs. The employment of different ligands was found to result in NiO _x NPs with different structural, optical and morphological properties. The impact of calcination temperatures of the MOFs was also studied and according to field emission scanning electron microscopy (FESEM), all MOF-derived NiO _x NPs exhibited lower particle size at lower calcination temperature. Upon optimization, Ni-TPA MOF derived NiO _x NPs calcined at 600 °C were identified to be the best for hole transport layer application. To explore the photovoltaic performance, these NiO _x NPs have been fabricated as a thin film and its structural, optical and electrical characteristics were analyzed. According to the findings, the band energy gap (E _g) of the fabricated thin film has been found to be 3.25 eV and the carrier concentration, hole mobility and resistivity were also measured to be 6.8 × 10¹⁴ cm^-3; 4.7 × 10¹⁴ Ω cm and 2.0 cm² V^-1 s^-1, respectively. Finally, a numerical simulation was conducted using SCAPS-1D incorporating the optical and electrical parameters from the thin film analysis. FTO/TiO₂/CsPbBr₃/NiO _x /C has been utilized as the device configuration which recorded an efficiency of 13.9% with V _oc of 1.89 V, J _sc of 11.07 mA cm^-2, and FF of 66.6%.

IoT-Based Medical Image Monitoring System Using HL7 in a Hospital Database

In recent years, the healthcare system, along with the technology that surrounds it, has become a sector in much need of development. It has already improved in a wide range of areas thanks to significant and continuous research into the practical implications of biomedical and telemedicine studies. To ensure the continuing technological improvement of hospitals, physicians now also must properly maintain and manage large volumes of patient data. Transferring large amounts of data such as images to IoT servers based on machine-to-machine communication is difficult and time consuming over MQTT and MLLP protocols, and since IoT brokers only handle a limited number of bytes of data, such protocols can only transfer patient information and other text data. It is more difficult to handle the monitoring of ultrasound, MRI, or CT image data via IoT. To address this problem, this study proposes a model in which the system displays images as well as patient data on an IoT dashboard. A Raspberry Pi processes HL7 messages received from medical devices like an ultrasound machine (ULSM) and extracts only the image data for transfer to an FTP server. The Raspberry Pi 3 (RSPI3) forwards the patient information along with a unique encrypted image data link from the FTP server to the IoT server. We have implemented an authentic and NS3-based simulation environment to monitor real-time ultrasound image data on the IoT server and have analyzed the system performance, which has been impressive. This method will enrich the telemedicine facilities both for patients and physicians by assisting with overall monitoring of data.

Deep learning application detecting SARS-CoV-2 key enzymes inhibitors

The fast spread of the COVID-19 over the world pressured scientists to find its cures. Especially, with the disastrous results, it engendered from human life losses to long-term impacts on infected people's health and the huge financial losses. In addition to the massive efforts made by researchers and medicals on finding safe, smart, fast, and efficient methods to accurately make an early diagnosis of the COVID-19. Some researchers focused on finding drugs to treat the disease and its symptoms, others worked on creating effective vaccines, while several concentrated on finding inhibitors for the key enzymes of the virus, to reduce its spreading and reproduction inside the human body. These enzymes' inhibitors are usually found in aliments, plants, fungi, or even in some drugs. Since these inhibitors slow and halt the replication of the virus in the human body, they can help fight it at an early stage saving the patient from death risk. Moreover, if the human body's immune system gets rid of the virus at the early stage it can be spared from the disastrous sequels it may leave inside the patient's body. Our research aims to find aliments and plants that are rich in these inhibitors. In this paper, we developed a deep learning application that is trained with various aliments, plants, and drugs to detect if a component contains SARS-CoV-2 key inhibitor(s) intending to help them find more sources containing these inhibitors. The application is trained to identify various sources rich in thirteen coronavirus-2 key inhibitors. The sources are currently just aliments, plants, and seeds and the identification is done by their names.

Human Fall Detection Using 3D Multi-Stream Convolutional Neural Networks with Fusion

Human falls, especially for elderly people, can cause serious injuries that might lead to permanent disability. Approximately 20-30% of the aged people in the United States who experienced fall accidents suffer from head trauma, injuries, or bruises. Fall detection is becoming an important public healthcare problem. Timely and accurate fall incident detection could enable the instant delivery of medical services to the injured. New advances in vision-based technologies, including deep learning, have shown significant results in action recognition, where some focus on the detection of fall actions. In this paper, we propose an automatic human fall detection system using multi-stream convolutional neural networks with fusion. The system is based on a multi-level image-fusion approach of every 16 frames of an input video to highlight movement differences within this range. This results of four consecutive preprocessed images are fed to a new proposed and efficient lightweight multi-stream CNN model that is based on a four-branch architecture (4S-3DCNN) that classifies whether there is an incident of a human fall. The evaluation included the use of more than 6392 generated sequences from the Le2i fall detection dataset, which is a publicly available fall video dataset. The proposed method, using three-fold cross-validation to validate generalization and susceptibility to overfitting, achieved a 99.03%, 99.00%, 99.68%, and 99.00% accuracy, sensitivity, specificity, and precision, respectively. The experimental results prove that the proposed model outperforms state-of-the-art models, including GoogleNet, SqueezeNet, ResNet18, and DarkNet19, for fall incident detection.

