F-score Performance Research Articles

Advanced Supply Chain Management Using Adaptive Serial Cascaded Autoencoder with LSTM and Multi-Layered Perceptron Framework

Supply chain management is essential for businesses to handle uncertainties, maintain efficiency, and stay competitive. Financial risks can arise from various internal and external sources, impacting different supply chain stages. Companies that effectively manage these risks gain a deeper understanding of their procurement activities and implement strategies to mitigate financial threats. This paper explores financial risk assessment in supply chain management using advanced deep learning techniques on big data. The Adaptive Serial Cascaded Autoencoder (ASCA), combined with Long Short-Term Memory (LSTM) and Multi-Layered Perceptron (MLP), is used to evaluate financial risks. A data transformation process is used to clean and prepare financial data for analysis. Additionally, Sandpiper Galactic Swarm Optimization (SGSO) is employed to optimize the deep learning model’s performance. The SGSO-ASCALSMLP-based financial risk prediction model demonstrated superior accuracy compared to traditional methods. It outperformed GRU (gated recurrent unit)-ASCALSMLP by 3.03%, MLP-ASCALSMLP by 7.22%, AE-LSTM-ASCALSMLP by 10.7%, and AE-LSTM-MLP-ASCALSMLP by 10.9% based on F1-score performance. The SGSO-ASCALSMLP model is highly efficient in predicting financial risks, outperforming conventional prediction techniques and heuristic algorithms, making it a promising approach for enhancing financial risk management in supply chain networks.

DEEP LEARNING BASED NETWORK INTRUSION DETECTION

As a direct consequence of the unrelenting march of technological innovation, the use of the Internet has become an unavoidable condition for the life of modern humans. The Internet has increased both the quantity and range of situations in which information products can be useful or non-useful. It’s no surprise that as the number of different systems and users has grown, so have the number of different ways to exploit those systems. A security issue has arisen with such diversity and growth. Its diversity and increase in quantity introduce new system weaknesses and thus new attack strategies. Methods for detecting both internal and external attacks are suggested as a solution to this issue. The purpose of this research, a Convolutional Neural Network was utilized to identify intrusions, also known as attacks for the imbalanced class distribution in the NF-BoT-IoT data set, Synthetic Minority Over Sampling Technique, Random Over Sampling and Random Under Sampling methods were used. K-Fold Cross Validation, one of the strategies for splitting the data set, was utilized to evaluate the performance of classification models and to train the developed model. The model’s performance was evaluated using the accuracy, precision, recall, and F1-score performance criteria.

Deep Convolutional Neural Network for Automated Staging of Periodontal Bone Loss Severity on Bite-wing Radiographs: An Eigen-CAM Explainability Mapping Approach.

Periodontal disease is a significant global oral health problem. Radiographic staging is critical in determining periodontitis severity and treatment requirements. This study aims to automatically stage periodontal bone loss using a deep learning approach using bite-wing images. A total of 1752 bite-wing images were used for the study. Radiological examinations were classified into 4 groups. Healthy (normal), no bone loss; stage I (mild destruction), bone loss in the coronal third (< 15%); stage II (moderate destruction), bone loss is in the coronal third and from 15 to 33% (15-33%); stage III-IV (severe destruction), bone loss extending from the middle third to the apical third with furcation destruction (> 33%). All images were converted to 512 × 400 dimensions using bilinear interpolation. The data was divided into 80% training validation and 20% testing. The classification module of the YOLOv8 deep learning model was used for the artificial intelligence-based classification of the images. Based on four class results, it was trained using fivefold cross-validation after transfer learning and fine tuning. After the training, 20% of test data, which the system had never seen, were analyzed using the artificial intelligence weights obtained in each cross-validation. Training and test results were calculated with average accuracy, precision, recall, and F1-score performance metrics. Test images were analyzed with Eigen-CAM explainability heat maps. In the classification of bite-wing images as healthy, mild destruction, moderate destruction, and severe destruction, training performance results were 86.100% accuracy, 84.790% precision, 82.350% recall, and 84.411% F1-score, and test performance results were 83.446% accuracy, 81.742% precision, 80.883% recall, and 81.090% F1-score. The deep learning model gave successful results in staging periodontal bone loss in bite-wing images. Classification scores were relatively high for normal (no bone loss) and severe bone loss in bite-wing images, as they are more clearly visible than mild and moderate damage.

