Dynamic Detection System Research Articles

A sensing system and solving method for dynamic detection of relative pose of hydraulic support group

The precise detection of the pose of hydraulic support groups is crucial for the construction of intelligent coal mines. Addressing current challenges in comprehensive position sensing of support groups, such as one-sided descriptions, missing information, and limited detection capabilities, this paper, based on the concept of digital twin, proposes a sensing system and solving method for dynamic detection of the relative pose of hydraulic support group. Initially, a relative pose detection model, based on the six-point localization principle, is proposed by combining existing sensor information. Then, a sensing system is designed, incorporating a photoelectric detection device for monitoring key position parameters and virtual sensors for determining pose information. Consequently, a method for dynamically deriving relative positions, driven by the fusion of real-virtual iterative solving, real-virtual error feedback, and iterative condition optimization, is established. Finally, a relative pose dynamic detection system for a hydraulic support prototype is constructed in a laboratory environment. Experimental results demonstrate that the sensor system and the relative position detection method designed in this paper achieve a relative position accuracy of over 95.32 % for the hydraulic support, with a dynamic reconstruction time of less than 0.2 s. This verifies the rationality of the sensor system and the feasibility and accuracy of the dynamic deduction method. To sum up, this work provides a theoretical foundation and technical support for the autonomous perception of hydraulic support group, autonomous frame adjustment between frames, and overall straightness adjustment. It also lays the groundwork for further research and the advancement of information-physical systems in the fully-mechanized mining face.

CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING

The project "Credit Card Fraud Detection with FBA" aims to develop a robust and efficient system for identifying and preventing fraudulent activities associated with credit card transactions within the context of Fulfilment by Amazon (FBA). With the increasing prevalence of online transactions, credit card fraud has become a significant concern for both consumers and businesses. FBA, being a prominent e-commerce platform, requires a sophisticated fraud detection mechanism to ensure secure and trustworthy transactions. The project utilizes advanced machine learning algorithms to analyse transaction data and detect patterns indicative of potential fraud. These algorithms are trained on historical data, enhancing their ability to recognize anomalies in real-time transactions. The system incorporates a multi- layered approach, utilizing address verification, device fingerprinting, and IP geolocation to validate the legitimacy of transactions and minimize false positives. Real-time monitoring is a key component of the system, allowing for immediate detection and response to suspicious activities. Manual review processes are integrated, involving trained personnel to investigate flagged transactions and make informed decisions based on additional information or customer verification. This human element adds an extra layer of scrutiny, contributing to the reliability of the fraud detection system. The project aims to create a dynamic and adaptive fraud detection system that evolves wit emerging fraud tactics. Regular updates and improvements will be implemented to address new challenges and enhance the overall security of credit card transactions within the FBA ecosystem. The successful implementation of this project will contribute to a safer and more secure online shopping experience for FBA users, fostering trust and confidence in the platform. Index terms: Credit card fraud detection, Fulfilment by Amazon (FBA), Machine learning algorithms, Fraudulent activities, Online transactions, Real-time monitoring, Multi-layered approach, Address verification, Device fingerprinting, IP geolocation, Manual review processes, Dynamic and adaptive system, Emerging fraud tactics, Security enhancements, Online shopping experience, Trust and confidence building

Sequence-based malware detection using a single-bidirectional graph embedding and multi-task learning framework

As an important part of malware detection and classification, sequence-based analysis can be integrated into dynamic detection system for real-time detection. This work presents a novel learning method for malware detection models that leverages advances in graph embedding for fusing the n-gram data into a one-hot feature space with different transmission directions. By capturing the information flow, our method finds a better feature representation for detection tasks with rely solely on sequence information. To enhance the stability of feature representation, this work adopts a multi-task learning strategy which achieves better performance in independent testing. We evaluate our method on two different realworld datasets and compare it against four superior malware detection models. During malware detection using our method, we conducted in-depth discussions on feature length, graph embedding direction, model depth, and different multi-task learning strategies. Experimental and discussion results show that our method significantly outperforms alternative approaches across evaluation settings.