Analysis of IoT-Related Ergonomics-Based Healthcare Issues Using Analytic Hierarchy Process Methodology

The objective of the present work is for assessing ergonomics-based IoT (Internet of Things) related healthcare issues with the use of a popular multi-criteria decision-making technique named the analytic hierarchy process (AHP). Multiple criteria decision making (MCDM) is a technique that combines alternative performance across numerous contradicting, qualitative, and/or quantitative criteria, resulting in a solution requiring a consensus. The AHP is a flexible strategy for organizing and simplifying complex MCDM concerns by disassembling a compound decision problem into an ordered array of relational decision components (evaluation criteria, sub-criteria, and substitutions). A total of twelve IoT-related ergonomics-based healthcare issues have been recognized as Lumbago (lower backache), Cervicalgia (neck ache), shoulder pain; digital eye strain, hearing impairment, carpal tunnel syndrome; distress, exhaustion, depression; obesity, high blood pressure, hyperglycemia. "Distress" has proven itself the most critical IoT-related ergonomics-based healthcare issue, followed by obesity, depression, and exhaustion. These IoT-related ergonomics-based healthcare issues in four categories (excruciating issues, eye-ear-nerve issues, psychosocial issues, and persistent issues) have been compared and ranked. Based on calculated mathematical values, "psychosocial issues" have been ranked in the first position followed by "persistent issues" and "eye-ear-nerve issues". In several industrial systems, the results may be of vital importance for increasing the efficiency of human force, particularly a human-computer interface for prolonged hours.

A Novel QKD Approach to Enhance IIOT Privacy and Computational Knacks

The industry-based internet of things (IIoT) describes how IIoT devices enhance and extend their capabilities for production amenities, security, and efficacy. IIoT establishes an enterprise-to-enterprise setup that means industries have several factories and manufacturing units that are dependent on other sectors for their services and products. In this context, individual industries need to share their information with other external sectors in a shared environment which may not be secure. The capability to examine and inspect such large-scale information and perform analytical protection over the large volumes of personal and organizational information demands authentication and confidentiality so that the total data are not endangered after illegal access by hackers and other unauthorized persons. In parallel, these large volumes of confidential industrial data need to be processed within reasonable time for effective deliverables. Currently, there are many mathematical-based symmetric and asymmetric key cryptographic approaches and identity- and attribute-based public key cryptographic approaches that exist to address the abovementioned concerns and limitations such as computational overheads and taking more time for crucial generation as part of the encipherment and decipherment process for large-scale data privacy and security. In addition, the required key for the encipherment and decipherment process may be generated by a third party which may be compromised and lead to man-in-the-middle attacks, brute force attacks, etc. In parallel, there are some other quantum key distribution approaches available to produce keys for the encipherment and decipherment process without the need for a third party. However, there are still some attacks such as photon number splitting attacks and faked state attacks that may be possible with these existing QKD approaches. The primary motivation of our work is to address and avoid such abovementioned existing problems with better and optimal computational overhead for key generation, encipherment, and the decipherment process compared to the existing conventional models. To overcome the existing problems, we proposed a novel dynamic quantum key distribution (QKD) algorithm for critical public infrastructure, which will secure all cyber-physical systems as part of IIoT. In this paper, we used novel multi-state qubit representation to support enhanced dynamic, chaotic quantum key generation with high efficiency and low computational overhead. Our proposed QKD algorithm can create a chaotic set of qubits that act as a part of session-wise dynamic keys used to encipher the IIoT-based large scales of information for secure communication and distribution of sensitive information.

Federated learning-based AI approaches in smart healthcare: concepts, taxonomies, challenges and open issues

Federated Learning (FL), Artificial Intelligence (AI), and Explainable Artificial Intelligence (XAI) are the most trending and exciting technology in the intelligent healthcare field. Traditionally, the healthcare system works based on centralized agents sharing their raw data. Therefore, huge vulnerabilities and challenges are still existing in this system. However, integrating with AI, the system would be multiple agent collaborators who are capable of communicating with their desired host efficiently. Again, FL is another interesting feature, which works decentralized manner; it maintains the communication based on a model in the preferred system without transferring the raw data. The combination of FL, AI, and XAI techniques can be capable of minimizing several limitations and challenges in the healthcare system. This paper presents a complete analysis of FL using AI for smart healthcare applications. Initially, we discuss contemporary concepts of emerging technologies such as FL, AI, XAI, and the healthcare system. We integrate and classify the FL-AI with healthcare technologies in different domains. Further, we address the existing problems, including security, privacy, stability, and reliability in the healthcare field. In addition, we guide the readers to solving strategies of healthcare using FL and AI. Finally, we address extensive research areas as well as future potential prospects regarding FL-based AI research in the healthcare management system.

Electroencephalogram-Based Motor Imagery Signals Classification Using a Multi-Branch Convolutional Neural Network Model with Attention Blocks

Brain signals can be captured via electroencephalogram (EEG) and be used in various brain–computer interface (BCI) applications. Classifying motor imagery (MI) using EEG signals is one of the important applications that can help a stroke patient to rehabilitate or perform certain tasks. Dealing with EEG-MI signals is challenging because the signals are weak, may contain artefacts, are dependent on the patient’s mood and posture, and have low signal-to-noise ratio. This paper proposes a multi-branch convolutional neural network model called the Multi-Branch EEGNet with Convolutional Block Attention Module (MBEEGCBAM) using attention mechanism and fusion techniques to classify EEG-MI signals. The attention mechanism is applied both channel-wise and spatial-wise. The proposed model is a lightweight model that has fewer parameters and higher accuracy compared to other state-of-the-art models. The accuracy of the proposed model is 82.85% and 95.45% using the BCI-IV2a motor imagery dataset and the high gamma dataset, respectively. Additionally, when using the fusion approach (FMBEEGCBAM), it achieves 83.68% and 95.74% accuracy, respectively.