ENHANCE SKIN CANCER DEEP LEARNING-BASED CATEGORIZATION: A THOROUGH EXAMINATION AND COMPARATIVE STUDY

Abstract: One of the most prevalent types of cancer in the world is skin cancer, which includes melanoma, squamous cell carcinoma, and basal cell carcinoma. While increasing survival rates requires early discovery and treatment, conventional diagnostic techniques frequently have subjectivity and inconsistent results. The purpose of this study is to better understand how deep learning techniques, namely convolutional neural networks (CNNs), might improve the detection of skin cancer. Using the ISIC dataset, eight advanced models—DenseNet121, InceptionV3, ResNet50V2, VGG16, VGG19, InceptionResNetV2, Xception, and CNN—were trained and verified to categorize different types of skin lesions. The outcomes highlight the superior accuracy that models like as Xception and InceptionV3 can accomplish, highlighting their potential for accurate and timely detection. This investigation assesses how well different deep learning models diagnose different skin diseases. Models like Densenet121, InceptionV3, and VGG16 are compared based on metrics like accuracy, recall, precision, and F1-score. When it comes to multi-classification, InceptionResNetV2 and VGG16 stand out as the best performers with 0.9547 accuracy, while Custom CNN performs the worst with 0.8040. A thorough comparison of the accuracy, precision, recall, and F1-score performance indicators identifies the unique advantages and disadvantages of each model. This study demonstrates how artificial intelligence (AI) is revolutionizing medical imaging by offering a reliable, unbiased, and highly accurate method for detecting skin cancer. The integration of deep learning models into clinical practice is made possible by these discoveries, which might enhance patient outcomes and diagnostic accuracy in dermatology. IndexTerms – Python, Machine Learning, Deep Learning, Skin Cancer, Deep Learning Algorithms, Medical Imaging, Neural Network Models.

AI-Driven localization of all impacted teeth and prediction of winter angulation for third molars on panoramic radiographs: Clinical user interface design

PurposeImpacted teeth are abnormal tooth disorders under the gums or jawbone that cannot take their normal position even though it is time to erupt. This study aims to detect all impacted teeth and to classify impacted third molars according to the Winter method with an artificial intelligence model on panoramic radiographs. MethodsIn this study, 1197 panoramic radiographs from the dentistry faculty database were collected for all impacted teeth, and 1000 panoramic radiographs were collected for Winter classification. Some pre-processing methods were performed and the images were doubled with data augmentation. Both datasets were randomly divided into 80% training, 10% validation, and 10% testing. After transfer learning and fine-tuning processes, the two datasets were trained with the YOLOv8 deep learning algorithm, a high-performance artificial intelligence model, and the detection of impacted teeth was carried out. The results were evaluated with precision, recall, mAP, and F1-score performance metrics. A graphical user interface was designed for clinical use with the artificial intelligence weights obtained as a result of the training. ResultsFor the detection of impacted third molar teeth according to Winter classification, the average precision, average recall, and average F1 score were obtained to be 0.972, 0.967, and 0.969, respectively. For the detection of all impacted teeth, the average precision, average recall, and average F1 score were obtained as 0.991, 0.995, and 0.993, respectively. ConclusionAccording to the results, the artificial intelligence-based YOLOv8 deep learning model successfully detected all impacted teeth and the impacted third molar teeth according to the Winter classification system.

