Search

Abstract In the twenty-first century, global warming has become one of the severe challenges. Around one-fourth of the total carbon footprint is contributed by transport vehicles. It is crucial to provide alternative solutions to unsustainable transportation systems. This study compares the present travel modes of students of the Capital University of Science and Technology, Islamabad, with the proposed sustainable travel mode. A campus survey (N = 565) was conducted to understand travel choices, travel times, origin and destinations, and student preferences, considering university buses and private vehicles. A comparison was made between the travel time analysis of university bus users and non-bus users. A sustainability analysis has been conducted to evaluate the effects of the present travel modes on students and the proposed university bus transport system. Five main factors were compared: fuel consumption and associated fuel costs, carbon and vehicular emissions, traffic noise pollution, traffic congestion, and accident ratio. The results show that 38% of students commute by private cars and 18% by motorbikes. Around 25% of the students avoid university buses due to long travel times, and 30% prefer because their parents ask them. On average, university buses take 56.8 min, and non-bus transports take 38.8 min for one-way travel. If all students travel by university busses, they could be 86% more sustainable in fuel costs and carbon emissions than non-bus travel modes. These results give useful policy implications for providing sustainable travel alternatives to educational institutions.

Abstract Medical image machines serve as a valuable tool to monitor and diagnose a variety of diseases. However, manual and centralized interpretation are both error-prone and time-consuming due to malicious attacks. Numerous diagnostic algorithms have been developed to improve precision and prevent poisoning attacks by integrating symptoms, test methods, and imaging data. But in today’s digital technology world, it is necessary to have a global cloud-based diagnostic artificial intelligence model that is efficient in diagnosis and preventing poisoning attacks and might be used for multiple purposes. We propose the Healthcare Federated Ensemble Internet of Learning Cloud Doctor System (FDEIoL) model, which integrates different Internet of Things (IoT) devices to provide precise and accurate interpretation without poisoning attack problems, thereby facilitating IoT-enabled remote patient monitoring for smart healthcare systems. Furthermore, the FDEIoL system model uses a federated ensemble learning strategy to provide an automatic, up-to-date global prediction model based on input local models from the medical specialist. This assures biomedical security by safeguarding patient data and preserving the integrity of diagnostic processes. The FDEIoL system model utilizes local model feature selection to discriminate between malicious and non-malicious local models, and ensemble strategies use positive and negative samples to optimize the performance of the test dataset, enhancing its capability for remote patient monitoring. The FDEIoL system model achieved an exceptional accuracy rate of 99.24% on the Chest X-ray dataset and 99.0% on the MRI dataset of brain tumors compared to centralized models, demonstrating its ability for precision diagnosis in IoT-enabled healthcare systems.

Abstract Hyperspectral image (HSI) data has a wide range of valuable spectral information for numerous tasks. HSI data encounters challenges such as small training samples, scarcity, and redundant information. Researchers have introduced various research works to address these challenges. Convolution Neural Network (CNN) has gained significant success in the field of HSI classification. CNN’s primary focus is to extract low-level features from HSI data, and it has a limited ability to detect long-range dependencies due to the confined filter size. In contrast, vision transformers exhibit great success in the HSI classification field due to the use of attention mechanisms to learn the long-range dependencies. As mentioned earlier, the primary issue with these models is that they require sufficient labeled training data. To address this challenge, we proposed a spectral-spatial feature extractor group attention transformer that consists of a multiscale feature extractor to extract low-level or shallow features. For high-level semantic feature extraction, we proposed a group attention mechanism. Our proposed model is evaluated using four publicly available HSI datasets, which are Indian Pines, Pavia University, Salinas, and the KSC dataset. Our proposed approach achieved the best classification results in terms of overall accuracy (OA), average accuracy (AA), and Kappa coefficient. As mentioned earlier, the proposed approach utilized only 5%, 1%, 1%, and 10% of the training samples from the publicly available four datasets.

Abstract The gradual decline of production of the major fields of the Indus Basin has influenced the field pressure. Therefore, the prospects need to be assessed by the petro-elastic relationship. This study highlights the value-addition for identifying gas pockets within the E-Sand of the Lower Goru Formation through estimating and populating petro-elastic properties. A probabilistic neural network (PNN) was employed to develop the relationship of pore pressure to the inverted properties. The outcomes will help identify the high-pressure areas in accordance with the petro-elastic relationship for optimizing production strategy. In order to evaluate the petro-elastic relationship, stochastic seismic inversion was employed to holistically capture the reservoir’s variability. Pore pressure volumetric was estimated from inverted attributes using a PNN, a non-linear algorithm that was more suited to heterogeneous reservoirs. The main objective of the research is achieved via enhanced resolution of elastic properties attained through the integration of stochastic inversion and PNN processes. The high-resolution elastic properties including P-impedance, S-impedance, and Vp/Vs ratio can delineate the heterogeneities more profoundly. The petrophysical volumes obtained via enhanced inverted properties combined with pore-pressure through PNN illuminated the potential facies and the correlations in predicting the properties. The procedure provides a linkage of elastic, petrophysical, and geomechanical properties that is helpful for professionals covering a broad field of the petroleum sector. The developed workflow can be followed globally where problems occur regarding heterogeneities and early depletion.

Abstract Maternal health risks can cause a range of complications for women during pregnancy. High blood pressure, abnormal glucose levels, depression, anxiety, and other maternal health conditions can all lead to pregnancy complications. Proper identification and monitoring of risk factors can assist to reduce pregnancy complications. The primary goal of this research is to use real-world datasets to identify and predict Maternal Health Risk (MHR) factors. As a result, we developed and implemented the Quad-Ensemble Machine Learning framework to predict Maternal Health Risk Classification (QEML-MHRC). The methodology used a vacxsriety of Machine Learning (ML) models, which then integrated with four ensemble ML techniques to improve prediction. The dataset collected from various maternity hospitals and clinics subjected to nineteen training and testing tests. According to the exploratory data analysis, the most significant risk factors for pregnant women include high blood pressure, low blood pressure, and high blood sugar levels. The study proposed a novel approach to dealing with high-risk factors linked to maternal health. Dealing with class-specific performance elaborated further to properly understand the distinction between high, low, and medium risks. All tests yielded outstanding results when predicting the amount of risk during pregnancy. In terms of class performance, the dataset associated with the “HR” class outperformed the others, predicting 90% correctly. GBT with ensemble stacking outperformed and demonstrated remarkable performance for all evaluation measure (0.86) across all classes in the dataset. The key success of the models used in this work is the ability to measure model performance using a class-wise distribution. The proposed approach can help medical experts assess maternal health risks, saving lives and preventing complications throughout pregnancy. The prediction approach presented in this study can detect high-risk pregnancies early on, allowing for timely intervention and treatment. This study’s development and findings have the potential to raise public awareness of maternal health issues.

The arrival of virtual power plants (VPPs) marks important progress in the energy sector, providing optimistic solutions to the increasing need for energy flexibility, resilience, and improved energy systems’ integration. VPPs harness several characteristics to bring together distributed energy resources (DERs), resulting in economic gains and improved power grid reliability. Nevertheless, VPPs encounter major challenges when it comes to engaging in energy markets, mainly because there is no all-encompassing policy and regulatory framework specifically designed to accommodate their unique characteristics. This underscores the necessity for research endeavours to develop more advanced methods and structures for the long-term viability of VPPs. To address this concern, the study advocates for the implementation of a multi-aspect framework (MAF) as a systematic approach to thoroughly examine each aspect of virtual power plants (VPPs). A STEEP (social, technological, environmental, economic, and political) analytical tool is utilized to evaluate the challenges, opportunities, and benefits of a VPP in the existing energy markets. The proposed approach highlights important factors and actions that need to be taken to tackle the challenges related to VPP’ entry into energy markets. This study suggests that further support is required to promote the fast and widespread adoption of long-term VPP implementations. For this reason, a more favourable policy and regulatory framework based on social, technological, economic, environmental, and policy considerations is necessary to realize the genuine contributions of VPPs.

