Detection Of Abnormalities Research Articles

Concept of Early Prediction and Identification of Truck Vehicle Failures Supported by In-Vehicle Telematics Platform Based on Abnormality Detection Algorithm

Concept of Early Prediction and Identification of Truck Vehicle Failures Supported by In-Vehicle Telematics Platform Based on Abnormality Detection Algorithm

Thermal Imaging-Based Abnormal Heating Detection for High-Voltage Power Equipment

Thermal infrared imaging could detect hidden faults in various types of high-voltage power equipment, which is of great significance for power inspections. However, there are still certain issues with thermal-imaging-based abnormal heating detection methods due to varying appearances of abnormal regions and complex temperature interference from backgrounds. To solve these problems, a contour-based instance segmentation network is first proposed to utilize thermal (T) and visual (RGB) images, realizing high-accuracy segmentation against complex and changing environments. Specifically, modality-specific features are encoded via two-stream backbones and fused in spatial, channel, and frequency domains. In this way, modality differences are well handled, and effective complementary information is extracted for object detection and contour initialization. The transformer decoder is further utilized to explore the long-range relationships between contour points with background points, and to achieve the deformation of contour points. Then, the auto-encoder-based reconstruction network is developed to learn the distribution of power equipment using the proposed random argument strategy. Meanwhile, the UNet-like discriminative network directly explores the differences between the reconstructed and original image, capturing the deviation of poor reconstruction regions for abnormal heating detection. Many images are acquired in transformer substations with different weathers and day times to build the datasets with pixel-level annotation. Several extensive experiments are conducted for qualitative and quantitative evaluation, while the comparison results fully prove the effectiveness and robustness of the proposed instance segmentation method. The practicality and performance of the proposed abnormal heating detection method are evaluated on image patches with different kinds of insulators.

Optimizing electroencephalogram duration for efficient detection of epileptiform abnormalities in diverse patient groups: a retrospective study

BackgroundThere is no standardized EEG duration guideline for detecting epileptiform abnormalities in patients, and research on this topic is scarce. This study aims to determine an optimal EEG duration for efficient detection of epileptiform abnormalities across different patient groups.MethodsRetrospective analysis was performed on EEG recordings and clinical data of patients with the first seizure and epilepsy. Patients were categorized based on various factors, including the interval time since the last seizure, use of anti-seizure medication (ASM), and seizure frequency. The detection ratio (DR) of epileptiform abnormalities and latency time for their discovery were calculated. Statistical analyses, including chi-square tests, logistic regression, and survival analysis were utilized to illustrate DR and latency times.ResultsIn whole-night EEG recordings, the DR was 37.6% for the first seizure group and 57.4% for the epilepsy group. Although the maximum latency times were 720 min in both two groups, DR in the first seizure group was distinctly decreased beyond 300 min. Significant factors influencing the DR included the use of ASM in the first seizure group (P < 0.05) and seizure frequency in the epilepsy group (P < 0.001). For epilepsy patients who experience a seizure at least once a month or undergo timely EEG recordings (within 24 h after a seizure), the DR significantly increases, and the maximum latency time is reduced to 600 min (P < 0.001). Additionally, the DR was significantly reduced after 240 min in epilepsy patients who had been seizure-free for more than one year.ConclusionsIn this retrospective study, we observed a maximum latency of 720 min for detecting epileptiform abnormalities in whole-night EEG recordings. Notably, epilepsy patients with a higher seizure frequency or timely EEG recordings demonstrated both a higher detection ratio and a shorter maximum latency time. For patients exhibiting a low detection ratio, such as those experiencing their first seizure or those with epilepsy who have been seizure-free for more than a year, a shorter EEG duration is recommended. These findings underscore the importance of implementing customized EEG strategies to meet the specific needs of different patient groups.

Application of deep learning-based Intrusion Detection System (IDS) in network anomaly traffic detection

This study discusses the application of deep learning technology in network intrusion detection systems (IDS) and focuses on a new model named CNN-Focal. First, reviewing traditional IDS technology, it analyzes its limitations in dealing with complex network traffic. Then, the design principle of the CNN-Focal model is described in detail, which uses threshold convolution and SoftMax multi-class classification technology to improve abnormal traffic detections accuracy and efficiency effectively. The experimental results show that CNN-Focal performs well on the open data set, demonstrating the potential and advantages of its application in the natural network environment and providing a new perspective and method for further research of deep learning in the field of network security in the future.

