High Performance Metrics Research Articles

Integrating attention mechanism and boundary detection for building segmentation from remote sensing images

Accurate building segmentation has become critical in various fields such as urban management, urban planning, mapping, and navigation. With the increasing diversity in the number, size, and shape of buildings, convolutional neural networks have been used to segment and extract buildings from such images, resulting in increased efficiency and utilization of image features. We propose a building semantic segmentation method to improve the traditional Unet convolutional neural network by integrating attention mechanism and boundary detection. The attention mechanism module combines attention in the channel and spatial dimensions. The module captures image feature information in the channel dimension using a one-dimensional convolutional cross-channel method and automatically adjusts the cross-channel dimension using adaptive convolutional kernel size. Additionally, a weighted boundary loss function is designed to replace the traditional semantic segmentation cross-entropy loss to detect the boundary of a building. The loss function optimizes the extraction of building boundaries in backpropagation, ensuring the integrity of building boundary extraction in the shadow part. Experimental results show that the proposed model AMBDNet achieves high-performance metrics, including a recall rate of 0.9046, an IoU of 0.7797, and a pixel accuracy of 0.9140 on high-resolution remote sensing images, demonstrating its robustness and effectiveness in precise building segmentation. Experimental results further indicate that AMBDNet improves the single-class recall of buildings by 0.0322 and the single-class pixel accuracy by 0.0169 in the high-resolution remote sensing image recognition task.

AI-enhanced interface for colonic polyp segmentation using DeepLabv3+ with comparative backbone analysis

Polyps are one of the early stages of colon cancer. The detection of polyps by segmentation and their removal by surgical intervention is of great importance for making treatment decisions. Although the detection of polyps through colonoscopy images can lead to multiple expert needs and time losses, it can also include human error. Therefore, automatic, fast, and highly accurate segmentation of polyps from colonoscopy images is important. Many methods have been proposed, including deep learning-based approaches. In this study, a method using DeepLabv3+ with encoder-decoder structure and ResNet architecture as backbone network is proposed for the segmentation of colonic polyps. The Kvasir-SEG polyp dataset was used to train and test the proposed method. After images were preprocessed, the training of the proposed network was performed. The trained network was then tested and performance metrics were calculated, and additionally, a GUI (Graphical User Interface) was designed to enable the segmentation of colonoscopy images for polyp segmentation. The experimental results showed that the ResNet-50 based DeepLabv3+ model had high performance metrics such as DSC: 0.9609, mIoU: 0.9246, demonstrating its effectiveness in the segmentation of colonic polyps. In conclusion, our method utilizing DeepLabv3+ with a ResNet-50 backbone achieves highly accurate colonic polyp segmentation. The obtained results demonstrate its potential to significantly enhance colorectal cancer diagnosis and planning for polypectomy surgery through automated image analysis.&#xD.

Romanian Fake News Detection Using Machine Learning and Transformer-Based Approaches

Nowadays, the consequence of quick access to information has lead to the spread of fake news, which has a strong damaging impact on democracy, justice, and public trust. Thus, it is crucial to analyze and evaluate detection methods for fake news. This paper focuses on the detection of Romanian fake news. In this study, we made a comparative analysis of machine learning algorithms and Transformer-based models on Romanian fake news detection using three datasets—FakeRom, NEW, and both FakeRom + NEW. The NEW dataset was build using a scrapping algorithm applied on the Veridica platform. Our approach uses the following machine learning models for detection: Naive Bayes (NB), Logistic Regression (LR), and Support Vector Machine (SVM). We also used two Transformer-based models—BERT-based-multilingual-cased and RoBERTa-large. The performance of the models was evaluated using various metrics: accuracy, precision, recall, and F1 score. The results revealed that the BERT model trained on the NEW dataset consistently achieved the highest performance metrics across all test sets, with 96.5%. Also, Support Vector Machine trained on NEW was another top performer, reaching a very good accuracy of 94.6% on the combined test set.

