Degradation In Detection Performance Research Articles

MTC-NET: A Multi-Channel Independent Anomaly Detection Method for Network Traffic.

In recent years, deep learning-based approaches, particularly those leveraging the Transformer architecture, have garnered widespread attention for network traffic anomaly detection. However, when dealing with noisy data sets, directly inputting network traffic sequences into Transformer networks often significantly degrades detection performance due to interference and noise across dimensions. In this paper, we propose a novel multi-channel network traffic anomaly detection model, MTC-Net, which reduces computational complexity and enhances the model's ability to capture long-distance dependencies. This is achieved by decomposing network traffic sequences into multiple unidimensional time sequences and introducing a patch-based strategy that enables each sub-sequence to retain local semantic information. A backbone network combining Transformer and CNN is employed to capture complex patterns, with information from all channels being fused at the final classification header in order to achieve modelling and detection of complex network traffic patterns. The experimental results demonstrate that MTC-Net outperforms existing state-of-the-art methods in several evaluation metrics, including accuracy, precision, recall, and F1 score, on four publicly available data sets: KDD Cup 99, NSL-KDD, UNSW-NB15, and CIC-IDS2017.

Radar waveform generative design method

AbstractTo address the issue of radar detection performance degradation caused by interference in complex electromagnetic environments, this paper proposes a generative waveform design method and demonstrates its advantages. This method fully exploits waveform degrees of freedom to achieve a larger design space, generating a multitude of agile waveform parameters within the constraint envelope through algorithmic processes. This approach enables the radar to maintain detection performance in complex electromagnetic environments. Compared with the traditional waveform design method, the simulation experiment verifies the effectiveness of the generative waveform design method.

MATB for assessing different mental workload levels.

Multi-Attribute Task Battery (MATB) is a computerized flight simulator for aviation-related tasks, suitable for non-pilots and available in many versions, including open source. MATB requires the individual or simultaneous execution of 4 sub-tasks: system monitoring (SYSMON), tracking (TRACK), communications (COMM), and resource management (RESMAN). Fully customizable, the design of test duration, number of sub-tasks used, event rates, response times and overlap, create different levels of mental load. MATB can be combined with an additional auditory attention (Oddball) task, or with physiological constraints (i.e., sleep loss, exercise, hypoxia). We aimed to assess the main characteristics of MATB design for assessing the response to different workload levels. We identified and reviewed 19 articles for which the effects of low and high workload were analyzed. Although MATB has shown promise in detecting performance degradation due to increase workload, studies have yielded conflicting or unclear results regarding MATB configurations. Increased event rates, number of sub-tasks (multitasking), and overlap are associated with increased perceived workload score (ex. NASA-TLX), decreased performance (especially tracking), and neurophysiological responses, while no effect of time-on-task is observed. The median duration used for the test is 20min (range 12-60) with a level duration of 10min (range 4-15). To assess mental workload, the median number of stimuli is respectively 3 events/min (range 0.6-17.2) for low, and 23.5 events/min (range 9-65) for high workload level. In this review, we give some recommendations for standardization of MATB design, configuration, description and training, in order to improve reproducibility and comparison between studies, a challenge for the future researches, as human-machine interaction and digital influx increase for pilots. We also open the discussion on the possible use of MATB in the context of aeronautical/operational constraints in order to assess the effects combined with changes in mental workload levels. Thus, with appropriate levels of difficulty, MATB can be used as a suitable simulation tool to study the effects of changes on the mental workload of aircraft pilots, during different operational and physiological constraints.

An Effective Federated Object Detection Framework with Dynamic Differential Privacy

