Abnormal Detection System Research Articles

Anomaly Detection of Highway Vehicle Trajectory under the Internet of Things Converged with 5G Technology

The gradual increase in the density of highway vehicles and traffic flow makes the abnormal driving state of vehicles an indispensable tool for assisting traffic dispatch. Intelligent transportation systems can detect and track vehicles in real time, acquire characteristics such as vehicle traffic, vehicle speed, vehicle flow density, and vehicle trajectory, and further perform advanced tasks such as vehicle trajectory. The detection of abnormal vehicle trajectory is an important content of vehicle trajectory understanding. And the development of the Internet of Things (IoT) and 5G technology has led to a continuous increase in the rate of data information circulation. The “Internet of Vehicles” generated based on the practice of 5G communication technology constitutes a vehicle abnormal trajectory detection system, which has very high feasibility and safety and stability. Therefore, this research is aimed at the needs of preventing major accidents and forensic analysis during highway vehicles. Based on the integration of the Internet of Things 5G communication technology, a trajectorial anomaly detection of highway vehicle trajectory based on the integration of the Internet of Things 5G is proposed. By accurately sensing unsafe events at the perception layer, network layer, and application layer, the vehicle driving trajectory state is divided into several simple semantic representations. The semantic representation is analyzed, and then the moving target detection and moving target tracking algorithms needed to extract the vehicle trajectory are introduced. Through video detection and tracking of moving vehicle targets, the driving trajectory of the vehicle is obtained, and the movement characteristics of the vehicle in each frame of image are extracted. According to the relationship between the trajectory of the vehicle and the lane line, the vehicle trajectory analysis is realized, and then it is judged whether the vehicle has abnormal trajectory. Compared with the traditional method of manually detecting the driving condition of the vehicle, the abnormal trajectory detection of the vehicle based on the integration of the Internet of Things and 5G can quickly detect the abnormal trajectory of the vehicle in the traffic monitoring video.

Abnormal video homework automatic detection system.

Automatic abnormal detection of video homework is an effective method to improve the efficiency of homework marking. Based on the video homework review of “big data acquisition and processing project of actual combat” and other courses, this paper found some student upload their videos with poor images, face loss or abnormal video direction. However, it is time-consuming for teachers to pick out the abnormal video homework manually, which results in prompt feedback to students. This paper puts forward the AVHADS (Abnormal Video Homework Automatic Detection System). The system uses suffix and parameter identification, Open CV, and the audio classification model based on MFCC feature to realize the automatic detection and feedback of abnormal video homework. Experimental results show the AVHADS is feasible and effective.

Design of abnormal data detection system for protein gene library based on data mining technology

In view of the shortcomings of the current abnormal data detection system of the protein gene library, such as low detection rate and high error detection rate, the abnormal data detection system of the protein gene library based on data mining technology is designed. The protein gene enters the firewall module of the system, and enters the immune module when it does not match the firewall rules; the memory detector in the immune module presents the protein gene, if the memory detector does not match the protein gene, the mature detector presents the protein gene, if the mature detector does not match the protein gene, it is determined as the normal protein gene data package, if it matches, it is considered that The abnormal data of protein gene was processed by the collaborative stimulation module, and the control module controlled by C8051F060 chip to detect the abnormal data of protein gene library. The immune module generates new protein gene sequences through an immature detector, simulates the immune mechanism of protein gene through a mature detector module, and simulates the secondary response in the abnormal data detection system of protein gene library through memory detector. The system introduces data mining technology into the detection and uses a two-level dynamic optimization algorithm to calculate the ASG similarity value of protein gene secondary structure arrangement. According to this value, the abnormal data detection of the protein gene library is realized by randomly generating protein genes, negative selection, clone selection and copying memory cells through gene expression. The experimental results show that the system can quickly detect abnormal data of the protein gene library, ensure the detection efficiency, and the detection accuracy reaches 97.1%. The system can reduce the error rate of normal protein gene detection as an abnormal protein gene.