Classification of opening/closing hand motor imagery induced by left and right robotic gloves through EEG signals

This study presents a novel strategy for classifying Motor Imagery (MI) related to hand opening/closing actions using electroencephalography signals. This approach combines the passive motion induced by a robotic glove and action observation. Two groups of subjects executed a protocol based on left and right hand movement MI to address this. Subsequently, spectral features were used on $mu$ and $beta$ bands, and machine-learning algorithms were used for classification. The results showed better performance for right-hand motion recognition using k-Nearest Neighbors (kNN), which achieved the highest performance metrics of 0.71, 0.76, and 0.28 for Accuracy (ACC), true positive rate, and false positive rate, respectively. These findings demonstrate the feasibility of the proposed methodology for improving the recognition of MI tasks of the same limb, which can contribute to the design of more robust brain-computer interfaces for the enhancement of rehabilitation therapy for post-stroke patients.

Revolutionizing market surveillance: customer relationship management with machine learning

In the telecommunications industry, predicting customer churn is essential for retaining clients and sustaining profitability. Traditional CRM systems often fall short due to their static models, limiting responsiveness to evolving customer behaviors. To address these gaps, we developed the SmartSurveil CRM model, an ensemble-based system combining random forest, gradient boosting, and support vector machine to enhance churn prediction accuracy and adaptability. Using a comprehensive telecom dataset, our model achieved high performance metrics, including an accuracy of 0.89 and ROC-AUC of 0.91, surpassing baseline approaches. Integrated into a decision support system (DSS), SmartSurveil provides actionable insights to improve customer retention, enabling telecom companies to tailor strategies dynamically. Additionally, this model addresses ethical concerns, including data privacy and algorithmic transparency, ensuring a robust and responsible CRM approach. The SmartSurveil CRM model represents a substantial advancement in predictive accuracy and practical applicability within CRM systems.

The Effects of Flywheel Training with a Portable Device on Physical Performance in Soccer Players

Soccer is a team sport in which players expend high-intensity intermittent efforts that require the production of sprints, accelerations, decelerations, changes of direction, and jumps. The aim of this study was to analyze the effects of training with portable and low-cost flywheel devices, using multi-directional exercises over 8 weeks, on the performance of linear sprint, curve sprint, and change of direction in senior soccer players. Thirty-three players participated in the research, divided into a control group and an experimental group. The latter group performed the training protocol in addition to the technical–tactical soccer training. Before and after the application of the training protocol, the linear and curve sprint and change of direction (V-cut) were evaluated. At the end of the training program, significant improvements (p < 0.05) were found in change of direction and in curve sprint with respect to the control group. The results suggested that resistance training with flywheel devices with low training volumes improves performance in change of direction and in curve sprint, which are key performance variables in soccer. Therefore, this type of training could be added to technical–tactical soccer training to enhance the variables that are essential to reach high-performance metrics in soccer.

Novel approach for Arabic fake news classification using embedding from large language features with CNN-LSTM ensemble model and explainable AI

The widespread fake news challenges the management of low-quality information, making effective detection strategies necessary. This study addresses this critical issue by advancing fake news detection in Arabic and overcoming limitations in existing approaches. Deep learning models, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), EfficientNetB4, Inception, Xception, ResNet, ConvLSTM and a novel voting ensemble framework combining CNN and LSTM are employed for text classification. The proposed framework integrates the ELMO word embedding technique having contextual representation capabilities, which is compared with GloVe, BERT, FastText and FastText subwords. Comprehensive experiments demonstrate that the proposed voting ensemble, combined with ELMo word embeddings, consistently outperforms previous approaches. It achieves an accuracy of 98.42%, precision of 98.54%, recall of 99.5%, and an F1 score of 98.93%, offering an efficient and highly effective solution for text classification tasks.The proposed framework benchmark against state-of-the-art transformer architectures, including BERT and RoBERTa, demonstrates competitive performance with significantly reduced inference time and enhanced interpretability accompanied by a 5-fold cross-validation technique. Furthermore, this research utilizes the LIME XAI technique to provide deeper insights into the contribution of each feature in predicting a specific target class. These findings show the proposed framework’s effectiveness in dealing with the issues of detecting false news, particularly in Arabic text. By generating higher performance metrics and displaying comparable results, this work opens the way for more reliable and interpretable text classification solutions.

Multiclass arrhythmia classification using multimodal smartwatch photoplethysmography signals collected in real-life settings.