The proliferation of data across multiple domains necessitates the adoption of machine learning models that respect user privacy and data security, particularly in sensitive scenarios like surveillance and medical imaging. Federated learning (FL) offers a promising solution by decentralizing the learning process, allowing multiple participants to collaboratively train a model without sharing their data. However, when applied to complex tasks such as object detection, standard FL frameworks can fall short in balancing the dual demands of high accuracy and stringent privacy. This paper introduces a sophisticated federated object detection framework that incorporates advanced differential privacy mechanisms to enhance privacy protection. Our framework is designed to work effectively across heterogeneous and potentially large-scale datasets, characteristic of real-world environments. It integrates a novel adaptive differential privacy model that strategically adjusts the noise scale during the training process based on the sensitivity of the features being learned and the progression of the model’s accuracy. We present a detailed methodology that includes a privacy budget management system, which optimally allocates and tracks privacy expenditure throughout training cycles. Additionally, our approach employs a hybrid model aggregation technique that not only ensures robust privacy guarantees but also mitigates the degradation of object detection performance typically associated with DP. The effectiveness of our framework is demonstrated through extensive experiments on multiple benchmark datasets, including COCO and PASCAL VOC. Our results show that our framework not only adheres to strict DP standards but also achieves near-state-of-the-art object detection performance, underscoring its practical applicability. For example, in some settings, our method can lower the privacy success rate by 40% while maintaining high model accuracy. This study makes significant strides in advancing the field of privacy-preserving machine learning, especially in applications where user privacy cannot be compromised. The proposed framework sets a new benchmark for implementing federated learning in complex, privacy-sensitive tasks and opens avenues for future research in secure, decentralized machine learning technologies.

Robust speckle covariance matrix estimation of sea clutter based on spectral symmetry

Speckle covariance matrix estimation plays an important role in adaptive target detection of maritime radars. Spatial heterogeneity of sea clutter incurs insufficient secondary data in estimation, which degrades detection performance. It is an effective way of estimation improvement to exploit the Doppler spectrum knowledge of sea clutter for structural dimension reduction of the speckle covariance matrix. This paper proposes a speckle covariance matrix estimation method based on the spectral symmetry knowledge of sea clutter, indicating that the spectrum of sea clutter is symmetric with respect to the Doppler offset. First of all, the spectral symmetry of sea clutter is analyzed by using the measured data from several opened databases and the results show that most of the data excluding sea spikes have symmetric Doppler spectra. Secondly, the spectral symmetry constrains the speckle covariance matrix into the Hadamard product of a special rank-one Toeplitz matrix and a real positive definite symmetric matrix. The degrees of freedom are reduced to almost half of that of a Hermitian matrix and thus fewer secondary data are required. Thirdly, a robust iterative maximum likelihood estimator is proposed to estimate the speckle covariance matrix with structural constraint and is free of the clutter texture distribution. The performance of the estimator is verified by the measured data and the results show that it is superior to traditional estimators, particularly in fewer secondary data.

Dynamic center point learning for multiple object tracking under Severe occlusions

Multiple Object Tracking (MOT) methods based on per-pixel prediction and association have achieved remarkable progress recently. These approaches prefer to select points in central region of the bounding box as positive samples and other points as negative samples. Under severe occlusions, these sample allocation methods might lead to the central region being contaminated by occluding samples, resulting in significant degradation of both detection and association performance. To address this issue, we propose a novel Dynamic-Center-Point-based Multiple Object Tracking method (DCP-MOT), which aims to self-identify the visible center region for occluded objects. Compared with the previous bounding box center point, our Dynamic-Center-Point (DCP) can better represent the visible region of the occluded object. Specifically, we design an Iterative Refinement Branch to generate dynamic center points for each occluded object. It includes two parts: Center Probability Predictor and Center Generator. Initially, we utilize the Center Probability Predictor to derive an accurate probability map for the occluded object. Subsequently, we use Center Generator to quantify the probability map by introducing a Mutual Exclusive Potential Function, yielding a dynamic center point for the occluded object that is distinct from its occluding counterpart. Finally, by joining the bounding box center points for unoccluded objects and our dynamic center points for occluded objects, our JDE branch can achieve better tracking performance. Extensive experiments demonstrate our DCP-based MOT method surpasses the bounding box center based SOTA in metrics MOTA (+0.7,+2.1,+1.3) and IDF1 (+0.7,+0.9,+1.5) on the challenging MOT16, MOT17, MOT20 datasets.