Anomaly detection of aircraft lead‐acid battery

AbstractThe lead‐acid battery has been widely used in various fields. In civil aviation aircraft, it plays a vital role in the power system to maintain normal operation during the flight mission. Thus, an effective abnormal detection system for monitoring and diagnosing the status of aircraft lead‐acid battery is essential to ensure its safety and reliability. This paper aims to effectively identify aircraft battery faulty using unsupervised anomaly detection techniques. It introduces state‐of‐the‐art anomaly detection algorithms and evaluates their performance on a large real civil aviation battery data. The experimental results show that the latest isolation‐based anomaly detectors, iForest and iNNE, have outstanding performance on this task and have promising applicability as efficient methods for guaranteeing the lead‐acid battery quality and reliability in civil aviation aircraft.

An adaptive anomaly request detection framework based on dynamic web application profiles

Web application firewall is a highly effective application in protecting the application layer and database layer of websites from attack access. This paper proposes a new web application firewall deploying method based on Dynamic Web application profiling (DWAP) analysis technique. This is a method to deploy a firewall based on analyzing website access data. DWAP is improved to integrate deeply into the structure of the website to increase the compatibility of the anomaly detection system into each website, thereby improving the ability to detect abnormal requests. To improve the compatibility of the web application firewall with protected objects, the proposed system consists of two parts with the main tasks are: i) Detect abnormal access in web application (WA) access; ii) Semi-automatic update the attack data to the abnormal access detection system during WA access. This new method is applicable in real-time detection systems where updating of new attack data is essential since web attacks are increasingly complex and sophisticated.

NeuroAED: Towards Efficient Abnormal Event Detection in Visual Surveillance With Neuromorphic Vision Sensor

Abnormal event detection is an important task in research and industrial applications, which has received considerable attention in recent years. Existing methods usually rely on standard frame-based cameras to record the data and process them with computer vision technologies. In contrast, this paper presents a novel neuromorphic vision based abnormal event detection system. Compared to the frame-based camera, neuromorphic vision sensors, such as Dynamic Vision Sensor (DVS), do not acquire full images at a fixed frame rate but rather have independent pixels that output intensity changes (called events ) asynchronously at the time they occur. Thus, it avoids the design of the encryption scheme. Since events are triggered by moving edges on the scene, DVS is a natural motion detector for the abnormal objects and automatically filters out any temporally-redundant information. Based on this unique output, we first propose a highly efficient method based on the event density to select activated event cuboids and locate the foreground. We design a novel event -based multiscale spatio-temporal descriptor to extract features from the activated event cuboids for the abnormal event detection. Additionally, we build the NeuroAED dataset, the first public dataset dedicated to abnormal event detection with neuromorphic vision sensor. The NeuroAED dataset consists of four sub-datasets: Walking, Campus, Square, and Stair dataset. Experiments are conducted based on these datasets and demonstrate the high efficiency and accuracy of our method.

Accuracy of radiographer comment following a two-month experiential and blended learning in appendicular skeleton X-ray interpretation: The Singapore experience

IntroductionThe value of combined blended and experiential learning on radiographer diagnostic comment has not been explored. This study aims to examine the accuracy of image interpretation comment of radiographers who received a period of blended and experiential learning in Radiographer Abnormality Detection Systems (RADS). MethodsWe evaluated the diagnostic opinions of 13 radiographers who received a blended training and experiential learning (a process of self-learning and reflection) in RADS. Radiographers' opinions on 16,483 images were examined using the final radiologists’ report as a reference standard. For each radiographer, we recorded the number of true positive, true negative, false positive and false negative opinions and MedCal® was used to calculate diagnostic performance and error rates. A t-test was used to assess whether the number of images read was associated with performance and whether the radiographers retained performance over time. ResultsSensitivity ranged from 87.4 (84.0–90.2) to 98.9 (97.5–99.7) with a mean of 94.3 (93.6–94.8). Specificity varied from 96.4 (94.8–97.5) to 99.9 (99.41–100.0) with a mean of 98.2 (97.9–98.4). Diagnostic accuracy ranged from 93.1 (91.5–94.4) to 99.5 (98.9–99.8) with a mean of 96.9 (96.6–97.1). The mean false positive rate was 0.018 (range: 0.010–0.031) with a false negative rate of 0.057 (range: 0.026–0.11). There were no differences in performance between the first and latter nine months of providing opinions and the number of images reviewed was not associated with performance. ConclusionRadiographers who received blended and experiential learning in RADS provide accurate diagnostic comments on plain emergency appendicular skeleton radiographs. Implication for practiceA combined blended and experiential learning can equip radiographers to provide diagnostic opinion on plain appendicular skeleton radiographs.