In the early stages of atrial fibrillation (AF), most cases are paroxysmal (pAF), making identification only possible with continuous and prolonged monitoring. With the advent of wearables, smartwatches equipped with photoplethysmographic (PPG) sensors are an ideal approach for continuous monitoring of pAF. There have been numerous studies demonstrating successful capture of pAF events, especially using deep learning. However, deep learning requires a large amount of data and independent testing on diverse datasets, to ensure the generalizability of the model, and most prior studies did not meet these requirements. Moreover, most prior studies using wearable-based PPG sensor data collection were limited either to controlled environments, to minimize motion artifacts, or to short duration data collection. Most importantly, frequent premature atrial and ventricular contractions (PAC/PVC) can confound most AF detection algorithms. This has not been well studied, largely due to limited datasets containing these rhythms. Note that the recent deep learning models show 97% AF detection accuracy, and the sensitivity of the current state-of-the-art technique for PAC/PVC detection is only 75% on minimally motion artifact corrupted PPG data. Our study aims to address the above limitations using a recently completed NIH-funded Pulsewatch clinical trial which collected smartwatch PPG data over two weeks from 106 subjects. For our approach, we used multi-modal data which included 1D PPG, accelerometer, and heart rate data. We used a computationally efficient 1D bi-directional Gated Recurrent Unit (1D-Bi-GRU) deep learning model to detect three classes: normal sinus rhythm, AF, and PAC/PVC. Our proposed 1D-Bi-GRU model's performance was compared with two other deep learning models that have reported some of the highest performance metrics, in prior work. For three-arrhythmia-classification, testing data for all deep learning models consisted of using independent data and subjects from the training data, and further evaluations were performed using two independent datasets that were not part of the training dataset. Our multimodal model achieved an unprecedented 83% sensitivity for PAC/PVC detection while maintaining a high accuracy of 97.31% for AF detection. Our model was computationally more efficient (14 times more efficient and 2.7 times faster) and outperformed the best state-of-the-art model by 20.81% for PAC/PVC sensitivity and 2.55% for AF accuracy. We also tested our models on two independent PPG datasets collected with a different smartwatch and a fingertip PPG sensor. Our three-arrhythmia-classification results show high macro-averaged area under the receiver operating characteristic curve values of 96.22%, and 94.17% for two independent datasets, demonstrating better generalizability of the proposed model.

Optimal thresholds and key parameters for predicting influenza A virus transmission events in ferrets

Although assessments of influenza A virus transmissibility in the ferret model play a critical role in pandemic risk evaluations, few studies have investigated which virological data collected from virus-inoculated animals are most predictive of subsequent virus transmission to naïve contacts. We compiled viral titer data from >475 ferrets inoculated with 97 contemporary IAV (including high- and low-pathogenicity avian, swine-origin, and human viruses of multiple HA subtypes) that served as donors for assessments of virus transmission in the presence of direct contact (DCT) or via respiratory droplets (RDT). A diversity of molecular determinants, clinical parameters, and infectious titer measurements and derived quantities were examined to identify which metrics were most statistically supported with transmission outcome. Higher viral loads in nasal wash (NW) specimens were strongly associated with higher transmission frequencies in DCT, but not RDT models. However, viruses that reached peak titers in NW specimens early (day 1 p.i.) were strongly associated with higher transmission in both models. Interestingly, viruses with ‘intermediate’ transmission outcomes (33–66%) had NW titers and derived quantities more similar to non-transmissible viruses (<33%) in a DCT setting, but with efficiently transmissible viruses (>67%) in a RDT setting. Machine learning was employed to further assess the predictive role of summary measures and varied interpretation of intermediate transmission outcomes in both DCT and RDT models, with models employing these different thresholds yielding high performance metrics against both internal and external datasets. Collectively, these findings suggest that higher viral load in inoculated animals can be predictive of DCT outcomes, whereas the timing of when peak titers are detected in inoculated animals can inform RDT outcomes. Identification that intermediate transmission outcomes should be contextualized relative to the transmission mode assessed provides needed refinement towards improving interpretation of ferret transmission studies in the context of pandemic risk assessment.