Fintech is an industry that uses technology to enhance and automate financial services. Fintech firms use software, mobile apps, and digital technologies to provide financial services that are faster, more efficient, and more accessible than those provided by traditional banks and financial institutions. Fintech companies take care of processes such as lending, payment processing, personal finance, and insurance, among other financial services. A data breach refers to a security liability when unapproved individuals gain access to or pilfer susceptible data. Data breaches pose a significant financial, reputational, and legal liability for companies. In 2017, Equifax suffered a data breach that revealed the personal information of over 143 million customers. Combining federated learning (FL) and blockchain can provide financial institutions with additional insurance and safeguards. Blockchain technology can provide a transparent and secure platform for FL, allowing financial institutions to collaborate on machine learning (ML) models while maintaining the confidentiality and integrity of their data. Utilizing blockchain technology, FL can provide an immutable and auditable record of all transactions and data exchanges. This can ensure that all parties adhere to the protocols and standards agreed upon for data sharing and collaboration. We propose the implementation of an FL framework that uses multiple ML models to protect consumers against fraudulent transactions through blockchain. The framework is intended to preserve customer privacy because it does not mandate the exchange of private customer data between participating institutions. Each bank trains its local models using data from its consumers, which are then combined on a centralised federated server to produce a unified global model. Data is neither stored nor exchanged between institutions, while models are trained on each institution’s data.

The widespread global adoption of wind energy sources has established a significant presence in the existing power grid. However, the massive integration of intermittent wind energy poses forecasting errors, prompting the need for supplementary reserves from conventional energy sources with increased operational expenses and carbon emissions. Hence, to facilitate the seamless operation of large-scale wind-integrated power grids, it is imperative to harness the potential of renewable energy sources and leverage flexible loads to deliver power-balancing services. In this research, dynamic real-time power dispatch strategies have been developed for the Automatic Generation Control (AGC) system to integrate the reserve capacities of conventional generation units and wind power plants and utilize the demand response capabilities of flexible loads for power balancing services. A comprehensive power system grid model was developed in DigSilent PowerFactory software, consisting of coal-based energy systems, wind energy systems, gas turbines, and cold storage units as flexible loads. The study is divided into different case studies to assess the impact of each scenario on system operation in mitigating the forecasting errors of wind power plants. Further, a comparative analysis was performed to illustrate the effectiveness of each case study. The analysis showed that Case Study III, where reserves are provided by coal energy systems and cold storage units, yielded the highest reduction in Positive Regulation (PR) and Negative Regulation (NR) errors, at 89.0% and 94.15%, respectively. Conversely, Case Study IV demonstrated the least reduction in errors, with 67.82% in PR and 78.41% in NR. However, it indicates that reserves can be supplied from wind energy systems and flexible loads without the support of conventional power plants.

Brain tumor (BT) is an awful disease and one of the foremost causes of death in human beings. BT develops mainly in 2 stages and varies by volume, form, and structure, and can be cured with special clinical procedures such as chemotherapy, radiotherapy, and surgical mediation. With revolutionary advancements in radiomics and research in medical imaging in the past few years, computer-aided diagnostic systems (CAD), especially deep learning, have played a key role in the automatic detection and diagnosing of various diseases and significantly provided accurate decision support systems for medical clinicians. Thus, convolution neural network (CNN) is a commonly utilized methodology developed for detecting various diseases from medical images because it is capable of extracting distinct features from an image under investigation. In this study, a deep learning approach is utilized to extricate distinct features from brain images in order to detect BT. Hence, CNN from scratch and transfer learning models (VGG-16, VGG-19, and LeNet-5) are developed and tested on brain images to build an intelligent decision support system for detecting BT. Since deep learning models require large volumes of data, data augmentation is used to populate the existing dataset synthetically in order to utilize the best fit detecting models. Hyperparameter tuning was conducted to set the optimum parameters for training the models. The achieved results show that VGG models outperformed others with an accuracy rate of 99.24%, average precision of 99%, average recall of 99%, average specificity of 99%, and average f 1-score of 99% each. The results of the proposed models compared to the other state-of-the-art models in the literature show better performance of the proposed models in terms of accuracy, sensitivity, specificity, and f 1-score. Moreover, comparative analysis shows that the proposed models are reliable in that they can be used for detecting BT as well as helping medical practitioners to diagnose BT.

Abstract Kadanwari is a major gas-producing field in Pakistan's Lower Indus Basin (LIB), extensively explored for optimized production. However, the reservoir sands of the Lower Goru Formation (LGF), deposited in a complex river-dominated delta, bear severe variability and hinder accurate facies approximation for optimal production. Furthermore, the regionally extended NNW-SSE directed horst and graben structures significantly compartmentalized these reservoir facies. The main E-sand interval is analyzed for its geological properties, depositional environment, and distribution. The integration of various approaches, including seismic interpretation, attribute extraction, well-based facies modeling, and petrophysical evaluation, proved significant in evaluating the heterogeneous and tectonically influenced E-sands. The discontinuity attribute substantially highlighted the structural style and aided in analyzing the geometries of faults. The low values of the frequency attribute (

Conventional vehicles emit many pollutants and natural gases, such as carbon dioxide and nitrogen oxides, which reduce air quality and global warming. Due to their extensive consumption, another driving force behind the search for alternatives is the fast depletion of fossil fuels, oil, and natural gas. Consequently, Hybrid Electric Vehicles (HEVs) have recently been the subject of substantial research to tackle the dual problems of harmful emissions and resource depletion. This research attempts to develop a novel barrier function-based adaptive sliding mode controller (BFASMC) for a hybrid energy storage system (HESS) of electric Vehicle (EV). The HESS comprises a fuel cell (FC), battery, supercapacitor (SC), and photovoltaic (PV). The FC serves as a primary source, while the others are auxiliary sources. DC converters are employed to couple these sources to a DC bus. The proposed BFASMC stabilizes and regulates the DC bus voltage. The system’s global stability has been assured through Lyapunov criteria and verified through phase plane (error and error differential) analysis. The proposed controller is compared with conventional sliding mode controller (SMC), integral SMC (ISMC), and double integral SMC (DISMC). The simulation (MATLAB/Simulink) and hardware in loop results (dSPACE MicroLabBox RTI1202) authenticate robustness, efficacy, resilience, chattering free operation, and superiority of proposed BFASMC compared with conventional SMC variants.

In recent times, credit card fraud has emerged as a substantial financial challenge for both cardholders and the issuing authorities. To address this demanding issue, researchers have employed machine learning techniques to identify fraudulent activities within labeled transaction records. However, these techniques have primarily been evaluated on limited or specific datasets, which may not adequately represent the broader real-world scenario. These limitations motivated us to comprehensively assess the existing machine learning classifiers and propose an Optimized Deep Event-based Network (OptDevNet) framework capable of addressing these challenges. To evaluate the performance of the proposed model, we implemented and assessed five different machine learning classifiers using the well-known Credit Card Fraud Detection (CCFD) Dataset. Upon careful analysis, we found that our model surpasses these classifiers in terms of fraudulent transaction detection accuracy. Given these findings, we are confident that our proposed model has the potential for effective real-world deployment in detecting and preventing malicious transactions.