Spatiotemporal deep networks for detecting abnormality in videos

Detecting and localizing anomalous behavior in the surveillance video is explored and spatiotemporal model, which jointly learns the appearance and motion-based feature is proposed. The general solution is to learn from the normal-data as reference models and uses various hands designed features. However, huge variations can occur within normal-behavior patterns. It is a challenge to represent higher-level concepts of a normal or abnormal event explicitly from raw input data. In the proposed framework, spatiotemporal features learned at various hidden layer are analyzed. Based on the learned representation, the reconstruction of video volumes are performed. Finally, the structural distortion based abnormality score is computed by considering luminance, contrast, and structural information to detect the presence of abnormality and localize them. Further, we also explored the performance of GMM and one-class SVM in a given scenario. The proposed structural distortion based abnormality detection and localization are evaluated on the publicly available UCSD and UMN dataset. The performance of the developed system is found to outperform the existing state-of-art methods for detecting and localizing abnormality at the frame as well as pixel-level. Recently, deep architecture is also found to be vulnerable to adversarial attacks and can easily be tricked to fool the system. However, most of the existing attacks are designed for the classification task. In this work, we utilize the gradient-based approach to generate adversarial samples for an abnormality detection system. Finally, we build the defense mechanism to detect the abnormality in the presence of such adversarial attacks.

Abnormal Human Activity Detection using Unsupervised Machine Learning Techniques

Nowadays there is a significant study effort due to the popularity of CCTV to enhance analysis methods for surveillance videos and video-based images in conjunction with machine learning techniques for the purpose of independent assessment of such information sources. Although recognition of human intervention in computer vision is extremely attained subject, abnormal behavior detection is lately attracting more research attention. In this paper, we are interested in the studying the two main steps that compose abnormal human activity detection system which are the behavior representation and modelling. And we use different techniques, related to feature extraction and description for behavior representation as well as unsupervised classification methods for behavior modelling. In addition, available datasets and metrics for performance evaluation will be presented. Finally, this paper will be aimed to detect abnormal behaved object in crowd, such as fast motion in a crowd of walking people

Hierarchical Coherent Anomaly Fall Detection Low Bandwidth System With Combination of Wearable Sensors for Identifying Behavioral Abnormalities

To build cleverly assisted life systems for elderly people, the identification of behavioral abnormalities in human life is essential. Fall detection is a significant public health concern, particularly for the elderly fitness is unavoidable, and consistent monitoring of negative effects is required on time. This paper introduces Hierarchical Coherent Anomaly Fall Detection Low Bandwidth System (HCAFDLBS) to effectively identify behavioral abnormalities in human life based on data obtained from wearable sensors and related location contexts. The machine tracks human body activity, identifies an efficient quaternion algorithm as a decrease in normal daily activities, and sends automatic requests for assistance to caregivers in the region of the patient. The probabilistic theoretical paradigm is used to identify three types of irregularities, including spatial deviations, timing anomalies, and anomalies of sequence. This technique relies on a hierarchical analytical network for the detection of complex behavior; the maximum approximate algorithm and the smoothing Laplace method are used to learn anomaly detection model parameters. The classification is spread on various sensor nodes, and a computer for a specific station, the distribution of multiple action classes is demonstrated to follow a mixture of subspace model for each action class and one subspace. The findings have confirmed the feasibility of the proposed background so that the behavior study can be incorporated in future intelligent elderly homes, this behavioral abnormality detection system is predicted, and their results have been verified.

