Sensitivity And Specificity Research Articles

GreenFruitDetector: Lightweight green fruit detector in orchard environment

Detecting green fruits presents significant challenges due to their close resemblance in color to the leaves in an orchard environment. We designed GreenFruitDetector, a lightweight model based on an improved YOLO v8 architecture, specifically for green fruit detection. In the Backbone network, we replace ordinary convolution with Deformable Convolution to enhance the extraction of geometric features. Additionally, we designed MCAG-DC (Multi-path Coordinate Attention Guided Deformer Convolution) to replace the convolution in C2f, enhancing the Backbone’s feature extraction capability when encountering occlusion problems. For the Neck part of the algorithm, we designed a Fusion-neck structure that integrates spatial detail information from feature maps at different scales, thereby enhancing the network’s ability to extract multi-scale information. Additionally, we devised a new detection head that incorporates multi-scale information, significantly improving the detection of small and distant objects. Finally, we applied channel pruning techniques to reduce the model size, parameter count, and FLOPs to 50%, 55%, and 44% of the original, respectively. We trained and evaluated the improved model on three green fruit datasets. The accuracy of the improved model reached 94.5%, 84.4%, and 85.9% on the Korla Pear, Guava, and Green Apple datasets, respectively, representing improvements of 1.17%, 1.1%, and 1.77% over the baseline model. The mAP@0.5 increased by 0.72%, 6.5%, and 0.9%, respectively, and the recall rate increased by 1.97%, 1.1%, and 0.49%, respectively.

Synchronized stepwise control of firing and learning thresholds in a spiking randomly connected neural network toward hardware implementation

Spiking randomly connected neural network (RNN) hardware is promising as ultimately low power devices for temporal data processing at the edge. Although the potential of RNNs for temporal data processing has been demonstrated, randomness of the network architecture often causes performance degradation. To mitigate such degradation, self-organization mechanism using intrinsic plasticity (IP) and synaptic plasticity (SP) should be implemented in the spiking RNN. Therefore, we propose hardware-oriented models of these functions. To implement the function of IP, a variable firing threshold is introduced to each excitatory neuron in the RNN that changes stepwise in accordance with its activity. We also define other thresholds for SP that synchronize with the firing threshold, which determine the direction of stepwise synaptic update that is executed on receiving a pre-synaptic spike. To discuss the effectiveness of our model, we perform simulations of temporal data learning and anomaly detection using publicly available electrocardiograms (ECGs) with a spiking RNN. We observe that the spiking RNN with our IP and SP models realizes the true positive rate of 1 with the false positive rate being suppressed at 0 successfully, which does not occur otherwise. Furthermore, we find that these thresholds as well as the synaptic weights can be reduced to binary if the RNN architecture is appropriately designed. This contributes to minimization of the circuit of the neuronal system having IP and SP.

Identification of Predictors of Sarcopenia in Older Adults Using Machine Learning: English Longitudinal Study of Ageing

Background: After its introduction in the ICD-10-CM in 2016, sarcopenia is a condition widely considered to be a medical disease with important consequences for the elderly. Considering its high prevalence in older adults and its detrimental effects on health, it is essential to identify its risk factors to inform targeted interventions. Methods: Taking data from wave 2 of the ELSA, using ML-based methods, this study investigates which factors are significantly associated with sarcopenia. The Minimum Redundancy Maximum Relevance algorithm has been used to allow for an optimal set of features that could predict the dependent variable. Such a feature is the input of a ML-based prediction model, trained and validated to predict the risk of developing or not developing a disease. Results: The presented methods are suitable to identify the risk of acquired sarcopenia. Age and other relevant features related with dementia and musculoskeletal conditions agree with previous knowledge about sarcopenia. The present classifier has an excellent performance since the “true positive rate” is 0.81 and the low “false positive rate” is 0.26. Conclusions: There is a high prevalence of sarcopenia in elderly people, with age and the presence of dementia and musculoskeletal conditions being strong predictors. The new proposed approach paves the path to test the prediction of the incidence of sarcopenia in older adults.

