Intelligent Detection Research Articles

A Scoping Review of Artificial Intelligence Detection of Voice Pathology: Challenges and Opportunities.

Survey the current literature on artificial intelligence (AI) applications for detecting and classifying vocal pathology using voice recordings, and identify challenges and opportunities for advancing the field forward. PubMed, EMBASE, CINAHL, and Scopus databases. A comprehensive literature search was performed following the Preferred Reporting Items for Systematic Reviews and Meta-analysesExtension for Scoping Reviews guidelines. Peer-reviewed journal articles in the English language were included if they used an AI approach to detect or classify pathological voices using voice recordings from patients diagnosed with vocal pathologies. Eighty-two studies were included in the review between the years 2000 and 2023, with an increase in publication rate from one study per year in 2012 to 10 per year in 2022. Seventy-two studies (88%) were aimed at detecting the presence of voice pathology, 24 (29%) at classifying the type of voice pathology present, and 4 (5%) at assessing pathological voice using the Grade, Roughness, Breathiness, Asthenia, and Strainscale. Thirty-six databases were used to collect and analyze speech samples. Fourteen articles (17%) did not provide information about their AI model validation methodology. Zero studies moved beyond the preclinical and offline AI model development stages. Zero studies specified following a reporting guideline for AI research. There is rising interest in the potential of AI technology to aid the detection and classification of voice pathology. Three challenges-and areas of opportunities-for advancing this research are heterogeneity of databases, lack of clinical validation studies, and inconsistent reporting.

Novel intrusion detection system based on a downsized kernel method for cybersecurity in smart agriculture

Smart farming aims to ameliorate the quantity and quality of farms products using modern information and communication technologies. Agriculture has always used cutting-edge technology to improve profitability, efficiency, and safety as well as creating the opportunity for more environmentally friendly operations. In smart agriculture network communication between smart devices is necessary to managing the agriculture process. Consequently, the possibility of information being exposed to hacking is very likely, which makes the information security system extremely important and cannot be neglected. Even though many solutions have been developed to overcome cyberattacks in smart networks, some limitations are observed, such as solving multi-class problems, high feature dimensions, and overhead computation. To address the aforementioned issues, an intelligent Intrusion Detection System (IDS) for identifying cyberattacks in the Internet of Agriculture Things (IoAT) is proposed. The developed model uses a proposed reduced kernel method, the Downsized Kernel Partial Least Square (DKPLS) to extract and reduce data feature dimension to improve detection performance. The DRKPLS approach is used to reduce the dimension of a kernel matrix generated using the Kernel Partial Least Square (KPLS) technique by selecting the most important features. In classification phase, the Kernel Extreme Learning Machine (KELM) is used to classify data for binary and multi-class classification. The proposed IDS is evaluated on a new Industrial IoT Dataset, X-IIoTID. The developed approach achieved higher performances for binary classification and for multi–class classification compared to others machine learning and deep learning approaches. The proposed approach achieved an accuracy rate of 99.92% for binary classification and 99.99% for multi–class classification. Furthermore, the higher percentage in multi-class classification is obtained for the two types of attacks Ransom Denial of Service (RDoS) and Command_Control respectively.

Intelligent detection method of microparticle virus in silkworm based on YOLOv8 improved algorithm

AbstractThe presence of microparticle viruses significantly impacts the quality of silkworm seeds for domestic sericulture, making their exclusion from detection in silkworm seed production crucial. Traditional methods for detecting microparticle viruses in silkworms, such as manual microscopic observation, molecular biology, and immunological approaches, are cumbersome and unable to achieve intelligent, batch real-time detection. To address this challenge, we employ the YOLOv8 algorithm in this paper. Firstly, NAM attention is introduced in the original algorithm’s Backbone component, allowing the model to extract more generic feature information. Secondly, ODConv replaces Conv in the Head component of the original algorithm, enhancing the model’s ability to identify microparticle viruses. Finally, NWD-LOSS modifies the CIoU loss of the original algorithm to obtain a more accurate prediction box. Experimental results demonstrate that the NN-YOLOv8 model outperforms mainstream detection algorithms in detecting silkworm microparticle diseases. With an average detection time of 22.6 milliseconds per image, the model shows promising prospects for future applications. This model improvement enhances detection efficiency and reduces human resource costs, effectively realizing detection intelligence.

