Search

Abstract Rifampicin-resistant tuberculosis (RR-TB) is a critical issue with significant implications for patient care, public health, and TB control efforts that necessitate comprehensive strategies for detection. This study presents a novel point-of-care diagnostic tool for RR-TB detection employing a peptide nucleic acid (PNA)-paper-based sensor combined with isothermal recombinase polymerase amplification (RPA). The sensor targets mutations in codons 516, 526, and 531 of the rpoB gene, the top three common mutations associated with rifampicin-resistant strains. PNA probes specifically recognised wild-type sequences, generating a visual signal through a reverse hybridisation assay. The absence of a signal was observed when the mutant strains were detected because of the inability to bind the mutant sequence. Our proof-of-concept assay displayed high accuracy (100% for detecting mutations at codons 516, 526, and 531), a short turnaround time (110 min), no cross-reactivity with other bacterial pathogens, and ultrasensitivity. This PNA-paper-based sensor model can be a valuable diagnostic tool for RR-TB detection, providing an accessible diagnostic platform that can be advantageous in resource-limited settings where sophisticated laboratory infrastructure may be lacking.

Abstract The pulp and paper manufacturing wastewater is as complicated as any other industrial effluent. A promising approach to treating water is to combine photocatalysis and membrane processes. This paper demonstrates a novel photocatalytic membrane technique for solar-powered water filtration. The method is based on creating green-prepared TiO2, and MnO2 nanoparticles (NPs) using Pomegranate peels and Seder leaf extracts and incorporation into polyvinylidene chloride to produce a novel water purification system that combines semiconductor photocatalysis with membrane filtration. The prepared heterostructure of the TiO2/MnO2 nanocomposite membrane provides photogenerated charge separation. To ensure chemical bonding at the membrane surface, Raman and Fourier transform infrared spectroscopy (FT-IR) were employed. The modified membrane’s hydrophilicity and roughness increased significantly. Additionally, the modified nanocomposite membrane’s porosity was measured. The integrated process demonstrated much higher removal of humic acid and high efficiency of wastewater treatment for pulp and paper. In sunlight, humic acid removal was 98% from synthetic wastewater. While using the produced membrane on pulp and paper effluent, these studies indicate that: in the dark, the removal was 50%, while in the sunlight, the removal increased to 70%, with a reduction in the COD from 1500 mg/L to 247 mg/L. Additionally, the TDS decreased from 1630 to 452 ppt in the sunlight. This research sheds light on how solar energy can clean wastewater from the pulp and paper industry while improving membrane separation. Also, an alternative source to sunlight was used to manufacture a photocatalytic membrane with high efficiency for wastewater treatment and an inexpensive price.

Abstract This research investigates the pulp and paper industry's transition to sustainability by valorizing unused roadside and natural grasses for paper production. Large-scale production from residual grass poses multifaceted challenges, requiring collaboration across stakeholders, from biomass collection to manufacturing. To understand key drivers and barriers within this complex system, experts from various fields, including local farmers, researchers, policymakers, and industry executives were interviewed, leading to the development of a Fuzzy Cognitive Map (FCM). The analysis explores various scenarios to assess how socio-economic, technological, and political factors influence the transition to low-carbon practices. These scenarios highlight the effects of varying levels of technology development, economic conditions, and policy support on the transition's progress and outcomes. Results show that the system is highly sensitive to shifts in socio-economic and political conditions. Political interventions play a crucial role, especially during energy crises and increased public demand for sustainable solutions. Grass-based paper production is seen as a viable pathway, but challenges such as the economic feasibility of emerging technologies remain. We recommend targeted policies to improve the economic viability of grass-based products and optimize biomass allocation between energy and bio-based products, ensuring a more balanced and sustainable transition.

Abstract This manuscript proposes the Jellyfish Search Optimization (JSO) algorithm-based Fractional Order Proportional-Integral-Derivative (FOPID) controller tuning for a paper machine headbox. The novelty of this method lies in integrating the JSO technique for optimizing the parameters of the FOPID controller to monitor and control headbox pressure and stock level efficiently and effectively. The JSO algorithm ensures optimal tuning of controller parameters by minimizing error indices such as Integral of Squared Error (ISE), Integral of Time Absolute Error (ITAE), and Integral of Absolute Error (IAE). Simulations conducted on the MATLAB/Simulink platform demonstrate that the FOPID controller tuned using JSO achieves superior performance compared to conventional PI (Proportional-Integral) and PID (Proportional-Integral-Derivative) controllers. Specifically, the JSO-tuned FOPID controller exhibited a 25% reduction in rise time, a 30% improvement in settling time, and a 20% decrease in overshoot when compared to the PID controller. Furthermore, comparative analyses with other optimization techniques, including Moth Flame Optimization (MFO), Ant Lion Optimization (ALO), and Elephant Herding Optimization (EHO), reveal that the JSO algorithm provides higher accuracy and stability in diverse operating conditions. This study underscores the efficacy of the JSO-tuned FOPID controller as a robust solution for complex industrial applications, such as paper machine headbox systems, and highlights its potential to enhance process efficiency and control precision.

Abstract Cervical cancer, while preventable through screening and treatment of cervical precancer, remains a global challenge with a disproportionately high burden of disease in resource-limited settings, especially in low- and middle-income countries (LMICs). Lack of affordable, easy-to-use screening and diagnostic tests contributes to this disparity. Most commercially available tests are not appropriate for use in LMICs due to resource constraints. Specifically, HPV mRNA and oncoprotein tests that have high specificity for cervical precancer and cancer require complex sample preparation protocols and expensive instrumentation. To address these limitations, an HPV E7 oncoprotein assay for HPV16, 18, and 45 was developed that is appropriate for use at the point of care. The assay is paper-based, involves only five simple steps, and does not require instrumentation. A clinically relevant limit of detection was demonstrated with cellular samples. Additionally, clinical performance was demonstrated with a small pilot study (n = 19), in which the HPV E7 paper-based assay was found to have 95% accuracy when compared to histopathologic diagnosis of cervical intraepithelial neoplasia grade 2 or more severe (CIN2+). With further clinical validation, this assay could enable highly specific point-of-care testing for cervical precancer and cancer that is instrumentation-free, affordable, and ideal for use in resource-limited settings.

Abstract To ensure the fairness and trustworthiness of machine learning (ML) systems, recent legislative initiatives and relevant research in the ML community have pointed out the need to document the data used to train ML models. Besides, data-sharing practices in many scientific domains have evolved in recent years for reproducibility purposes. In this sense, academic institutions’ adoption of these practices has encouraged researchers to publish their data and technical documentation in peer-reviewed publications such as data papers. In this study, we analyze how this broader scientific data documentation meets the needs of the ML community and regulatory bodies for its use in ML technologies. We examine a sample of 4041 data papers of different domains, assessing their coverage and trends in the requested dimensions and comparing them to those from an ML-focused venue (NeurIPS D&B), which publishes papers describing datasets. As a result, we propose a set of recommendation guidelines for data creators and scientific data publishers to increase their data’s preparedness for its transparent and fairer use in ML technologies.