Progressive Detection of Uncertainty in Natural Language Processing Using a Labeled Variable Dimension Kalman Filter

Owing to rapid advancements in information and communication technology, natural language processing (NLP) methods have attracted considerable attention. Estimating uncertainty is a well‐established problem in NLP. Developing systems capable of automatically detecting uncertain terms within a natural language is critical for developing effective text‐analysis algorithms. Consequently, several NLP tools have been developed for this purpose. However, there are several obstacles to the design of fast and effective NLP technologies that effectively analyze ambiguous terms in natural languages. This work focuses on a particular method for detecting uncertainty, termed progressive detection, which can be accomplished using a dynamic probabilistic graphical model to solve these challenges. We iteratively upgraded the Kalman Filter to Labeled Variable Dimension Kalman Filter (LVDKF) based on observations from real datasets. The LVDKF learns two basic features from positive and negative words. The formula was then derived using a dynamic detection system, designed based on conditional probability. Finally, we simulated progressive detection experimental conditions and assessed the LVDKF on two publicly available datasets. It performs better than the baseline methods in these tests, which shows that it is effective at detecting changes over time.

Analyzing the effectiveness of IDS/IPS in real-time with a custom in-vehicle design

The era of ubiquitously interconnected, intelligent, and self-driving automobiles approaches as contemporary vehicles undergo gradual enhancements in terms of security catalyzed by security analysis in various modules, algorithms, operating systems, and soft and hardware nodes. This work examines the application of a dynamic Intrusion Detection System (IDS) and Intrusion Prevention System (IPS) in real-time using a Renault T520 Heavy-duty truck. It assesses the effectiveness of the security analysis procedure and its execution, focusing on the quality of the analysis concerning data derived from experiment sources. The validation of the security implementation adheres to a unified inbound and outbound.

A Novel Relocalization Method-Based Dynamic Steel Billet Flaw Detection and Marking System

In the current steel production process, occasional flaws within the billet are somewhat inevitable. Overlooking these flaws can compromise the quality of the resulting steel products. To address and mark these flaws for further handling, Magnetic Particle Testing (MT) in conjunction with machine vision is commonly utilized. This method identifies flaws on the billet’s surface and subsequently marks them via a device, eliminating the need for manual intervention. However, certain processes, such as magnetic particle cleaning, require substantial spacing between the vision system and the marking device. This extended distance can lead to shifts in the billet position, thereby potentially affecting the precision of flaw marking. In response to this challenge, we developed a detection-marking system consisting of 2D cameras, a manipulator, and an integrated 3D camera to accurately pinpoint the flaw’s location. Importantly, this system can be integrated into active production lines without causing disruptions. Experimental assessments on dynamic billets substantiated the system’s efficacy and feasibility.

AdaDeepStream: streaming adaptation to concept evolution in deep neural networks

Typically, Deep Neural Networks (DNNs) are not responsive to changing data. Novel classes will be incorrectly labelled as a class on which the network was previously trained to recognise. Ideally, a DNN would be able to detect changing data and adapt rapidly with minimal true-labelled samples and without catastrophically forgetting previous classes. In the Online Class Incremental (OCI) field, research focuses on remembering all previously known classes. However, real-world systems are dynamic, and it is not essential to recall all classes forever. The Concept Evolution field studies the emergence of novel classes within a data stream. This paper aims to bring together these fields by analysing OCI Convolutional Neural Network (CNN) adaptation systems in a concept evolution setting by applying novel classes in patterns. Our system, termed AdaDeepStream, offers a dynamic concept evolution detection and CNN adaptation system using minimal true-labelled samples. We apply activations from within the CNN to fast streaming machine learning techniques. We compare two activation reduction techniques. We conduct a comprehensive experimental study and compare our novel adaptation method with four other state-of-the-art CNN adaptation methods. Our entire system is also compared to two other novel class detection and CNN adaptation methods. The results of the experiments are analysed based on accuracy, speed of inference and speed of adaptation. On accuracy, AdaDeepStream outperforms the next best adaptation method by 27% and the next best combined novel class detection/CNN adaptation method by 24%. On speed, AdaDeepStream is among the fastest to process instances and adapt.