New Combined Metric for Full-Reference Image Quality Assessment

In recent years, many new metrics highly correlated with the Mean Opinion Score (MOS) have been proposed for assessing image quality through Full-Reference Image Quality Assessment (FR-IQA) methods, such as MDSI, HPSI, and GMSD. Eight of these selected metrics, which compare reference and distorted images in a symmetrical manner, are briefly described in this article, and their performance is evaluated using correlation criteria (PLCC, SROCC, and KROCC), as well as RMSE. The aim of this paper is to develop a new, efficient quality index based on a combination of several high-performance metrics already utilized in the field of Image Quality Assessment (IQA). The study was conducted on four benchmark image databases (TID2008, TID2013, KADID-10k, and PIPAL) and identified the three best-performing metrics for each database. The paper introduces a New Combined Metric (NCM), which is a weighted sum of three component metrics, and demonstrates its superiority over each of its component metrics across all the examined databases. An optimization method for determining the weights of the NCM is also presented. Additionally, an alternative version of the combined metric, based on the fastest metrics and employing symmetric calculations for pairs of compared images, is discussed. This version also demonstrates strong performance.

Advancements in Geohazard Investigations: Developing a Machine Learning Framework for the Prediction of Vents at Volcanic Fields Using Magnetic Data

This study investigates the application of machine learning techniques for predicting volcanic vent locations based on aeromagnetic geophysical data. Magnetic data, known to reflect subsurface geological structures, presents a valuable source of information for understanding volcanic activity. Leveraging this data, we aim to develop and validate predictive models capable of discerning the presence of volcanic vents. Through a comprehensive data analysis, feature engineering, and model training, we explore the intricate relationships between magnetic variations and volcanic vent locations. Various machine learning algorithms were evaluated for their efficacy in binary classification, with a focus on identifying areas with a high likelihood of volcanic vent presence. The Random Forest model (RFM) was adopted given its high performance metrics, achieving a prediction accuracy of 92%. Our results demonstrate the successful prediction of volcanic vent locations, with a significant correlation of 86% between the actual and predicted vent locations and a high Degree of Certainty (DC) at 97%. This research contributes to the advancement of geospatial data analysis within the field of geoscience, showcasing the potential of machine learning in interpreting and utilizing magnetic data for volcanic hazard assessment and early warning systems. The findings represent a significant step towards enhancing our understanding of volcanic dynamics and improving the predictive tools available for volcanic hazard assessment.

Contribution of Scalp Regions to Machine Learning-Based Classification of Dementia Utilizing Resting-State qEEG Signals.

This study aims to investigate using eyes-open (EO) and eyes-closed (EC) resting-state EEG data to diagnose cognitive impairment using machine learning methods, enhancing timely intervention and cost-effectiveness in dementia research. A total of 890 participants aged 40-90 were included in the study, comprising 269healthy controls (HC), 356 individuals with mild cognitive impairment (MCI), and 265 with Alzheimer's disease (AD) from a cohort study. Resting-state EEG (rEEG) signals were recorded and transformed into relative power spectral density (PSD) data for analysis. The processed PSD data, representing 19 scalp regions, were then input into a Random Forest (RF) machine learning classifier to identify distinctive EEG patterns across the groups. Statistical comparisons between the groups were conducted using one-way ANOVA, applied to the relative PSD features extracted from the EEG data, to assess significant differences in EEG activity across the diagnostic categories. The study found that rEEG-based categorization effectively differentiates between cognitively impaired individuals and healthy individuals. The EO rEEG achieved the highest performance metrics across various models. For HC vs MCI (combined hemisphere), the accuracy, sensitivity, specificity, and AUC were 92%, 99%, 83%, and 96%, respectively. For HC vs AD (parietal, temporal, occipital), these metrics were 95%, 96%, 94%, and 99%. The HC vs CASE (MCI + AD) (combined hemisphere) results were 90%, 99%, 73%, and 92%. The metrics for HC vs MCI vs AD (frontal, parietal, temporal) were 89%, 88%, 94%, and 96%. The study demonstrates that EO rEEG can effectively distinguish between cognitive impairment and healthy states, leading to early diagnosis, cost-effective treatment, and better clinical outcomes for dementia patients. EO and EC rEEG models trained with relative PSD, particularly from parietal, temporal, occipital, and central scalp regions, can significantly assist clinicians in practice.