Abstract Due to the scarcity of wood in some countries, it is necessary to replace it with other raw materials and at the same time use the waste material. The aim of this research is to use poppy waste straw for the efficient conversion of possible lignocellulosic materials – pulps and particleboards. Their suitability for the production of composites is assessed on the basis of selected physical or mechanical properties. Tensile strength index, burst strength index and air permeability by Gurley have been identified as critical properties of pulp made from poppy straw through two delignification methods. The better mechanical properties, i.e., tensile strength index, were achieved at 52.7 N·m/g for the sodium pulp, but the nitrate-alkali method also showed corresponding values at 45.9 N·m/g. Similar parameters to those of bagasse or similar fast-growing plants were achieved in particleboard production. The results of this research are used to evaluate poppy straw as an alternative raw material to produce biocomposites.

Abstract Slopes influenced by multiple faults are prone to large-scale landslides triggered by multi-regional failures. Understanding the failure process and sequence is essential for the sustainable development of mining operations. This paper presents a method combining InSAR monitoring and numerical simulation to analyze the failure processes of slopes affected by multiple faults. Using the 298–710 m bench in the central area of the eastern slope of the Nanfen open-pit mine as a case study, the multidimensional small baseline subset (MSBAS) technique of InSAR was employed to calculate the vertical and horizontal deformation time series in the study area, enabling an analysis of the deformation characteristics of multizone bedding sliding. Subsequently, a numerical simulation was performed to replicate the three-dimensional evolution of the multizone failure. The simulation results aligned well with field surveys and InSAR monitoring data. Furthermore, the failure sequence analysis identified critical trigger zones within the region. The findings demonstrate that the proposed method effectively identifies the critical areas and movement sequence of multi-regional failures. In this paper, the faults disrupted the connectivity between slopes, acting as the initial trigger for entire landslide. The first failure occurred in a critical area, creating space for further sliding in other regions and reducing lateral constraints in neighboring areas, eventually leading to significant deformations. Therefore, by using this method to identify potential critical areas before landslides occur, targeted mitigation measures can be implemented to reduce the risk of such events.

Abstract This study examines the performance of asymmetric three-phase distribution systems under the influence of FACT deives such as a static VAR compensator (SVC) and a unified power controller (UPC). Each suggested device’s operating principle is developed in this paper in order to provide the best model to be used in the power flow analysis. The performance of the IEEE-13 bus imbalanced distribution model is investigated using the Newton-Raphson method. To improve network asymmetry, an optimization analysis is carried out to ascertain how each proposed device will work. In this paper, the mode of operation of each device is determined every hour to flow the changing in loads according to their daily load curve. The genetic algorithm (GA) is utilized to determine the contribution of the unified flow controller to balance the loads between phases. The multi-objective function is constructed to combine the total system losses and the average voltage unbalance coefficient. The paper provides an optimal dynamic technique to optimally operate the unified power flow controller installed in the unbalanced three-phase distribution system.

Abstract In order to solve the limitations of flipped classroom in personalized teaching and interactive effect improvement, this paper designs a new model of flipped classroom in colleges and universities based on Virtual Reality (VR) by combining the algorithm of Contrastive Language-Image Pre-Training (CLIP). Through cross-modal data fusion, the model deeply combines students’ operation behavior with teaching content, and improves teaching effect through intelligent feedback mechanism. The test data shows that the similarity between video and image modes reaches 0.89, which indicates that different modal information can be effectively integrated to ensure the semantic consistency and intuitive understanding of teaching content. The minimum Kullback–Leibler (KL) divergence is 0.12, which ensures the stability of data distribution and avoids information loss. The accuracy of automatically generating feedback reaches 93.72%, which significantly improves the efficiency of personalized learning guidance. In the adaptability test of virtual scene, the frequency of scene adjustment is 2.5 times/minute, and the consistency score is stable above 8.6, ensuring the consistency of teaching goals under complex interaction. This paper aims to enhance personalized learning experience, improve teaching efficiency and autonomous learning effect through VR technology and intelligent feedback, and promote the innovation of interactive teaching mode.

Abstract This paper introduces an optimal sizing approach for battery energy storage systems (BESS) that integrates frequency regulation via an advanced frequency droop model (AFDM). In addition, based on the AFDM, a new formulation for charging/discharging of the battery with the purpose of system frequency control is presented. The studied MG system that consists of PV units, a diesel generator (DG), a combined heat and power (CHP) unit, a gas boiler, and a BESS is designed to meet the consumers’ thermal and electrical load requirements as well as system frequency regulation. In the proposed optimization model, the net present value of expansion planning costs (EPC) over the project lifetime should be minimized according to the capacity of installed BESS. The EPC consist of four components including, (i) MG operation cost pertaining to the DG, CHP units and gas boilers, (ii) value of lost load, (iii) BESS investment cost, and (iv) replacement cost of BESS, recognizing its shorter lifetime relative to the project’s lifespan. The effectiveness of the proposed method and its advantages compared other methods are demonstrated via a case study simulation. Compared to the conventional frequency droop characteristic, the utilized AFDM can reduce the total EPC while a broader range of power/frequency control capabilities of the BESS is achieved to regulate the frequency in a desired band. Furthermore, the paper examines the impact of the AFDM on the selection of battery technology.

Abstract With the wide application of hydrogen-doped natural gas (HBNG) in end users, laying pipelines in urban, comprehensive pipe corridors has become increasingly common. However, the leakage and diffusion of hydrogen-doped natural gas in confined or semi-confined spaces (e.g., utility corridors) can pose a severe safety hazard, as methane and hydrogen gas mixtures have a higher risk of explosion. Therefore, studying hydrogen-doped natural gas’s leakage and diffusion behavior in the comprehensive pipe gallery is essential to ensure its safe operation. This paper establishes a numerical model to study the diffusion law of hydrogen-doped natural gas leakage, and the concentration distribution under different conditions is analyzed. The evolution of the leakage and diffusion of hydrogen-doped natural gas under different hydrogen doping ratios, wind speeds, inlet and outlet spacing, and leakage port sizes were simulated, and the effects of these factors on gas diffusion and explosion hazard volume were discussed. In addition, the backpropagation neural network (BPNN) combined with the global optimization capability of genetic algorithm and the nonlinear mapping capability of neural network is used in this paper to provide a reliable technical means for the accurate prediction of explosion risk volume, which has important application value in the safety design of pipeline corridor and accident prevention and control. The results show that the diffusion range of gas in the pipe corridor increases significantly with the increase of hydrogen mixing ratio. When the hydrogen mixing ratio decreases from 20% to 0, the explosion volume of CH4 decreases by 12.25%. The explosion volume of H2 is close to 0. At the same time, the greater the distance between inlet and outlet, the wider the spread of the dangerous area, when the distance between inlet and outlet is reduced from 200 m to 100 m, the explosion volume of CH4 is reduced by 99.92%, and the explosion volume of H2 is reduced by 100%. In the case of emergency, the reasonable design of Distance between inlet and outlet and air flow configuration can help to quickly discharge harmful gases, ensure the safe evacuation and equipment maintenance in the pipe corridor, and have guiding significance for the ventilation design of the pipe corridor.