Short-term load forecasting (STLF) is vital in effectively managing the reserve requirement in modern power grids. Subsequently, it supports the grid operator in making effective and economical decisions during the power balancing operation. Therefore, this study comprehensively reviews STLF methods, including time series analysis, regression-based frameworks, artificial neural networks (ANNs), and hybrid models that employ different forecasting approaches. Detailed mathematical and graphical analyses and a comparative evaluation of these methods are provided, highlighting their advantages and disadvantages. Further, the study proposes a hybrid CNN-LSTM model comprised of Convolutional neural networks (CNN) for feature extraction of high dimensional data and Long short-term memory (LSTM) networks to boost the model’s efficiency for temporal sequence prediction. This study assessed the model using a comprehensive dataset from Pakistan’s NTDC national grid. The analysis revealed superior performance in short-term load prediction, achieving enhanced accuracy. For single-step forecasting, the model yielded an RMSE of 538.71, MAE of 371.97, and MAPE of 2.72. In 24-hour forecasting, it achieved an RMSE of 951.94, MAE of 656.35, and MAPE of 4.72 on the NTDC dataset. Moreover, the model has outperformed previous models in comparison using the AEP dataset, demonstrating its superiority in enhancing reserve management and balancing supply and demand in modern electricity networks.

The most frequent and dangerous hazard to the electrical insulation of high voltage (HV) and high field (HF) equipment is partial discharges (PD). The development of PD activity is both a cause and an indicator of insulation degradation, which could ultimately lead to insulation breakdown. For electrical power equipment to operate safely and dependably, continuous and efficient PD monitoring must be conveniently performed to prevent associated damages and any harm to electrical power equipment. This work presents the design of a new UHF antenna for detecting PD in medium-voltage gas-insulated applications. The working frequency band of the proposed UHF antenna is 370 MHz–1300 MHz, which translates into a total bandwidth of 930 MHz UHF frequency band. Over the whole operating frequency of the antenna, the return loss is less than -10dB. Recently, an eco-friendly insulating gas, HFO1336mzz(E), is considered to be a good substitute for sulfur hexafluoride (SF6) in medium-voltage gas-insulated equipment (MV-GIE). The HFO(E) gas in a mixture with CO2 can reach the dielectric strength of SF6 gas. Hence, the HFO(E)/CO2 gas mixture’s partial discharge properties are systematically investigated in this research work. In particular, a detailed examination focuses on the partial discharge extinction voltage (PDEV) and partial discharge inception voltage (PDIV) under varying electric field conditions at different gas pressure levels and mixing ratios. The PDIV of the HFO(E)/CO2 gas mixture exhibited a linear-saturation rising pattern with both mixing ratio and gas pressure, mirroring the trend observed in SF6 when the HFO(E) gas concentration ranged between 25% and 30%.

Nowadays global market products are readily accessible worldwide, and a vast array of reviews across numerous platforms are posted daily in several categories, making it challenging for customers to stay informed about their product interests. To make informed decisions regarding product quality, users require access to reviews and ratings. Owners and managers must analyze customer ratings and the underlying emotional content of reviews to enhance the product’s quality, cost, customer service, and environmental impact. The primary aim of our proposed research is to accurately predict product helpfulness through customer reviews using the Large Language Model (LLM), thereby assisting customers in saving time and money. We employed a benchmark dataset, the Amazon Fine Food Reviews, to develop numerous advanced machine-learning techniques. We introduced a novel transformer approach BERF (BERT Random Forest) for feature engineering to enhance the value of user evaluations for Amazon’s gourmet food products. The BERF method utilizes BERT embeddings and class probability features derived from product helpfulness online reviews textual data. We have balanced the dataset using the Synthetic Minority Over-sampling TEchnique (SMOTE) approach. Our comprehensive study results demonstrated that the Light Gradient Boosting Machine (LGBM) strategy outperformed existing state-of-the-art approaches, achieving an accuracy of 98%. The performance of each method is confirmed using a k-fold method and further improved through hyperparameter optimization. Our innovative study employing a transformer model has significantly enhanced the utility of customer reviews, substantially reducing online product scams and preventing wasted time and money.

Depression constitutes a significant mental health condition, impacting an individual’s emotional state, thought processes, and ability to carry out everyday tasks. Depression is defined by ongoing feelings of sadness, diminished interest in previously enjoyed activities, alterations in hunger, sleep disturbances, decreased vitality, and challenges with focus. The impact of depression extends beyond the individual, affecting society at large through decreased productivity and higher healthcare costs. In the realm of social media, users often express their thoughts and emotions through posts, which can provide insightful data for identifying patterns of depression. This research aims to detect depression early by analyzing social media user content with machine learning techniques. We have built advanced machine learning models using a benchmark depression database containing 20,000 tagged tweets from user profiles identified as depressed or non-depressed. We are introducing an innovative BERT-RF feature engineering method that extracts Contextualized Embeddings and Probabilistic Features from textual input. The Bidirectional Encoder Representations from Transformers (BERT) model, based on the Transformer architecture, is used to extract Contextualized Embedding features. These features are then fed into a random forest model to generate class probabilistic features. These prominent features aid in enhancing the identification of depression from social media. In order to classify tweets using the features derived from the BERT-RF features selection step, we have used five popular classifiers: Random Forest (RF), Multilayer Perceptron (MLP), K-Neighbors Classifier (KNC), Logistic Regression (LR), and Long Short-Term Memory (LSTM). Evaluation experiments show that our approach, using BERT-RF for feature engineering, enables the Logistic Regression model to outperform state-of-the-art methods with a high accuracy score of 99%. We have validated the results through k-fold cross-validation and statistical T-tests. We achieved 99% k-fold accuracy during the validation of the proposed approach. This research contributes significantly to computational linguistics and mental health analytics by providing a robust approach to the early detection of user depression from social media content.

Gas-insulated systems are widely utilized in the electric power sector to transmit and distribute electrical energy. Sulphur-hexafluoride (SF6) has dominated gas insulation in high-voltage insulation technology since the early 60s. It is a greenhouse gas with a protracted lifespan in the atmosphere. This paper proposes an economical and comparatively more environmentally friendly R507 gas alternative to SF6 for medium-voltage applications. R507 has been analyzed experimentally through power frequency breakdown and lightning impulse testing to validate the performance and theoretical concepts. R507 has a very low liquefication temperature of $-46.7^{\circ }\text{C}$ , but it must still be mixed with buffer gases such as CO2, N2, or dry air to meet the diverse liquefaction temperature applications. Various field utilization factors under AC and lightning impulse voltages are used in the experiments, along with different electrode geometries, including sphere-to-plane and rod-to-plane (i.e., quasi-homogeneous and inhomogeneous electric field distribution). For comparison, identical experiments are conducted with pure SF6. R507 gas was found to be a promising substitute for SF6 gas, with its dielectric strength being approximately 0.95 times that of SF6 gas. A positive synergistic effect is present between R507 and CO2, along with the good self-recoverability property of the gas mixture. The current research study serves as a fundamental resource for characterizing the R507/CO2 gas mixture insulation properties to be utilized in practical applications.

Enhancement of the dispatching capacity and grid management efficiency requires knowledge of photovoltaic power generation beforehand. Intrinsically, photovoltaic power generation is highly volatile and irregular, which impedes its prediction accuracy. This paper proposes deep learning-based approaches and a pre-processing algorithm to handle these constraints. The proposed scheme employs Pearson’s Correlation Coefficient to find the similarity between atmospheric variables and PV power generation. Based on high PCC values, top atmospheric variables and PV power generated time series data are passed through the Empirical Mode Decomposition (EMD) to simplify the complex data streams into Intrinsic Mode Functions (IMFs). Further, to streamline the prediction process, the proposed correlation-based signal synthesis (CBSS) algorithm finds combinations of these IMFs, which have a high correlation value between atmospheric variables and PV power data. Deep learning models of algorithms Long Short Term Memory (LSTM) and Nonlinear Autoregressive Network with Exogenous Inputs (NARX) network with the configurations of three networks, a single network, and the direct approach employed for the prediction of IMFs combinations. The LSTM network was analyzed under the Adaptive moment estimation (ADAM), Stochastic Gradient Descent with Momentum (SGDM), and Root Mean Square Propagation (RMSP) optimization. Extensive experimentation was evaluated using atmospheric data from the Climate, Energy, and Water Research Institute (CEWRI), NARC, Islamabad, Pakistan. RMSE, MAE, MAPE, and $R^{2}$ performance measures show promising prediction results for the LSTM under the configuration of three networks and ADAM optimization.