A Lightweight Barcode Detection Algorithm Based on Deep Learning

For existing situations of missed detections, false detections, and repeated detections in barcode detection algorithms in real-world scenarios, a barcode detection algorithm based on improved YOLOv8 is proposed. The EfficientViT block based on a linear self-attention mechanism is introduced into the backbone of the original model to enhance the model’s attention to barcode features. In the model’s neck, linear mapping and grouped convolution are used to improve the C2f module, and the ADown convolution block is utilized to modify the model’s downsampling, which reduces the model’s parameters and computational cost while improving the efficiency of model feature fusion. Finally, the reconstruction of the model’s detection head and the modification of the loss function are implemented to enhance the model’s training quality and reduce the model’s error in barcode detection. Experimental results indicate that the improved model exhibits an increase of 1.8% in recall rate and 1.9% in mAP50:95 for barcode localization and classification. The FPS is improved by 40 frames per second. The model’s parameter count is reduced by 74.2%, and FLOPs are decreased by 79.6%. Furthermore, the proposed model outperforms other models in terms of model size and barcode detection accuracy.

An Enhanced Detection Method of Hardware Trojan Based on CNN- Attention-LSTM

The security issues caused by the insertion of hardware Trojans seriously threaten the security and reliability of the entire hardware device. This article constructs a detection model that combines convolutional neural networks (CNN) and long short-term memory networks (LSTM), and introduces attention mechanism to enhance the model's ability to recognize complex circuits. This method can automatically learn and optimize feature extraction and classification models, reduce reliance on manual experience through training on large amounts of data, and improve the intelligence level of detection. Especially, by combining attention mechanisms and LSTM models, it is possible to more effectively capture small anomalies in circuit design and improve the accuracy and efficiency of hardware Trojan detection. The experimental results show that the proposed CNN-Attention-LSTM model exhibits superior Trojan detection performance and good generalization ability on different datasets, with an precision of 96.3%, a recall rate of 94.7%, and an F1 score of 95.5%.

Correlation of the L-mode density limit with edge collisionality

Abstract The ``density limit'' is one of the fundamental bounds on tokamak operating space, and is commonly estimated via the empirical Greenwald scaling. This limit has garnered renewed interest in recent years as it has become clear that ITER and many tokamak pilot plant concepts must operate near or above the widely-used Greenwald limit to achieve their objectives. Evidence has also grown that the Greenwald scaling - in its remarkable simplicity - may not capture the full complexity of the disruptive density limit. In this study, we assemble a multi-machine database to quantify the effectiveness of the Greenwald limit as a predictor of the L-mode density limit and identify alternative stability metrics. We find that a two-parameter dimensionless boundary in the plasma edge, $\nu_{*\rm, edge}^{\rm limit} = 3.0 \beta_{T,{\rm edge}}^{-0.4}$, achieves significantly higher accuracy (true negative rate of 97.7\% at a true positive rate of 95\%) than the Greenwald limit (true negative rate 86.1\% at a true positive rate of 95\%) across a multi-machine dataset including metal- and carbon-wall tokamaks (AUG, C-Mod, DIII-D, and TCV). The collisionality boundary presented here can be applied for density limit avoidance in current devices and in ITER, where it can be measured and responded to in real time.

Enhancing YOLOv8’s Performance in Complex Traffic Scenarios: Optimization Design for Handling Long-Distance Dependencies and Complex Feature Relationships