Genomic insights into prenatal diagnosis of congenital heart defects: value of CNV-seq and WES in clinical practice.

This study aimed to assess the efficiency of CNV-seq and WES in detecting genetic cause of congenital heart disease (CHDs) in prenatal diagnoses and to compare CNV detection rate between isolated and non-isolated CHD cases. We conducted a retrospective study of 118 Chinese fetuses diagnosed with CHD by prenatal ultrasound. Participants underwent CNV-seq and, if necessary, WES to detect chromosomal and single nucleotide variations. The overall detection rate for pathogenic or likely pathogenic chromosomal abnormalities was 16.9%, including 7.6% aneuploidies and 9.3% pathogenic/likely pathogenic copy number variations (CNVs), predominantly 22q11.2 deletion syndrome (54.4%). The sensitivity and specificity of CNV-Seq for detecting P/Lp CNVs were 95% and 100%, respectively. CNV-Seq offered a 6.7% improvement in detecting chromosomal abnormalities over karyotyping. WES further identified significant single nucleotide and small indel variations contributing to CHD in genes such as TMEM67, PLD1, ANKRD11, and PNKP, enhancing diagnostic yield by 14.8% in cases negative for CNVs. Non-isolated CHD cases exhibited higher rates of detectable chromosomal abnormalities compared to isolated cases (32.4% vs. 9.9%, p = 0.005), underlining the genetic complexity of these conditions. The combined use of CNV-seq and WES provides a comprehensive approach to prenatal genetic testing for CHDs, unveiling significant genetic cause that could impact clinical management and parental decision-making. This study supports the integration of these advanced genomic technologies in routine prenatal diagnostics to increase detection diagnostic yields of causal genetic variants associated with CHDs.

Rapid detection technology of sewing thread based on DeblurGAN-BSV3 defuzzification algorithm and ST-FPN detection algorithm

Stitch defect detection is an important means to ensure the quality of stitched fabrics. In order to realize the intellectualization of the sewing process, a rapid defect detection method based on machine vision was proposed. In order to solve the problem of motion blur caused by sewing speed, an image DeblurGAN-BSV3 algorithm is proposed. Firstly, different attention fusion mechanisms are introduced to achieve accurate extraction of image features. Secondly, the depth-separable convolution of the trunk network is replaced by blueprint convolution to ensure the processing speed of the detection algorithm and the clarity of the output image. In order to solve the difficulty of rapid detection of pin defects, a student–teacher feature pyramid matching method was proposed. Firstly, the abnormal region interpretation technology was used to explicitly visualize the defect area of the identified abnormal instances, and then the abnormal detection score was performed on the detected images to make a quality judgment. The experimental results show that the combination of the above two methods has a good ability for rapid defect detection. Rapid detection of common pin defects is realized.

Multi-level glowworm swarm convolution neural networks for abnormal event detection in online surveillance video

Multi-level glowworm swarm convolution neural networks for abnormal event detection in online surveillance video

Multi-Layer Feature Restoration and Projection Model for Unsupervised Anomaly Detection

The anomaly detection of products is a classical problem in the field of computer vision. Image reconstruction-based methods have shown promising results in the field of abnormality detection. Most of the existing methods use convolutional neural networks to build encoding–decoding structures to do image restoration. However, the limited receptive field of convolutional neural networks makes the information considered in the image restoration process limited, and the downsampling in the encoder causes information loss, which is not conducive to performing fine-grained restoration of images. To solve this problem, we propose a multi-layer feature restoration and projection model (MLFRP), which enables the restoration process to be carried out on multi-scale feature maps through a block-level feature restoration module that fully considers the detail information and semantic information required for the restoration process. We conducted in-depth experiments on the MvtecAD anomaly detection benchmark dataset, which showed that our model outperforms current state-of-the-art anomaly detection methods.

Subclinical Ocular Motility Dysfunction and Extraocular Muscle Changes in Inactive Graves' Orbitopathy.