This paper presents a novel Robust Feedback Linearization (RFBL) controller for Quadrotor Unmanned Aerial Vehicle (UAV) when subjected to external disturbances. A Robust Feedback Linearization controller is achieved by augmenting the conventional Feedback Linearization-based control with the Supertwisting Algorithm in the outer loop. To estimate the external disturbances acting on a quadrotor a Nonlinear Harmonic Disturbance Observer (NHDO) is patched with the robust controller. The efficacy and superiority of the results can be seen in terms of tracking error, rise time and robustness to disturbances when comparing it with other three robust controllers i.e. Integral Sliding Mode Controller (ISMC), Terminal Synergetic Controller (TSC) and Finite-Time supertwisting controller. Lyapunov’s stability analysis is performed to prove stability while numerical simulation is carried out using MATLAB/Simulink. The results are also validated by testing the system in a Hardware-In-Loop (HIL) environment on the MicroLabBox dSPACE RTI-1202 platform.

Accurate speed measurement and running records are integral to ensure safety and periodic maintenance of vehicles. This paper presents a novel structure of a solid rotary inverter (DAC) sensor for linear speed measurement of vehicles by eliminating reliance on magnets, coils, armatures, and toothed rings. The electromechanical sensor is exited through the vehicle’s DC power from the battery and utilizes a specially designed solid rotary part that is rotated mechanically by the wheel, enabling conversion of the DC into three-phase AC. The frequency of the produced AC voltage is proportional to the rotation speed. The three-phase alternating voltage is then used to run an analog speedometer gauge (a three-phase AC motor) to display the linear speed. The study determines stability analysis and response assessment by modeling a novel electromechanical rotational system and then evaluating its optimal design parameters. Real-time output voltage data from the sensor is acquired using a Rohde & Schwarz RTM 2034 oscilloscope and processed in MATLAB R2022b for frequency analysis. Experimental tests are conducted in a laboratory setting, varying the rotational speed sweep of the sensor from 150 to 450 RPM and translating the results into linear speed. A machine learning regression technique is applied to features such as shaft rotational speed, angular velocity, frequency, and period with linear speed. The obtained results reveal a total harmonic distortion (THD) value of −28.9778 dB (3.557%), meeting the criteria outlined in the IEEE 519–2014 “Recommended Practice and Requirements for Harmonic Control in Electric Power Systems.”

Abstract Background In multicultural societies, traditional knowledge among minorities faces several challenges. Minority groups often face difficult situations living in specific peripheral geographies and striving to retain their biocultural heritage, including medicinal plant knowledge and practices. Folk medicinal plant knowledge is a dynamic eco-cultural complex influenced by various environmental, socio-cultural, and political factors. Examining medicinal plant knowledge among minorities has been an increasingly popular topic in cross-cultural ethnobiology. It also helps understand the dynamics of local/traditional ecological knowledge (LEK/TEK) change within a given community. The current study was designed to investigate the status of medicinal plant knowledge among two linguistic groups, i.e. Ormurs and Pathans, living in a remote valley of West Pakistan. Methods We recruited 70 male study participants from the studied groups for semi-structured interviews to record the medicinal plant use of their communities. Data were compared among the two studied communities using the stacked charts employing the presence or absence of data with Past 4.03 and Venn diagrams. Use reports (URs) were counted for each recorded taxon. Results and Discussion A total of seventy-four medicinal plants were quoted as used as ethnomedicines by the researched communities. Most of the reported plants were used to treat digestive and liver problems. The cross-cultural comparison revealed a considerable homogeneity of medicinal plant knowledge (the two groups commonly used more than seventy plants); however, comparing uses recorded for the widely utilised medicinal plants showed numerous idiosyncratic uses among Ormurs but very few among Pathans. Ormurs reported a higher number of cultivated, wild, and imported plant uses than did Pathans. These results indicate that, compared to Pathans, the Ormur linguistic minority retain more folk medicinal plant knowledge, which may be explained by the fact that they have incorporated different folk remedies: their “own knowledge” plus that of Pathans, with whom they have lived together for centuries. Moreover, the local plant nomenclature among Ormurs was highly affected by the plant nomenclature of Pathans. Conclusion The current study revealed that living together for a few centuries has not implied sharing plant knowledge (as the Pathans do not seem to have learnt from the Ormurs) or, in other words, that plant knowledge exchanges have been unidirectional. The findings show that the Pashto dominant culture may have possibly put pressure on the minority groups and affected local plant-centred cultural practices, as we see in the case of local plant nomenclature hybridisation among Omuri speakers. Hence, it is imperative to employ diverse educational strategies to revitalise the decline of medicinal plant knowledge in the studied communities, especially among Ormurs, who need more attention as they face more challenges than the other group. Locally based strategies should be devised to restore the fading connection with nature, which will be advantageous for revitalising plant knowledge.

Enhancing the transparency of high-transmission-ratio linear actuators is crucial for improving the safety and capability of high-force robotic systems having physical contact with humans in unstructured environments. However, realizing such enhancement is challenging. A proposed solution for active body weight support systems involves employing a macro–mini linear actuator incorporating an electrorheological-fluid brake to connect a high-force unit with an agile, highly back-drivable unit. This paper introduces the use of an electromagnetic (EM) brake with reduced rotor inertia to address this challenge. The increased torque capacity of the EM brake enables integration with a low-gear-ratio linear transmission. The agile translation of the endpoint is propelled by a low-inertia motor (referred to as the “mini”) via a pulley-belt mechanism to achieve high transparency. The rotor of the EM brake is linked to the pulley. Damping modulation under high driving force is achieved through the adjustment of the brake torque relative to the rotational speed of the pulley. When the brake is engaged, it prevents any relative motion between the endpoint and the moving carrier. The endpoint is fully controlled by the ball screw of the high-force unit, referred to as the “macro”. A scaled prototype was constructed to experimentally characterize the damping force generated by the mini motor and the EM brake. The macro–mini linear actuator, equipped with an intrinsic failsafe feature, can be utilized for active body weight support systems that demand high antigravity force.

Abstract Arsenic (As), contamination in drinking groundwater resources is commonly environmental problem in many developing countries including Pakistan, with significant human health risk reports. In order to examine the groundwater quality concerning As contamination, its geochemical behavior along with physicochemical parameters, 42 samples were collected from community tube wells from District Bahawalpur, Punjab, Pakistan. The results showed the concentration of elevated As, its source of mobilization, and associated public health risk. The As concentration detected in groundwater samples varied from 0.12 to 104 µg/L with an average value of 34.7 µg/L. Among 42 groundwater samples, 27 samples were beyond the permitted limit of 10 µg/L recommended by World Health Organization (WHO), for drinking purposes. Statistical analysis result show that the groundwater cations values are in decreasing order such as: Na+ > Mg2+ > Ca2+ > K+, while anions were HCO3 – > SO4 2– > Cl– > NO3 –. Hydrochemical facies result depict that the groundwater samples of the study area, 14 samples belong to CaHCO3 type, 5 samples belong to NaCl type, 20 samples belong to Mixed CaMgCl type, and 3 samples belong to CaCl2 type. It can be accredited due to weathering and recharge mechanism, evaporation processes, and reverse ion exchange. Gibbs diagram shows that rock water interaction controls the hydrochemistry of groundwater resources of the study area. Saturation Index (SI) result indicated the saturation of calcite, dolomite, gypsum, geothite, and hematite mineral due their positive SI values. The principal component analysis (PCA) results possess a total variability of 80.69% signifying the anthropogenic and geogenic source of contamination. The results of the exposure-health-risk-assessment method for measuring As reveal significant potential non-carcinogenic risk (HQ), exceeding the threshold level of (> 1) for children in the study area. Water quality assessment results shows that 24 samples were not suitable for drinking purposes.