Precision Geolocation of Medicinal Plants: Assessing Machine Learning Algorithms for Accuracy and Efficiency

This study investigates the precision geolocation of medicinal plants, a critical endeavor bridging ecology, conservation, and pharmaceutical research. By employing machine learning algorithms—gradient boosting machine (GBM), random forest (RF), and support vector machine (SVM)—within the cross-industry standard process for data mining (CRISP-DM) framework, both the accuracy and efficiency of medicinal plant geolocation are enhanced. The assessment employs precision, recall, accuracy, and F1 score performance metrics. Results reveal that SVM and GBM algorithms exhibit superior performance, achieving an accuracy of 97.29%, with SVM showing remarkable computational efficiency. Meanwhile, despite inferior performance, RF remains competitive especially when model interpretability is required. These outcomes highlight the efficacy of SVM and GBM in medicinal plant geolocation and accentuate their potential to advance environmental research, conservation strategies, and pharmaceutical explorations. The study underscores the interdisciplinary significance of accurately geolocating medicinal plants, supporting their conservation for future pharmaceutical innovation and ecological sustainability.

Multi-strategy enhanced Marine Predators Algorithm with applications in engineering optimization and feature selection problems

This paper introduces a novel meta-heuristic optimization algorithm named Clustering Wavelet Opposition-based Marine Predators Algorithm (CWOMPA) to address some limitations present in the well-established Marine Predators Algorithm (MPA). CWOMPA incorporates three key strategies: a fuzzy clustering approach for escaping local optima, using wavelet basis function-based impact coefficient adjustment for elites to prevent premature convergence, and finally an adaptive opposition-based learning strategy for maintaining population diversity. Compared with some recent meta-heuristic algorithms, extensive evaluations conducted affirm that CWOMPA achieves the best Friedman rank, 4.30 and 1.95 respectively, on 23 benchmark functions and the CEC 2017 benchmark set. Not only does CWOMPA demonstrate significant effectiveness on six constrained problems from the CEC 2020 real-world benchmarks, but also when applied to 14 medical datasets, it gains superior Friedman ranks in terms of selected features, classification accuracy, F-Score, and objective function value, 2.5, 2.25, 2.96, 2.93 respectively, outperforming other common methods. Finally, CWOMPA exhibits the highest classification accuracy across all datasets and the best F-Score performance in nine datasets compared to traditional feature selection algorithms. The obtained results reveal that CWOMPA is a powerful and versatile optimization algorithm with significant potential in various real-world applications, including feature selection for medical datasets.

Integrated clinical and genomic models using machine-learning methods to predict the efficacy of paclitaxel-based chemotherapy in patients with advanced gastric cancer

BackgroundPaclitaxel is commonly used as a second-line therapy for advanced gastric cancer (AGC). The decision to proceed with second-line chemotherapy and select an appropriate regimen is critical for vulnerable patients with AGC progressing after first-line chemotherapy. However, no predictive biomarkers exist to identify patients with AGC who would benefit from paclitaxel-based chemotherapy.MethodsThis study included 288 patients with AGC receiving second-line paclitaxel-based chemotherapy between 2017 and 2022 as part of the K-MASTER project, a nationwide government-funded precision medicine initiative. The data included clinical (age [young-onset vs. others], sex, histology [intestinal vs. diffuse type], prior trastuzumab use, duration of first-line chemotherapy), and genomic factors (pathogenic or likely pathogenic variants). Data were randomly divided into training and validation sets (0.8:0.2). Four machine learning (ML) methods, namely random forest (RF), logistic regression (LR), artificial neural network (ANN), and ANN with genetic embedding (ANN with GE), were used to develop the prediction model and validated in the validation sets.ResultsThe median patient age was 64 years (range 25–91), and 65.6% of those were male. A total of 288 patients were divided into the training (n = 230) and validation (n = 58) sets. No significant differences existed in baseline characteristics between the training and validation sets. In the training set, the areas under the ROC curves (AUROC) for predicting better progression-free survival (PFS) with paclitaxel-based chemotherapy were 0.499, 0.679, 0.618, and 0.732 in the RF, LR, ANN, and ANN with GE models, respectively. The ANN with the GE model that achieved the highest AUROC recorded accuracy, sensitivity, specificity, and F1-score performance of 0.458, 0.912, 0.724, and 0.579, respectively. In the validation set, the ANN with GE model predicted that paclitaxel-sensitive patients had significantly longer PFS (median PFS 7.59 vs. 2.07 months, P = 0.020) and overall survival (OS) (median OS 14.70 vs. 7.50 months, P = 0.008). The LR model predicted that paclitaxel-sensitive patients showed a trend for longer PFS (median PFS 6.48 vs. 2.33 months, P = 0.078) and OS (median OS 12.20 vs. 8.61 months, P = 0.099).ConclusionsThese ML models, integrated with clinical and genomic factors, offer the possibility to help identify patients with AGC who may benefit from paclitaxel chemotherapy.