Automated crack detection of train rivets using fluorescent magnetic particle inspection and instance segmentation

The railway rivet is one of the most important and easily damaged parts of the connection. If rivets develop cracks during the production process, their load-bearing capacity will be reduced, thereby increasing the risk of failure. Fluorescent magnetic particle flaw detection (FMPFD) is a widely used inspection method for train fasteners. Manual inspection is not only time-consuming but also prone to miss detection, therefore intelligent detection system has important application value. However, the fluorescent crack images obtained by FMPFD present challenges for intelligent detection, such as the dense, multi-scaled and uninstantiated cracks. In addition, there is limited research on fluorescent rivet crack detection. This paper adopts instance segmentation to achieve automatic cracks detection of rivets. A decentralized target center and low overlap rate labeling method is proposed, and a Gaussian-weighted correction post-processing method is introduced to improve the recall rate in the areas of dense cracks. An efficient channel spatial attention mechanism for feature extraction is proposed in order to enhance the detection of multi-scale cracks. For uninstantiated cracks, an improvement of crack detection in uninstantiated regions based on multi task feature learning is proposed, thoroughly utilizing the semantic and spatial features of the fluorescent cracks. The experimental results show that the improved methods are better than the baseline and some cutting-edge algorithms, achieving a recall rate and mAP0.5 of 86.4% and 90.3%. In addition, a single coil non-contact train rivet composite magnetization device is built for rivets that can magnetize different shapes of rivets and has universality.

Trajectory Tracking Algorithm Study of Coal Mine Water Detector Drilling Bar Installation

Mechanical water detection is recognized as the most reliable and safe production technology for coal mines, mainly for the detection of water hazards in pre-mining operations. Intelligent water detectors are currently the main research direction in mechanical water detection, and the automatic installation of drilling bars is the key to achieving intelligent water detection. Improving the connection accuracy in the process of installing drilling bars is an important research topic for the improvement of control links. To improve the connection accuracy of the drilling bars at the time of supplying material, we used the modified Denavit–Hartenberg method to analyze the motion gestures of the supplied material device and the Lagrange equation to establish a dynamic analysis model. We aimed at better control precision by improving the sliding mode control algorithm and at increasing the convergence rate of tracking errors with a sliding controller based on an exponential approximation law and using saturated functions instead of the symbol functions in the reaching law to weaken the vibration in the control process. We then used particle swarm optimization (PSO) to find the optimum combination parameters of the sliding mode controllers and test the performance of the sliding mode controllers before and after PSO with MATLAB/Simulink. The results showed that the optimized controller has a strong resistance to parameter fluctuations, and the system responds quickly, achieves a good performance, and improves the convergence rate of tracking errors.

Unsupervised anomaly detection for power batteries: A temporal convolution autoencoder framework

Abstract To prevent potential abnormalities from escalating into critical faults, a rapid and precise algorithm should be employed for detecting power battery anomalies. An unsupervised model based on temporal convolutional autoencoder (TCAE) that can quickly and accurately identify abnormal power battery data was proposed. Its encoder utilized a temporal convolutional network (TCN) structure with residuals to parallelly process data while capturing time dependencies. A novel TCN structure with an effect–cause relationship was developed for the decoder. The same-time-scale connection was established between the encoder and decoder to improve the model performance. The validity of the proposed model was confirmed using a real-world car dataset. Compared with the GRU-AE model, the proposed approach reduced the parameter count and mean square error by 19.5% and 71.9%, respectively. This study provides insights into the intelligent battery pack abnormality detection technology.

Diagnostic accuracy of artificial intelligence versus manual detection in marginal bone loss around fixed semicolon. a systematic review.