Abstract It is challenging to achieve high-speed and accurate multicooperation of turtle-inspired amphibious spherical robots (ASRs) in turbid water and confined spaces when the robots are underwater movement with multiple degrees of freedom (MDOF). This paper innovatively proposes a control strategy for modelling and experimental platforms that can communicate and cooperate between multiple robots. First, a novel underwater kinematic model using the unit quaternion (UQ) algorithm is proposed based on attitude interpolation to realize MDOF movement. Then, the ASRs use a camera acquisition compartment to realize underwater target recognition and tracking by adjusting their motion trajectory. Finally, multirobot cooperation and three-dimensional (3-D) movement experiments using ASRs verifies the effectiveness of the proposed cooperation mode and 3-D underwater movement according to the control strategy implemented. The control strategy and experimental results presented in this paper can inspire the efficient communication and cooperation of multiple bionic robots, which are currently popular research topics.

Abstract In recent years, a significant rise in international sudden risk events has resulted in impacts and disruptions to maritime supply chains (MSC). The resilience of maritime supply chains has garnered attention from the academic, industrial, and government sectors. The paper proposes a methodological framework based on the structural equation model (SEM), Necessary Condition Analysis (NCA), fuzzy set qualitative comparative analysis (fsQCA), and utilizes questionnaire data from the maritime industry in China to evaluate the resilience in MSC. The computational results indicate that: (1) The high resilience of MSC is the result of the synergistic interaction among multiple factors, and these factors boost MSC resilience through diverse paths; (2) There are four pathways for high MSC resilience: the ‘collaboration + carbon reduction + digitization’ path, the ‘early warning + collaboration’ path, the ‘agility + early warning’ path, and the ‘carbon reduction’ path; (3) Digitization level can play a catalytic role in increasing the resilience of MSC by helping other factors. This paper reveals the multiple routes to enhance the resilience of MSC, which can instruct MSC members to choose the correct resilience management strategies based on their existing resources and situations and can help both practitioners and researchers to understand in more detail of the various dimensions and nuances of resilience in the context of MSC.

Abstract Detecting ship targets in remote sensing images within complex scenarios faces numerous challenges. The limited feature information of small-scale targets and their random orientation angles often result in missed and false detections. To address these issues, this paper proposes a Multi-Scale Rotated Detection Network (MSRO-Net) for detecting rotated ship targets in remote sensing images. The network adopts a CNN-Transformer hybrid architecture for collaborative feature extraction and integrates our proposed Coordinate-Aware Pyramid Feature Aggregation module (CAPP). This backbone network retains the capability of local feature extraction while also connecting global context and capturing long-range dependencies. The model can gather information from any position in the sequence, extract contextual information of targets at different scales, and enhance global feature representation. Additionally, this paper proposes an Upsampling Feature Reconstruction Pyramid (ARFPN-C), based on Adaptive Rotated Convolution (ARC). This network combines ARC adaptive rotating convolution with a multi-scale feature fusion mechanism to enhance the model’s perceptual capability, addressing the issues of limited target feature information and random orientation angles. The proposed algorithm is validated on two public remote sensing image datasets, HRSC2016 and DOTA. The mAP07, mAP12 on the HRSC2016 dataset, as well as the mAP in the ship category of the DOTA dataset, show a significant advantage over other commonly used object detection algorithms, with accuracies of 90.70%, 98.98%, and 89.46%, respectively. These results further validate the accuracy and effectiveness of the proposed MSRO-Net in object detection.

Abstract This paper presents an open-source dataset intended to enhance the analysis and optimization of photovoltaic (PV) power generation in urban environments, serving as a valuable resource for various applications in solar energy research and development. The dataset comprises measured PV power generation data and corresponding on-site weather data gathered from 60 grid-connected rooftop PV stations in Hong Kong over a three-year period (2021-2023). The PV power generation data was collected at 5-minute intervals at the inverter-level. The meteorological data was collected at 1-minute intervals from an on-site weather station. The metadata was represented using the Brick schema, which simplifies data comprehension and the development of smart analytics applications. This paper provides a detailed description on the site specifications, data collection method, data records, and data validation. This dataset can be used in various applications - PV generation benchmarking, PV degradation analysis, PV fault detection, solar radiation and PV power generation forecasting, and the simulation and design of PV systems.

Abstract The existing UAV inspection images are faced with many challenges for insulator defect recognition. A new multi-resolution Context Cluster CenterNet++ model is proposed. First, this paper proposes the Context Cluster method to solve the problem of low recognition accuracy caused by non-uniform distribution of targets. The cluster region is used to identify and predict the location of the target, and the improved loss function is used to modify the cluster center. Secondly, this paper uses deformable convolution operator (DCNv2) combined with path aggregation network (PAN) to carry out deformable convolution operation on the image, and accurately predicts the regression box and key point triplet (KP), so as to improve the accurate positioning of the target position of any shape and any scale. The sensitivity of the model to target scale change and deformation is reduced, and the recognition accuracy of the model is improved. Then, Bhattacharyya distance is used to calculate the triplet prediction loss of key points and the target center point offset loss, so as to significantly improve the positioning accuracy of the same target in different frames. Finally, experiments are carried out on the MS-COCO dataset and the National Grid standardized UAV inspection insulator image dataset. Our code is at https://github.com/mengbonannan88/CC-CenterNet .

Abstract Public health emergencies are critical to people’s lives and health, economic development and social stability. Understanding how to respond correctly to public health emergencies is the focus of societal attention. This paper focuses on the tripartite entities of public health emergencies: local governments, pharmaceutical enterprises and the public. On the basis of the assumption of finite rationality, it delves into the game-theoretic interaction among these groups during such crises. By constructing an evolutionary game model, this paper analyses the dynamic adjustment process of the decision-making behaviors of these three parties, leading to the identification of evolutionarily stable strategies for the local government, pharmaceutical enterprises, and the public under different conditions. Moreover, MATLAB is used to carry out simulation experiments to analyse the influence of the local government’s reward and punishment mechanism on the strategic choices of the involved parties in the game. The research findings indicate that (1) For the tripartite entities of public health emergencies, the key for strategy choices is to reduce the gain obtained from illegal production and non-cooperation with prevention and control. (2) The strength of the initial willingness to participate has a significant effect on the evolution strategies of each subject. (3) For pharmaceutical companies and the public, the incentives and penalties of local governments can promote the former’s compliance and the latter’s cooperation in prevention and control. Based on these results, countermeasure suggestions to promote mutual collaboration among local governments, pharmaceutical enterprises, and the public to jointly respond to public health emergencies are proposed.

Abstract Power quality (PQ) disturbances, such as voltage sags, are significant issues that can lead to damage in electrical equipment and system downtime. Detecting and classifying these disturbances accurately is essential for maintaining reliable power systems. This paper introduces a novel approach to voltage sag analysis by employing wavelet packet analysis combined with energy-based feature extraction to enhance PQ monitoring. The study decomposes voltage sag signals into different frequency bands to extract key features for disturbance detection. We compare six commonly used mother wavelets (db1, db4, db10, dmey, sym5, and coif5) to identify the most suitable wavelet for voltage sag detection. The energy distribution curve analysis is used to evaluate the energy characteristics of each wavelet’s decomposition, with a focus on identifying the most effective signal features for PQ monitoring. The paper presents a thorough error analysis and compares the energy values extracted by different wavelet functions to demonstrate the reliability and accuracy of the proposed method. The results show that wavelet packet analysis significantly improves the detection and classification of voltage sag disturbances, providing a robust and efficient tool for real-time PQ monitoring. This study contributes to the development of advanced PQ monitoring systems by offering a more precise and computationally efficient method for voltage sag analysis, ultimately helping to protect electrical systems from potential damage and reducing operational costs. Wavelet packet analysis is applied as a novel feature extraction method for voltage sag detection by offering improved time-frequency analysis over traditional methods. Energy features are extracted from wavelet packet coefficients for sag identification. This work utilizes wavelet packet analysis to extract energy-based features for voltage sag detection.