The construction of mine water recycling performance evaluation index system under the Internet of Things environment

The utilization rate of water resources of mines in China is still relatively low. The evaluation of mine water recycling has practical guiding significance for the planning, positioning, development, and construction of groundwater in today’s society. This article constructs an evaluation system for mine water recycling based on the key performance index (KPI) via the Internet of Things and big data platforms. This system evaluates the recycling status of mine water. First, the micro-seismic monitoring system and the hydrological dynamic detection system are deployed in work. The installation and debugging methods are compared to meet the monitoring requirements. Second, the filtered clear water is used for equipment cooling and firefighting dust removal at the mining face through the constant pressure supply pump. The excess clear water is discharged to the surface. Finally, 16 indicators are screened from four dimensions to construct a key KPI mine water evaluation system for evaluation and optimization. The results demonstrate that the first mine water monitoring system runs well and is fully functional, achieving the expected goal. The utilization rate evaluation score has increased yearly, from 3.05 points in 2016 to 3.39 points in 2020. However, the per capita utilization rate score still needs improvement. It is essential to improve the rationality of development and utilization.

Abstract P1-05-09: Targeting treatment to tumor response: demonstration of response monitoring with subsequent impact on treatment choices in real time utilizing a novel technology

Abstract Breast cancers, both early and advanced, are heterogeneous causing differential responses to targeted therapy. Explosion in targeted treatment choices requires real time assessment of tumor characteristics in patients initially and over time. A dynamic detection system, not a static pathology specimen, is required for continuous profiling while treatment changes; hence, the interest in circulating tumor cells (CTCs). Our novel QCDx br™ system analyzes all nucleated cells from a blood sample aliquot, morphologically intact and immobilized in hydrogel, after multiplex, immunofluorescent (IF) staining. We characterize increased numbers of CTCs (nucleated, CD45-negative cells) as single cells, in clusters and in connection with circulating inflammatory cells, stained with two, separate IF marker cocktails, denoting (1) epithelial (EpCAM, Cytokeratin CK), mesenchymal (Vimentin VIM) phenotypes and (2) therapeutic HER2, ER and TROP2 targets which are the basis for targeted therapy in breast cancer. In the ongoing, prospective CLINBREAC trial, we enrolled to date 9 neoadjuvant (early stage, ES) and 21 metastatic (late stage, LS) breast cancer patients, collecting 7.5 ml of blood at 3-month intervals or at change of therapy. We are now out over 2 years with the earliest ES and LS patients showing changes in CTCs with disease progression and in response to treatment, often pre-dating changes seen in follow up biopsies. Detection of HER2+ CTCs was of particular interest in patients with HER2 low cancers¬ (1+ or 2+). Results presented here, contain the more complete datasets from 8 ES and 11 LS patients. QCDx br™ detected CTCs in all 19 Stage I-IV patients that could exceed 100 CTCs/2500 nucleated cells in LS and 50 CTCs/2500 nucleated cells in ES patients. The table shows count averages of CTCs/2500 nucleated cells detected by different IF markers. Of note, CTCs showed combinations of IF markers (hybrid cells). For example, CTCs expressed both VIM and CK indicating epithelial to mesenchymal transition (EMT) phenotype, which may signify higher metastatic potential. ER+ CTC were seen in LS, not ES patients. All ES patients including those with HER2 low tumors, showed HER2+ CTCs. Of note, not included in the table are two, triple-positive patients with oligo-metastatic disease now 4 and 10 years out from diagnosis without evidence of disease and on maintenance HER2 and ER-directed therapy. No CTCs are seen at their first data point. We were unable to detect CTCs in 13 healthy volunteers. In ES patients, CTC numbers did not associate with tumor size, nodal involvement, ER or HER2 status. For example, one TNBC patient with a T3 tumor and positive nodes had some of the lowest numbers of CTCs. The more complete quantification of the LS patients is in process. As development of QCDx br™ continues, multiplex IF staining of 12+ markers per CTC and identification of single CTC mutational changes is expected. This powerful technology enables targeted treatment decisions with specific drugs resulting in maximal responses. Average CTC counts/2500 nucleated cells detected by phenotypic and therapeutic IF cocktails Citation Format: Susan Tannenbaum, Emily Hsu, jasmin Hundal, Amber Wilkes, Austin Fergusson, Fahmy Mamuya, Triantafyllos Tafas. Targeting treatment to tumor response: demonstration of response monitoring with subsequent impact on treatment choices in real time utilizing a novel technology [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P1-05-09.