WBNet: Weakly-supervised salient object detection via scribble and pseudo-background priors

Weakly supervised salient object detection (WSOD) methods endeavor to boost sparse labels to get more salient cues in various ways. Among them, an effective approach is using pseudo labels from multiple unsupervised self-learning methods, but inaccurate and inconsistent pseudo labels could ultimately lead to detection performance degradation. To tackle this problem, we develop a new multi-source WSOD framework, WBNet, that can effectively utilize pseudo-background (non-salient region) labels combined with scribble labels to obtain more accurate salient features. We first design a comprehensive salient pseudo-mask generator from multiple self-learning features. Then, we pioneer the exploration of generating salient pseudo-labels via point-prompted and box-prompted Segment Anything Models (SAM). Then, WBNet leverages a pixel-level Feature Aggregation Module (FAM), a mask-level Transformer-decoder (TFD), and an auxiliary Boundary Prediction Module (EPM) with a hybrid loss function to handle complex saliency detection tasks. Comprehensively evaluated with state-of-the-art methods on five widely used datasets, the proposed method significantly improves saliency detection performance. The code and results are publicly available at https://github.com/yiwangtz/WBNet.

An Advanced Scheme for Radar Clutter Suppression Scheme Based on Blind Source Separation

In cluttered electromagnetic environments, radar is often disturbed by varied clutter, making target detection challenging. Therefore, achieving effective clutter suppression is crucial for radar target detection. However, traditional clutter suppression methods face three key challenges: (1) significant degradation in target signal detection performance when the clutter’s Doppler spectrum completely masks the target signal; (2) heavy reliance on prior knowledge for optimal performance; and (3) inherent signal energy loss during clutter suppression. To address these challenges, we propose a clutter suppression scheme based on blind source separation (BSS). Initially, the scheme utilizes parallel principal skewness analysis (PPSA) to process the echo signals in the range domain, which helps in identifying the position of moving targets. Subsequently, PPSA is applied once more to process the moving targets in the Doppler domain, allowing for the precise determination of their relative velocities. Subsequently, we evaluate the scheme’s performance with simulated and real data, comparing it with traditional clutter suppression methods and other BSS techniques. The results confirm the effectiveness of the scheme in clutter suppression.

Data-driven integrated study on operational performance degradation detection and recovery control of VFDR

The Variable Flow Ducted Rocket (VFDR) serves as the preferred propulsion system for hypersonic aircraft. However, it is prone to health degradation issues due to component failures, aging, and changes in operational conditions, which significantly challenge flight safety. This study introduces a data-driven integrated control approach for modeling, diagnosing, and remedying performance deterioration. Initially, a method for open-set modeling of performance degradation is developed using the Linear Parameter-Varying (LPV) modeling technique and gap metric theory, tackling the hurdles of data collection, overlapping fault classes, and modeling of unidentified faults in the VFDR system; thus, providing vital data support for detecting performance degradation. Moreover, employing the LPV model for performance degradation, a hybrid deep neural network combining multi-scale CNN and LSTM is trained to diagnose system performance issues online using multi-dimensional time-domain sequential data. Subsequently, a smooth transition control method utilizing sliding mode compensation is applied to regain control of system performance based on diagnostic outcomes and a pre-established VFDR performance recuperation controller. Simulations of three types of performance deterioration scenarios caused by changes in actuators, sensors, and the system's operational environment are conducted to demonstrate the efficiency of the proposed approach. The simulation outcomes affirm that the proposed approach is capable of effectively modeling system performance deterioration, diagnosing faults, and controlling recovery, offering promising technical support for the secure operation of intricate closed-loop control systems with stringent precision and reliability requirements.

Structural Engineering Enables Suppressed Ion Migration and Enhanced Hard X‐Ray Detection Performance in Novel Oxide Single Crystals

AbstractX‐ray detectors have obtained great attention in medical diagnostics, security checks, and space exploration. However, ion migration of X‐ray detectors results in dark current drift, low signal‐to‐noise ratio, and degradation of detection performance. Here, ion migration properties of Li2ZrTeO6 and ZrTe3O8 are comprehensively investigated by theoretical analysis and experimental results. ZrTe3O8 single crystal exhibits a high migration barrier of O2− ion (1.89 eV), a high ion activation energy (992.6 meV), and an ultralow dark current drift (3.16 × 10−9 nA cm−1 s−1 V−1) due to the absence of Li+ cations and the disconnecting of adjacent ZrO6 octahedra, which is better than Li2ZrTeO6 single crystal. These results show that the absence of low atomic number elements and the disconnecting of adjacent octahedra in crystal structure can inhibit ion migration essentially. Owing to a high resistivity, a high mobility lifetime product, suppressed ion migration, and the lone‐pair electrons enhancement effect of detection performance for Te4+ cations, ZrTe3O8 X‐ray detector shows a high sensitivity of 348 µC Gy−1 cm−2 and an ultralow detection limit of 15.4 nGyair s−1. This work proposes an effective strategy to inhibit ion migration and proves the enhancement effect of detection performance for the cations containing lone‐pair electrons.