This study aimed to investigate the presence of structural and functional changes in extraocular muscles (EMs) among patients with inactive Graves' orbitopathy (GO) classified according to the Clinical Activity Score (CAS). Sixty-seven patients with Graves' disease (GD) and inactive GO were included. The data collected included clinical parameters, thyroid function, autoantibody levels, EOM morphology via orbital ultrasound (US), and ocular motility. Patients were stratified into Red Filter Test (RFT)-positive or RFT-negative groups based on the presence or absence of latent diplopia during the RFT examination. Thirty-three patients (49.25%) exhibited latent diplopia on the RFT, despite not reporting double vision during standard ocular motility tests. Significant differences were observed between the two groups in terms of age, disease duration, intraocular pressure (IOP) elevation in up-gaze, and medial rectus muscle thickness (p < 0.05). No significant differences were found in thyroid status, TRAb and ATA levels, CASs, exophthalmos, or lateral rectus thickness between the two groups. This study revealed that in inactive GO, subclinical EM dysfunction and morphological changes may be present, which might not be apparent through routine ocular examinations. The RFT is effective in detecting latent diplopia, highlighting its utility in identifying subtle ocular motility issues and subclinical muscle involvement. Comprehensive evaluations combining functional tests like the RFT and imaging are essential for early detection of GO-related abnormalities, enabling tailored and prompt management and improving patient outcomes.

Exploring health disparities in diagnosing multiple myeloma

ABSTRACT Background Multiple myeloma (MM) is a plasma cell neoplasm, which accounts for 1–2% of cancers and approximately 17% of hematological malignancies in the United States each year. Fifty percent of patients with symptomatic MM have three or more primary care visits before being referred to a specialist, which is greater than any other cancer. A delay in the diagnosis of multiple myeloma has been shown to negatively impact the clinical course of the disease; patients with longer diagnostic intervals have been shown to experience shorter disease-free survival and higher rates of treatment-related complications. Research design and methods We performed a retrospective analysis of patients diagnosed with MM in our institution, to determine the time from the first detectable lab abnormality to the diagnosis of MM. Results We included 92 patients in this study. Fifty-two percent of patients had isolated anemia at the time of diagnosis. Twenty-nine percent of patients had a delay in diagnosis of ≥1 year, while 18% had a delay of ≥3 years. Nine patients in our cohort had anemia and an elevated serum total protein (31%). This group had the longest time to diagnosis with a median of 38 months. Conclusions Our results did not show any difference in time to diagnosis by race, ethnicity, gender, or socioeconomic status.

Small for gestational age: concept, diagnosis and neonatal characterization, follow-up and recommendations

Newborns who do not reach a weight appropriate for their gestational age and sex can be classified in different ways. This article defines the concepts of small for gestational age (SGA) and intrauterine growth restriction, as well as the underlying causes of these conditions, with the goal of establishing consensus definitions for these patients, in whom treatment with growth hormone throughout childhood may be indicated and who may be at risk of developing endocrine or metabolic disorders in puberty and adulthood. Most SGA children experience spontaneous catch-up growth that is usually completed by age 2 years. In SGA children who remain short, treatment with recombinant human growth hormone is effective, increasing adult height. Small for gestational age infants with rapid catch-up growth and marked weight gain are at increased risk of premature adrenarche, early puberty, polycystic ovary syndrome (girls), insulin resistance and obesity, all of which are risk factors for type 2 diabetes and metabolic syndrome in adulthood. The SGA status can affect different areas of neurodevelopment and manifest at different stages in life; neurodevelopmental outcomes are better in SGA infants with spontaneous catch-up growth. Due to the potential risks associated with SGA, adequate characterization of these patients at birth is imperative, as it allows initiation of appropriate follow-up and early detection of abnormalities.

Laboratory Abnormal Behavior Detection Based on Multimodal Information Fusion

The traditional laboratory anomaly detection methods mainly focus on the hidden dangers caused by chemical leaks and other items, ignoring the impact of abnormal behaviors such as incorrect operations and improper behavior on safety in the laboratory. This paper proposes a laboratory abnormal behavior detection method based on multimodal information fusion. The method generates a dense optical flow field of RGB image sequences based on optical flow theory and global smoothing constraints, and mines motion mode information. Meanwhile, the contour modal information of behavior is captured through convolution and adjacency matrix operations. Using decision level and proximity functions to integrate student behavior motion mode information and contour mode information, and using the maximum value as the behavior detection result. The experimental results show that the method can effectively detect abnormal behavior in the laboratory environment, with small detection errors and a specificity close to 1.00, effectively ensuring the safety of the laboratory environment.