Abstract Nowadays, Egypt is treating the Nile River Water to produce drinking water, and this process generates large amounts of waste, around 635 million m3 annually, which is called water treatment plant sludge (WTPS). This WTPS cost the government around 30 million US dollars to return it back to the Nile River in addition to negatively affecting the environment. Therefore, there is an urgent need to find environmentally friendly alternatives that reduce the impact of such an issue. This paper focuses on treating WTPS by drying, grinding and calcining to develop it as an alternative binder for use in alkali-activated concrete. This approach would not only provide green construction material but also reveal an environmental disposal route for the sludge produced in Egypt or in any country has the same issue. The treatment methodology used in this study was based on finding the optimum calcination temperature regime for WTPS after drying and grinding. Fifteen specimens of WTPS powder were used to investigate the optimum calcination temperature and duration by applying different temperatures ranging from 500 °C to 800 °C for various exposure durations of 30, 60 and 90 min. XRD and Chapelle tests were employed to chemically investigate the efficiency of the obtained calcined WTPS specimens, while strength activity index and compressive strength tests were used to mechanically verify the findings of the chemical tests. The results indicated that the calcination regime, which involved applying a maximum temperature of 650 °C for 90 min, achieved the best chemical characteristics and a strength activity index of 145%. Moreover, this regime resulted in a compressive strength of 21 MPa when WTPS powder was used as a precursor in alkali-activated concrete. Additionally, this paper presented a brief comparison of the production cost and energy consumption between cement and WTPS. The comparison demonstrated the efficiency of using WTPS as a replacement for cement, showing that the production of WTPS costs 50% less and consumes 92% less energy than cement.

Abstract This paper proposes the YOLOv8n_H method to address issues regarding parameter redundancy, slow inference speed, and suboptimal detection precision in contemporary helmet-wearing target recognition algorithms. The YOLOv8 C2f module is enhanced with a new SC_Bottleneck structure, incorporating the SCConv module, now termed SC_C2f, to mitigate model complexity and computational costs. Additionally, the original Detect structure is substituted with the PC-Head decoupling head, leading to a significant reduction in parameter count and an enhancement in model efficiency. Moreover, the original Detect structure is replaced by the PC-Head decoupling head, significantly reducing parameter count and enhancing model efficiency. Finally, regression accuracy and convergence speed are boosted by the dynamic non-monotonic focusing mechanism introduced through the WIoU boundary loss function. Experimental results on the expanded SHWD dataset demonstrate a 46.63% reduction in model volume, a 44.19% decrease in parameter count, a 54.88% reduction in computational load, and an improvement in mean Average Precision (mAP) to 93.8% compared to the original YOLOv8 algorithm. In comparison to other algorithms, the model proposed in this paper markedly reduces model size, parameter count, and computational load while ensuring superior detection accuracy.

Abstract Drug discovery and development is a challenging and time-consuming process. Laboratory experiments conducted on Vidarabine showed IC50 6.97 µg∕mL, 25.78 µg∕mL, and ˃ 100 µg∕mL against non-small Lung cancer (A-549), Human Melanoma (A-375), and Human epidermoid Skin carcinoma (skin/epidermis) (A-431) respectively. To address these challenges, this paper presents an Artificial Intelligence (AI) model that combines the capabilities of Deep Learning (DL) to identify potential new drug candidates, Fuzzy Rough Set (FRS) theory to determine the most important chemical compound features, Explainable Artificial Intelligence (XAI) to explain the features’ importance in the last layer, and medicinal chemistry to rediscover anticancer drugs based on natural products like Vidarabine. The proposed model aims to identify potential new drug candidates. By analyzing the results from laboratory experiments on Vidarabine, the model identifies Sulfur and magnesium oxide (MgO) as new potential anticancer agents. The proposed model selected Sulfur and MgO based on Interpreting their promising features, and further laboratory experiments were conducted to validate the model’s predictions. The results demonstrated that, while Vidarabine was inactive against the A-431 cell line (IC50 ˃ 100 µg∕mL), Sulfur and MgO exhibited significant anticancer activity (IC50 4.55 and 17.29 µg/ml respectively). Sulfur displayed strong activity against A-549 and A-375 cell lines (IC50 3.06 and 1.86 µg/ml respectively) better than Vidarabine (IC50 6.97 and 25.78 µg/ml respectively). However, MgO showed weaker activity against these two cell lines. This paper emphasizes the importance of uncovering hidden chemical features that may not be discernible without the assistance of AI. This highlights the ability of AI to discover novel compounds with therapeutic potential, which can significantly impact the field of drug discovery. The promising anticancer activity exhibited by Sulfur and MgO warrants further preclinical studies.

Abstract The application of artificial neural networks (ANNs) can be found in numerous fields, including image and speech recognition, natural language processing, and autonomous vehicles. As well, intrusion detection, the subject of this paper, relies heavily on it. Different intrusion detection models have been constructed using ANNs. While ANNs are relatively mature to construct intrusion detection models, some challenges remain. Among the most notorious of these are the bloated models caused by the large number of parameters, and the non-interpretability of the models. Our paper presents Convolutional Kolmogorov-Arnold Networks (CKANs), which are designed to overcome these difficulties and provide an interpretable and accurate intrusion detection model. Kolmogorov-Arnold Networks (KANs) are developed from the Kolmogorov-Arnold representation theorem. Meanwhile, CKAN incorporates a convolutional computational mechanism based on KAN. The model proposed in this paper is constructed by incorporating attention mechanisms into CKAN’s computational logic. The datasets CICIoT2023 and CICIoMT2024 were used for model training and validation. From the results of evaluating the performance indicators of the experiments, the intrusion detection model constructed based on CKANs has an attractive application prospect. As compared with other methods, the model can predict a much higher level of accuracy with significantly fewer parameters. However, it is not superior in terms of memory usage, execution speed and energy consumption.

Abstract This paper aims to construct a green environmental protection system by advancing database energy-saving techniques and optimizing the energy-saving mechanism against the backdrop of blockchain integration. The protocol classification of wireless sensor networks is examined within the context of the rapid growth of information technology. The analysis draws upon the database storage and sharing model and recent research examples that connect blockchain and database technology. Additionally, the paper investigates the blockchain data structure and storage path by analyzing the spatial–temporal correlation properties of blockchain data. The findings demonstrate that increasing the number of network nodes in the database system within a reasonable range can reduce the overall execution time. Additionally, as time progresses, the query traffic of the system database continues to increase. The research has practical implications in the domains of databases and the Internet of Things.