In recent years, the field of deep learning and computer vision has increasingly focused on the problem of vehicle target detection, becoming the forefront of many technological innovations. YOLOv8, as an efficient vehicle target detection model, has achieved good results in many scenarios. However, when faced with complex traffic scenarios, such as occluded targets, small target detection, changes in lighting, and variable weather conditions, YOLOv8 still has insufficient detection accuracy and robustness. To address these issues, this paper delves into the optimization strategies of YOLOv8 in the field of vehicle target detection, focusing on the EMA module in the backbone part and replacing the original SPPF module with focal modulation technology, all of which effectively improved the model’s performance. At the same time, modifications to the head part were approached with caution to avoid unnecessary interference with the original design. The experiment used the UA-DETRAC dataset, which contains a variety of traffic scenarios, a rich variety of vehicle types, and complex dynamic environments, making it suitable for evaluating and validating the performance of traffic monitoring systems. The 5-fold cross-validation method was used to ensure the reliability and comprehensiveness of the evaluation results. The final results showed that the improved model’s precision rate increased from 0.859 to 0.961, the recall rate from 0.83 to 0.908, and the mAP50 from 0.881 to 0.962. Meanwhile, the optimized YOLOv8 model demonstrated strong robustness in terms of detection accuracy and the ability to adapt to complex environments.

Segmentation and classification of brain tumor using Taylor fire hawk optimization enabled deep learning approach

ABSTRACT The brain is a crucial organ that controls the body’s neural system. The tumor develops and spreads across the brain as a result of irregular cell generation. The provision of substantial treatment to patients requires the early diagnosis of malignancies. However, timely diagnosis and accurate classification were difficult in the conventional models. Thus, the Taylor Fire Hawk optimization (TFHO) is implemented here for effective segmentation and classification. The TFHO is the merging of the Taylor series and Fire Hawk Optimizer (FHO). The de-noising is accomplished by the adaptive median filter, and the segmentation is carried out using M-Net, which has been trained by TFHO. Subsequently, image augmentation is performed to increase the image dimension, followed by the extraction of effective features. Finally, DenseNet is used for the classification, and the training is done by TFHO. The introduced method obtained 94.86% accuracy, 92.83% Negative Predictive Values, 89.33% Positive Predictive Values (PPV), 95.91% True Positive Rate (TPR), 4.37% False Negative Rate (FNR), and 90.98% F1-score.

UCapsNet: A Two-Stage Deep Learning Model Using U-Net and Capsule Network for Breast Cancer Segmentation and Classification in Ultrasound Imaging

Background/Objectives: Breast cancer remains one of the biggest health challenges for women worldwide, and early detection can be truly lifesaving. Although ultrasound imaging is commonly used to detect tumors, the images are not always of sufficient quality, and, thus, traditional U-Net models often miss the finer details needed for accurate detection. This outcome can result in lower accuracy, making early and precise diagnosis more difficult. Methods: This study presents an enhanced U-Net model integrated with a Capsule Network (called UCapsNet) to overcome the limitations of conventional techniques. Our approach improves segmentation by leveraging higher filter counts and skip connections, while the capsule network enhances classification by preserving spatial hierarchies through dynamic routing. The proposed UCapsNet model operates in two stages: first, it segments tumor regions using an enhanced U-Net, followed by a classification of the segmented images with the capsule network. Results: We have tested our model against well-known pre-trained models, including VGG-19, DenseNet, MobileNet, ResNet-50, and Xception. By properly addressing the limitations found in previous studies and using a capsule network trained on the Breast Ultrasound Image (BUSI) dataset, our model resulted in top-achieving impressive precision, recall, and accuracy rates of 98.12%, 99.52%, and 99.22%, respectively. Conclusions: By combining the U-Net’s powerful segmentation capabilities with the capsule network’s high classification accuracy, UCapsNet boosts diagnostic precision and addresses key weaknesses in existing methods. The findings demonstrate that the proposed model is not only more effective in detecting tumors but also more reliable for practical applications in clinical settings.

Bias and Its Consequences : A Study of Machine Learning Performance

This paper addresses the concern about bias affecting the results of machine learning models. For this purpose, it uses the Adult Income dataset from OpenML for income classification. The conditions for bias are induced by underrepresenting people that earn <= $50K in training data, thus checking the behavior of different models when encountering such a skewed distribution. Key metrics, namely accuracy and specificity (True Negative Rate), were analyzed for unbiased and biased training scenarios. The results show that Naive Bayes and Random Forest models were resistant to bias, but others, including SVM and Logistic Regression, suffered major performance drops. This study throws light on the robustness of different classifiers when exposed to biased data, requiring further bias mitigation strategies in real-world applications. This paper actually examines critically how bias in training data can significantly affect the performance of prediction, fairness, and model selection in income classification tasks.