Data-Driven Price Trends Prediction of Ethereum: A Hybrid Machine Learning and Signal Processing Approach

Due to the recent fluctuations in cryptocurrency prices, Ethereum has gained recognition as an investment asset. Given its volatile nature, there is a significant demand for accurate predictions to guide investment choices. This paper examines the most influential features of the daily price trends of Ethereum using a novel approach that combines the Random Forest classifier and the ReliefF method. Integrating the Adaptive Neuro-Fuzzy Inference System (ANFIS) and Short-Time Fourier Transform (STFT) resulted in high accuracy and performance metrics for Ethereum price trend predictions. This method stands out from prior research, primarily based on time series analysis, by enhancing pattern recognition across time and frequency domains. This adaptability leads to better prediction capabilities with accuracy reaching 76.56% in a highly chaotic market such as cryptocurrency. The STFT's ability to reveal cyclical trends in Ethereum's price provides valuable insights for the ANFIS model, leading to more precise predictions and addressing a notable gap in cryptocurrency research. Hence, compared to models in literature such as Gradient Boosting, Long Short-Term Memory, Random Forest, and Extreme Gradient Boosting, the proposed model adapts to complex data patterns and captures intricate non-linear relationships, making it well-suited for cryptocurrency prediction.

RAG-based explainable prediction of road users behaviors for automated driving using knowledge graphs and large language models

The prediction of road user behaviors in the context of autonomous driving has attracted considerable attention from the scientific community in recent years. Most works focus on predicting behaviors based on kinematic information alone, a simplification of reality since road users are humans, and as such they are highly influenced by their surrounding context. In addition, a large plethora of research works rely on powerful Deep Learning techniques, which exhibit high-performance metrics in prediction tasks but may lack the ability to fully understand and exploit the contextual semantic information contained in the road scene, not to mention their inability to provide explainable predictions that can be understood by humans. In this work, we propose an explainable road users’ behavior prediction system that integrates the reasoning abilities of Knowledge Graphs (KG) and the expressiveness capabilities of Large Language Models (LLM) by using Retrieval Augmented Generation (RAG) techniques. For that purpose, Knowledge Graph Embeddings (KGE) and Bayesian inference are combined to allow the deployment of a fully inductive reasoning system that enables the issuing of predictions that rely on legacy information contained in the graph, as well as on current evidence gathered in real-time by onboard sensors. Two use cases have been implemented following the proposed approach: 1) Prediction of pedestrians’ crossing actions; and 2) Prediction of lane change maneuvers. In both cases, the performance attained exceeds the current state-of-the-art in terms of anticipation and F1 score, showing a promising avenue for future research in this field.

A Performance Comparison of Different YOLOv7 Networks for High-Accuracy Cell Classification in Bronchoalveolar Lavage Fluid Utilising the Adam Optimiser and Label Smoothing.

Accurate classification of cells in bronchoalveolar lavage (BAL) fluid is essential for the assessment of lung disease in pneumology and critical care medicine. However, the effectiveness of BAL fluid analysis is highly dependent on individual expertise. Our research is focused on improving the accuracy and efficiency of BAL cell classification using the "You Only Look Once" (YOLO) algorithm to reduce variability and increase the accuracy of cell detection in BALF analysis. We assess various YOLOv7 iterations, including YOLOv7, YOLOv7 with Adam and label smoothing, YOLOv7-E6E, and YOLOv7-E6E with Adam and label smoothing focusing on the detection of four key cell types of diagnostic importance in BAL fluid: macrophages, lymphocytes, neutrophils, and eosinophils. This study utilised cytospin preparations of BAL fluid, employing May-Grunwald-Giemsa staining, and analysed a dataset comprising 2032 images with 42,221 annotations. Classification performance was evaluated using recall, precision, F1 score, mAP@.5, and mAP@.5;.95 along with a confusion matrix. The comparison of four algorithmic approaches revealed minor distinctions in mean results, falling short of statistical significance (p < 0.01; p < 0.05). YOLOv7, with an inference time of 13.5 ms for 640 × 640 px images, achieved commendable performance across all cell types, boasting an average F1 metric of 0.922, precision of 0.916, recall of 0.928, and mAP@.5 of 0.966. Remarkably, all four cell types were classified consistently with high-performance metrics. Notably, YOLOv7 demonstrated marginally superior class value dispersion when compared to YOLOv7-adam-label-smoothing, YOLOv7-E6E, and YOLOv7-E6E-adam-label-smoothing, albeit without statistical significance. Consequently, there is limited justification for deploying the more computationally intensive YOLOv7-E6E and YOLOv7-E6E-adam-label-smoothing models. This investigation indicates that the default YOLOv7 variant is the preferred choice for differential cytology due to its accessibility, lower computational demands, and overall more consistent results than more complex models.