Abstract The ability to conduct research and utilize its findings has been a fundamental competency for medical students, often assessed through the observable research outcomes. This study aims to compare the research competency of medical students before, during, and after the COVID-19 pandemic to explore the future direction of research education in medical schools. We collected information on research outcomes submitted by medical students as graduation requirements during the pre-COVID-19, pandemic, and post-COVID-19 periods based on the duration of social distancing. The research outcomes were classified into two categories: publication of a paper and presentation at a conference. We compared variables such as authorship, type of journal or conference, and type of literature or presentation. The research outcomes submitted by all medical school graduates at their senior year from 2018 to 2023 were included in the analysis. The graduation requirements were usually achieved by publishing a paper (67.5%) with a faculty of clinical medicine (63.5%) in the fourth year (50.0%), regardless of COVID-19 pandemic. The findings highlighted the significant impact of the COVID-19 pandemic on the research outcomes of medical students. Post hoc analysis revealed that while the quality of published papers improved during the COVID-19 pandemic, there was a regression in author contributions in the post-pandemic period. The impact of the COVID-19 pandemic on medical students’ experiences with research is likely that the weakened student initiative observed in participating in and conducting research will persist, especially after the pandemic. Therefore, it is imperative to implement strategies to increase motivation and empower medical students to research.

Abstract Symbolic anchoring is an important topic in robotics, as it enables robots to obtain symbolic knowledge from the perceptual information acquired through their sensors and maintain the link between that knowledge and the sensory data. In cognitive-based robots, this process of transforming sub-symbolic data generated by sensors to obtain and maintain symbolic knowledge is still an open problem. To address this issue, this paper presents SAILOR, a framework for symbolic anchoring integrated into ROS 2. SAILOR aims to maintain the link between symbolic data and perceptual data in real robots over time. It provides a semantic world modeling approach using two deep learning-based sub-symbolic robotic skills: object recognition and matching function. The object recognition skill allows the robot to recognize and identify objects in its environment, while the matching function enables the robot to decide if new perceptual data corresponds to existing symbolic data. This paper describes the proposed method and the development of the framework, as well as its integration in MERLIN2 (a hybrid cognitive architecture fully functional in robots running ROS 2) and the validation of SAILOR using public datasets and a real-world scenario.

Abstract This study presents a novel approach to identifying meters and their pointers in modern industrial scenarios using deep learning. We developed a neural network model that can detect gauges and one or more of their pointers on low-quality images. We use an encoder network, jump connections, and a modified Convolutional Block Attention Module (CBAM) to detect gauge panels and pointer keypoints in images. We also combine the output of the decoder network and the output of the improved CBAM as inputs to the Object Heatmap-Scalarmap Module to find pointer tip heat map peaks and predict pointer pointing. The method proposed in this paper is compared with several deep learning networks. The experimental results show that the model in this paper has the highest recognition correctness, with an average precision of 0.95 and 0.763 for Object Keypoint Similarity and Vector Direction Similarity, and an average recall of 0.951 and 0.856 in the test set, respectively, and achieves the best results in terms of efficiency and accuracy achieve the best trade-off, and performs well in recognizing multiple pointer targets. This demonstrates its robustness in real scenarios and provides a new idea for recognizing pointers in low-quality images more efficiently and accurately in complex industrial scenarios.

Abstract In order to reduce turnout rail wear, the paper establishes a coupled dynamics model and a turnout rail wear model that consider the true profile of the turnout rail, the vehicle’s continuous traction force while passing, and the operational resistance. Comparative analysis of various models for predicting turnout rail wear indicates that the wear energy model is better suited for this purpose. The ideal profile update step for the turnout rail is 0.05 mm, and the adaptive filtering algorithm, tailored to the turnout characteristics, smooths wear distribution effectively while retaining crucial data features. The wear model developed in the paper predicts wear depth that is 89.91% consistent with the measured data. The grinding model introduced in the paper significantly enhances the wheel-rail contact conditions in the turnout, with lateral and vertical vibration accelerations of the vehicle reduced by 52.56% and 30.43%, respectively, during turnout passage. The research offers theoretical support for mitigating rail wear in high-speed turnouts.

Abstract Pakistan’s geographic location makes it an important land hub between Central Asia, Middle East-North Africa, and China. However, the railways, roads, farmland, riverways, and residential quarters in the Piedmont plains of Baluchistan province in northwestern Pakistan are under serious threat of flooding in the summer of 2022. The urgency and severity of climate change’s impact on humanity are underscored by the significant threats posed to human life and property in Piedmont Plains environments through extreme flood events, which has garnered widespread concerns. In flood scenarios, accurately predicting the extent of flooding is crucial for disaster assessment, emergency response, and the efficient allocation of resources. Previous research has primarily predicted flooding likelihood based on topographical factors or integrated annual rainfall data, failing to account for the extent of flooding from short-term rainfall before and after an event. Flood disasters are not caused by a single factor but are influenced by a variety of elements, including terrain and climate. Therefore, current research still lacks a comprehensive consideration of these influencing factors to accurately predict both the range and severity of flood impacts. In this paper, in response to the inability to accurately predict the flood damage in the pre-hill plains region in previous studies, combined with the current Pakistan mega-flood disaster, will couple the impacts of various flood-inducing factors on flooding, construct a prediction model for the degree of inundation of the Pakistani pre-hill plains flood disaster, and combined with the distribution of regional bearers, analyze the risk-resistant capacity of different types of bearers, and draw a comprehensive risk map piece under the flooding disaster. This paper bridges the gap of not integrating various factors in previous studies. Our research results provide strong evidence for flood prediction in Pakistan and similar regions, which is of great significance in reducing the loss of life and property of people around the world.

Abstract Due to the low contrast of abdominal CT (Computer Tomography) images and the similar color and shape of the liver to other organs such as the spleen, stomach, and kidneys, liver segmentation presents significant challenges. Additionally, 2D CT images obtained from different angles (such as sagittal, coronal, and transverse planes) increase the diversity of liver morphology and the complexity of segmentation. To address these issues, this paper proposes a Detail Enhanced Convolution (DE Conv) to improve liver feature learning and thereby enhance liver segmentation performance. Furthermore, to enable the model to better learn liver features at different scales, a Multi-Scale Feature Fusion module (MSFF) is added to the skip connections in the model. The MSFF module enhances the capture of global features, thus improving the accuracy of the liver segmentation model. Through the aforementioned research, this paper proposes a liver segmentation network based on detail enhancement and multi-scale feature fusion (DEMF-Net). We conducted extensive experiments on the LiTS17 dataset, and the results demonstrate that the DEMF-Net model achieved significant improvements across various evaluation metrics. Therefore, the proposed DEMF-Net model can achieve precise liver segmentation.

Abstract Integrating the Internet of Things (IoT) in smart grids has revolutionized the energy sector, enabling real-time data collection and efficient energy distribution. However, this integration also introduces significant security challenges, particularly data encryption. Traditional encryption algorithms used in IoT are vulnerable to various attacks, and the advent of quantum computing exacerbates these vulnerabilities. To address the above challenges, this paper proposes a novel encryption mechanism, the Quantum-Resistant Hybrid Encryption for IoT (QRHE-IoT), designed to enhance the security of communications in IoT-enabled smart grids. QRHE-IoT combines the strengths of symmetric and asymmetric encryption algorithms and incorporates quantum-resistant algorithms to provide robust security. This paper explains the QRHE-IoT mechanism, its theoretical basis, and how it addresses the security challenges in smart grid communications. It also presents the results of tests conducted to evaluate the effectiveness of QRHE-IoT in a simulated smart grid environment. The proposed QRHE-IoT mechanism presents a promising solution to these challenges, offering robust security for smart grid communications in the face of emerging threats, including quantum computing.