Arduino Based Vehicle Abnormal Behavior Detection System using Camera with SD Card

Arduino Based Vehicle Abnormal Behavior Detection System using Camera with SD Card

Development of Photovoltaic abnormal condition detection system using combined regression and Support Vector Machine

It is essential to monitor and detect the abnormal conditions in Photovoltaic (PV) system as early as possible to maintain its productivity. This paper presents the development of a PV abnormal condition detection system by combining regression and Support Vector Machine (SVM) models. The regression model is used to estimate the expected power generation under the respective solar irradiance, which is used as the input for the SVM model. The SVM model is then used to identify the abnormal condition of a PV system. The proposed model does not require installing additional measurement devices and can be developed at low cost, because the data that is used as the input variable for the model is retrieved from the Power Conversion System (PCS). Furthermore, the accuracy of the detection system is improved by taking into consideration the daylight time and the interactions between the independent variables, as well as the implementation of the multi-stage k-fold cross-validation technique. The proposed detection system is validated by using actual data retrieved from a PV site, and the results show that it can successfully distinguish the normal condition, as well as identify the abnormal condition of a PV system by using the basic measurements.

Detecting abnormal thyroid cartilages on CT using deep learning.

The purpose of this study was to evaluate the performance of a deep learning algorithm in detecting abnormalities of thyroid cartilage from computed tomography (CT) examination. A database of 515 harmonized thyroid CT examinations was used, of which information regarding cartilage abnormality was provided for 326. The process consisted of determining image abnormality and, from these preprocessed images, finding the best learning algorithm to appropriately characterize thyroid cartilage as normal or abnormal. CT images were cropped to be centered around the cartilage in order to focus on the relevant area. New images were generated from the originals by applying simple transformations in order to augment the database. Characterizations of cartilage abnormalities were made using transfer learning, by using the architecture of a pre-trained neural network called VGG16 and adapting the final layers to a binary classification problem. The best algorithm yielded an area under the receiving operator characteristic curve (AUC) of 0.72 on a sample of 82 thyroid test images. The sensitivity and specificity of the abnormality detection were 83% and 64% at the best threshold, respectively. Applying the model on another independent sample of 189 new thyroid images resulted in an AUC of 0.70. This study demonstrates the feasibility of using a deep learning-based abnormality detection system to evaluate thyroid cartilage from CT examinations. However, although promising results, the model is not yet able to match an expert's diagnosis.

Design and application of real-time network abnormal traffic detection system based on Spark Streaming

In order to realise the rapid analysis and identification of abnormal traffic in real-time networks, a distributed real-time network abnormal traffic detection system (DRNATDS) was designed, which could effectively analyse abnormal network traffic. DRNATDS provided effective real-time big data analysis platform and guaranteed network security. The paper proposes K-means algorithm based on relative density and distance, integrated with Spark Streaming and Kafka. It could effectively detect various network attacks under real-time data stream. The experimental results show that DRNATDS has good high availability and stability. Compared to other algorithms, K-means algorithm based on relative density and distance could more effectively identify abnormal network traffic and improve the recognition rate.

Design and application of real-time network abnormal traffic detection system based on Spark Streaming

Design and application of real-time network abnormal traffic detection system based on Spark Streaming

A frame reduction system based on a color structural similarity (CSS) method and Bayer images analysis for capsule endoscopy.