Persymmetric detection based on asymptotically optimal convex linear combination

Persymmetric structure has been utilized in space-time adaptive processing for heterogeneous environment, which leads to some detection methods based on persymmetric structure, such as persymmetric adaptive matched filter (PS-AMF). However, when the sample support is extremely limited, these methods still suffer the serious degradation in detection performance due to the large error in estimating covariance matrix. In this paper, an asymptotically optimal convex linear combination between transformed sample covariance matrix and identity matrix is considered herein to improve PS-AMF. The asymptotically optimal convex linear combination is conducive to diminishing the estimate error in estimating the transformed covariance matrix by weighting the transformed sample covariance matrix and identity matrix. Furthermore, the asymptotically optimal convex linear combination is improved by the reutilization of the convex linear combination, and the corresponding coefficients are derived. Then, the detection performance of the proposed method is approximately analyzed. At last, numerical simulations show that the proposed method performs well, compared with its counterparts, when the sample support is extremely limited.

Privacy and security trade‐off in cyber‐physical systems: An information theory‐based framework

AbstractThis article investigates the trade‐off between privacy and security in cyber‐physical systems, with the goal of designing a privacy‐preserving mechanism based on information theory. Considering the unreliability of the communication channel, we assume that the private data is vulnerable to eavesdropping and bias injection attacks. To maintain privacy, the system is equipped with a privacy‐preserving mechanism achieved by injecting Gaussian‐type privacy noise into transmitted data, which inevitably leads to degraded detecting performance. Therefore, we investigate the trade‐off between privacy level and detection performance, where the privacy level and the detection performance are measured by mutual information and Kullback–Leibler divergence, respectively. Then, the optimal privacy noise is obtained by solving a convex optimization problem for maximizing the privacy degree and constraining a bound on detection performance degradation. Furthermore, to optimize the detection performance, another convex optimization problem is proposed to minimize both the false alarm rate and the missed alarm rate while guaranteeing a level of the privacy. Finally, a numerical example of the vehicle tracking problem is adopted to illustrate the effectiveness of the designed framework.

Colorectal image analysis for polyp diagnosis.

Colorectal polyp is an important early manifestation of colorectal cancer, which is significant for the prevention of colorectal cancer. Despite timely detection and manual intervention of colorectal polyps can reduce their chances of becoming cancerous, most existing methods ignore the uncertainties and location problems of polyps, causing a degradation in detection performance. To address these problems, in this paper, we propose a novel colorectal image analysis method for polyp diagnosis via PAM-Net. Specifically, a parallel attention module is designed to enhance the analysis of colorectal polyp images for improving the certainties of polyps. In addition, our method introduces the GWD loss to enhance the accuracy of polyp diagnosis from the perspective of polyp location. Extensive experimental results demonstrate the effectiveness of the proposed method compared with the SOTA baselines. This study enhances the performance of polyp detection accuracy and contributes to polyp detection in clinical medicine.

FOLD: Low-Level Image Enhancement for Low-Light Object Detection Based on FPGA MPSoC

Object detection has a wide range of applications as the most fundamental and challenging task in computer vision. However, the image quality problems such as low brightness, low contrast, and high noise in low-light scenes cause significant degradation of object detection performance. To address this, this paper focuses on object detection algorithms in low-light scenarios, carries out exploration and research from the aspects of low-light image enhancement and object detection, and proposes low-level image enhancement for low-light object detection based on the FPGA MPSoC method. On the one hand, the low-light dataset is expanded and the YOLOv3 object detection model is trained based on the low-order image enhancement technique, which improves the detection performance of the model in low-light scenarios; on the other hand, the model is deployed on the MPSoC board to achieve an edge object detection system, which improves the detection efficiency. Finally, validation experiments are conducted on the publicly available low-light object detection dataset and the ZU3EG-AXU3EGB MPSoC board, and the results show that the method in this paper can effectively improve the detection accuracy and efficiency.