Abstract In this paper, a miniaturized 2 × 2 MIMO dual-wideband ground radiation antenna targeting Wi-Fi 6/6E/7 standards using 2.4 GHz, 5 GHz, and 6 GHz frequency bands with sufficient antenna performance was designed. The proposed antenna system contains four identical 4 mm × 6 mm antennas of the internal loop type and two identical 6 mm × 6 mm isolators containing lumped LC elements. This paper considers maximizing the impedance bandwidth using an advanced impedance control technique and isolation enhancement through T-shaped isolators. To achieve dual-wideband resonance, an impedance control method using LC parameter value control is employed by utilizing the coupling between the ground plane, the voltage source, the feed loop, and the radiation loop in each radiation band. The operating principle of the T-shaped isolator was proposed using the scattering matrix and impedance matching. Simulated results showed that the proposed antenna can cover 96 MHz at the 2.4 GHz band and 2,232 MHz at both the 5 GHz and 6 GHz bands with an impedance bandwidth of -10 dB and isolation performance of less than − 20 dB across all frequency bands. Average measured efficiencies of 52%, 74%, and 80% were obtained for the corresponding operating bands.

Abstract The production stage of an automated job shop is closely linked to the automated guided vehicle (AGV), which needs to be planned in an integrated manner to achieve overall optimization. In order to improve the collaboration between the production stages and the AGV operation system, a two-layer scheduling optimization model is proposed for simultaneous decision making of batching problems, job sequences and AGV obstacle avoidance. Under the AGV automatic path seeking mode, this paper adopts a data-driven Bayesian network method to portray the transportation time of AGVs based on the historical operation data to control the uncertainty of the transportation time of AGVs. Meanwhile, a time window is established to control the risk of AGV delay, and a data-driven Bayesian network is constructed to optimize the two-layer scheduling model of automated job shop and AGV. To solve the model, we design an improved particle swarm algorithm combining genetic operators, crossover operators and elite retention operator. The results show that the model in this paper can effectively improve the collaboration between the production stage and AGV operation system within the shop floor, and successfully solve the actual operation scale case to enhance the effectiveness of the production and transportation system.

Abstract While the abilities of language models are thoroughly evaluated in areas like general domains and biomedicine, academic chemistry remains less explored. Chemical QA tools also play a crucial role in both education and research by effectively translating complex chemical information into an understandable format. Addressing this gap, we introduce ScholarChemQA, a large-scale QA dataset constructed from chemical papers. Specifically, the questions are from paper titles with a question mark, and the multi-choice answers are reasoned out based on the corresponding abstracts. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unlabeled data that can be potentially useful. Correspondingly, we introduce a ChemMatch model, specifically designed to effectively answer chemical questions by fully leveraging our collected data. Experiments show that Large Language Models (LLMs) still have significant room for improvement in the field of chemistry. Moreover, ChemMatch significantly outperforms recent similar-scale baselines: https://github.com/iriscxy/chemmatch .

Abstract Independent pitch control (IPC) is a crucial technology for enhancing the performance of wind turbines, optimizing the power output, and reducing the loads by managing each blade. This paper explores the primary vibration modes of semi-submersible wind turbines under wind-wave coupling. Given the effectiveness of pitch control in vibration suppression, this paper addresses the limitations of conventional collective pitch control (CPC) by designing an independent pitch control method based on an equivalent wind speed model (EWIPC). This model constructs an effective representation of the actual wind speed’s influence on pitch angle by comprehensively considering the spatial distribution of wind speeds. This way, the control accuracy and response speed are significantly improved, making the control strategy more intuitive and efficient in complex wind speed environments. The proposed independent pitch control method is validated through simulations on the International Energy Agency (IEA) 15 MW wind turbine. The simulation results indicate that the EWIPC stabilizes wind turbine power output and reduces structural loads. Additionally, it demonstrates significant effectiveness in reducing vibrations of the blades and tower, as well as in eliminating 1P oscillations in the blade root bending moment.

Abstract The integration of radar technology into smart furniture represents a practical approach to health monitoring, circumventing the concerns regarding user convenience and privacy often encountered by conventional smart home systems. Radar technology’s inherent non-contact methodology, privacy-preserving features, adaptability to diverse environmental conditions, and high precision characteristics collectively establish it a compelling alternative for comprehensive health monitoring within domestic environments. In this paper, we introduce a millimeter (mm)-wave radar system positioned strategically behind a seat, featuring an algorithm capable of identifying unique cardiac waveform patterns for healthy subjects. These patterns are characterized by two peaks followed by a valley in each cycle, which can be correlated to Electrocardiogram (ECG), enabling effective cardiac waveform monitoring. The provided algorithm excels in discerning variations in heart patterns, particularly in individuals with prolonged corrected QT intervals, by minimizing high frequency breathing interference and ensuring accurate pattern recognition. Additionally, this paper addresses the influence of body movements in seated individuals, conducting a comprehensive study on heart rate variability and estimation. Experiment results demonstrate a maximum interbeat intervals (IBI) error of 30 milliseconds and an average relative error of 4.8% in heart rate estimation, showcasing the efficacy of the proposed method utilizing variational mode decomposition and a multi-bin approach.

Abstract Trade policy differences among different countries are important factors affecting international trade cooperation. In this paper, we build an evolutionary game model of international trade in which complex networks portray game relationships and trade policy differences are game strategies of players. Compared with the fully coupled game relationship and two-strategies game, the game relationship dynamic adjustment, trade policy differences and stochastic game payoffs in this paper are more in line with the real international trade context. We use mathematical analyses and computer simulation methods to reveal the impact of trade policy differences on the game payoffs of countries and the overall international trade networks. The results show that the reduce of the tolerance “t” of fair-trade is difficult to eliminate the opportunism trade policy and lead to a decline in the game payoffs of all countries and the global trading network. Dynamic adjustment of trade relations can not only improve the game payoffs of all countries and the trade network, but also offset the negative impact of the decline of the tolerance “t”. In terms of long-term, only the win-win trade policy can maximize the payoffs of the global trade network and achieve a balanced distribution of trade benefits.

Abstract Food security is the foundation of national security, which is related to economic development and social stability. Shanxi Province, as China’s grain production and marketing balance area, has rich agricultural resources and profound farming civilization, its food security situation is not only related to its own economic development, but also has a strategic position that can not be ignored in the national food security system. Based on the concept and goal of the development of food security in Shanxi Province, from the five aspects of quantity security, economic security, policy security, resource sustainability and ecological sustainability, this paper constructs the evaluation index system of food security in Shanxi Province, including the fluctuation rate of grain production and the sown area of grain, and establishes the entropy TOPSIS model to evaluate the development level of food security in Shanxi Province. The results show that the overall level of food security in Shanxi Province from 2001 to 2022 shows a trend of first decline and then rise, and the importance of food economic security, policy security and resource sustainability is increasing year by year. In the process of improving the level of food security development in Shanxi Province, it is also affected by structural imbalance, scientific and technological level, grain storage and transportation. Finally, the paper puts forward some policy suggestions to ensure food security in Shanxi Province.