Antioxidant and cytotoxic activities of different solvent fractions from Murraya koenigii shoots: HPLC quantification And molecular docking of identified phenolics with anti-apoptotic proteins

ABSTRACT. Murraya koenigii is known for its health benefits against constipation, diarrhea, bacterial infections, wounds and skin related diseases. Aim of this project is to determine cytotoxic aptitude of antioxidant compounds present in M. koenigii. The fractionation of M. koenigii shoots methanol extract was carried out with different solvents followed by determination of total phenolic content, radical scavenging potential along with phenolic profile. M. koenigii shoot fractions were analyzed for their cytotoxic potential by MTT assay besides evaluating molecular interactions between identified phenolics with Bcl-2, Bcl-xl and MCL-1. The results revealed that butanol fraction contains maximum amount of quercetin, 4-hydroxy-3-methoxy benzoic acid and trans-4-hydroxy-3-methoxy cinnamic acid. Ferulic acid is abundant in water fraction whereas n-hexane fractions contain sinapic and vanillic acids. The ethyl acetate fraction possess the highest level of phenolics as well as radical scavenging potential. HPLC results show that 9 organic acids are present in ethyl acetate and butanol fractions. The highest cytotoxic activity was exhibited by n-hexane and ethyl acetate fractions. Molecular docking studies supports that ethyl acetate and n-hexane fractions are the major sources of antioxidant and cytotoxic compounds. Also, molecular interactions exist between identified phenolics from plant shoots fractions with anti-apoptotic proteins Bcl-2, Bcl-xl and MCL-1.   KEY WORDS: Morraya koenigii, Fractionation, Antioxidant, Cytotoxic, Molecular docking Bull. Chem. Soc. Ethiop. 2022, 36(3), 651-666.                                                               DOI: https://dx.doi.org/10.4314/bcse.v36i3.14                                                      

Proactive Caching in D2D Assisted Multitier Cellular Network

Cache-enabled networks suffer hugely from the challenge of content caching and content delivery. In this regard, cache-enabled device-to-device (D2D) assisted multitier cellular networks are expected to relieve the network data pressure and effectively solve the problem of content placement and content delivery. Consequently, the user can have a better opportunity to get their favored contents from nearby cache-enabled transmitters (CETs) through reliable and good-quality links; however, as expected, designing an effective caching policy is a challenging task due to the limited cache memory of CETs and uncertainty in user preferences. In this article, we introduce a joint content placement and content delivery technique for D2D assisted multitier cellular networks (D2DMCN). A support vector machine (SVM) is employed to predict the content popularity to determine which content is to be cached and where it is to be cached, thereby increasing the overall cache hit ratio (CHR). The content request is satisfied either by the neighboring node through the D2D link or by the cache-enabled base stations (BSs) of the multitier cellular networks (MCNs). Similarly, to solve the problem of optimal content delivery, the Hungarian algorithm is employed aiming to improve the quality of satisfaction. The simulation results indicate that the proposed content placement strategy effectively optimizes the overall cache hit ratio of the system. Similarly, an effective content delivery approach reduces the request content delivery delay and power consumption.

Seroprevalence and Molecular Evidence of Coxiella burnetii in Dromedary Camels of Pakistan

Coxiellosis is a zoonosis in animals caused by Coxiella burnetii. A cross-sectional study was conducted on 920 (591 female and 329 male) randomly selected camels (Camelus dromedarius) of different age groups from 13 districts representative of the three different ecological zones in the Province Punjab, Pakistan to determine the prevalence and associated risk factors of coxiellosis. The blood samples were collected and tested for anti-C. burnetti antibodies using indirect multispecies ELISA. Real-time PCR was used for the detection of C. burnetii DNA to determine the prevalence in heparinized blood pools. Out of 920 investigated camels, anti-C. burnetii antibodies were detected in 288 samples (31.3%) (95% CI: 28.3–34.4%). The highest (78.6%) and lowest (1.8%) seroprevalence were detected in Rahimyar Khan (southern Punjab) and in Jhang (central Punjab), respectively. Potential risk factors associated with seropositivity of the Q fever in camels included desert area (42.5%; OR = 2.78, 95% CI 1.12–3.21) summer season (35.7%; OR = 2.3, 95% CI: 1.31–3.2), sex (female) (39.1; OR = 2.35, 95% CI: 1.34–2.98), tick infestation (51.3%;OR = 2.81, 95% CI: 1.34–3.02), age (>10 years; 46.4%; OR = 1.56, 95% CI: 0.33–2.05) and herd size (38.5%; OR = 1.21, 95% CI: 0.76–1.54). Coxiella burnetii DNA was amplified in 12 (20%) and 1 (10%) of 60 ELISA-negative and 10 suspected camels, respectively. DNA could not be detected in ELISA positive blood pools. This study emphasizes the seroprevalence and associated risk factors of coxiellosis as well as its potential to spill over to animals and humans in contact with these camel herds.

Spatial Attention-Based 3D Graph Convolutional Neural Network for Sign Language Recognition

Sign language is the main channel for hearing-impaired people to communicate with others. It is a visual language that conveys highly structured components of manual and non-manual parameters such that it needs a lot of effort to master by hearing people. Sign language recognition aims to facilitate this mastering difficulty and bridge the communication gap between hearing-impaired people and others. This study presents an efficient architecture for sign language recognition based on a convolutional graph neural network (GCN). The presented architecture consists of a few separable 3DGCN layers, which are enhanced by a spatial attention mechanism. The limited number of layers in the proposed architecture enables it to avoid the common over-smoothing problem in deep graph neural networks. Furthermore, the attention mechanism enhances the spatial context representation of the gestures. The proposed architecture is evaluated on different datasets and shows outstanding results.