Dynamic Detection Based on Planar Array Capacitance for Adhesive Defects of Thermal Protection Structure

The defect detection of thermal protective structures is of great significance in ensuring the safe flight of aircraft. In this paper, a dynamic measurement method based on the planar capacitance sensing principle is proposed to solve the problem of detecting defects in the adhesive layer of large-area thermal protection structures. This paper analyses the principle of capacitive sensing and establishes a planar array capacitive dynamic detection system. The dielectric distribution of the structural components to be measured is obtained at different locations by moving the array of electrode sensors regularly. To obtain the dielectric distribution information of the complete structure, the dielectric distribution at adjacent locations is spliced and fused. To achieve the precise location of the overlapping areas in the image to be fused, an image alignment method based on coordinates is adopted. The experimental results show that our proposed method can detect defects in the adhesive layer of large-area thermal protection structures and achieve complete visualization of the adhesive layer.

A Dynamic Intrusion Detection System Capable of Detecting Unknown Attacks

A Dynamic Intrusion Detection System Capable of Detecting Unknown Attacks

An efficient credit card fraud detection approach using cost‐sensitive weak learner with imbalanced dataset

AbstractThe usage of credit cards is increasing in the digitization era to purchase goods online or offline, and the number of fraudulent credit card transactions has also increased. Fraudulent transaction detection is a big issue in the credit card domain because the data set is highly imbalanced. The performance of traditional classification techniques has decreased due to this issue. Therefore, a dynamic fraud detection system is required to overcome this issue. This article proposes an efficient cost‐sensitive weak learner approach with a bagging and random forest classifier (CSWLB) to minimize misclassification problems and overcome the class imbalance issue. The proposed CSWLB approach is included in an adaptive algorithmic method (cost‐sensitive) with two weak learner ensembles (bagging‐random forest), which assigns high weight to the fraudulent transactions using the cost‐sensitive learning classifier and generates weight bags using a bagging ensemble classifier. Therefore, the random forest classifier has been implemented on the weight bags to improve classification accuracy. The proposed approach's effectiveness and efficiency have been computed on the Brazilian credit card data set. Its results have been compared with sampling, cost‐sensitive, and machine learning techniques. The proposed CSWLB approach obtained 765 total costs and 97.361% accuracy. The experimental results show that the proposed approach has outperformed compared to other techniques.

Intelligent Vehicle Engine Dynamic Test System Based on Internet of Things

In the context of technological modernization in the field of automotive engine testing, the development of an intelligent automotive engine testing system based on IQ has become an important trend in the future. This paper mainly studies the development of engine test software platform, the technical control of test process conditions, and the intelligent conversion of important components such as temporary fuel flow meters. By comparing the traditional bench test system and the dynamic test system based on the Internet of Things, the efficiency of data information transmission, information security, perception ability, and response speed between them are compared, and the intelligent dynamic engine detection based on the Internet of Things is found. The system is more secure and more efficient in information transmission, with a 12% increase in perception performance and a 48% increase in system response time. This also fully shows that the intelligent dynamic engine detection system based on the Internet of Things will be more suitable for current equipment and can also be detected more accurately, which can realize effective supervision of the running status of the test prototype and remote online feedback of the analysis results, and solve the engine test process. It solves the problem of efficient, reliable, and safe transmission and transmission of data and information between all levels and layers, and improves the ability of rapid perception and response in the process of engine testing.