ML-based Anomaly Detection for CAN Bus Network in Agriculture Machinery

The adoption of advanced automation and next-generation technologies like the Internet of Things (IoT) and modern communication networks has revolutionized the food and agriculture sector, boosting the efficiency and precision of farm machinery. However, this increased inter-connectivity has also exposed significant vulnerabilities, particularly in Controller Area Network (CAN) protocols, widely used in advanced agricultural machinery and equipment. Due to its lack of inherent security features, CAN is susceptible to various cyber-attacks, potentially leading to severe consequences if these attacks remain undetected and unmitigated. This paper introduces a supervised machine learning (ML)-based anomaly detection system (CAN-ADS) designed to detect various cyber-attacks on CAN-based agricultural machinery. The system leverages network traffic augmentation and data balancing techniques to train ML algorithms on CAN-specific datasets. Experimental results show that CAN-ADS achieves high accuracy (approx 98%) and true-positive rates with low false-negative rates (approx 1%).

Employing Xception convolutional neural network through high-precision MRI analysis for brain tumor diagnosis

The classification of brain tumors from medical imaging is pivotal for accurate medical diagnosis but remains challenging due to the intricate morphologies of tumors and the precision required. Existing methodologies, including manual MRI evaluations and computer-assisted systems, primarily utilize conventional machine learning and pre-trained deep learning models. These systems often suffer from overfitting due to modest medical imaging datasets and exhibit limited generalizability on unseen data, alongside substantial computational demands that hinder real-time application. To enhance diagnostic accuracy and reliability, this research introduces an advanced model utilizing the Xception architecture, enriched with additional batch normalization and dropout layers to mitigate overfitting. This model is further refined by leveraging large-scale data through transfer learning and employing a customized dense layer setup tailored to effectively distinguish between meningioma, glioma, and pituitary tumor categories. This hybrid method not only capitalizes on the strengths of pre-trained network features but also adapts specific training to a targeted dataset, thereby improving the generalization capacity of the model across different imaging conditions. Demonstrating an important improvement in diagnostic performance, the proposed model achieves a classification accuracy of 98.039% on the test dataset, with precision and recall rates above 96% for all categories. These results underscore the possibility of the model as a reliable diagnostic tool in clinical settings, significantly surpassing existing diagnostic protocols for brain tumors.

A robust distance-based approach for detecting multidimensional outliers

ABSTRACT Identifying outliers in data analysis is a critical task, as outliers can significantly influence the results and conclusions drawn from a dataset. This study explores the use of the Mahalanobis distance metric for detecting outliers in multivariate data, focusing on a novel approach inspired by the work of M. Falk, [On mad and comedians, Ann. Inst. Stat. Math. 49 (1997), pp. 615–644]. The proposed method is rigorously tested through extensive simulation analysis, where it demonstrates high True Positive Rates (TPR) and low False Positive Rates (FPR) when compared to other existing outlier detection techniques. Through extensive simulation analysis, we empirically evaluate the affine equivariance and breakdown properties of our proposed distance measure and it is evident from the outputs that our robust distance measure demonstrates effective results with respect to the measures FPR and TPR. The proposed method was applied to seven different datasets, showing promising true positive rates (TPR) and false positive rates (FPR), and it outperformed several well-known outlier identification approaches. We can effectively use our proposed distance measure in fields demanding outlier detection.

Experimental identification of ion cyclotron emission on HL-2A using YOLO neural network algorithm

Abstract Identification of magnetohydrodynamics (MHD) instabilities with neural networks has been extensively applied in the research of magnetically controlled fusion plasmas. Ion Cyclotron Emission (ICE) is a potential fast ion diagnostic method in burning plasmas. To assess ICE as a fast ion diagnostic for International Thermonuclear Experimental Reactor, real-time identification of ICE is required in the fast ion diagnostic flow. In the present work, we employed YOLO (You Only Look Once) to identify core and edge ICE in a large labeled database of HL-2A discharges, achieving a precision of 85.4% and a recall rate of 77.3%. Subsequent improvements to the YOLO model resulted in a noteworthy 8.3% increment in the recall rate. The developed identification method demonstrates significant potential for real-time application in identifying MHD instabilities.