The Impact of Different Regions and Dietary Structures on Blood Glucose and Lipid Levels

&amp;lt;i&amp;gt;Objective: &amp;lt;/i&amp;gt;To explore the effects of different regions and dietary structures on the blood glucose and lipid levels of residents. &amp;lt;i&amp;gt;Method: &amp;lt;/i&amp;gt;1220 examinees from Fenyang City, Shanxi Province were selected as the research subjects and included in the study group. In addition, 1225 examinees from Xinjiang Communist Youth League Farm were selected as the control group 1, and 1200 examinees from Wujiaqu City, Xinjiang Uygur Autonomous Region (limited to regular physical labor and light diet) were selected as the control group 2. Collect general information such as the regional situation and dietary structure of personnel in each group, and use a fully automated biochemical analyzer to detect blood glucose (GLU) and lipid indicators (including total cholesterol (TC) and triglycerides (TG)). Compare the levels of the above indicators and the differences in the abnormal detection rates of each indicator in each group. &amp;lt;i&amp;gt;The results: &amp;lt;/i&amp;gt;The levels of GLU, TC, and TG in the study group were significantly higher than those in control group 1 and control group 2 [GLU (mmol/L): 5.30±1.45 compared to 5.03±1.50, 4.18±0.39; TC (mmol/L): 1.67± 1.20 compared to 1.58±1.01, 0.69±0.36; TG (mmol/L): 5.02±1.71 compared to 4.72±1.17, 3.19±0.89], and the differences were statistically significant (all P&amp;lt;0.01). The abnormal detection rates of GLU, TC, and TG in the study group were significantly higher than those in the control group 1 and control group 2 (GLU: 18.43% compared to 13.64% and 2.00%, TC: 35.43% compared to 28.42% and 0.00%, TG: 14.05% compared to 5.63% and 0.00%), and the differences were statistically significant (all P&amp;lt;0.01). &amp;lt;i&amp;gt;Conclusion: &amp;lt;/i&amp;gt;Regional differences and dietary structures are important factors affecting the blood sugar and lipid levels of residents. Balanced diet is beneficial for the stability of blood indicators and physical health of residents.

Machine Learning Using Template-Based-Predicted Structure of Haemagglutinin Predicts Pathogenicity of Avian Influenza.

Deep learning presents a promising approach to complex biological classifications, contingent upon the availability of well-curated datasets. This study addresses the challenge of analyzing three-dimensional protein structures by introducing a novel pipeline that utilizes open-source tools to convert protein structures into a format amenable to computational analysis. Applying a two-dimensional convolutional neural network (CNN) to a dataset of 12,143 avian influenza virus genomes from 64 countries, encompassing 119 hemagglutinin (HA) and neuraminidase (NA) types, we achieved significant classification accuracy. The pathogenicity was determined based on the presence of H5 or H7 subtypes, and our models, ranging from zero to six mid-layers, indicated that a four-layer model most effectively identified highly pathogenic strains, with accuracies over 0.9. To enhance our approach, we incorporated Principal Component Analysis (PCA) for dimensionality reduction and one-class SVM for abnormality detection, improving model robustness through bootstrapping. Furthermore, the K-nearest neighbor (K-NN) algorithm was fine-tuned via hyperparameter optimization to corroborate the findings. The PCA identified distinct clustering for pathogenic HA, yielding an AUC of up to 0.85. The optimized K-NN model demonstrated an impressive accuracy between 0.96 and 0.97. These combined methodologies underscore our deep learning framework's capacity for rapid and precise identification of pathogenic avian influenza strains, thus providing a critical tool for managing global avian influenza threats.

Application of Video Abnormal Behavior Detection Algorithm in Evaluation of Track and Field Teaching and Training Effect

With the development of track and field, people pay more and more attention to the quality of classroom teaching of track and field technology, and the evaluation of teaching quality plays a key role in it. In today's educational reform, teaching evaluation plays an important role as an important method to test teachers' teaching and students' learning. With the rapid development of machine learning, especially deep learning, image-based individual abnormal behavior detection technology is becoming more and more mature, but there are still many difficulties to be solved in video-based group abnormal behavior detection technology. Therefore, it is necessary to study the detection algorithm. Based on machine vision theory, image processing theory and video analysis technology, this paper studies three key technologies involved in human abnormal behavior detection in video: moving target detection, moving target tracking and abnormal behavior detection.