Covid-19 has triggered a massive global challenge with 1,576,069 overall confirmed cases, 1,545,429 recovered cases, and 30,640 deaths across Pakistan. Epidemiological models have always played an important role in understanding the dynamics of such infectious diseases. The severity of Covid-19 infection depends on several factors such as immune system and virus variants. Although detailed epidemiological models which consider these factors are generally more accurate, their complexity limits their application due to the unavailability of comprehensive historical data. Therefore, in this paper, we proposed a Susceptible-Non-severely Infected-Severely Infected-Recovered-Deceased model, for the prediction of Covid-19 infections. The proposed model broadly classifies Covid-19 infections into non-severe and severe infections. This classification is based on the overall effect of virus variants and individual immune systems. The important epidemiological proprieties of the model such as equilibrium points, stabilities and bifurcation analysis are discussed. The model is fitted to the Covid-19 data of Pakistan to predict the non-severe and severe infections over the next four months. The comparison of predicted and actual infections shows the forecasting efficiency of the model. Moreover, the prediction of a severely-infected population in the upcoming months can be of significant help to policy-makers in the efficient management of hospitalization services.

Abstract Misuse of antibiotics leads to the worldwide spread of antibiotic resistance, which motivates scientists to create new antibiotics. The recurring UTI due to antibiotics-resistant microorganism’s challenges scientists globally. The biogenic nanoparticles have the potential to meet the escalating requirements of novel antimicrobial agents. The green synthesis of nanoparticles (NPs) gained more attention due to their reliable applications against resistant microbes. The current study evaluates the biogenic ZnO NPs of Mentha piperata extract against resistant pathogens of urinary tract infections by agar well diffusion assay. The biogenic ZnO NPs revealed comparatively maximum inhibition in comparison to synthetic antibiotics against two bacterial strains (Proteus mirabilis, Pseudomonas aeruginosa) and a fungal strain (Candida albicans).The synthesized biogenic ZnO NPs alone revealed maximum activities than the combination of plant extract (PE) and ZnO NPs, and PE alone. The physiochemical features of ZnO NPs characterized through UV–Vis spectroscopy, FTIR, XRD, SEM, and EDX. The UV–Vis spectroscopy revealed 281.85 nm wavelengths; the XRD pattern revealed the crystalline structure of ZnO NPs. The FTIR analysis revealed the presence of carboxylic and nitro groups, which could be attributed to plant extract. SEM analysis revealed spherical hollow symmetry due to electrostatic forces. The analysis via EDX confirmed the presence of Zn and oxygen in the sample. The physiochemical features of synthesized ZnO NPs provide pivotal information such as quality and effectiveness. The current study revealed excellent dose-dependent antimicrobial activity against the pathogenic isolates from UTI-resistant patients. The higher concentration of ZnONPs interacts with the cell membrane which triggers oxidative burst. They may bind with the enzymes and proteins and brings epigenetic alteration which leads to membrane disruption or cell death.

Abstract Drought is one of the most important wheat production limiting factor, and can lead to severe yield losses. This study was designed to examine the effect of drought stress on wheat physiology and morphology under three different field capacities (FC) viz. 80% (control), 50% (moderate) and 30% (severe drought stress) in a diverse collection of wheat germplasm including cultivars, landraces, synthetic hexaploid and their derivatives. Traits like grain weight, thousand grain weight and biomass were reduced by 38.23%, 18.91% and 26.47% respectively at 30% FC, whereas the reduction rate for these traits at 50% FC were 19.57%, 8.88% and 18.68%. In principal component analysis (PCA), the first two components PC1 and PC2 accounted for 58.63% of the total variation and separated the cultivars and landraces from synthetic-based germplasm. Landraces showed wide range of phenotypic variations at 30% FC compared to synthetic-based germplasm and improved cultivars. However, least reduction in grain weight was observed in improved cultivars which indicated the progress in developing drought resilient cultivars. Allelic variations of the drought-related genes including TaSnRK2.9-5A, TaLTPs-11, TaLTPs-12, TaSAP-7B-, TaPPH-13, Dreb-B1 and 1fehw3 were significantly associated with the phenological traits under drought stress in all 91 wheats including 40 landraces, 9 varieties, 34 synthetic hexaploids and 8 synthetic derivatives. The favorable haplotypes of 1fehw3, Dreb-B1, TaLTPs-11 and TaLTPs-12 increased grain weight, and biomass. Our results iterated the fact that landraces could be promising source to deploy drought adaptability in wheat breeding. The study further identified drought tolerant wheat genetic resources across various backgrounds and identified favourable haplotypes of water-saving genes which should be considered to develop drought tolerant varieties.

Abstract Diabetic retinopathy (DR) is a diabetes complication that can cause vision loss among patients due to damage to blood vessels in the retina. Early retinal screening can avoid the severe consequences of DR and enable timely treatment. Nowadays, researchers are trying to develop automated deep learning-based DR segmentation tools using retinal fundus images to help Ophthalmologists with DR screening and early diagnosis. However, recent studies are unable to design accurate models due to the unavailability of larger training data with consistent and fine-grained annotations. To address this problem, we propose a semi-supervised multitask learning approach that exploits widely available unlabelled data (i.e., Kaggle-EyePACS) to improve DR segmentation performance. The proposed model consists of novel multi-decoder architecture and involves both unsupervised and supervised learning phases. The model is trained for the unsupervised auxiliary task to effectively learn from additional unlabelled data and improve the performance of the primary task of DR segmentation. The proposed technique is rigorously evaluated on two publicly available datasets (i.e., FGADR and IDRiD) and results show that the proposed technique not only outperforms existing state-of-the-art techniques but also exhibits improved generalisation and robustness for cross-data evaluation.

Groundwater quality was investigated in three urban semi-arid multi-industrial metropolitan areas i.e. (Hayatabad Industrial Estate, Peshawar (HIEP), Gadoon Industrial Estate, Swabi (GIES) and Hattar Industrial Estate, Haripur (HIEH). The main aim of the study was to determine their physicochemical parameters, potentially harmful elements (PHEs) concentration, pollution sources and public health risks in semi-arid multi-industrial metropolitan areas of Khyber Pakhtunkhwa (KPK), Pakistan. The physicochemical parameters (pH, TDS and EC), PHEs (Cd, Zn, Pb, Cr and Ni) concentrations and Mg in drinking water sources were found within the permissible limits, except Fe, which exceeded the World Health Organization (WHO) acceptable limit. Among PHEs, Zn had the highest contribution rates of 69.6%, 58.2% and 67.64% in HIEP, GIES and HIEH, respectively, while Cd showed the lowest contribution rates (3.15%, 1.98% and 2.06%) for HIEP, GIES and HIEH respectively. Principal component analysis (PCA) showed significant correlations between parameters, with contributions of industrial effluents and wastewater discharge (46.81%), mixed sources (34.05%) and geo-genic sources (19.14%) for drinking water in the study area. The carcinogenic risk (CR) for Cd, Cr, Ni and Pb, were found within the acceptable threshold value of 1 × 10−4. This study suggests that urban groundwater should also be regularly monitored for PHEs contamination as over-extraction, industrialization and informal E-waste recycling events surges the public health risks globally, facing related environmental contamination difficulties of the urban groundwater.