Deep learning in multimedia healthcare applications: a review

The increase in chronic diseases has affected the countries' health system and economy. With the recent COVID-19 virus, humanity has experienced a great challenge, which has led to make efforts to detect it and prevent its spread. Hence, it is necessary to develop new solutions that are based on technology and low cost, to satisfy the citizens' needs. Deep learning techniques is a technological solution that has been used in healthcare lately. Nowadays, with the increase in chips processing capabilities, increase size of data, and the progress in deep learning research, healthcare applications have been proposed to provide citizens' health needs. In addition, a big amount of data is generated every day. Development in Internet of Things, gadgets, and phones has allowed the access to multimedia data. Data such as images, video, audio and text are used as input of applications based on deep learning methods to support healthcare system to diagnose, predict, or treat patients. This review pretends to give an overview of proposed healthcare solutions based on deep learning techniques using multimedia data. We show the use of deep learning in healthcare, explain the different types of multimedia data, show some relevant deep learning multimedia applications in healthcare, and highlight some challenges in this research area.

Tuberculosis detection in chest radiograph using convolutional neural network architecture and explainable artificial intelligence

In most regions of the world, tuberculosis (TB) is classified as a malignant infectious disease that can be fatal. Using advanced tools and technology, automatic analysis and classification of chest X-rays (CXRs) into TB and non-TB can be a reliable alternative to the subjective assessment performed by healthcare professionals. Thus, in the study, we propose an automatic TB detection system using advanced deep learning (DL) models. A significant portion of a CXR image is dark, providing no information for diagnosis and potentially confusing DL models. Therefore, in the proposed system, we use sophisticated segmentation networks to extract the region of interest from multimedia CXRs. Then, segmented images are fed into the DL models. For the subjective assessment, we use explainable artificial intelligence to visualize TB-infected parts of the lung. We use different convolutional neural network (CNN) models in our experiments and compare their classification performance using three publicly available CXR datasets. EfficientNetB3, one of the CNN models, achieves the highest accuracy of 99.1%, with a receiver operating characteristic of 99.9%, and an average accuracy of 98.7%. Experiment results confirm that using segmented lung CXR images produces better performance than does using raw lung CXR images.

A Multi-Branch Convolutional Neural Network with Squeeze-and-Excitation Attention Blocks for EEG-Based Motor Imagery Signals Classification

Electroencephalography-based motor imagery (EEG-MI) classification is a critical component of the brain-computer interface (BCI), which enables people with physical limitations to communicate with the outside world via assistive technology. Regrettably, EEG decoding is challenging because of the complexity, dynamic nature, and low signal-to-noise ratio of the EEG signal. Developing an end-to-end architecture capable of correctly extracting EEG data’s high-level features remains a difficulty. This study introduces a new model for decoding MI known as a Multi-Branch EEGNet with squeeze-and-excitation blocks (MBEEGSE). By clearly specifying channel interdependencies, a multi-branch CNN model with attention blocks is employed to adaptively change channel-wise feature responses. When compared to existing state-of-the-art EEG motor imagery classification models, the suggested model achieves good accuracy (82.87%) with reduced parameters in the BCI-IV2a motor imagery dataset and (96.15%) in the high gamma dataset.

A Multibranch of Convolutional Neural Network Models for Electroencephalogram-Based Motor Imagery Classification

Automatic high-level feature extraction has become a possibility with the advancement of deep learning, and it has been used to optimize efficiency. Recently, classification methods for Convolutional Neural Network (CNN)-based electroencephalography (EEG) motor imagery have been proposed, and have achieved reasonably high classification accuracy. These approaches, however, use the CNN single convolution scale, whereas the best convolution scale varies from subject to subject. This limits the precision of classification. This paper proposes multibranch CNN models to address this issue by effectively extracting the spatial and temporal features from raw EEG data, where the branches correspond to different filter kernel sizes. The proposed method's promising performance is demonstrated by experimental results on two public datasets, the BCI Competition IV 2a dataset and the High Gamma Dataset (HGD). The results of the technique show a 9.61% improvement in the classification accuracy of multibranch EEGNet (MBEEGNet) from the fixed one-branch EEGNet model, and 2.95% from the variable EEGNet model. In addition, the multibranch ShallowConvNet (MBShallowConvNet) improved the accuracy of a single-scale network by 6.84%. The proposed models outperformed other state-of-the-art EEG motor imagery classification methods.

Degradation of Perovskite Thin Films and Solar Cells with Candle Soot C/Ag Electrode Exposed in a Control Ambient

Perovskite solar cells (PSCs) have already achieved efficiencies of over 25%; however, their instability and degradation in the operational environment have prevented them from becoming commercially viable. Understanding the degradation mechanism, as well as improving the fabrication technique for achieving high-quality perovskite films, is crucial to overcoming these shortcomings. In this study, we investigated details in the changes of physical properties associated with the degradation and/or decomposition of perovskite films and solar cells using XRD, FESEM, EDX, UV-Vis, Hall-effect, and current-voltage (I-V) measurement techniques. The dissociation, as well as the intensity of perovskite peaks, have been observed as an impact of film degradation by humidity. The decomposition rate of perovskite film has been estimated from the structural and optical changes. The performance degradation of novel planner structure PSCs has been investigated in detail. The PSCs were fabricated in-room ambient using candle soot carbon and screen-printed Ag electrode. It was found that until the perovskite film decomposed by 30%, the film properties and cell efficiency remained stable.