Miscarriages after Natural Conception &amp; IVF: Comparative Study of Genetic Analysis of Products of Conception

Assisted reproductive technologies (ART), including in vitro fertilization (IVF), are modern medical technologies widely used in developed countries. A frequent complication of pregnancy resulting from ART is miscarriage. The leading cause of miscarriage, both sporadic and recurrent, is chromosomal abnormalities (CA) of the embryo. To compare the frequency and structure of chromosomal abnormalities (CA) of the embryo during miscarriages after IVF and natural conception. Retrospective cohort comparative study. The study, conducted in 2018-2022, included 1,000 products of conception (POCs) samples from patients with miscarriage. The study participants were divided into 2 groups depending on the origin of pregnancy: group 1 – women whose pregnancy occurred naturally (n = 862), group 2 – women whose pregnancy occurred as a result of in vitro fertilization (IVF) (n = 138). Miscarriage was confirmed by ultrasound performed at 6-10 weeks of pregnancy. A genetic study of POCs was carried out using chromosomal microarray analysis (CMA). In total, CA was detected in 580 samples (58%), and a normal molecular karyotype was determined in 420 (42%). CAs in abortive material during pregnancy loss are detected with a frequency of 59.05% in cases of natural conception and with a frequency of 51.05% in pregnancies resulting from IVF (p = 0.093). There were no statistically significant differences in the frequency and structure of CA in the study groups. Autosomal trisomies were most often detected. In our study, among all autosomal trisomies, the most common were trisomy 16, trisomy 22 and trisomy 15. Among the sex chromosome abnormalities, monosomy X was most often detected - in total, it was determined in 66 (6.6%) samples, which significantly exceeds the frequency of monosomy X among live births. Only in 0.2-0.3% of cases, when the embryo has monosomy X, pregnancy progresses and ends in a live birth. Copy number variations (CNVs) were often detected - a total of 52 (5.2%) samples with different CNVs, respectively 46 (5.3%) and 6 (4.3%) in groups 1 and 2. Detection of such abnormality is critically important, as it can be the result of carriage of a balanced CAs in one of the parents, which significantly increases the risk of miscarriage in the future. In pregnancies resulting from IVF, mosaicism in abortive material was more common, but the differences were not statistically significant. In group 1, mosaicism was detected in 66 (7.6%) cases and in group 2 - 13 (9.4%) cases. The IVF procedure does not increase the risk of CA in the embryo but also does not significantly reduce it. Considering the high frequency of CA in miscarriage, persons referred for IVF and with a history of idiopathic recurrent pregnancy loss should be informed about the possibility of PGT.

ViCubeLab-An Integrated Platform Using VR to Visualise and Analyse Road Traffic Conditions

The main contribution of this paper is to introduce a framework for integrating Machine Learning (ML), Human, and Virtual Reality (VR) into one platform to promote a collaborative visualisation environment that can assist in better analysis and improve the human-machine teaming capability. This platform was demonstrated using a case study in ana-lysing road traffic conditions. The ‘Ab-normal Machine Learning Road Traffic Detection in VR (AbnMLRTD-VR)’ prototype system was developed to assist the human analyst. The proposed system has two main integrative components: a data-driven ML model and a 3D real-time visualisation in a VR environment. An unsupervised ML model was built using real traffic data. The AbnMLRTD-VR system highlights the outliers in the road sections in actual road contexts of a road traffic network. This gives the human analyst a 3D real-time immersive visualisation in a VR environment to evaluate road conditions. The AbnMLRTD-VR system demonstrated that it could help minimise the need for human pre-labelling of the data. It enables the visualisation of the road traffic conditions more meaningfully and to understand the context of the road traffic conditions of road sections at any given time.