Retrieve–Revise–Refine: A novel framework for retrieval of concise entailing legal article set

The retrieval of entailing legal article sets aims to identify a concise set of legal articles that holds an entailment relationship with a legal query or its negation. Unlike traditional information retrieval that focuses on relevance ranking, this task demands conciseness. However, prior research has inadequately addressed this need by employing traditional methods. To bridge this gap, we propose a three-stage Retrieve–Revise–Refine framework which explicitly addresses the need for conciseness by utilizing both small and large language models (LMs) in distinct yet complementary roles. Empirical evaluations on the COLIEE 2022 and 2023 datasets demonstrate that our framework significantly enhances performance, achieving absolute increases in the macro F2 score by 3.17% and 4.24% over previous state-of-the-art methods, respectively. Specifically, our Retrieve stage, employing various tailored fine-tuning strategies for small LMs, achieved a recall rate exceeding 0.90 in the top-5 results alone—ensuring comprehensive coverage of entailing articles. In the subsequent Revise stage, large LMs narrow this set, improving precision while sacrificing minimal coverage. The Refine stage further enhances precision by leveraging specialized insights from small LMs, resulting in a relative improvement of up to 19.15% in the number of concise article sets retrieved compared to previous methods. Our framework offers a promising direction for further research on specialized methods for retrieving concise sets of entailing legal articles, thereby more effectively meeting the task’s demands.

CrackNet: A Hybrid Model for Crack Segmentation with Dynamic Loss Function

Cracks are a common form of damage in infrastructure, posing significant risks to both personal safety and property. Along with the development of deep learning, visual-based crack automatic detection has been widely studied. However, this task is still challenging due to complex crack topology, noisy backgrounds, unbalanced categories, etc. To address these challenges, this research proposes a novel hybrid network, named CrackNet, which leverages the strengths of both CNN and transformer. On the encoder side, CNNs are employed to extract multi-level local features, while transformers are used to model global dependencies. Additionally, a strip pooling module is introduced to suppress irrelevant regions and enhance the network’s ability to segment narrow and elongated cracks. On the decoder side, an attention-based skip connection strategy and a mixed up-sampling module are implemented to restore detailed information. Furthermore, a joint learning loss combining Dice and cross-entropy with dynamic weighting is proposed to mitigate the effects of severe class imbalance. CrackNet is trained and evaluated on three public crack datasets, and experimental results show that the proposed model outperforms several well-known deep neural networks, with a particularly noticeable improvement in recall rate.

Infrared and Visible Camera Integration for Detection and Tracking of Small UAVs: Systematic Evaluation

Given the recent proliferation of Unmanned Aerial Systems (UASs) and the consequent importance of counter-UASs, this project aims to perform the detection and tracking of small non-cooperative UASs using Electro-optical (EO) and Infrared (IR) sensors. Two data integration techniques, at the decision and pixel levels, are compared with the use of each sensor independently to evaluate the system robustness in different operational conditions. The data are submitted to a YOLOv7 detector merged with a ByteTrack tracker. For training and validation, additional efforts are made towards creating datasets of spatially and temporally aligned EO and IR annotated Unmanned Aerial Vehicle (UAV) frames and videos. These consist of the acquisition of real data captured from a workstation on the ground, followed by image calibration, image alignment, the application of bias-removal techniques, and data augmentation methods to artificially create images. The performance of the detector across datasets shows an average precision of 88.4%, recall of 85.4%, and mAP@0.5 of 88.5%. Tests conducted on the decision-level fusion architecture demonstrate notable gains in recall and precision, although at the expense of lower frame rates. Precision, recall, and frame rate are not improved by the pixel-level fusion design.