Development of single measuring point overall balancing method based on multi-cylinder dynamic balance detection system

The combine harvester with multi-cylinder has a wide application in improving the operation efficiency. Therefore, as an important process in combine harvester, threshing operated by multi-cylinder usually makes the working structures suffer hit from the blockage of stones or materials. Consequently, the cylinders fail to guarantee the original balance. Several studies have been performed in this area, based on the dynamic balance method and vibration signal processing. However, most of them are not efficient for multi-cylinder. This study aims at developing an online dynamic balance detection system for multi-cylinder in combine harvester, in order to enhance the efficiency and accuracy of online dynamic balance detection. A multi-cylinder test rig is developed, and unbalanced vibration experiments under different working conditions are performed. The results show that the different measuring positions have different sensitivities to unbalanced mass. The vibrations will be transmitted through the frame, and coupled with each other. Under the multi-cylinder rotation, the vibration has strong randomness and poor convergence. For this purpose, the single measuring point overall balancing method is proposed. An adaptive multiple filter algorithm relying on the LabVIEW platform, is also proposed. Through phase relation between cylinders, the single measuring point overall balancing algorithm is developed. The comparison experimental results show that the proposed algorithm is more robust under the multi-cylinder rotation. The proposed method simultaneously installs sensors on the bearing seat of No. 1 tangential cylinder and balance 3 cylinders. The traditional method balance 3 cylinders separately change the sensor position. The effect of the proposed method is almost 76%, while that of the traditional balance method is almost 66%. For the multi-cylinder system, the single measuring point overall balancing method can efficiently improve the balance effect by 10%. Finally, it can be deduced from the experiment on the combine harvester that the accuracy of the proposed method reaches G3.9.

Effects of MiR-214-3p Regulation of SERCA2a Expression on Contractility of Cardiomyocytes in Heart Failure Model.

This study aimed to explore the targeted regulation of microRNA-214-3p (miR-214-3p) on sarcoplasmic/endoplasmic reticulum Ca(2+)-ATPase 2a (SERCA2a) and its mechanism on heart failure (HF). In this study, a rat model of HF was established by injecting isoproterenol to detect the changes in heart function. Then the primary rat cardiomyocytes were extracted and cultured. The cells were divided into the normal group, HF model group, miR-214-3p mimic group, and inhibitor group according to treatment methods. The expression differences of SERCA2a in each group were detected. The binding sites of miR-214-3p and SERCA2a were predicted, wild-type or mutant SERCA2a was prepared and co-transfected into cardiomyocytes with mimic, and the targeting effect was detected by the dual-luciferase reporter gene. Finally, the systolic function of each group was detected by a single-cell systolic dynamic edge detection system. The results showed that cardiac output and left ventricular ejection fraction of HF rats were significantly lower than those of normal rats (P<0.05). The results of the cell test showed that messenger ribonucleic acid (mRNA) and protein expression levels of SERCA2a in the model group and the mimic group were significantly lower than those in the mimic group (P<0.05), but there were no differences between normal group and inhibitor group (P>0.05). Target prediction revealed that miR-214-3p had a complementary pairing of 6 bases with the SERCA2a 3'non-coding region. After co-transfection with miR-214-3p mimic and wild-type SERCA2a expression vector, the dual-luciferase activity was significantly decreased (P<0.05). The percentage of maximal contraction amplitude, peak contraction time, and 50% diastolic time of cells in the model group and mimic group decreased significantly. The mimic group was significantly smaller (P<0.05), but there were no differences between the normal group and the inhibitor group (P>0.05). These results indicated that SERCA2a expression was significantly reduced in HF cells, and miR-214-3p could inhibit SERCA2a expression by targeting the SERCA2a 3'UTR region. Inhibition of miR-214-3p could promote the expression of SERCA2a, which in turn promoted the contractile function of HF rat cardiomyocytes.

Dynamic selective auditory attention detection using RNN and reinforcement learning

The cocktail party phenomenon describes the ability of the human brain to focus auditory attention on a particular stimulus while ignoring other acoustic events. Selective auditory attention detection (SAAD) is an important issue in the development of brain-computer interface systems and cocktail party processors. This paper proposes a new dynamic attention detection system to process the temporal evolution of the input signal. The proposed dynamic SAAD is modeled as a sequential decision-making problem, which is solved by recurrent neural network (RNN) and reinforcement learning methods of Q-learning and deep Q-learning. Among different dynamic learning approaches, the evaluation results show that the deep Q-learning approach with RNN as agent provides the highest classification accuracy (94.2%) with the least detection delay. The proposed SAAD system is advantageous, in the sense that the detection of attention is performed dynamically for the sequential inputs. Also, the system has the potential to be used in scenarios, where the attention of the listener might be switched in time in the presence of various acoustic events.