Algorithm for detecting abnormal electricity usage by customers based on electricity big data and deep learning

Abstract In order to optimize the effect of individuals’ aberrant power utilization detection and reinforce the recognition rate and accuracy of abnormal power consumption detection of electricity use, an aberrant power utilization identification algorithm based on electric power big data and deep learning is proposed. Taking the two-way dialogue between power users and the power company as the basic perspective, real-time monitoring and collection of power consumption dynamics of users is carried out, and the power big data collection framework is designed. The retrieval of aberrant power utilization detection indexes is completed. Based on the deep learning algorithm, the artificial neural network base operation medium is combined to quantitatively solve the aberrant power utilization indexes, completing the design of a user aberrant power utilization detection algorithm. Experimental results show that the accuracy of the designed algorithm is 0.963, the F1 value is 0.985, and the AUC value is 0.942, which can effectively identify the aberrant power utilization and has a better performance of abnormal power consumption identification and detection.

A Clinical Study of Thyroid Abnormalities and Autoantibodies in Patients Diagnosed With Anti-nuclear Antibody Positive Autoimmune Connective Tissue Disorders: An Observational Cross-Sectional Study.

Autoimmune connective tissue disorders (CTDs) are characterized by inflammation of the connective tissue structures and immune system aberrations, such as autoantibody production. This study investigates the prevalence and clinical significance of thyroid abnormalities in patients with anti-nuclear antibody (ANA)-positive autoimmune CTDs. This prospective cross-sectional observational study was conducted at Dr. D. Y. Patil Medical College, Hospital and Research Centre, Dr. D. Y. Patil Vidyapeeth (Deemed to be University), Pune, from September 2022 to June 2024. Eighty patients diagnosed with ANA-positive CTDs were included. Comprehensive histories were collected from them and clinical examinationsand routine investigations were performed. Blood samples were collected for thyroid function tests and autoantibody tests. Thyroid ultrasound investigations were also performed. Ethical approval and informed consent were obtained. The study revealed a significant prevalence of thyroid dysfunction among participants, with 39 (48.75%) exhibiting some form of thyroid abnormality. Subclinical hypothyroidism was the most common condition in 18 (22.50%) participants, predominantly affecting females. Thyroid autoantibodies were present in 32 (40%) participants, with thyroid peroxidase antibodies (anti-TPO Ab) being the most common seen in 17 (21.25%) participants. Systemic lupus erythematosus (SLE) was the most prevalent CTD among participants, seen in 44 (55%) participants, followed by Sjogren's syndrome (SS)seen in 19 (23.75%) participants. The study underscores the necessity of routine thyroid function screening in patients with ANA-positive CTDs to facilitate early detection and management of thyroid abnormalities, thereby preventing progression to overt hypothyroidism or hyperthyroidism. The findings highlight the significant association between thyroid dysfunction and autoimmune CTDs, advocating for a holistic approach to patient care.

Application of the International Endometrial Tumor Analysis (IETA) in Ultrasound Evaluation of Abnormal Uterine Bleeding.

Abnormal uterine bleeding (AUB) affects a significant proportion of women, particularly around the ages of menarche and menopause. While ultrasonography is a primary diagnostic tool for AUB, techniques like the International Endometrial Tumor Analysis (IETA) scoring system have enhanced diagnostic accuracy for endometrial abnormalities. IETA provides a standardized approach to evaluating endometrial features, which aids in distinguishing benign from malignant lesions. This study applied the IETA scoring system to the ultrasound evaluation of 50 women presenting with AUB. The study assessed various endometrial characteristics, including thickness, echogenicity, midline appearance, junction regularity, and vascular patterns. Data were analyzed to correlate IETA scores with histopathological findings and to compare the ultrasound features of benign and malignant lesions. The study found that non-uniform endometrial characteristics and irregular midline appearances were more common in malignant lesions. Specifically, interrupted or irregular endometrial-myometrial junctions, absence of the bright edge, higher color scores, and complex vascular patterns were significantly associated with malignancy. Mean endometrial thickness was notably higher in malignant cases compared to benign ones, with a statistically significant difference. The most frequent IETA scores were 7, 12, and 13. Integrating the IETA scoring system into ultrasound evaluation enhances the detection of endometrial abnormalities, improving the differentiation between benign and malignant lesions. This approach provides a reliable framework for diagnosing and managing AUB, potentially reducing the need for invasive procedures and facilitating better clinical decision-making.