Phishing URL detection generalisation using Unsupervised Domain Adaptation

Phishing attacks are a prevailing problem in cybersecurity. In many data breaches, the initial entry can be traced back to phishing. URL-based phishing detection is one of the many ways of phishing attempt detection where solely the properties of the URLs are used to decide whether a given URL is phishing or not. While there are multiple existing works that use machine learning and deep learning to detect phishing URLs, in this paper, we show that such methods lack generalisation (i.e., they work effectively only when the test sets are split from the same training dataset). This is a significant issue since the vast majority of phishing attempts are short-lived and use freshly created domain names. Also, many network vantage points and middleboxes record URLs in slightly different formats and as such, URL data collected at various companies may be different. To address this, we propose an Unsupervised Domain Adaptation-based framework to increase the model transferability between datasets. We evaluate our approach using three datasets and show that the increase in cross-dataset F1 score performance is 0.06 on average and in some cases approximately as high as 0.2.

Emotional analysis of joint sports quality expansion tasks based on multi-modal feature fusion

A multi-modal feature based motion emotion analysis model based on a fusion deep learning model is proposed for the problem of analyzing the motion emotions of participants in the joint exercise quality expansion task. This model involves three major modalities: EEG signals, peripheral physiological signals, and facial expression signals, and processes and fuses the information of these three main modalities to achieve the effect of processing multi-dimensional motor emotional information. At the same time, this study introduces the design concept of residual networks, using self attention modules and multi head mutual attention modules to process different modal features. The results showed that the combination of peripheral physiological modality and facial expression modality had the highest accuracy among the three modality combinations, with an accuracy rate of 88.8 %. The feature fusion method based on the cascaded residual attention mechanism module has better accuracy and F1 Score performance than other methods. In addition, different emotional states can be effectively identified and distinguished in these three modalities, indicating that the model has a wide range of possibilities in practical applications.

Can cross-domain term extraction benefit from cross-lingual transfer and nested term labeling?

Automatic term extraction (ATE) is a natural language processing task that eases the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms. In this paper, we treat ATE as a sequence-labeling task and explore the efficacy of XLMR in evaluating cross-lingual and multilingual learning against monolingual learning in the cross-domain ATE context. Additionally, we introduce NOBI, a novel annotation mechanism enabling the labeling of single-word nested terms. Our experiments are conducted on the ACTER corpus, encompassing four domains and three languages (English, French, and Dutch), as well as the RSDO5 Slovenian corpus, encompassing four additional domains. Results indicate that cross-lingual and multilingual models outperform monolingual settings, showcasing improved F1-scores for all languages within the ACTER dataset. When incorporating an additional Slovenian corpus into the training set, the multilingual model exhibits superior performance compared to state-of-the-art approaches in specific scenarios. Moreover, the newly introduced NOBI labeling mechanism enhances the classifier’s capacity to extract short nested terms significantly, leading to substantial improvements in Recall for the ACTER dataset and consequentially boosting the overall F1-score performance.

Clustering-based incremental learning for imbalanced data classification

Imbalanced data classification presents a significant challenge when there is a substantial disparity in sample sizes across different classes. This issue severely affects classifier accuracy in predicting minority classes, hampering numerous real-world applications. Traditional methods address data imbalance by using undersampling or oversampling techniques. However, these methods may lead to information loss during sample reduction or introduce noise and model bias through synthetic sample generation. In this paper, we introduce DRIL, an innovative clustering-based incremental learning approach designed to overcome these limitations and improve the classification of minority class samples. Specifically, we employ a “two-step clustering” method to rebalance the dataset, partitioning it into similar and representative sub-dataset. Subsequently, incremental learning is applied to enable the classifier to gradually acquire knowledge about these sub-data, establishing a comprehensive understanding of all features present in the imbalanced dataset. Experimental results on twenty datasets demonstrate that our incremental learning-based algorithm outperforms baseline methods in correctly classifying minority classes while exhibiting improved precision and F1 score performance.