Development of Single Measuring Point Overall Balancing Method Based on Multi-Cylinder Dynamic Balance Detection System

Development of Single Measuring Point Overall Balancing Method Based on Multi-Cylinder Dynamic Balance Detection System

Distributed fiber vibration sensing with single-shot measurement and moving time-gating method

The single-shot measurement method is proposed to improve measurement accuracy in distributed dynamic strain sensing by using time-resolved optical frequency domain reflectometry (OFDR). Time-domain information can be obtained without reference scan by single-shot measurement with standard polarization-maintaining fiber as the sensing fiber via auto-correlation calculation to measure Rayleigh backscatter spectrum in different wavelength ranges. Experimental results verify that the information of vibrated and non-vibrated state can be determined by monitoring the side peak shifts in the local Rayleigh backscatter spectrum along the sensing fiber. Furthermore, moving time-gating method is illustrated and used to broaden the detection bandwidth. The effective sampling rate can be increased so that the measurable frequency range can be further increased. In the further proof of concept experiment, for a conventional OFDR system, the measurable frequency of vibration event can be achieved up to 30Hz along the polarization-maintaining fiber with a tunable laser sweeping rate of 40nm/s by single-shot measurement and moving time-gating method. The measurable frequency range could be further broadened by using tunable laser sources with higher sweeping speeds. The proposed schemes provide new approach to enhance the measurement accuracy via single-shot measurement in the OFDR system which is of great significance in distributed dynamic signal detection system.

TIDCS: A Dynamic Intrusion Detection and Classification System Based Feature Selection

Machine learning techniques are becoming mainstream in intrusion detection systems as they allow real-time response and have the ability to learn and adapt. By using a comprehensive dataset with multiple attack types, a well-trained model can be created to improve the anomaly detection performance. However, high dimensional data present a significant challenge for machine learning techniques. Processing similar features that provide redundant information increases the computational time, which is a critical problem especially for users with constrained resources (battery, energy). In this paper, we propose two models for intrusion detection and classification scheme Trust-based Intrusion Detection and Classification System (TIDCS) and Trust-based Intrusion Detection and Classification System- Accelerated (TIDCS-A) for secure network. TIDCS reduces the number of features in the input data based on a new algorithm for feature selection. Initially, the features are grouped randomly to increase the probability of making them participating in the generation of different groups, and sorted based on their accuracy scores. Only the high ranked features are then selected to obtain a classification for any received packet from the nodes in the network, which is saved as part of the node’s past performance. TIDCS proposes a periodic system cleansing where trust relationships between participant nodes are evaluated and renewed periodically. TIDCS-A proposes a dynamic algorithm to compute the exact time for nodes cleansing states and restricts the exposure window of the nodes. The final classification decision for both models is estimated by incorporating the node’s past behavior with the machine learning algorithm. Any detected attack reduces the trustworthiness of the nodes involved, leading to a dynamic system cleansing. An evaluation of TIDCS and TIDCS-A using the NSL-KDD and UNSW datasets shows that both models can detect malicious behaviors providing higher accuracy, detection rates, and lower false alarm than state-of-art techniques. For instance, for UNSW dataset, the accuracy detection is 91% for TICDS, 83.47%by using online AODE, 88% for CADF, 90% for EDM, 90% for TANN and 69.6% for NB. Consequently, TICDS has better performance than the state of art techniques in terms of accuracy detection, while providing good detection and false alarm rates.

Research on sports simulation and fatigue characteristics of athletes based on machine learning

The research on the fatigue characteristics of athletes has a certain role in promoting the development of sports. In order to detect fatigue more accurately in the state of human fatigue, this article uses a method of fusing characteristic information of many physiological parameters related to fatigue to design a multi-physical parameter-based exercise fatigue recognition method with high research value and significance. Moreover, this study combines machine learning technology to construct a dynamic fatigue detection system based on BP neural network and multiple physiological parameters. In addition, this study uses samples to construct a BP neural network and achieves dynamic detection of fatigue through multiple physiological parameters. Finally, by constructing controlled trials, fatigue is predicted. The results show that the predicted output of the fatigue value is in good agreement with the expected output, and the research method has certain practical effects.