Smart grid is the primary stakeholder in smart cities integrated with modern technologies as the Internet of Things (IoT), smart healthcare systems, industrial IoT, renewable energy, energy communities, and the 6G network. Smart grids provide bidirectional power and information flow by integrating many IoT devices and software. These advanced IOTs and cyber layers introduced new types of vulnerabilities and could compromise the stability of smart grids. Some anomalous consumers leverage these vulnerabilities, launch theft attacks on the power system, and steal electricity to lower their electricity bills. The recent developments in numerous detection methods have been supported by cutting-edge machine learning (ML) approaches. Even so, these recent developments are practically not robust enough because of the limitations of single ML approaches employed. This research introduced a stacked ensemble method for electricity theft detection (ETD) in a smart grid. The framework detects anomalous consumers in two stages; in the first stage, four powerful classifiers are stacked and detect suspicious activity, and the output of these consumers is fed to a single classifier for the second-stage classification to get better results. Furthermore, we incorporate kernel principal component analysis (KPCA) and localized random affine shadow sampling (LoRAS) for feature engineering and data augmentation. We also perform comparative analysis using adaptive synthesis (ADASYN) and independent component analysis (ICA). The simulation findings reveal that the proposed model outperforms with 97% accuracy, 97% AUC score, and 98% precision.

The Distributed Renewable Energy Sources (DRESs) integrate hybrid microgrid and prosumer activities that constitute a dynamic system characterized by unknown network parameters. The dynamic system faces challenges, such as intermittent power supply due to low inertia, renewable intermittence, plug-and-play prosumer activities, network topology variations, and a lack of constraint handling. These complexities pose significant issues in designing effective control for frequency regulation and consensus-based economic load dispatch (ELD) within DRES to meet varying load demands. To address the above challenges, this research employs a machine learning-based distributed multiagent consensus design that offers a rapid and robust approach, mitigating the limitations associated with the Distributed Average Integral (DAI) control design. The proposed multiagent scheme empowers the successful implementation of ELD and frequency regulation, accommodating the intermittent DRES, diverse network topologies, and the dynamic plug-and-play activities of prosumers. Moreover, an optimization-based DAI tuning model is introduced to overcome tuning limitations. Intelligent renewable energy agents are trained through machine learning-based regression models that use root mean square error metrics for performance evaluations. The intelligent agents employ DAI control to overcome inherent limitations. The effectiveness of the machine learning-based DAI is thoroughly evaluated using the DRES-based IEEE 14-bus hybrid microgrid system. The quantitative results prove its efficacy in addressing the complex challenges of integrated microgrid dynamics.

The surging electricity demand in Pakistan has led to frequent blackouts, prompting government initiatives to expand power plant capacities and improve the national grid. The government prioritizes integrating large-scale renewable energy sources, such as wind and solar power, to reduce dependence on conventional power plants. However, the intermittency of renewables leads to forecasting errors, requiring extra power reserves from conventional units, thereby escalating operational costs and CO2 emissions. The country currently utilizes a manual mechanism for power balancing operations, overlooking critical grid constraints of the transmission line loadings. In such conditions, injecting large-scale power from renewables can lead to significant fluctuations in line power flows, risking transmission line loadings and compromising the system’s secure operation. Hence, this paper has developed an automatic generation control (AGC) model for the highly wind-integrated power system to alleviate line congestions in the network and enhance the economic operation of the system. The study utilizes the Pakistan power system as a case study to simulate the proposed model. The developed real-time power dispatch strategy for the AGC system considers the constraints of the transmission line to avoid congestion. It integrates wind energy as operating reserves to enhance the economic operation of the system. When managing line congestion, it identifies overloaded bus lines and adjusts power regulation accordingly while compensating for shortfalls by augmenting transmitted power from regional grid stations. However, it maintains a constant dispatch ratio without line overloads, aligned with generation capacities. Additionally, the strategy integrates reserve power from the wind power plant and traditional generating units to further improve economic operations. Simulations have been conducted using PowerFactory software, employing the eight-bus and five-machine models to replicate the characteristics of the Pakistan power system. The results demonstrate the effectiveness of the proposed AGC design in mitigating transmission line congestion of power systems that are heavily integrated with wind energy sources while simultaneously ensuring the economic operation of generating units.

In this article, we address the challenge of solving the nonlinear fractional Burger’s KdV equation, time-fractional Burger’s equation, and the fractional modified Burger’s equation. This is achieved by employing the Caputo and conformable derivatives. To tackle these equations, we introduce a new numerical method which is the combination of the local fractional Mohand transform and the Adomian decomposition method. This choice is driven by its straightforward methodology and reduced computational complexity. Moreover, to demonstrate the versatility of this technique, we provide several illustrative examples along with their corresponding exact or approximate solutions. These solutions are accompanied by graphical representations, further enhancing the clarity of the presented approach.

The producing fields often observe early decline due to many misapprehended factors concerning structural interpretation, facies identification, and proper estimation of geological properties. The accuracy of the estimation of these characteristics is critical for enhanced recovery. An integrated approach based on well identified potential lithofacies distribution in relation to seismic trace responses and accurate fluid estimation is vital. In the present study, gas-bearing sands are appraised for their reservoir characteristics within a complex anticline structure. The faulted anticline's hanging wall provided suitable locations for optimum gas entrapment; however, its connection with the footwall through lateral ramps allows the aquifer's early encroachment into the reservoir. For enhanced recovery, the combination of well-derived petrophysical parameters with seismic extracted responses provided insight into the producing facies with quantitative fluids identification using fluid replacement modeling (FRM) and their amplitude variation with offset (AVO) responses. The reliable AVO responses of substituted fluids comprising 85% gas with 15% brine are observed for identified potential sands, classifying sands as class-II. Similarly, the intercept (A), gradient (B), and product (A*B) of angle dependent seismic traces were mapped within the Pab Formation and showed amplitude anomalies for porous channelized gas-bearing sands. Finally, crossplotting intercept-gradient volumes differentiated the gas-bearing sands and precisely demarcated the identified gas sands throughout the field, with confirmation at producing well locations. Hence, the integrated assessment of the outcomes resulting from structural interpretation, petrophysical evaluation, and seismic trace valuation can be readily employed for distinguishing the producing sand facies in complex structures and demarcating risk-efficient zones.

Vector quantization (VQ) is a block coding method that is famous for its high compression ratio and simple encoder and decoder implementation. Linde–Buzo–Gray (LBG) is a renowned technique for VQ that uses a clustering-based approach for finding the optimum codebook. Numerous algorithms, such as Particle Swarm Optimization (PSO), the Cuckoo search algorithm (CS), bat algorithm, and firefly algorithm (FA), are used for codebook design. These algorithms are primarily focused on improving the image quality in terms of the PSNR and SSIM but use exhaustive searching to find the optimum codebook, which causes the computational time to be very high. In our study, our algorithm enhances LBG by minimizing the computational complexity by reducing the total number of comparisons among the codebook and training vectors using a match function. The input image is taken as a training vector at the encoder side, which is initialized with the random selection of the vectors from the input image. Rescaling using bilinear interpolation through the nearest neighborhood method is performed to reduce the comparison of the codebook with the training vector. The compressed image is first downsized by the encoder, which is then upscaled at the decoder side during decompression. Based on the results, it is demonstrated that the proposed method reduces the computational complexity by 50.2% compared to LBG and above 97% compared to the other LBG-based algorithms. Moreover, a 20% reduction in the memory size is also obtained, with no significant loss in the image quality compared to the LBG algorithm.