A data envelopment analysis model for opinion leaders’ identification in social networks

Through Online Social Networks (OSNs) such as Instagram, X (Twitter), and Facebook, employing Opinion Leaders (OLs) is becoming integral to companies’ strategies for influencing the public. The graph-based methods are one of the most important approaches for finding OLs in OSNs. Social Network Analysis (SNA)-based OLs finding methods deal with a considerable amount of data due to using entire relationships between all of the users in a network, which makes the algorithms time-consuming. Our main goal is to introduce a new method of OLs discovery that works with fewer data and maintains or improves performance metrics. Consequently, a new application of the Data Envelopment Analysis (DEA) method is presented here for OLs identification in social media. Another contribution of this paper is introducing a new framework (OL-Finder Evaluator or OLFE) for validating the OLs’ detection algorithms under imbalanced datasets. DEA methods, when compared with SNA methods, have the advantage of being able to apply over non-graph-based datasets and to work with substantially smaller datasets. In contrast, SNA methods require transparent relationships between people. In this study, we compare both DEA (including CCR and BCC) and SNA measures (including “Betweenness (BC),” “Degree (DC),” “Page Rank (PRC),” “Closeness (CC),” and “Eigenvector (EC)” centralities) on a real Instagram network for OLs detection. Compared with SNA, our proposed method can identify OLs with considerably fewer data. Besides the advantages of DEA for time-saving, close competition exists between the DEA and the SNA methods. On average, DEA performs better in accuracy, precision, recall, and F1-score performance metrics.

A novel approach to recognition of Alzheimer's and Parkinson's diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image.

Artificial intelligence technologies have great potential in classifying neurodegenerative diseases such as Alzheimer's and Parkinson's. These technologies can aid in early diagnosis, enhance classification accuracy, and improve patient access to appropriate treatments. For this purpose, we focused on AI-based auto-diagnosis of Alzheimer's disease, Parkinson's disease, and healthy MRI images. In the current study, a deep hybrid network based on an ensemble classifier and convolutional neural network was designed. First, a very deep super-resolution neural network was adapted to improve the resolution of MRI images. Low and high-level features were extracted from the images processed with the hybrid deep convolutional neural network. Finally, these deep features are given as input to the k-nearest neighbor (KNN)-based random subspace ensemble classifier. A 3-class dataset containing publicly available MRI images was utilized to test the proposed architecture. In experimental works, the proposed model produced 99.11% accuracy, 98.75% sensitivity, 99.54% specificity, 98.65% precision, and 98.70% F1-score performance values. The results indicate that our AI system has the potential to provide valuable diagnostic assistance in clinical settings.

A user-friendly AI-based clinical decision support system for rapid detection of pandemic diseases: Covid-19 and Monkeypox