The aim of the review is to evaluate the existing precision of artificial intelligence (AI) in detecting Marginal Bone Loss (MBL) around prosthetic crowns using 2-Dimentional radiographs. It also summarises the recent advances and future challenges associated to their clinical application. A literature survey of electronic databases was conducted in November 2023 to recognize the relevant articles. MeSH terms/keywords were used to search ("panoramic" OR "pantomogram" OR "orthopantomogram" OR "opg" OR "periapical") AND ("artificial intelligence" OR "deep" OR "machine" OR "automated" OR "learning") AND ("periodontal bone loss") AND ("prosthetic crown") in PubMed database, SCOPUS, COCHRANE library, EMBASE, CINAHL and Science Direct. The searches identified 49 relevant articles, of them 5 articles met the inclusion criteria were included. The outcomes measured were sensitivity, specificity and accuracy of AI models versus manual detection in panoramic and intraoral radiographs. Few studies reported no significant difference between AI and manual detection, whereas majority demonstrated the superior ability of AI in detecting MBL. AI models show promising accuracy in analysing complex datasets and generate accurate predictions in the MBL around fixed prosthesis. However, these models are still in the developmental phase. Therefore, it is crucial to assess the effectiveness and reliability of these models before recommending their use in clinical practice.

An automated approach for real-time informative frames classification in laryngeal endoscopy using deep learning.

Informative image selection in laryngoscopy has the potential for improving automatic data extraction alone, for selective data storage and a faster review process, or in combination with other artificial intelligence (AI) detection or diagnosis models. This paper aims to demonstrate the feasibility of AI in providing automatic informative laryngoscopy frame selection also capable of working in real-time providing visual feedback to guide the otolaryngologist during the examination. Several deep learning models were trained and tested on an internal dataset (n = 5147 images) and then tested on an external test set (n = 646 images) composed of both white light and narrow band images. Four videos were used to assess the real-time performance of the best-performing model. ResNet-50, pre-trained with the pretext strategy, reached a precision = 95% vs. 97%, recall = 97% vs, 89%, and the F1-score = 96% vs. 93% on the internal and external test set respectively (p = 0.062). The four testing videos are provided in the supplemental materials. The deep learning model demonstrated excellent performance in identifying diagnostically relevant frames within laryngoscopic videos. With its solid accuracy and real-time capabilities, the system is promising for its development in a clinical setting, either autonomously for objective quality control or in conjunction with other algorithms within a comprehensive AI toolset aimed at enhancing tumor detection and diagnosis.

The 2023 top 10 list of endoscopy topics in medical publishing: an annual review by the American Society for Gastrointestinal Endoscopy Editorial Board

Using a systematic literature search of original articles published during 2023 in Gastrointestinal Endoscopy (GIE) and other high-impact medical and gastroenterology journals, the GIE Editorial Board of the American Society for Gastrointestinal Endoscopy compiled a list of the top 10 most significant topic areas in general and advanced GI endoscopy during the year. Each GIE Editorial Board member was directed to consider 3 criteria in generating candidate topics-significance, novelty, and impact on global clinical practice-and subject matter consensus was facilitated by the Chair through electronic voting and a meeting of the entire GIE Editorial Board. The 10 identified areas collectively represent advances in the following endoscopic spheres: GI bleeding, endohepatology, endoscopic palliation, artificial intelligence and polyp detection, artificial intelligence beyond the colon, better polypectomy and endoscopic mucosal resection, how to make endoscopy units greener, high quality upper endoscopy, endoscopic tissue apposition/closure devices, and endoscopic submucosal dissection. Each board member was assigned a topic area around which summarized relevant important articles, thereby generating this overview of the "top 10" endoscopic advances of 2023.

False alarm suppressing for passive underwater acoustic target detecting with computer visual techniques

Given the complexity of marine environments, the detection of underwater acoustic targets frequently relies on manual visual interpretation of the imagery displayed on monitoring screens, which limits the application of related technologies on unmanned platforms. To replace human visual observation, understanding, and reasoning within underwater unmanned equipment, this study explores an intelligent detection method for Bearing Time Records based on computer vision techniques, drawing inspiration from human visual perception in detecting targets on BTR images. Firstly, an unsupervised learning method is employed to extract the bases representing various signal patterns from BTR images, with clear physical meanings. Subsequently, we utilize both algorithm-driven and data-driven methods for automated base classification, and both methods achieve a remarkable 100% accuracy rate in automatic base classification. In comparison to human visual detection, this automated approach exhibits a false alarm rate of less than 3%.