Abstract The paper introduces a method for predicting damage intensity in masonry residential buildings situated in mining areas, focusing on the impact of large-scale continuous ground deformation. The research utilizes in situ data collected in a database, encompassing structural and material features, as well as information on maintenance quality and building durability. In addition to this information, the database collected data on the intensity of continuous deformation of the mining area at the location of the building, as well as the range and intensity of damage identified in buildings. The information included in the database was the result of many years of observations of buildings during the disclosure of impacts from mining exploitation and was based on: the results of in-situ building inventory, analysis of available building documentation and information provided by mining companies. The archived data were categorized variables labeled. The transformation of the data to a labeled value was dictated directly by the assumptions of the GOBNILP algorithm. Ultimately, a predictive model, represented by an optimal Bayesian network structure, is established. The optimisation of the network structure is achieved through the adaptation of the GOBNILP Bayesian network learning algorithm from data. This optimisation process is executed through the Gurobi Optimizer. It is worth noting that this interdisciplinary approach represents one of the first applications of such a methodology in the field of civil and environmental engineering. The results obtained can therefore be of significant value given the fact that the methodology of detecting the structure of Bayesian networks from data is still developing intensively in other scientific fields. In the course of the analyses, metric scores are examined, and various network structures are assessed based on their complexity. Great values of classification accuracies over 91% were obtained. This meticulous evaluation allows for the selection of the optimal Bayesian network that best generalises the knowledge acquired during the learning process. The paper also demonstrates the potential application of the obtained model in diagnosing damage causes and predicting future occurrences, highlighting the versatility of the proposed approach for addressing issues in the field.

Abstract In field of location prediction, trajectory recognition is one of the most widely research issues. Since trajectory includes various information such as position, time, and speed, many scientific methods are applied to extracting meaningful features, and discovering valuable knowledges. This paper pays more attention on case study of in-store trajectory, and proposes a series of recurrent neural network (RNN) for location prediction based on trajectory. The trajectory is provided by a indoor location system (ILS) in supermarket, and used radio frequency identification (RFID) technique to collect customer mobility data namely RFID data. After reviewing relatively previous studies, scholars mostly pursue customer segmentation and classification tasks based on trajectory, this paper briefly focus on regression analysis and pattern recognition of original trajectory itself. This paper also includes two improvements of experimental and methodological design. In ILS experiments, we select crossing sections as universal background to filtering customers and their trajectories, and choose fish, vegetable, and meat sections as experiment target, so as to train a general prediction model for heterogeneous shopping behaviors. In methodologies, we propose several RNNs with hybrid gate units on pre-defined trajectory based on RFID data, and also investigate their advances on time-series regression task for trajectory prediction. According to comparative and numerical results, the proposed models show higher performance on in-store trajectory prediction than other benchmark methods and other classic neural networks.

Abstract With the advancement of this digital era and the emergence of DApps and Blockchain, secure, robust and transparent network transaction has become invaluable today. These traditional methods of securing the transactions and maintaining transparency have encountered many challenges. It includes some such issues as follows: data privacy, centralized vulnerability, inefficiency in fraud detection and much more. To that effect, and to address such limitations, this paper provides a blockchain technology framework that is driven by advanced machine learning techniques, which will enhance security and transparency throughout the network of transactions. We begin with a design framework based on Federated Learning for Blockchain Integration where distributed datasets across blockchain nodes contribute to a global machine learning model but do not share raw data samples. Different nodes learn their own models. After that, these local models are aggregated towards a common, global model using secure aggregation methods, which makes sure that there is nozza of data privacy and hence, in the process making sure that more accurate models can be obtained due to diversified data sets. With LSTMs Autoencoders, more excellent security protocols are created for anomaly detection and fraud. So, by training the autoencoder on normal transaction data, the system can alert transactions with high reconstruction errors, meaning real-time anomalies. This proactive detection of anomalies reduces fraudulent activities significantly as most of the threats are recognized early. To this end, this paper proposes Smart Contract-based Model Management for machine learning models in a decentralized environment. Smart contracts are responsible for the submission, validation, and execution of the locally updated models in a decentralized fashion such that the management process is transparent and tamper resistant. Integrity and authenticity requirements are fulfilled by enforcing consensus mechanisms. Privacy in Machine Learning is guaranteed through Differential Privacy and Homomorphic Encryption. Differential privacy techniques, so as to ensure individual transaction data privacy in the updates of the local model before aggregation. In homomorphic encryption, computations are made in the encrypted form so when forming privacy preserving global model, privacy is preserved. The Real-time analysis of the transactions can be done with CNNs to detect fraud. Streaming transaction data is analyzed by CNNs leveraging the privacy-preserving global model and producing immediate alerts and actions for detected fraud. This real timing makes the network even more reliable and trustworthy. Our proposed framework is effective according to the interim outcomes where the aggregation of local models occurred without data leakage, detected anomalies very efficiently, managed models very transparently, with privacy of data at a very high level, and easily detected fraudulent transactions. The work presented here provides a great boost to send secure and very easily transparent transactions across the network, and thus resulted in enhanced network trust and decentralization.

Abstract This paper describes the database The global Multidimensional Poverty Index (MPI): Harmonised level estimates and their changes over time. The global MPI is an international poverty measure based on ten deprivation indicators in three dimensions: health, education, and living standards. The database contains estimates for the MPI itself (the adjusted headcount ratio); related partial indices such as headcount ratio, intensity, indicator-specific indices, and several auxiliary statistics; and changes over time for most quantities. For this database, all deprivation indicators have been harmonised over time. Our database covers estimates for 84 countries and 814 subnational regions for up to four points of observation. The estimates are based on 211 individual survey datasets, provided primarily by the Demographic Health Surveys (DHS) and the Multiple Indicator Cluster Surveys (MICS). Combining information about different dimensions of human wellbeing, the global MPI inherently invites interdisciplinary research.

Abstract In response to the increasing prevalence of dental diseases, dental health, a vital aspect of human well-being, warrants greater attention. Panoramic X-ray images (PXI) and Cone Beam Computed Tomography (CBCT) are key tools for dentists in diagnosing and treating dental conditions. Additionally, deep learning for tooth segmentation can focus on relevant treatment information and localize lesions. However, the scarcity of publicly available PXI and CBCT datasets hampers their use in tooth segmentation tasks. Therefore, this paper presents a multimodal dataset for Semi-supervised Tooth Segmentation (STS-Tooth) in dental PXI and CBCT, named STS-2D-Tooth and STS-3D-Tooth. STS-2D-Tooth includes 4,000 images and 900 masks, categorized by age into children and adults. Moreover, we have collected CBCTs providing more detailed and three-dimensional information, resulting in the STS-3D-Tooth dataset comprising 148,400 unlabeled scans and 8,800 masks. To our knowledge, this is the first multimodal dataset combining dental PXI and CBCT, and it is the largest tooth segmentation dataset, a significant step forward for the advancement of tooth segmentation.