Accurate and rapid diagnosis is a significant factor in reducing incidence rate; especially when the number of people inflicted with a disease is considerably high. In the healthcare sector, the decision-making process might be a complex and error-prone one due to excessive workload, negligence, time restrictions, incorrect or incomplete evaluation of medical reports and analyses, and lack of experience as well as insufficient knowledge and skills. Clinical decision support systems (CDSSs) are those developed to improve effectiveness of decisions by supporting physicians’ decision-making process regarding their patients. In this study, a new artificial intelligence-based CDSS and a user-friendly interface for this system were developed to ensure rapid and accurate detection of pandemic diseases. The proposed CDSS, which is called panCdss, uses hybrid models consisting of the Convolutional Neural Network (CNN) model and Machine Learning (ML) methods in order to detect covid-19 from lung computed tomography (CT) images. Transfer Learning (TL) models were used to detect monkeypox from skin lesion images and covid-19 from chest X-Ray images. The results obtained from these models were evaluated according to accuracy, precision, recall and F1-score performance metrics. Of these models, the ones with the highest classification performance were used in the panCdss. The highest classification values obtained for each dataset were as follows: % 91.71 accuracy, % 92.07 precision, % 90.29 recall and % 91.71 F1-score for covid-19 CT dataset by using CNN+RF hybrid model; % 99.56 accuracy, % 100 precision, % 99.12 recall and % 99.55 F1-score for covid-19 X-ray dataset by using VGG16 model; and % 90.38 accuracy, % 93.32 precision, % 88.11 recall and % 90.64 F1-score for monkeypox dataset by using MobileNetV2. It is believed that panCdss can be successfully employed for rapid and accurate classification of pandemic diseases and can help reduce physicians’ workload. Furthermore, the study showed that the proposed CDSS is an adaptable, flexible and dynamic system that can be practiced not only for the detection of pandemic diseases but also for other diseases. To the authors’ knowledge, this proposed CDSS is the first CDSS developed for pandemic disease detection.

Flood Susceptibility Assessment with Random Sampling Strategy in Ensemble Learning (RF and XGBoost)

Due to the complex interaction of urban and mountainous floods, assessing flood susceptibility in mountainous urban areas presents a challenging task in environmental research and risk analysis. Data-driven machine learning methods can evaluate flood susceptibility in mountainous urban areas lacking essential hydrological data, utilizing remote sensing data and limited historical inundation records. In this study, two ensemble learning algorithms, Random Forest (RF) and XGBoost, were adopted to assess the flood susceptibility of Kunming, a typical mountainous urban area prone to severe flood disasters. A flood inventory was created using flood observations from 2018 to 2022. The spatial database included 10 explanatory factors, encompassing climatic, geomorphic, and anthropogenic factors. Artificial Neural Network (ANN) and Support Vector Machine (SVM) were selected for model comparison. To minimize the influence of expert opinions on model training, this study employed a strategy of uniformly random sampling in historically non-flooded areas for negative sample selection. The results demonstrated that (1) ensemble learning algorithms offer higher accuracy than other machine learning methods, with RF achieving the highest accuracy, evidenced by an area under the curve (AUC) of 0.87, followed by XGBoost at 0.84, surpassing both ANN (0.83) and SVM (0.82); (2) the interpretability of ensemble learning highlighted the differences in the potential distribution of the training data’s positive and negative samples. Feature importance in ensemble learning can be utilized to minimize human bias in the collection of flooded-site samples, more targeted flood susceptibility maps of the study area’s road network were obtained; and (3) ensemble learning algorithms exhibited greater stability and robustness in datasets with varied negative samples, as evidenced by their performance in F1-Score, Kappa, and AUC metrics. This paper further substantiates the superiority of ensemble learning in flood susceptibility assessment tasks from the perspectives of accuracy, interpretability, and robustness, enhances the understanding of the impact of negative samples on such assessments, and optimizes the specific process for urban flood susceptibility assessment using data-driven methods.

Artificial Intelligence in primary care: Intelligent risk predicting platform for non-communicable chronic diseases

Chronic Non-Communicable Diseases with multifactorial and non-infectious characteristics in their origin have been a matter of growing concern for society and governments, as they put people at greater risk of complications, disability, and death. They are the leading cause of death worldwide, i.e. a global threat to health. Modern medicine relies heavily on a variety of biochemical, behavioral, clinical, etc. data to advance the chronic diseases field. Machine learning techniques have a wide range of applications, for example for diabetes classifications, phenotypic resistance of whole genomic sequences and heart disease. These approaches, in general, concentrate efforts on a single Chronic Non-Communicable Diseases. Thus, identifying multiple chronic diseases simultaneously is an open challeng. Our study demonstrated that the intelligent risk prediction platform for non-communicable chronic diseases using Multi-Label Classification methods can be used to model multiple Chronic Non-Communicable Diseases. We use ensemble methods developed on top of algorithm adaptation techniques, including Random Forest, Extra Trees and Decision Tree Classifiers. Among the models in the experiment, the Random Forest achieved the best accuracy and F1-score performance with 96.16% and 90.48%, respectively. Our results suggest that the platform is promising and can be used to support medical teams in the early diagnosis of Chronic Non-Communicable Diseases, allowing them to provide adequate treatment options to patients in a timely manner in primary care, as well as contributing to reducing the risk of complications, disability, and deaths by Chronic Non-Communicable Diseases.