Genome-Wide, Non-Invasive Prenatal Testing for rare chromosomal abnormalities: A systematic review and meta-analysis of diagnostic test accuracy.

Genome-Wide Non-Invasive Prenatal Testing (GW-NIPT) can provide positive results not only for common autosomal aneuploidies but also for rare autosomal trisomies (RATs) and structural chromosomal abnormalities (StrCAs). Due to their rarity, there is currently insufficient information on positive predictive value PPV of RAT and StrCA-positive cases in the literature. In this study, the screening accuracy and pregnancy outcomes of cases positive for rare chromosomal abnormalities were examined based on publications in which GW-NIPT testing was performed. True positive cases were determined using two different methodologies. One was a confirmed methodology, where only cases validated by genetic testing were considered true positives with a definite diagnosis, and the other was an extended methodology, where, in addition to cases confirmed by genetic testing, intrauterine fetal death and termination of pregnancy due to an abnormality confirmed by ultrasound examination were also considered true positives, where no diagnosis had been made but the fetus was probably affected. Seventeen studies were analyzed, with a total GW-NIPT population of 740,076. Of these, 1,738 were RAT positive. Using the confirmed method, we found the highest rates of true positives in T16, followed by T22, and T2, using the extended method, the highest rate of true positives in T15, T16 and T22. This is the first meta-analysis to determine the frequency of rare chromosomal abnormalities, test-positive rates, and the PPV of each chromosomal abnormality with high precision. Our results could aid pre- and post-test genetic counselling and help patients and clinicians in their decision-making.

Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection

Credit card fraud detection is a critical challenge in the financial sector due to the rapidly evolving tactics of fraudsters and the significant class imbalance betweenegitimate and fraudulent transactions. Traditional models, while effective to some extent, often suffer from high false positive rates and fail to generalize well to emerging fraud patterns. In this paper, we propose a novel approach that integrates a Mixture of Experts (MoE) model with a Deep Neural Network-based Synthetic Minority Over-sampling Technique (DNN-SMOTE) to enhance fraud detection performance. The MoE modeleverages multiple specialized expert networks, each trained to detect specific types of fraud, while the DNN-SMOTE generates high-quality synthetic samples to address the class imbalance. Our experimental results on a publicly available dataset demonstrate that the proposed method achieves a classification accuracy of 99.93%, a true positive rate of 84.69%, and a true negative rate of 99.95%. The Matthews Correlation Coefficient (MCC) of 0.7883 further highlights the model’s balanced performance in detecting fraudulent transactions. These results underscore the effectiveness of combining MoE with DNN-SMOTE, offering a robust solution for real-world credit card fraud detection scenarios.

When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?

With the development of blockchain technology, smart contracts have become an important component of blockchain applications. Despite their crucial role, the development of smart contracts may introduce vulnerabilities and potentially lead to severe consequences, such as financial losses. Meanwhile, large language models, represented by ChatGPT, have gained great attentions, showcasing great capabilities in code analysis tasks. In this paper, we presented an empirical study to investigate the performance of ChatGPT in identifying smart contract vulnerabilities. Initially, we evaluated ChatGPT's effectiveness using a publicly available smart contract dataset. Our findings discover that while ChatGPT achieves a high recall rate, its precision in pinpointing smart contract vulnerabilities is limited. Furthermore, ChatGPT's performance varies when detecting different vulnerability types. We delved into the root causes for the false positives generated by ChatGPT, and categorized them into four groups. Second, by comparing ChatGPT with other state-of-the-art smart contract vulnerability detection tools, we found that ChatGPT's F-score is lower than others for 3 out of the 7 vulnerabilities. In the case of the remaining 4 vulnerabilities, ChatGPT exhibits a slight advantage over these tools. Finally, we analyzed the limitation of ChatGPT in smart contract vulnerability detection, revealing that the robustness of ChatGPT in this field needs to be improved from two aspects: its uncertainty in answering questions; and the limited length of the detected code. In general, our research provides insights into the strengths and weaknesses of employing large language models, specifically ChatGPT, for the detection of smart contract vulnerabilities.