An AI-assisted explainable mTMCNN architecture for detection of mandibular third molar presence from panoramic radiography

ObjectiveThis study aimed to design and systematically evaluate an architecture, proposed as the Explainable Mandibular Third Molar Convolutional Neural Network (E-mTMCNN), for detecting the presence of mandibular third molars (m-M3) in panoramic radiography (PR). The proposed architecture seeks to enhance the accuracy of early detection and improve clinical decision-making and treatment planning in dentistry. MethodsA new dataset, named the Mandibular Third Molar (m-TM) dataset, was developed through expert labeling of raw PR images from the UESB dataset. This dataset was subsequently made publicly accessible to support further research. Several advanced image preprocessing techniques, including Gaussian filtering, gamma correction, and data augmentation, were applied to improve image quality. Various Deep learning (DL) based Convolutional Neural Network (CNN) architectures were trained and validated using Transfer Learning (TL) methodologies. Among these, the E-mTMCNN, leveraging the GoogLeNet architecture, achieved the highest performance metrics. To ensure transparency in the model’s decision-making process, Local Interpretable Model-Agnostic Explanations (LIME) were integrated as an eXplainable Artificial Intelligence (XAI) approach. Clinical reliability and applicability were assessed through an expert survey conducted among specialized dentists using a decision support system based on the E-mTMCNN. ResultsThe E-mTMCNN architecture demonstrated a classification accuracy of 87.02%, with a sensitivity of 75%, specificity of 94.73%, precision of 77.68%, an F1 score of 75.51%, and an area under the curve (AUC) of 87.01%. The integration of LIME provided visual explanations of the model’s decision-making rationale, reinforcing the robustness of the proposed architecture. Results from the expert survey indicated high clinical acceptance and confidence in the reliability of the system. ConclusionThe findings demonstrate that the E-mTMCNN architecture effectively detects the presence of m-M3 in PRs, outperforming current state-of-the-art methodologies. The proposed architecture shows considerable potential for integration into computer-aided diagnostic systems, advancing early detection capabilities and enhancing the precision of treatment planning in dental practice.

Towards Accurate Flood Predictions: A Deep Learning Approach Using Wupper River Data

The increasing frequency and severity of floods due to climate change underscores the need for precise flood forecasting systems. This study focuses on the region surrounding Wuppertal in Germany, known for its high precipitation levels, as a case study to evaluate the effectiveness of flood prediction through deep learning models. Our primary objectives are twofold: (1) to establish a robust dataset from the Wupper river basin, containing over 19 years of time series data from three sensor types such as water level, discharge, and precipitation at multiple locations, and (2) to assess the predictive performance of nine advanced machine learning algorithms, including Pyraformer, TimesNet, and SegRNN, in providing reliable flood warnings 6 to 48 h in advance, based on 48 h of input data. Our models, trained and validated using k-fold cross-validation, achieved high quantitative performance metrics, with an accuracy reaching up to 99.7% and F1-scores up to 91%. Additionally, we analyzed model performance relative to the number of sensors by systematically reducing the sensor count, which led to a noticeable decline in both accuracy and F1-score. These findings highlight critical trade-offs between sensor coverage and predictive reliability. By publishing this comprehensive dataset alongside performance benchmarks, we aim to drive further innovation in flood risk management and resilience strategies, addressing urgent needs in climate adaptation.