Abstract With climate extremes’ rising frequency and intensity, robust analytical tools are crucial to predict their impacts on terrestrial ecosystems. Machine learning techniques show promise but require well-structured, high-quality, and curated analysis-ready datasets. Earth observation datasets comprehensively monitor ecosystem dynamics and responses to climatic extremes, yet the data complexity can challenge the effectiveness of machine learning models. Despite recent progress in deep learning to ecosystem monitoring, there is a need for datasets specifically designed to analyse compound heatwave and drought extreme impact. Here, we introduce the DeepExtremeCubes database, tailored to map around these extremes, focusing on persistent natural vegetation. It comprises over 40,000 globally sampled small data cubes (i.e. minicubes), with a spatial coverage of 2.5 by 2.5 km. Each minicube includes (i) Sentinel-2 L2A images, (ii) ERA5-Land variables and generated extreme event cube covering 2016 to 2022, and (iii) ancillary land cover and topography maps. The paper aims to (1) streamline data accessibility, structuring, pre-processing, and enhance scientific reproducibility, and (2) facilitate biosphere dynamics forecasting in response to compound extremes.

Abstract Acute liver failure is a rapidly progressing, life-threatening condition most commonly caused by an overdose of acetaminophen (paracetamol). The antidote, N-acetylcysteine (NAC), has limited efficacy when liver injury is established. If acute liver damage is severe, liver failure can rapidly develop with associated high mortality rates. We have previously demonstrated that alternatively, activated macrophages are a potential therapeutic option to reverse acute liver injury in pre-clinical models. In this paper, we present data using cryopreserved human alternatively activated macrophages (hAAMs)—which represent a potential, rapidly available treatment suitable for use in the acute setting. In a mouse model of APAP-induced injury, peripherally injected cryopreserved hAAMs reduced liver necrosis, modulated inflammatory responses, and enhanced liver regeneration. hAAMs were effective even when administered after the therapeutic window for NAC. This cell therapy approach represents a potential treatment for APAP overdose when NAC is ineffective because liver injury is established.

Abstract The terahertz (THz) security scanner offers advantages such as non-contact inspection and the ability to detect various types of dangerous goods, playing an important role in preventing terrorist attacks. We aim to accurately and quickly detect concealed objects in THz security images. However, current object detection algorithms face many challenges when applied to THz images. The main reasons for the detection difficulty are that the concealed objects are small, the image resolution is low, and there is back-ground noise. Many methods often ignore the contextual dependency of the objects, hindering the effective capture of the object’s features. To address this task, this paper first proposes an adaptive context-aware attention network (ACAN), which models global contextual association features in both spatial and channel dimensions. By dynamically combining local features and their global relationships, contextual association information can be obtained from the input features, and enhanced attention features can be achieved through feature fusion to enable precise detection of concealed objects. Secondly, we improved the adaptive convolution and developed the dynamic adaptive convolution block (DACB). DACB can adaptively adjust convolution filter parameters and allocate the filters to the corresponding spatial regions, then filter the feature maps to suppress interference information. Finally, we integrated these two components to YOLOv8, resulting in Adaptation-YOLO. Through wide-ranging experiments on the active THz image dataset, the results demonstrate that the suggested method effectively improves the accuracy and efficiency of object detectors.

Abstract Deep learning has achieved significant success in the field of defect detection; however, challenges remain in detecting small-sized, densely packed parts under complex working conditions, including occlusion and unstable lighting conditions. This paper introduces YOLOv8-n as the core network to propose VEE-YOLO, a robust and high-performance defect detection model. Firstly, GSConv was introduced to enhance feature extraction in depthwise separable convolution and establish the VOVGSCSP module, emphasizing feature reusability for more effective feature engineering. Secondly, improvements were made to the model’s feature extraction quality by encoding inter-channel information using efficient multi-Scale attention to consider channel importance. Precise integration of spatial structural and channel information further enhanced the model’s overall feature extraction capability. Finally, EIoU Loss replaced CIoU Loss to address bounding box aspect ratio variability and sample imbalance challenges, significantly improving overall detection task performance. The algorithm’s performance was evaluated using a dataset to detect stranded elastic needle defects. The experimental results indicate that the enhanced VEE-YOLO model’s size decreased from 6.096 M to 5.486 M, while the detection speed increased from 179FPS to 244FPS, achieving a mAP of 0.926. Remarkable advancements across multiple metrics make it well-suited for deploying deep detection models in complex industrial environments.

Abstract Cancer, as a shocking disease, is one of the most common malignant tumors among women, posing a huge threat to the physical health and safety of women worldwide. With the continuous development of science and technology, more and more high and new technologies are involved in the diagnosis and prediction of breast cancer. In recent years, intelligent medical assistants supported by data mining and machine learning algorithms have provided necessary support for doctors’ diagnosis. This study proposes an improved LightGBM hybrid integration model. Introducing gradient harmonic loss and cross entropy loss to enhance the model’s attention to minority classes in the dataset and alleviate the impact of data imbalance on diagnostic results. Designing whale optimization algorithm to improve LightGBM to achieve iterative optimization of hyperparameters, and enhance the overall performance of the model. Proposing Jacobian regularization method to denoise LightGBM to solve the problem of model sensitivity to noise. Developing the LightGBM hybrid integration model to ensure the accuracy and stability of model diagnosis on diverse and imbalanced datasets. The effectiveness of the proposed method has been comprehensively compared and verified through the dataset in the UCI machine learning repository, and the results show that the proposed method has achieved good diagnostic performance in all indicators. The hybrid integration model proposed in this paper can provide effective auxiliary support for doctors to diagnose breast cancer.

Abstract This paper investigates the impact of treatment with chemical solutions of varying pH values on the micro-macroscopic damage in coal samples under load, employing a combination of Small Angle X-ray Scattering (SAXS) experiments and uniaxial compression tests. The experimental results show that soaking coal samples in NaOH, HCl, and distilled water for 7 days leads to reductions in uniaxial compressive strength by 39.19%, 47.26%, and 24.39%, respectively, compared to untreated coal. The elastic modulus exhibited similar reductions, further confirming the weakening effects of chemical solutions. SAXS experiments reveal that exposure to alkaline solutions promotes the expansion and connection of nanopores, while acidic solutions primarily dissolve mineral components, increasing brittleness. Distilled water causes milder effects on pore structure and mechanical properties. To model the synergic effects of chemical solution corrosion and stress, a chemical solution corrosion-stress coupling factor was introduced into the Weibull probability distribution-based constitutive model. The modified model accurately describes the strain–stress behavior and damage evolution under combined chemical and mechanical effects. These findings highlight the risks of chemical solution-induced damage to coal and provide theoretical support for disaster prevention and stability control in coal mining.

Abstract Under the backdrop of frequent emergencies, the rational layout of emergency service facilities (ESF) and the effective allocation of emergency supplies have emerged as crucial in determining the timeliness of post-disaster response. By adequately accounting for potential uncertainties and carrying out comprehensive pre-planning, the robustness of location-allocation decisions can be significantly improved. This paper delves into the ESF network design problem under demand uncertainty and formulates this problem as a two-stage robust optimization model. The presented model defines a generalized budget uncertainty set to capture victims’ uncertain demand and minimizes the sum of the costs involved in the two stages. The objective function integrates the input cost in the preparedness phase, the deprivation cost from the victims’ perspective and the environmental impact cost responding to sustainable development in the response phase, which respectively correspond to the comprehensive optimization of the deployment of ESF, the distribution of emergency supplies and the implementation of sustainable measures. Subsequently, we employ the column and constraint generation (C&CG) algorithm to solve the proposed model and take the COVID-19 epidemic in Wuhan as a case to verify the effectiveness of the model and algorithm. Finally, we examine the influence of demand uncertainty and environmental impact cost on the optimal solution, yielding valuable managerial insights.