Detecting performance degradation in a dead-ended hydrogen-oxygen proton exchange membrane fuel cell used for an unmanned underwater vehicle

Hydrogen-oxygen proton exchange membrane fuel cells (HO-PEMFCs) play a crucial role in the unmanned underwater vehicle (UUV) transportation field due to their distinct advantages of zero emission and low infrared radiation intensity. Effective water management is essential for the stable operation and performance output of HO-PEMFC. However, the vital role of increasing gas velocity to mitigate performance issues and catalyst degradation during prolonged fuel cell operation is frequently overlooked. The objective of this study is to systematically enhance both catalyst durability and overall system efficiency in dead-ended HO-PEMFCs by manipulating cathode flow velocities. The research findings demonstrate that a recirculation pump speed of 200 rpm (corresponding to a gas flow rate of approximately 0.4 m/s) can enhance cell performance by 58.39% at a current density of 1200 mA cm−2 compared to the dead-ended mode. With the gradual increase in pump speed, the flow pattern of liquid water at the cathode outlet transitions from film flow to droplet flow. Moreover, a weight coefficient is proposed to characterize the Pt oxidation states. Electrochemical and morphological characterization show that the increased gas flow rate mitigates water accumulation at the fuel cell outlet. In addition, the degradation of the catalyst due to dehydration of the membrane in the reactant gas inlet area is also mitigated by exhaust gas recirculation.

OVERVIEW OF FRAUD DETECTION SYSTEMS AND PERFORMANCE KPI DEVELOPMENT

In this article overview was provided on several fraud detection systems, analysis result of common scheme and development of KPIs to detect performance degradation or improvement from business logic point of view. Four different systems were reviewed. Following FMS were developed by Gigamon and Argyle Data cooperation, AWS, Subex, Cvidya Amdocs. Solution developed by Gigamon and Argyle Data consists of Gigamon fabric for information collection/filtering/enrichment and Argyle Data Fraud detection system, which is based on Hadoop technology to store collected data and analysis results by application. AWS Fraud Detection collects NRTRDE flow and process it by using ML technics provided by AWS. Subex fraud management system provides flexible ETL for data collection from different sources with adjustable detection rules and ML for suspicious behavior learning. FraudView by Cvidya Amdocs collects information from varying points like OSS/BSS, CRM customer details, Prepaid platforms, HLR, Switch CDRs, Probe (SS7, VoIP, IP) and process it by different detection engines. Simplified processing FMS processing scheme and KPIs based on different timestamps were made. Following conclusions were made: In reviewed FMS was noticed that instead of using traditional NRTRDE and TAP3 file formats, data can be collected directly from network by using network tap or port mirroring with next data enrichment, cleaning, formatting for fraud detection system to consume. Following real time method can be realized by using probes to perform data preparation or some complex solution described by Gigamon; Detection is performed by rules, provided by vendor or by ML modules, which learns behavior of subscriber in order to create detection rules. Most of systems allow to modify threshold of following rules in order to meet system user demands to check data within specific time (for example fraudster night calls to subscriber) or detect specific number of suspicious sessions, etc; In order speedup fraud detection hotlists, whitelists can be used for enrichment to filter out fraudsters, emergency or business numbers. Geographical location can be used to identify fraudster’s location within network and make correlation with other possible fraud sessions; During analysis of each FMS architecture, 3 processing stages were highlighted, which allowed to create simple KPIs for business logic and data arrival check; Developed methodology allows to check data arrival and fraud recognition with used data type to define which information provides better detection or view on rules for detection in order to show, which of them should be adjusted.

Detecting interference between applications and improving the scheduling using malleable application clones

This paper presents a novel feature for improving the scheduling process based on the performance prediction and the detection of CPU and I/O interference between applications. This feature consists of using malleable synthetic benchmarks – called clones – that reproduce the behaviour of applications executed in a cluster. These proxies can be used with two objectives: to build large and representative datasets that can be used to train the machine learning algorithms for modelling the platform workload, and to evaluate in advance if two executing applications can potentially produce contention hazards related to the shared use of the system resources like CPU, cache memory or I/O bandwidth. The proposed framework generates application clones based on generic-purpose performance information collected from monitoring. Unlike other works based on the use of micro-architectures or metrics obtained from simulators, in the approach presented in this work, the application clones generate similar behaviour without extracting data from the binaries, avoiding the necessity of managing code or data from the applications. One advantage of this approach is that they can be shared securely because they have not been generated using any piece of the original code. In addition, the proposed clones are malleable, so they also able to model the application behaviour under a different number of processes. In this work, we show how the use of clones contributes to improving the application scheduling by reducing the number of evaluations that is necessary to perform, and to detect performance degradation (interference) without the necessity of involving the execution of the actual applications. We evaluate the proposed clone generation approach on two sets of benchmarks (CPU and I/O oriented) and several applications. We also compare the performance obtained during the execution of the proxies and the applications to show their similarity. Finally, we include an evaluation of the interference detection using this novel approach.