Dry-Processed Silicon-Graphite Composite Electrodes for Lithium-Ion Battery

As the demand for increased energy density grows in the contemporary electric vehicle (EV) sector, lithium-ion batteries (LIBs) have emerged as the preferred choice within modern secondary battery technologies [1]. These batteries, owing to their remarkable characteristics, are valued for their outstanding energy density, enhanced specific energy efficiency, and high-performance metrics compared to alternative battery technologies [2]. With noticeable constraints becoming evident, endeavors are currently underway to discover effective solutions for commercial LIBs. These efforts primarily focus on advancing both cathode and anode electrodes to achieve high-energy density approaches. To attain this high energy density, the use of a dry-process technique is necessary. Dry processing offers several advantages over traditional solvent processes, particularly in terms of operational cost and energy efficiency, making it a promising alternative for electrode manufacturing in LIBs. Moreover, the absence of solvents allows to produce electrodes with higher mass loadings, potentially facilitating battery miniaturization. In this study, electrodes employing a solvent-free dry-process method were fabricated utilizing a blend of silicon and graphite as the anode material. Each step was meticulously optimized, particularly in the utilization of Polytetrafluoroethylene (PTFE) material, which is not typically used in electrode materials, resulting in significant advancements in alleviating potential issues. Building upon this, high-loading, high-density electrodes were successfully produced using the dry-process method. In this research, a current density of 6 mA/cm2 and an electrode density of 1.6 g/cc were successfully achieved using a dry process method. The manufactured electrode utilizes 20% silicon content to address the limitations of silicon oxide, achieving performance equal to or exceeding that of slurry state electrodes. These dry-process electrodes show potential to facilitate the development of lithium-ion batteries under harsh cell design conditions in the future. Reference s [1] Nano Energy, 2017. 31: p. 113-143.[2] Nature Chem 7, 19–29 (2015).

Predicting Monthly Runoff: A BO-CNN-LSTM Approach for Enhanced Water Resource Management

Monthly runoff prediction is critical for sustainable water resource management, flood control, and drought preparedness. Accurate forecasts assist decision-making and management of water resources, which are critical for human and environmental demands. Previous prediction algorithms frequently lack accuracy due to human-defined hyperparameters. Autonomous hyperparameter tuning is required for improved predictions. Objectives: To improve the accuracy of monthly runoff predictions, this research proposes a BO-CNN-LSTM model that integrates Bayesian optimization (BO) with a convolutional neural network-long short-term memory neural network (CNN-LSTM). Methods/Analysis: The BO algorithm is utilized to enhance the CNN-LSTM model's hyperparameters, which helps to overcome the limits of human-set parameters. Model training and validation were carried out using monthly runoff data from 1956 to 2019 from Lanxi Station in the Hulan River Basin. The model's prediction performance was assessed using root mean square error (RMSE), mean absolute error (MAE), fitting coefficient (R²), and mean relative error (MAPE), and compared with other previous models. Findings: The results show that the BO-CNN-LSTM model outperforms conventional models in prediction accuracy and reduction of errors. The BO method efficiently enhances hyperparameters, resulting in higher performance metrics. This model gives more precise and dependable monthly runoff forecasts, which are critical for handling the Hulan River Basin's water resources. Novelty/Improvement: By combining BO and CNN-LSTM, the proposed model solves the constraints of previous models, improving prediction accuracy and reducing errors. This innovative technique presents a promising novel approach for monthly runoff prediction, with possible applications in larger hydrological prediction.

Evaluation of Dental Panoramic Radiographs by Artificial Intelligence Compared to Human Reference: A Diagnostic Accuracy Study.

Background/Objectives: The role of artificial intelligence (AI) in dentistry is becoming increasingly significant, particularly in diagnosis and treatment planning. This study aimed to assess the sensitivity, specificity, accuracy, and precision of AI-driven software in analyzing dental panoramic radiographs (DPRs) in patients with permanent dentition. Methods: Out of 638 DPRs, 600 fulfilled the inclusion criteria. The radiographs were analyzed by AI software and two researchers. The following variables were assessed: (1) missing tooth, (2) root canal filling, (3) endodontic lesion, (4) implant, (5) abutment, (6) pontic, (7) crown, (8) and sound tooth. Results: The study revealed very high performance metrics for the AI algorithm in detecting missing teeth, root canal fillings, and implant abutment crowns, all greater than 90%. However, it demonstrated moderate sensitivity and precision in identifying endodontic lesions and the lowest precision (65.30%) in detecting crowns. Conclusions: AI software can be a valuable tool in clinical practice for diagnosis and treatment planning but may require additional verification by clinicians, especially for identifying endodontic lesions and crowns. Due to some limitations of the study, further research is recommended.