Intelligent detection of left ventricular hypertrophy from pediatric echocardiography videos

AbstractLeft ventricular hypertrophy (LVH) is a common clinical manifestation associated with cardiovascular adverse events. Relying solely on the subjective judgment, it is challenging to promptly and accurately diagnose mild LVH. Quantitatively measuring the interventricular septum and left ventricular posterior wall to diagnose mild LVH is a time‐consuming and labor‐intensive process that is prone to errors. To propose a novel method for rapid and automatic end‐to‐end diagnosis of mild LVH. We propose a novel end‐to‐end automated method for detecting mild LVH. This method achieves rapid end‐to‐end detection of mild LVH in echocardiographic videos without the need for quantitative measurements. Initially, representative frames are extracted from echocardiographic videos, and these frames are then automatically diagnosed by the proposed network to detect LVH. The network architecture primarily consists of three key components: a feature extractor, bidirectional LSTM, and attention module. The Vit‐b model achieved 88% video classification accuracy in the experiment where 32 frames are extracted, and the ViT‐l model achieves 92% video classification accuracy in the experiment where 16 frames are extracted. It is shown experimentally that extracting fewer video frames can diagnose LVH more accurately. The experiments illustrate the superior performance and competitiveness of this method compared to other approaches, potentially applicable to the clinic.

Enhanced Fire Alarm Systems using Deep Learning for Smoke and Fire Detection

Enhanced Fire Alarm Systems using Deep Learning for Smoke and Fire Detection

EResNet-SVM: an overfitting-relieved deep learning model for recognition of plant diseases and pests.

The accurate recognition and early warning for plant diseases and pests are a prerequisite of intelligent prevention and control for plant diseases and pests. As a result of the phenotype similarity of the hazarded plant after plant diseases and pests occur, as well as the interference of the external environment, traditional deep learning models often face the overfitting problem in phenotype recognition of plant diseases and pests, which leads to not only the slow convergence speed of the network, but also low recognition accuracy. Motivated by the above problems, the present study proposes a deep learning model EResNet-support vector machine (SVM) to alleviate the overfitting for the recognition and classification of plant diseases and pests. First, the feature extraction capability of the model is improved by increasing feature extraction layers in the convolutional neural network. Second, the order-reduced modules are embedded and a sparsely activated function is introduced to reduce model complexity and alleviate overfitting. Finally, a classifier fused by SVM and fully connected layers are introduced to transforms the original non-linear classification problem into a linear classification problem in high-dimensional space to further alleviate the overfitting and improve the recognition accuracy of plant diseases and pests. The ablation experiments further demonstrate that the fused structure can effectively alleviate the overfitting and improve the recognition accuracy. The experimental recognition results for typical plant diseases and pests show that the proposed EResNet-SVM model has 99.30% test accuracy for eight conditions (seven plant diseases and one normal), which is 5.90% higher than the original ResNet18. Compared with the classic AlexNet, GoogLeNet, Xception, SqueezeNet and DenseNet201 models, the accuracy of the EResNet-SVM model has improved by 5.10%, 7%, 8.10%, 6.20% and 1.90%, respectively. The testing accuracy of the EResNet-SVM model for 6 insect pests is 100%, which is 3.90% higher than that of the original ResNet18 model. This research provides not only useful references for alleviating the overfitting problem in deep learning, but also a theoretical and technical support for the intelligent detection and control of plant diseases and pests. © 2024 Society of Chemical Industry.

Efficient Large-Scale IoT Botnet Detection through GraphSAINT-Based Subgraph Sampling and Graph Isomorphism Network

In recent years, with the rapid development of the Internet of Things, large-scale botnet attacks have occurred frequently and have become an important challenge to network security. As artificial intelligence technology continues to evolve, intelligent detection solutions for botnets are constantly emerging. Although graph neural networks are widely used for botnet detection, directly handling large-scale botnet data becomes inefficient and challenging as the number of infected hosts increases and the network scale expands. Especially in the process of node level learning and inference, a large number of nodes and edges need to be processed, leading to a significant increase in computational complexity and posing new challenges to network security. This paper presents a novel approach that can accurately identify diverse intricate botnet architectures in extensive IoT networks based on the aforementioned circumstance. By utilizing GraphSAINT to process large-scale IoT botnet graph data, efficient and unbiased subgraph sampling has been achieved. In addition, a solution with enhanced information representation capability has been developed based on the Graph Isomorphism Network (GIN) for botnet detection. Compared with the five currently popular graph neural network (GNN) models, our approach has been tested on C2, P2P, and Chord datasets, and higher accuracy has been achieved.