A capsule endoscopy examination of the human small bowel generates a large number of images that have high similarity. In order to reduce the time it takes to review the high similarity images, clinicians will increase the playback speed, typically to 15 frames per second [1]. Associated with this behaviour is an increased probability of overlooking an image that may contain an abnormality. An alternative option to increasing the playback speed is the application of abnormality detection systems to detect abnormalities such as ulcers, tumors, polyps and bleeding. However, applying all of these detection systems requires significant computing time and still produces numerous images with high similarity depending on the specificity of the utilized detection systems. An interesting approach to reduce viewing time is the application of a frame reduction system that reduces the number of images by omitting those with a high similarity of information. The advantage of such a system is that the specialist only needs to review a single image that technically represents a series of images with high similarity. This reduces the total number of images that a specialist must review and importantly, images containing any abnormality are not removed from the review, but simply reduced in number. Thus, the current study developed a frame reduction system using various color models using Bayer images for color texture and a modified local binary pattern (LBP) for structural information. The proposed system achieved a reduction ratio of 93.87%, which is higher than the existing systems and required lesser computation due to the utilization of Bayer images.

Singular value based characterization and analysis of thermal patches for early breast abnormality detection

The purpose of this study is to develop a novel breast abnormality detection system by utilizing the potential of infrared breast thermography (IBT) in early breast abnormality detection. Since the temperature distributions are different in normal and abnormal thermograms and hot thermal patches are visible in abnormal thermograms, the abnormal thermograms possess more complex information than the normal thermograms. Here, the proposed method exploits the presence of hot thermal patches and vascular changes by using the power law transformation for pre-processing and singular value decomposition to characterize the thermal patches. The extracted singular values are found to be statistically significant (p < 0.001) in breast abnormality detection. The discriminability of the singular values is evaluated by using seven different classifiers incorporating tenfold cross-validations, where the thermograms of the Department of Biotechnology-Tripura University-Jadavpur University (DBT-TU-JU) and Database of Mastology Research (DMR) databases are used. In DMR database, the highest classification accuracy of 98.00% with the area under the ROC curve (AUC) of 0.9862 is achieved with the support vector machine using polynomial kernel. The same for the DBT-TU-JU database is 92.50% with AUC of 0.9680 using the same classifier. The comparison of the proposed method with the other reported methods concludes that the proposed method outperforms the other existing methods as well as other traditional feature sets used in IBT based breast abnormality detection. Moreover, by using Rank1 and Rank2 singular values, a breast abnormality grading (BAG) index has also been developed for grading the thermograms based on their degree of abnormality.

Enhanced ATM Security System With Automatic Abnormal Event Detection And Alert System to Reduce Banking Cost

Enhanced ATM Security System With Automatic Abnormal Event Detection And Alert System to Reduce Banking Cost

An investigation into the use of radiographer abnormality detection systems by Queensland public hospitals.

IntroductionA Radiographer Abnormality Detection System (RADS), such as the ‘red dot system’, involves radiographers highlighting the presence of potential acute abnormalities on radiographs in the emergency setting. The literature suggests little additional training is required of radiographers to participate in such a system, posing little impact on current workflow while remaining a cost‐effective, easy‐to‐implement program. However, its use outside the United Kingdom is sporadic. The purpose of this study was to investigate the frequency of use of a RADS in Queensland public hospitals.MethodsA cross‐sectional web‐based questionnaire was developed and distributed to 28 medical imaging department directors throughout metropolitan, rural and remote Queensland (Australia) public hospitals. The results of this survey were analysed using conventional descriptive statistics of response frequencies and the percentage of the sample.ResultsThe questionnaire was completed by 25 radiography directors (89% response rate). Sixteen percent of respondents, all metropolitan‐based, indicated a RADS was in operation (n = 4/25; 16%). Respondents without a RADS (n = 21/21; 100%) expressed interest in a trial. Just over half (n = 13/25; 52%) of the respondents believed their staff members were not trained appropriately to implement a RADS successfully.ConclusionThis study found an infrequent use of RADSs in Queensland public hospitals. This finding presents a unique opportunity for medical imaging professionals to enhance communication between the facets of a multidisciplinary emergency team via the implementation of RADS complemented by a radiographer commenting system.

The study for abnormal lesion detection system by gastric endoscope image by HSV color

The study for abnormal lesion detection system by gastric endoscope image by HSV color