Automatic Detection of Distant Metastasis Mentions in Radiology Reports in Spanish.

A critical task in oncology is extracting information related to cancer metastasis from electronic health records. Metastasis-related information is crucial for planning treatment, evaluating patient prognoses, and cancer research. However, the unstructured way in which findings of distant metastasis are often written in radiology reports makes it difficult to extract information automatically. The main aim of this study was to extract distant metastasis findings from free-text imaging and nuclear medicine reports to classify the patient status according to the presence or absence of distant metastasis. We created a distant metastasis annotated corpus using positron emission tomography-computed tomography and computed tomography reports of patients with prostate, colorectal, and breast cancers. Entities were labeled M1 or M0 according to affirmative or negative metastasis descriptions. We used a named entity recognition model on the basis of a bidirectional long short-term memory model and conditional random fields to identify entities. Mentions were subsequently used to classify whole reports into M1 or M0. The model detected distant metastasis mentions with a weighted average F1 score performance of 0.84. Whole reports were classified with an F1 score of 0.92 for M0 documents and 0.90 for M1 documents. These results show the usefulness of the model in detecting distant metastasis findings in three different types of cancer and the consequent classification of reports. The relevance of this study is to generate structured distant metastasis information from free-text imaging reports in Spanish. In addition, the manually annotated corpus, annotation guidelines, and code are freely released to the research community.

IntelliTrace: Intelligent Contact Tracing Method Based on Transmission Characteristics of Infectious Disease

The COVID-19 pandemic has underscored the necessity for rapid contact tracing as a means to effectively suppress the spread of infectious diseases. Existing contact tracing methods leverage location-based or distance-based detection to identify contact with a confirmed patient. Existing contact tracing methods have encountered challenges in practical applications, stemming from the tendency to classify even casual contacts, which carry a low risk of infection, as close contacts. This issue arises because the transmission characteristics of the virus have not been fully considered. This study addresses the above problem by proposing IntelliTrace, an intelligent method that introduces methodological innovations prioritizing shared environmental context over physical proximity. This approach more accurately assesses potential transmission events by considering the transmission characteristics of the virus, with a special focus on COVID-19. In this study, we present space-based indoor Wi-Fi contact tracing using machine learning for indoor environments and trajectory-based outdoor GPS contact tracing for outdoor environments. For an indoor environment, a contact is detected based on whether users are in the same space with the confirmed case. For an outdoor environment, we detect contact through judgments based on the companion statuses of people, such as the same movements in their trajectories. The datasets obtained from 28 participants who installed the smartphone application during a one-month experiment in a campus space were utilized to train and validate the performance of the proposed exposure-detection method. As a result of the experiment, IntelliTrace exhibited an F1 score performance of 86.84% in indoor environments and 94.94% in outdoor environments.

Improving the IoT Attack Classification Mechanism with Data Augmentation for Generative Adversarial Networks

The development of IoT technology has made various IoT applications and services widely used. Because IoT devices have weak information security protection capabilities, they are easy targets for cyber attacks. Therefore, this study proposes MLP-based IoT attack classification with data augmentation for GANs. In situations where the overall classification performance is satisfactory but the performance of a specific class is poor, GANs are employed as a data augmentation mechanism for that class to enhance its classification performance. The experimental results indicate that regardless of whether the training dataset is BoT-IoT or TON-IOT, the proposed method significantly improves the classification performance of classes with insufficient training data when using the data augmentation mechanism with GANs. Furthermore, the classification accuracy, precision, recall, and F1-score performance all exceed 90%.