An intelligent behavioral-based DDOS attack detection method using adaptive time intervals

An intelligent behavioral-based DDOS attack detection method using adaptive time intervals

Advanced Machine Learning-Driven Security and Anomaly Identification in Inverter-Based Cyber-Physical Microgrids

In a landscape dominated by the digitalization of energy networks, safeguarding cyber-physical microgrids and against breaches anomalies emerges as a critical imperative. This study pioneers inventive methodologies for Intelligent Detection of Intrusions and Anomalies in Inverter-centric Cyber-Physical Microgrids, leveraging state-of-the-art machine learning paradigms. Using the combined power of LSTM and Convolutional Neural Networks, our suggested approach finds breaches and aberrations in microgrid structures with remarkable accuracy and efficiency. Additionally, we integrate the effectiveness of Gradient Boosting Machines to enhance the overall detection capabilities. Experimental findings underscore the efficacy of our machine learning-driven approach, with CNN achieving a precision of 95%, recall of 92%, and F1-score of 93% in intrusion detection, while LSTM attains a precision of 93%, recall of 91%, and F1-score of 92% in anomaly identification. Furthermore, GBM contributes to achieving an overall efficiency of 96%. Our approach not only bolsters microgrid resilience but also lays the foundation for a secure energy future. In an increasingly interconnected world, the integration of these sophisticated techniques not only bolsters microgrid resilience but also lays the foundation for a secure energy future. By embracing innovation at the convergence of machine learning and energy systems, we stride toward fortified and dependable cyber-physical microgrids.

RotatedStomataNet: a deep rotated object detection network for directional stomata phenotype analysis.

Innovatively, we consider stomatal detection as rotated object detection and provide an end-to-end, batch, rotated, real-time stomatal density and aperture size intelligent detection and identification system, RotatedeStomataNet. Stomata acts as a pathway for air and water vapor in the course of respiration, transpiration, and other gas metabolism, so the stomata phenotype is important for plant growth and development. Intelligent detection of high-throughput stoma is a key issue. Nevertheless, currently available methods usually suffer from detection errors or cumbersome operations when facing densely and unevenly arranged stomata. The proposed RotatedStomataNet innovatively regards stomata detection as rotated object detection, enabling an end-to-end, real-time, and intelligent phenotype analysis of stomata and apertures. The system is constructed based on the Arabidopsis and maize stomatal data sets acquired destructively, and the maize stomatal data set acquired in a non-destructive way, enabling the one-stop automatic collection of phenotypic, such as the location, density, length, and width of stomata and apertures without step-by-step operations. The accuracy of this system to acquire stomata and apertures has been well demonstrated in monocotyledon and dicotyledon, such as Arabidopsis, soybean, wheat, and maize. The experimental results that the prediction results of the method are consistent with those of manual labeling. The test sets, the system code, and their usage are also given ( https://github.com/AITAhenu/RotatedStomataNet ).

Screening mammography performance according to breast density: a comparison between radiologists versus standalone intelligence detection