A Lightweight and Robust Secure Key Establishment Protocol for Internet of Medical Things in COVID-19 Patients Care

Due to the outbreak of COVID-19, the Internet of Medical Things (IoMT) has enabled the doctors to remotely diagnose the patients, control the medical equipment, and monitor the quarantined patients through their digital devices. Security is a major concern in IoMT because the Internet of Things (IoT) nodes exchange sensitive information between virtual medical facilities over the vulnerable wireless medium. Hence, the virtual facilities must be protected from adversarial threats through secure sessions. This article proposes a lightweight and physically secure mutual authentication and secret key establishment protocol that uses physical unclonable functions (PUFs) to enable the network devices to verify the doctor's legitimacy (user) and sensor node before establishing a session key. PUF also protects the sensor nodes deployed in an unattended and hostile environment from tampering, cloning, and side-channel attacks. The proposed protocol exhibits all the necessary security properties required to protect the IoMT networks, like authentication, confidentiality, integrity, and anonymity. The formal AVISPA and informal security analysis demonstrate its robustness against attacks like impersonation, replay, a man in the middle, etc. The proposed protocol also consumes fewer resources to operate and is safe from physical attacks, making it more suitable for IoT-enabled medical network applications.

COVID-19 and Non-COVID-19 Classification using Multi-layers Fusion From Lung Ultrasound Images

COVID-19 or related viral pandemics should be detected and managed without hesitation, since the virus spreads very rapidly. Often with insufficient human and electronic resources, patients need to be checked from stable patients using vital signs, radiographic photographs, or ultrasound images. Vital signs do not often offer the right outcome, and radiographic photos have a variety of other problems. Lung ultrasound (LUS) images can provide good screening without a lot of complications. This paper suggests a model of a convolutionary neural network (CNN) that has fewer learning parameters but can achieve strong accuracy. The model has five main blocks or layers of convolution connectors. A multi-layer fusion functionality of each block is proposed to improve the efficiency of the COVID-19 screening method utilizing the proposed model. Experiments are conducted using freely accessible LUS photographs and video datasets. The proposed fusion method has 92.5% precision, 91.8% accuracy, and 93.2% retrieval using the data collection. These efficiency metric levels are considerably higher than those used in any of the state-of-the-art CNN versions.

Impact of Ar Flow Rates on Micro-Structural Properties of WS2 Thin Film by RF Magnetron Sputtering

Tungsten disulfide (WS₂) thin films were deposited on soda-lime glass (SLG) substrates using radio frequency (RF) magnetron sputtering at different Ar flow rates (3 to 7 sccm). The effect of Ar flow rates on the structural, morphology, and electrical properties of the WS₂ thin films was investigated thoroughly. Structural analysis exhibited that all the as-grown films showed the highest peak at (101) plane corresponds to rhombohedral phase. The crystalline size of the film ranged from 11.2 to 35.6 nm, while dislocation density ranged from 7.8 × 10¹⁴ to 26.29 × 10¹⁵ lines/m². All these findings indicate that as-grown WS₂ films are induced with various degrees of defects, which were visible in the FESEM images. FESEM images also identified the distorted crystallographic structure for all the films except the film deposited at 5 sccm of Ar gas flow rate. EDX analysis found that all the films were having a sulfur deficit and suggested that WS₂ thin film bears edge defects in its structure. Further, electrical analysis confirms that tailoring of structural defects in WS₂ thin film can be possible by the varying Ar gas flow rates. All these findings articulate that Ar gas flow rate is one of the important process parameters in RF magnetron sputtering that could affect the morphology, electrical properties, and structural properties of WS₂ thin film. Finally, the simulation study validates the experimental results and encourages the use of WS₂ as a buffer layer of CdTe-based solar cells.

Defect Study and Modelling of SnX3-Based Perovskite Solar Cells with SCAPS-1D

Recent achievements, based on lead (Pb) halide perovskites, have prompted comprehensive research on low-cost photovoltaics, in order to avoid the major challenges that arise in this respect: Stability and toxicity. In this study, device modelling of lead (Pb)-free perovskite solar cells has been carried out considering methyl ammonium tin bromide (CH3NH3SnBr3) as perovskite absorber layer. The perovskite structure has been justified theoretically by Goldschmidt tolerance factor and the octahedral factor. Numerical modelling tools were used to investigate the effects of amphoteric defect and interface defect states on the photovoltaic parameters of CH3NH3SnBr3-based perovskite solar cell. The study identifies the density of defect tolerance in the absorber layer, and that both the interfaces are 1015 cm-3, and 1014 cm-3, respectively. Furthermore, the simulation evaluates the influences of metal work function, uniform donor density in the electron transport layer and the impact of series resistance on the photovoltaic parameters of proposed n-TiO2/i-CH3NH3SnBr3/p-NiO solar cell. Considering all the optimization parameters, CH3NH3SnBr3-based perovskite solar cell exhibits the highest efficiency of 21.66% with the Voc of 0.80 V, Jsc of 31.88 mA/cm2 and Fill Factor of 84.89%. These results divulge the development of environmentally friendly methyl ammonium tin bromide perovskite solar cell.