In recent decades, heavy metals (HMs) have emerged as a global health concern. Unfortunately, in Pakistan, there is a general lack of awareness regarding the potential health risks associated with HMs pollution among automobile workers. Herein, we investigated the concentration of heavy metals such as lead (Pb), cadmium (Cd), and chromium (Cr) among automobile workers who were occupationally exposed in Mingora City, Khyber Pakhtunkhwa, Pakistan. Three different automobile groups, i.e., battery recyclers, spray painters, and mechanics were studied in detail. A total of 40 blood samples were collected from automobile workers groups while 10 blood samples were collected as control individuals from different locations in the study area. We investigated heavy metals concentration with a standard method using an atomic absorption spectrometer AAS (PerkinElmer Analyst 700, United States). Based on our findings, the battery recycling group displayed the most elevated Pb levels (5.45 ± 2.11 μg/dL), exceeding those of both the spray painters’ group (5.12 ± 1.98 μg/dL) and the mechanics’ group (3.79 ± 2.21 μg/dL). This can be attributed to their higher exposure to Pb pollution resulting from the deterioration, dismantling, grinding, or crushing of old batteries. In the context of chromium (Cr) exposure, a similar trend was observed among the battery recycling group, as well as the spray painters and mechanics groups. However, in the case of cadmium (Cd), the mechanics’ group exhibited the highest level of exposure (4.45 ± 0.65 μg/dL), surpassing the battery recycling group (1.17 ± 0.45 μg/dL) and the spray painters’ group (1.35 ± 0.69 μg/dL), which was attributed to their greater exposure to welding fumes and other activities in their workplace. We believe that our findings will encourage regulatory measures to improve the health of automobile workers. However, further work is needed to determine various health-related issues associated with heavy metal exposure among automobile workers.

Electricity theft damages power grid infrastructure and is also responsible for huge revenue losses for electric utilities. Integrating smart meters in traditional power grids enables real-time monitoring and collection of consumers’ electricity consumption (EC) data. Based on the collected data, it is possible to identify the normal and malicious behavior of consumers by analyzing the data using machine learning (ML) and deep learning methods. This paper proposes a deep learning-based meta-learner model to distinguish between normal and malicious patterns in EC data. The proposed model consists of two stages. In Fold-0, the ML classifiers extract diverse knowledge and learns based on EC data. In Fold-1, a multilayer perceptron is used as a meta-learner, which takes the prediction results of Fold-0 classifiers as input, automatically learns non-linear relationships among them, and extracts hidden complicated features to classify normal and malicious behaviors. Therefore, the proposed model controls the overfitting problem and achieves high accuracy. Moreover, extensive experiments are conducted to compare its performance with boosting, bagging, standalone conventional ML classifiers, and baseline models published in top-tier outlets. The proposed model is evaluated using a real EC dataset, which is provided by the Energy Informatics Group in Pakistan. The model achieves 0.910 ROC-AUC and 0.988 PR-AUC values on the test dataset, which are higher than those of the compared models.

With the rapid advancement of technology and multimedia systems, ensuring security has become a critical concern. Connected and Autonomous Vehicles (CAVs) are vulnerable to various hacking techniques, including jamming and spoofing. Global Positioning System (GPS) location spoofing poses a significant threat to CAVs, compromising their security and potentially endangering pedestrians and drivers. To address this issue, this research proposes a novel methodology that uses deep learning (DL) algorithms, such as Convolutional Neural Networks (CNN), and machine learning (ML) algorithms, such as Support Vector Machine (SVM), to protect CAVs from GPS location spoofing attacks. The proposed solution is validated using real-time simulations in the CARLA simulator, and extensive analysis of different learning algorithms is conducted to identify the most suitable approach across three distinct trajectories. Training and testing data include GPS coordinates, spoofed coordinates, and localization algorithm values. The proposed machine learning algorithm achieved 99% and 96% accuracy for the best and worst case scenarios, respectively. In case of deep learning, it achieved as high as 99% for best and 82% for the worst case scenario.

Colorectal cancer (CRC) is the third most common cause of cancer-related deaths in the United States and is anticipated to cause another 52,580 deaths in 2023. The standard medical procedure for screening and treating colorectal disease is a colonoscopy. By effectively examining the colonoscopy to identify precancerous polyps early and remove them before they become cancerous, CRC mortality can be lowered significantly. Manual colonoscopy examination for precancerous polyps detection is time-consuming, tedious, and prone to human error. Automatic segmentation and analysis could be fast and practical; however, existing automated methods fail to attain adequate accuracy in polyps segmentation. Moreover, these methods do not assess the risk of detected polyps. In this paper, we proposed an autonomous CRC screening method to detect polyps and assess their potential threats. The proposed method utilized DoubleU-Net for polyps segmentation and Vision Transformer (ViT) for classifying them based on their risks. The proposed method has achieved a mean dice-coefficient of 0.834 and 0.956 in segmentation for the Endotech challenge and Kvasir-SEG dataset, accordingly outperforming the existing state-of-the-art polyps segmentation. Then, this method classified the segmented polyps as hyper-plastic or adenomatous with 99% test accuracy.

Vehicular Adhoc Networks (VANETs) are an emerging and promising technology that enables vehicles to communicate with roadside units (RSUs) and other vehicles. VANETs contribute to improved traffic efficiency, accident safety, and entertainment services for passengers and drivers. However, VANETs face limitations in areas with intermittent connectivity. To address this scenario, researchers have proposed a specialized use-case known as intermittently-connected-vehicular delay-tolerant-networks (ICV-DTNs), which are a subset of delay-tolerant-networks (DTNs). Security is less explored area compare to routing. Malicious nodes pose significant threats by launching selective packet drops, fake/bogus packets, and flood attacks, depleting limited resources such as bandwidth and node buffer space. Consequently, these attacks result in low message delivery ratios and high message loss ratios. Among these attacks, flood attacks are particularly challenging in ICV-DTNs/Flying Adhoc Networks/Internet of Drones. Various algorithms have been proposed to mitigate flood attacks, but previous approaches have exhibited shortcomings. Firstly, previously proposed algorithms lack efficiency in terms of detection time and accuracy. Secondly, the extent of resource waste or savings after implementing these schemes has not been adequately demonstrated, with no simulation results quantifying the amount of buffer consumption. Additionally, prior algorithms lack a comprehensive definition of flood attacks, which represents a critical research question in this field. To address these gaps, this article not only proposed a unique taxonomy of the flooding attacks but also evaluate various algorithms on diverse parameters. The article also contribute open research areas for the community to investigate the nitty gritty of flooding attacks in ICV-DTNs.

Abstract Automatic COVID-19 detection using chest X-ray (CXR) can play a vital part in large-scale screening and epidemic control. However, the radiographic features of CXR have different composite appearances, for instance, diffuse reticular-nodular opacities and widespread ground-glass opacities. This makes the automatic recognition of COVID-19 using CXR imaging a challenging task. To overcome this issue, we propose a densely attention mechanism-based network (DAM-Net) for COVID-19 detection in CXR. DAM-Net adaptively extracts spatial features of COVID-19 from the infected regions with various appearances and scales. Our proposed DAM-Net is composed of dense layers, channel attention layers, adaptive downsampling layer, and label smoothing regularization loss function. Dense layers extract the spatial features and the channel attention approach adaptively builds up the weights of major feature channels and suppresses the redundant feature representations. We use the cross-entropy loss function based on label smoothing to limit the effect of interclass similarity upon feature representations. The network is trained and tested on the largest publicly available dataset, i.e., COVIDx, consisting of 17,342 CXRs. Experimental results demonstrate that the proposed approach obtains state-of-the-art results for COVID-19 classification with an accuracy of 97.22%, a sensitivity of 96.87%, a specificity of 99.12%, and a precision of 95.54%.

Abstract Vegetation structures and dynamics are the result of interactions between abiotic and biotic factors in an ecosystem. The present study was designed to investigate vegetation structure and species diversity along various environmental variables in the Yakhtangay Hills of the Hindu-Himalayan Mountain Pakistan, by using multivariate statistical analysis. Quadrat quantitative method was used for the sampling of vegetation. PC-ORD version 5 software was used to classify the vegetation into different plants communities using cluster analysis. The results of regression analysis among various edaphic variables shows that soil organic matter, total dissolved solids, electrical conductivity, CaCO3 and moisture contents shows a significant positive correlation with species abundance, while the soil pH has inverse relationship with plant species abundance. Similarly, species richness increases with increase in soil organic matter, CaCO3 and moisture contents, while decrease with increase in soil pH, total dissolved solids and electrical conductivity (p < 0.05). The vegetation was classified into four major plant communities and their respective indicators were identified using indicator species analysis. Indicator species analysis reflects the indicators of the study area are mostly the indicators to the Himalayan or moist temperate ecosystem. These indicators could be considered for micro-habitat conservation and respective ecosystem management plans not only in the study area but also in other region with similar sort of environmental conditions.