BackgroundArtificial intelligence (AI) algorithms for the independent assessment of screening mammograms have not been well established in a large screening cohort of Asian women. We compared the performance of screening digital mammography considering breast density, between radiologists and AI standalone detection among Korean women.MethodsWe retrospectively included 89,855 Korean women who underwent their initial screening digital mammography from 2009 to 2020. Breast cancer within 12 months of the screening mammography was the reference standard, according to the National Cancer Registry. Lunit software was used to determine the probability of malignancy scores, with a cutoff of 10% for breast cancer detection. The AI’s performance was compared with that of the final Breast Imaging Reporting and Data System category, as recorded by breast radiologists. Breast density was classified into four categories (A–D) based on the radiologist and AI-based assessments. The performance metrics (cancer detection rate [CDR], sensitivity, specificity, positive predictive value [PPV], recall rate, and area under the receiver operating characteristic curve [AUC]) were compared across breast density categories.ResultsMean participant age was 43.5 ± 8.7 years; 143 breast cancer cases were identified within 12 months. The CDRs (1.1/1000 examination) and sensitivity values showed no significant differences between radiologist and AI-based results (69.9% [95% confidence interval [CI], 61.7–77.3] vs. 67.1% [95% CI, 58.8–74.8]). However, the AI algorithm showed better specificity (93.0% [95% CI, 92.9–93.2] vs. 77.6% [95% CI, 61.7–77.9]), PPV (1.5% [95% CI, 1.2–1.9] vs. 0.5% [95% CI, 0.4–0.6]), recall rate (7.1% [95% CI, 6.9–7.2] vs. 22.5% [95% CI, 22.2–22.7]), and AUC values (0.8 [95% CI, 0.76–0.84] vs. 0.74 [95% CI, 0.7–0.78]) (all P < 0.05). Radiologist and AI-based results showed the best performance in the non-dense category; the CDR and sensitivity were higher for radiologists in the heterogeneously dense category (P = 0.059). However, the specificity, PPV, and recall rate consistently favored AI-based results across all categories, including the extremely dense category.ConclusionsAI-based software showed slightly lower sensitivity, although the difference was not statistically significant. However, it outperformed radiologists in recall rate, specificity, PPV, and AUC, with disparities most prominent in extremely dense breast tissue.

Machine learning-assisted wide-gamut fluorescence visual test paper for propazine determination in fish and seawater samples

Molecularly imprinted polymer (MIP-QDs) with fluorescence quenching ability toward propazine was synthesized for propazine detection. b(Blue)-MIP-QDs were prepared using ZnCdS/ZnS QDs via reverse micro-emulsion, whereas r(red)-MIP-QDs were synthesized using CdSe/ZnS QDs. By utilizing graphene quantum dots (GQDs) as a stable fluorescence intensity reference, the wide-gamut fluorescence test paper was constructed on the basis of mixing b-MIP-QDs, r-MIP-QDs, and GQDs under the optimal ratio. When analyzing spiked propazine in fish and seawater samples using a test paper, satisfactory recoveries of 104.0 %–114.6 % and 92.0 %–96.4 % were obtained, with corresponding limits of detection of 5.0 μg/kg and 1.0 μg/L, respectively. The RGB extractor was utilized to extract the actual fluorescence color and construct a dataset consisting of R, G, and B values, as well as concentration data from 400 samples. The SVR model of Python 3.9.7 was used to obtain and analyze the concentration and feature data. After optimization, the constructed model achieved a correlation coefficient of 0.98 and an RMSE of only 1.81, indicating high prediction accuracy and excellent generalization ability that meet quenching prediction requirements. As an intelligent and rapid detection method, this model holds significant practical significance.

Algorithm of automatic identification of diabetic retinopathy foci based on ultra-widefield scanning laser ophthalmoscopy.

To propose an algorithm for automatic detection of diabetic retinopathy (DR) lesions based on ultra-widefield scanning laser ophthalmoscopy (SLO). The algorithm utilized the FasterRCNN (Faster Regions with CNN features)+ResNet50 (Residua Network 50)+FPN (Feature Pyramid Networks) method for detecting hemorrhagic spots, cotton wool spots, exudates, and microaneurysms in DR ultra-widefield SLO. Subimage segmentation combined with a deeper residual network FasterRCNN+ResNet50 was employed for feature extraction to enhance intelligent learning rate. Feature fusion was carried out by the feature pyramid network FPN, which significantly improved lesion detection rates in SLO fundus images. By analyzing 1076 ultra-widefield SLO images provided by our hospital, with a resolution of 2600×2048 dpi, the accuracy rates for hemorrhagic spots, cotton wool spots, exudates, and microaneurysms were found to be 87.23%, 83.57%, 86.75%, and 54.94%, respectively. The proposed algorithm demonstrates intelligent detection of DR lesions in ultra-widefield SLO, providing significant advantages over traditional fundus color imaging intelligent diagnosis algorithms.