Medical image-based detection of COVID-19 using Deep Convolution Neural Networks

The demand for automatic detection of Novel Coronavirus or COVID-19 is increasing across the globe. The exponential rise in cases burdens healthcare facilities, and a vast amount of multimedia healthcare data is being explored to find a solution. This study presents a practical solution to detect COVID-19 from chest X-rays while distinguishing those from normal and impacted by Viral Pneumonia via Deep Convolution Neural Networks (CNN). In this study, three pre-trained CNN models (EfficientNetB0, VGG16, and InceptionV3) are evaluated through transfer learning. The rationale for selecting these specific models is their balance of accuracy and efficiency with fewer parameters suitable for mobile applications. The dataset used for the study is publicly available and compiled from different sources. This study uses deep learning techniques and performance metrics (accuracy, recall, specificity, precision, and F1 scores). The results show that the proposed approach produced a high-quality model, with an overall accuracy of 92.93%, COVID-19, a sensitivity of 94.79%. The work indicates a definite possibility to implement computer vision design to enable effective detection and screening measures.

Secure and Provenance Enhanced Internet of Health Things Framework: A Blockchain Managed Federated Learning Approach

Recent advancements in the Internet of Health Things (IoHT) have ushered in the wide adoption of IoT devices in our daily health management. For IoHT data to be acceptable by stakeholders, applications that incorporate the IoHT must have a provision for data provenance, in addition to the accuracy, security, integrity, and quality of data. To protect the privacy and security of IoHT data, federated learning (FL) and differential privacy (DP) have been proposed, where private IoHT data can be trained at the owner's premises. Recent advancements in hardware GPUs even allow the FL process within smartphone or edge devices having the IoHT attached to their edge nodes. Although some of the privacy concerns of IoHT data are addressed by FL, fully decentralized FL is still a challenge due to the lack of training capability at all federated nodes, the scarcity of high-quality training datasets, the provenance of training data, and the authentication required for each FL node. In this paper, we present a lightweight hybrid FL framework in which blockchain smart contracts manage the edge training plan, trust management, and authentication of participating federated nodes, the distribution of global or locally trained models, the reputation of edge nodes and their uploaded datasets or models. The framework also supports the full encryption of a dataset, the model training, and the inferencing process. Each federated edge node performs additive encryption, while the blockchain uses multiplicative encryption to aggregate the updated model parameters. To support the full privacy and anonymization of the IoHT data, the framework supports lightweight DP. This framework was tested with several deep learning applications designed for clinical trials with COVID-19 patients. We present here the detailed design, implementation, and test results, which demonstrate strong potential for wider adoption of IoHT-based health management in a secure way.

LU Decomposition method to solve bipolar fuzzy linear systems

The aim of this work is to solve the linear system of equations using LU decomposition method in bipolar fuzzy environment. We assume a special case when the coefficient matrix of the system is symmetric positive definite. We discuss this point in detail by giving some numerical examples. Moreover, we investigate m × n inconsistent bipolar fuzzy matrix equation and find the least square solution of the inconsistent bipolar fuzzy matrix using the generalized inverse matrix theory. The existence of the strong bipolar fuzzy least square solution of the inconsistent bipolar fuzzy matrix is discussed. In the end, a numerical example is presented to illustrate our proposed method.

Resorcinol-Formaldehyde (RF) as a Novel Plasticizer for Starch-Based Solid Biopolymer Electrolyte

A starch-resorcinol-formaldehyde (RF)-lithium triflate (LiTf) based biodegradable polymer electrolyte membrane was synthesized via the solution casting technique. The formation of RF crosslinks in the starch matrix was found to repress the starch's crystallinity as indicated by the XRD data. Incorporation of the RF plasticizer improved the conductivity greatly, with the highest room-temperature conductivity recorded being 4.29 × 10-4 S cm-1 achieved by the starch:LiTf:RF (20 wt.%:20 wt.%:60 wt.%) composition. The enhancement in ionic conductivity was an implication of the increase in the polymeric amorphous region concurrent with the suppression of the starch's crystallinity. Chemical complexation between the plasticizer, starch, and lithium salt components in the electrolyte was confirmed by FTIR spectra.

Self-attention based recurrent convolutional neural network for disease prediction using healthcare data

BACKGROUND AND OBJECTIVE

Nowadays computer-aided disease diagnosis from medical data through deep learning methods has become a wide area of research. Existing works of analyzing clinical text data in the medical domain, which substantiate useful information related to patients with disease in large quantity, benefits early-stage disease diagnosis. However, benefits of analysis not achieved well when the traditional rule-based and classical machine learning methods used; which are unable to handle the unstructured clinical text and only a single method is not able to handle all challenges related to the analysis of the unstructured text, Moreover, the contribution of all words in clinical text is not the same in the prediction of disease. Therefore, there is a need to develop a neural model which solve the above clinical application problems, is an interesting topic which needs to be explored.

METHODS

Thus considering the above problems, first, this paper present self-attention based recurrent convolutional neural network (RCNN) model using real-life clinical text data collected from a hospital in Wuhan, China. This model automatically learns high-level semantic features from clinical text by using bi-direction recurrent connection within convolution. Second, to deal with other clinical text challenges, we combine the ability of RCNN with the self-attention mechanism. Thus, self-attention gets the focus of the model on essential convolve features which have effective meaning in the clinical text by calculating the probability of each convolve feature through softmax.

RESULTS

The proposed model is evaluated on real-life hospital dataset and used measurement metrics as Accuracy and recall. Experiment results exhibit that the proposed model reaches up to accuracy 95.71%, which is better than many existing methods for cerebral infarction disease.