Accelerated mining activities have increased water contamination with potentially toxic elements (PTEs) and their associated human health risk in developing countries. The current study investigated the distribution of PTEs, their potential sources and health risk assessment in both ground and surface water sources in mining and non-mining areas of Khyber Pakhtunkhwa, Pakistan. Water samples (n = 150) were taken from selected sites and were analyzed for six PTEs (Ni, Cr, Zn, Cu, Pb and Mn). Among PTEs, Cr showed a high mean concentration (497) μg L−1, followed by Zn (414) μg L−1 in the mining area, while Zn showed the lowest mean value (4.44) μg L−1 in non-mining areas. Elevated concentrations of Ni, Cr and a moderate level of Pb in ground and surface water of Mohmand District exceeded the permissible limits set by WHO. Multivariate statistical analyses showed that the pollution sources of PTEs were mainly from mafic-ultramafic rocks, acid mine drainage, open dumping of mine wastes and mine tailings. The hazard quotient (HQ) was the highest for children relative to that for adults, but not higher than the USEPA limits. The hazard index (HI) for ingestions of all selected PTEs was lower than the threshold value (HIing < 1), except for Mohmand District, which showed a value of HI >1 in mining areas through ingestion. Moreover, the carcinogenic risk (CR) values exceeded the threshold limits for Ni and Cr set by the USEPA (1.0E-04–1.0E-06). In order to protect the drinking water sources of the study areas from further contamination, management techniques and policy for mining operations need to be implemented. HIGHLIGHTS Elevated Ni, Cr and Pb levels exceeded the WHO permissible limits in ground and surface water.; Mafic-ultramafic rocks, acid mine drainage, mine wastes and mine tailings are the main primary factors influencing the distribution of PTEs and their contamination.; Health risk was relatively high for children than for adults in mining and non-mining areas.; Management policies and monitoring strategies need to be implemented for mining operations.;

The present study was the first comprehensive investigation of genetic mutation and expression levels of the p53 signaling genes in cutaneous melanoma through various genetic databases providing large datasets. The mutational landscape of p53 and its signaling genes was higher than expected, with TP53 followed by CDKN2A being the most mutated gene in cutaneous melanoma. Furthermore, the expression analysis showed that TP53 , MDM2 , CDKN2A , and TP53BP1 were overexpressed, while MDM4 and CDKN2B were under-expressed in cutaneous melanoma. Overall, TCGA data revealed that among all the other p53 signaling proteins, CDKN2A was significantly higher in both sun and non-sun-exposed healthy tissues than in melanoma. Likewise, MDM4 and TP53BP1 expressions were markedly greater in non-sun-exposed healthy tissues compared to other groups. However, CDKN2B expression was higher in the sun-exposed healthy tissues than in other tissues. In addition, various genes were expressed significantly differently among males and females. In addition, CDKN2A was highly expressed in the SK-MEL-30 skin cancer cell line, whereas, Immune cell type expression analysis revealed that the MDM4 was highly expressed in naïve B-cells. Furthermore, all six genes were significantly overexpressed in extraordinarily overweight or obese tumor tissues compared to healthy tissues. MDM2 expression and tumor stage were closely related. There were differences in gene expression across patient age groups and positive nodal status. TP53 showed a positive correlation with B cells, MDM2 with CD8+ T cells, macrophages and neutrophils, and MDM4 with neutrophils. CDKN2A/B had a non-significant correlation with all six types of immune cells. However, TP53BP1 was positively correlated with all five types of immune cells except B cells. Only TP53, MDM2 , and CDKN2A had a role in cutaneous melanoma-specific tumor immunity. All TP53 and its regulating genes may be predictive for prognosis. The results of the present study need to be validated through future screening, in vivo, and in vitro studies.

Land use has a great impact on soil dynamics. The soils of various land use systems in Central Karakoram have been under immense pressure in the recent past due to certain anthropogenic activities such as land use practices and land use cover changes. These influences have an impact on the spatial distribution of metallic elements (MEs) in the soils of various land uses. Herein, we investigated the occurrence of the MEs, copper (Cu), zinc (Zn), and nickel (Ni), in soils of various land uses such as the permafrost, pasture, forest, and agricultural lands of the Central Karakorum region. The MEs were extracted in exchangeable, adsorbed, organically bound, carbonated, precipitated, and residual forms. The concentrations of MEs showed a significant dependence on the extraction method used, and the extraction trend followed the order of EDTA > HNO3 > KNO3 > NaOH > H2O. Zn showed the highest concentration compared to Ni and Cu in all extractions, whereas the land uses’ ME concentration followed the order of agricultural land > permafrost > forest > pasturelands. The highest values of total Zn, Ni, and Cu were 712 ± 01 mg/kg, 656 ± 02 mg/kg, and 163 ± 02 mg/kg, respectively, in agricultural soil. The ME concentration showed significant variations between different land uses, and the highest concentration was noted in agricultural soil. Zn was found to be a dominant ME compared to Ni and Cu. We believe this effort will provide opportunities for scholars to investigate MEs around the globe.

Renewable energy sources (RESs) are becoming more prevalent as a source of clean energy, and their integration into the power market is speeding up. The fundamental reason for this is the growing global concern about climate change. However, their weather-dependent and uncertain nature raise questions about grid reliability particularly, when photovoltaics (PVs) and wind turbines (WTs) technologies are used. As a result, rationally managing Energy Storage Systems (ESSs) under the virtual power plant (VPP) setting is being encouraged as a way of minimizing the impact of the uncertain nature of renewable energies. A VPP is comparatively a new concept that aggregates the capacities of dispatchable and non-dispatchable energy sources, electrical loads, and energy storage systems for the purpose of improving energy supply and demand imbalance. It enables individual consumers and producers to participate in the power markets. In this study, a new market-based (MB)-VPP operational planning model is designed and developed with the aim to evaluate the optimal active power dispatched by (WT, PV, and ESS) operating in the day-ahead power market to maximize the social welfare (SW) of the market. SW can be described as the maximization of the consumer’s benefit function minus the cost of energy generation. The optimization process was carried out by using a scenario-based approach to model the uncertainties of renewable energy sources (i.e, WTs & PVs) and load demand. The proposed model and method performance is validated by simulation studies on a 16-bus UK generic distribution system (UKGDS). The simulation results reveal that the proposed approach maximizes overall system social welfare. The capacity of total active power dispatched by (WT, PV, and ESS) has a positive impact on the VPP profit maximization. This empirical study could be used as a reference baseline model for other energy services providers interested in conducting similar research in the future.

The losses in the power system vary the gap between energy supply and demand. Among these losses, the distribution system has major contributions compared to the transmission system. This paper thoroughly examines the PESCO distribution losses and implements a practical approach that forties in the loss’s minimization. Using the bifurcation and restoration strategies, the PESCO distribution system can be well-organized and an effective system can be designed. The proposed approach also helps in estimating the entailed capital investments and the rate of return over time. Both the HT (High Tension) and LT (Low Tension) distribution systems are considered for observation and the proposed systems are endorsed. Computer-based software, such as ELR (Energy Loss Reduction) and CADPAW (Computer-Aided Distribution Planning Work) is exploited to measure the results of both the proposed and existing system. After the restoration of a particular system, recommendations are concluded. The proposed approach applies to any existing power system.