Non-Intrusive Continuous Monitoring of Smart City Platforms

Smart city platforms provide several services to facilitate the development of applications. Such platforms typically manage several applications, deal with a large volume of data, and serve many devices and users that generate a high volume of requests. The large number of requests to handle and the complex operations to perform often cause overloads on the platform, degrading the quality of service provided to users and applications. In this context, monitoring the underlying computational infrastructure in which smart city platforms and applications are deployed and the platform operations is essential. The monitoring process can allow for examining fluctuations in the behavior of the platform's components to detect performance degradation and overloads (including unforeseen ones), contribute to avoiding interruptions in the platform's services, and increase its scalability to assimilate significant amounts of requests, devices, and users. This paper presents a strategy and architecture to enable the non-intrusive monitoring of operations on smart city platforms and their underlying infrastructure. The proposal covers monitoring at multiple levels and is based on the aspect-oriented programming (AOP) paradigm so that it is possible to monitor the platform's operations without intervening in the platform's implementation or generating coupling regarding monitoring. This paper presents the implementation of the monitoring architecture and its instantiation in the context of Smart Geo Layers (SGeoL), a platform that has been used in several real-world smart city applications. This paper also reports the results of computational experiments to evaluate the performance of the proposed monitoring architecture for response time to requests, CPU usage, and RAM utilization. The obtained results show an evident increase in response time with the number of simultaneous requests and a significant correlation between the response time and the CPU utilization in the deployment of the monitoring architecture.

Spaceborne SAR Time-Series Images Change Detection Based on SAR-SIFT-Logarithm Background Subtraction

Synthetic Aperture Radar (SAR) image change detection aims to detect changes with images of the same area acquired at different times. It has wide applications in environmental monitoring, urban planning and resource management. Traditional change detection methods for spaceborne SAR time-series images typically adopt a pairwise comparison strategy to obtain multi-temporal change information. However, this kind of method has the problem of losing the overall change information, which is time consuming. To address this problem, this paper proposes a new change detection algorithm for spaceborne SAR time-series data based on SAR-SIFT-Logarithm Background Subtraction. This algorithm combines the SAR-SIFT image registration technology with Logarithm Background Subtraction. The method first preprocesses the input time-series data with steps like noise reducing and radiometric calibration. Then, the images will be coregistered by the SAR-SIFT step to avoid mismatches-induced detection performance degradation. Next, the parts that remained unchanged throughout the time period are modeled with a median filter to obtain the static background. The change information is then obtained via the subtraction of background and CFAR detection and clustering. The proposed algorithm is validated using the Sentinel-1 GRD and PAZ-1 time-series dataset. Experimental results demonstrate that the proposed method effectively detects the overall change information and reduces processing time compared to traditional pairwise comparison methods.

Predictive Maintenance System for Rotating Machinery Onboard Ships for Detecting Performance Degradation

Maintenance of rotating machinery is crucial for extending the lifespan and increasing the reliability of equipment onboard ships. Presently, breakdown and preventive methodologies are used for the maintenance of equipment. Further, dataloggers collect critical machinery parameters, and parameter data is used for real-time parameter monitoring. The availability of such extensive monitoring data has also led to the adoption predictive maintenance methodologies in the industry, wherein machine learning-based analysis of recorded data is used to predict impending defects and prompt required maintenance. In this paper, we propose a predictive maintenance system that records data through a network of sensors installed over multiple electrical motor pump sets onboard the ship and uses statistical analysis to detect equipment degradation. Our system has been deployed onboard a ship to undertake real-time predictive maintenance of electrical motor pump sets used in firemain, AC plants, stabilizers, steering pumps and other auxiliary engine room machinery.