CONCLUSIONS

This article presented the self-attention based RCNN model by combining the RCNN with self-attention mechanism for prediction of cerebral infarction disease. The obtained results show that the presented model better predict the cerebral infarction disease risk compared to many existing methods. The same model can also be used for the prediction of other disease risks.

Association of Oxidative Stress and Production of Inflammatory Mediators Matrix Metalloproteinase-9 and Interleukin 6: Systemic Events in Radicular Cysts

Background

Matrix metalloproteinase-9 (MMP-9) and antioxidants are associated with the pathogenesis of cysts and may initiate and sustain the formation of new capillaries.

Objective

The objective of this study was to determine the association of oxidative stress and the production of inflammatory mediators MMP-9 and interleukin 6 (IL-6) in systemic events in radicular cyst growth.

Materials and methods

Fifty patients (34 men, 16 women) with periapical granulomas and radicular cysts were included in this cross-sectional study. Twenty subjects (12 men, eight women) with no signs of periodontal diseases were recruited as controls. Blood serum levels of MMP-9, IL-6, superoxide dismutase (SOD), malondialdehyde (MDA), and glutathione peroxidase (GPx) were recorded. We also recorded body mass index (BMI) and tumor necrosis factor-alpha (TNF-alpha) levels.

Results

The mean age of the test group patients and control patients was 45.9 and 48.8 years, respectively. The BMI of test group patients (23.77± 3.88 kg/m²) was higher than that of the controls (27.98 ± 3.88 kg/m²; p ≤ 0.000). Levels of serum MDA (p ≤ 0.033), IL-6 (p ≤ 0.041), TNF-alpha (p ≤ 0.004), and MMP-9 (p ≤ 0.033) were significantly increased in patients as compared with control values. SOD (p ≤ 0.003) and GPx (p ≤ 0.033) levels were significantly reduced in patients as compared with controls.

Conclusion

Oxidative imbalance and the increased production of inflammatory mediators may be associated with systemic events in radicular cysts. Bone-resorbing mediators and proinflammatory cytokines that were evaluated in the study (MMP-9, IL-6, C-reactive protein, TNF-alpha) were also elevated in the serum of the ailing group, thus documenting a well-established role for these circulating biochemical variables in the course of the progression and pathogenesis of radicular cyst development.

Date fruit dataset for intelligent harvesting

The date palm is one of the most valuable fruit trees in the world. Most methods used for date fruit inspection, harvesting, grading, and classification are manual, which makes them ineffective in terms of both time and economy. Research on automated date fruit harvesting is limited as there is no public dataset for date fruits to aid in this. In this work, we present a comprehensive dataset for date fruits that can be used by the research community for multiple tasks including automated harvesting, visual yield estimation, and classification tasks. The dataset contains images of date fruit bunches of different date varieties, captured at different pre-maturity and maturity stages. These images cover multiple sets of variations such as multi-scale images, variable illumination, and different bagging states. We also marked date bunches for selected palms and measured the weights of the bunches, captured their images on a graph paper, and recorded 360° video of the palms. This dataset can help in advancing research and automating date palm agricultural applications, including robotic harvesting, fruit detection and classification, maturity analysis, and weight/yield estimation. The dataset is freely and publicly available for the research community in the IEEE DataPort repository [1] (https://doi.org/10.21227/x46j-sk98).

Isolation and Identification of <i>Salmonella paratyphi </i>from Enteric Fever Patients at Different Hospitals of Quetta City

BACKGROUND AND OBJECTIVE

Salmonella paratyphi cause enteric fever which is an important public health problem worldwide. In Pakistan incidence is increasing and affect all age groups. Therefore, the present research was designed to study the different microbiological aspects of Salmonella paratyphi.

MATERIALS AND METHODS

The study was conducted to identify the Salmonella paratyphi from blood samples in Quetta. Total 480 blood samples were collected from different hospital of Quetta. Specific colony characters, microscopic examination, biochemical tests and PCR were used for identification of Salmonella paratyphi.

RESULTS

Total 55% samples were positive and 45% were negative for Salmonella paratyphi. Results showed that males (34%) were more affected with Salmonella paratyphi as compare to female (20%). Age wise distribution revealed that Salmonella paratyphi was high in 20-30 years (38%) followed by 10-20 years (9.16%) and 1-10 years (7.5%) age group patients. Paratyphoid fever cases were significantly high (25.41%) in Pashtoon population as compare to other population of Balochistan. The 40% paratyphoid fever was observed in the patients with low socioeconomic status, 9.16% in middle socioeconomic status and 5.83% in the patients belonged to high socioeconomic status. The Salmonella paratyphi were sensitive to Chloramphenicol (23 mm), Amikacin (24 mm), Gentamicin (12 mm), Quinolones (23) and Polypeptide (13 mm) classes. The PCR based identification of Salmonella paratyphi showed clear bands of 329 bp of flic-a gene.

CONCLUSION

To control paratyphoid fever strong initiatives must be taken to improve water sanitation, hygiene level, supply of save drinking water and vaccination is recommended in order to eradicate the disease.

Risk Factors and Microbiological Studies on <i>Streptococcus pneumoniae</i> Isolated from Pneumonia Patients of Quetta Balochistan

BACKGROUND AND OBJECTIVE

Pneumococcal diseases remain a major cause of morbidity and mortality worldwide. Streptococcus Pneumoniae causing pneumonia in India, Pakistan, Bangladesh and Afghanistan in children under 5 years of age and older adults. Therefore; the present research was design to study the different microbiological aspects of Streptococcus pneumoniae.

MATERIALS AND METHODS

A total of 480 sputum samples were collected from pneumonia patient at different government hospitals of Quetta. The detail of patient's gender, age, economical status and educational status were taken on performa. Sputum samples were inoculated into selective strep agar Streptococcus pneumonia colonies were observed on plates and confirmed through different biochemical tests and PCR.

RESULTS

Total 480 samples were collected in which 36.6% were Streptococcus pneumoniae positive and 63.3% were negative. The sex wise ratio showed that female (24.10%) were more affected with pneumoniae as compare to male (12.50%). The pneumonia infection age wise distribution was 9% in 1-10 years old patients, 16% in 10-20 years old patients and 11% in 20-30 years old patients. The status wise distribution of pneumonia infection showed that lower class (16%) was more affected as compare to middle class and higher class of Quetta. The percentage of pneumonia infection in hazara race was 14%, in Pathan 8.30%, in Punjabi 7.60% and in Baloch 6.60%. It was seen that illiterate patients were more affected with pneumonia infection (28.3%) than literate (8.3%). The Streptococcus pneumoniae was confirmed through gram staining, different biochemical tests, different sugar fermentation tests and PCR. Whereas confirmed by PCR showed clear band of 329 kb of ply gene.

CONCLUSION

It was concluded that the rate of pneumonia infection was high in female and lower class was more affected with pneumonia.

Diet effect on short- and long-term glycaemic response in adult healthy cats

In the paper the short- and long-term glycaemic response after 4 diet programmes was evaluated. Each diet programme was alternatively administered to 6 healthy cats for 30 days. At the end of each period cats were weighed and underwent blood sampling for glucose and fructosamine determination. Glycaemia was measured every 2 hours for 24 hours using an automated glucometer. Very high protein level and low starch (VHP÷LS) and high protein and moderate starch level (HP÷LS) diets showed glucose (Mean and Peak) and fructosamine values signi cantly lower compared to the moderate protein and high starch diets (MP/HS). It is likely that these results are due to the contemporary e ect of the following nutritional characteristics: protein level, protein/starch ratio and dietary bre. All these parameters were higher in VHP/LS and HP/MS diets. These preliminary results suggest that the use of diets with high protein/starch ratio and soluble bre levels favours the carbohydrate metabolism of healthy cats.

Prevalence, economic analysis and chemotherapeutic control of small ruminant fasciolosis in the Sargodha district of Punjab, Pakistan

This study describes the epidemiology, the economic significance of small ruminant fasciolosis in animals slaughtered in the abattoirs of the Sargodha district, Punjab, Pakistan between January and June 2012. In vivo fasciolicidal efficacy of commercially available compounds was examined using a randomised complete block design. Microscopically screened faecal samples revealed 40.51% positive animals for fasciolosis. The prevalent species included Fasciola hepatica (35.64%) and Fasciola gigantica (8.21%). Mixed infections were noted in 3.33% subjects. Prevalence rates were significantly higher in females (42.25%) than in males (39.52%), and in adults (51.20%) compared to younger animals (33.98%). The disease was recorded more often in emaciated animals (63.63%) followed in order by average (43.45%), thin (43.22%), and fat (32.12%) animals. Between January and June 2012, fasciolosis in Sargodha district, Punjab, Pakistan, was estimated to incur US$0.036 million and US$0.177 million direct (liver condemnation) and indirect (carcass depreciation) economic losses, respectively. In vivo fasciolicidal efficacy of oxyclozanide proved to be the most effective method of control, compared to triclabendazole, and levamisole. Results provide useful information on the frequency distribution of fasciolosis and its economic significance. Finally, data on in vivo fasciolicidal trials show that oxyclozanide is the most efficacious compound for the treatment of the disease in the district Sargodha, Punjab, Pakistan.

Effect of weaning age and milk feeding level on pre- and post-weaning growth performance of Sahiwal calves

The Sahiwal cow is a tropical dairy breed native to Pakistan. The objective of the present study was to evaluate pre- and post-weaning growth of Sahiwal calves weaned either at 8 or 12 weeks and offered milk at either 10% or 15% of bodyweight (BW) from birth to weaning. Colostrum fed Sahiwal calves (n = 48) were randomly allocated to four treatments of 12 calves each. Calves were offered milk either at 10% (low-milk) or 15% (high-milk) of BW in two weaning programs (early or late). Early weaned calves were offered milk until Day 35, adjusted weekly for liveweight and then reduced by one-third in each subsequent week until weaned at Day 56 (early weaned). Late-weaned calves were offered milk until Day 63 and were weaned at Day 84 (late-weaned) by reducing milk offered by one-third in each subsequent week. Calves were offered a concentrate ration (21% crude protein and 2.93 metabolisable energy, Mcal/kg) from Day 28 to Day 112. Final BW at 16 weeks was highest (77.6 ± 1.8 kg; P < 0.01) in high milk-fed late-weaned calves and lowest in low milk-fed early weaned calves (60.2 ± 1.8 kg). High-milk early weaned and low milk late-weaned calves had comparable final BW (70.7 ± 1.8 vs 72.0 ± 1.8 kg), although lower than that of high-milk late-weaned calves, but still at an acceptable lower feeding cost to gain per kg liveweight (US$ 3.2 vs 2.5). Thus, offering milk to Sahiwal calves at 15% of BW and weaning at 8 weeks saves milk and labour required for additional days to feed these calves.