Detection Alarm Research Articles

A Parameter-Free Pixel Correlation-Based Attention Module for Remote Sensing Object Detection

Remote sensing image object detection is a challenging task in the field of computer vision due to the complex backgrounds and diverse arrangements of targets in remote sensing images, forming intricate scenes. To overcome this challenge, existing object detection models adopt rotated target detection methods. However, these methods often lead to a loss of semantic information during feature extraction, specifically regarding the insufficient consideration of element correlations. To solve this problem, this research introduces a novel attention module (EuPea) designed to effectively capture inter-elemental information in feature maps and generate more powerful feature maps for use in neural networks. In the EuPea attention mechanism, we integrate distance information and Pearson correlation coefficient information between elements in the feature map. Experimental results show that using either type of information individually can improve network performance, but their combination has a stronger effect, producing an attention-weighted feature map. This improvement effectively enhances the object detection performance of the model, enabling it to better comprehend information in remote sensing images. Concurrently, this also improves missed detections and false alarms in object detection. Experimental results obtained on the DOTA, NWPU VHR-10, and DIOR datasets indicate that, compared with baseline RCNN models, our approach achieves respective improvements of 1.0%, 2.4%, and 1.8% in mean average precision (mAP).

Performance of Detectors for Cooperative Spectrum Sensing Under Laplacian Noise

Electronic systems in general can be impaired by impulsive noise generated by a variety of sources. Spectrum sensors are of particular interest herein, since their probabilities of detection and false alarm can be severely degraded under this impairment. Several models for impulsive noise have been studied in the literature, all of them having the common characteristic of being well represented by heavy-tailed probability density functions, like Laplace and some Stable distributions. This article addresses the performances of state-of-the-art detectors for cooperative spectrum sensing when the received signal is impaired by Laplacian noise. This is made by means of estimating the probability of detection for a fixed false alarm rate, when important system parameters are varied. It is demonstrated that the robustness against impulsive noise varies significantly depending on the adopted detection strategy.

Multi-agent reinforcement learning based optimal energy sensing threshold control in distributed cognitive radio networks with directional antenna

In CRNs, it is crucial to develop an efficient and reliable spectrum detector that consistently provides accurate information about the channel state. In this work, we investigate a CSS in a fully-distributed environment where all secondary users (SUs) are equipped with directional antennas and make decisions based solely on their local knowledge without information sharing between SUs. First, we establish a stochastic sequential optimization problem, which is an NP-hard, that maximizes the SU’s detection accuracy by the dynamic and optimal control of the energy sensing/detection threshold. It can enable SUs to select an available channel and sector without causing interference to the primary network. To address it in a distributed environment, the problem is transformed into a decentralized partially observed Markov decision process (Dec-POMDP) problem. Second, in order to determine the best control for the Dec-POMDP in a practical environment without any prior knowledge of state–action transition probabilities, we develop a multi-agent deep deterministic policy gradient (MADDPG)-based algorithm, which is referred to as MA-DCSS. This algorithm adopts the centralized training and decentralized execution (CTDE) architecture. Third, we analyzed its computational complexity and showed the proposed approach’s scalability by the polynomial computational complexity, in terms of the number of channels, sectors, and SUs. Lastly, the simulation confirms that the proposed scheme provides enhanced performance in terms of convergence speed, accurate detection, and false alarm probabilities when it is compared to baseline algorithms.

Advanced Cybercrime Detection: A Comprehensive Study on Supervised and Unsupervised Machine Learning Approaches Using Real-world Datasets

In the ever-evolving field of cybersecurity, sophisticated methods—which combine supervised and unsupervised approaches—are used to tackle cybercrime. Strong supervised tools include Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), while well-known unsupervised methods include the K-means clustering model. These techniques are used on the publicly available StatLine dataset from CBS, which is a large dataset that includes the individual attributes of one thousand crime victims. Performance analysis shows the remarkable 91% accuracy of SVM in supervised classification by examining the differences between training and testing data. K-Nearest Neighbors (KNN) models are quite good in the unsupervised arena; their accuracy in detecting criminal activity is impressive, at 79.56%. Strong assessment metrics, such as False Positive (FP), True Negative (TN), False Negative (FN), False Positive (TP), and False Alarm Rate (FAR), Detection Rate (DR), Accuracy (ACC), Recall, Precision, Specificity, Sensitivity, and Fowlkes–Mallow's scores, provide a comprehensive assessment.

Efficient Intrusion Detection System Data Preprocessing Using Deep Sparse Autoencoder with Differential Evolution

A great amount of data is generated by the Internet and communication areas’ rapid technological improvement, which expands the size of the network. These cutting‐edge technologies could result in unique network attacks that present security risks. This intrusion launches many attacks on the communication network which is to be monitored. An intrusion detection system (IDS) is a tool to prevent from intrusions by inspecting the network traffic and to make sure the network integrity, confidentiality, availability, and robustness. Many researchers are focused to IDS with machine and deep learning approaches to detect the intruders. Yet, IDS face challenges to detect the intruders accurately with reduced false alarm rate, feature selection, and detection. High dimensional data affect the feature selection methods effectiveness and efficiency. Preprocessing of data to make the dataset as balanced, normalized, and transformed data is done before the feature selection and classification process. Efficient data preprocessing will ensure the whole IDS performance with improved detection rate (DR) and reduced false alarm rate (FAR). Since datasets are required for the various feature dimensions, this article proposes an efficient data preprocessing method that includes a series of techniques for data balance using SMOTE, data normalization with power transformation, data encoding using one hot and ordinal encoding, and feature reduction using a proposed deep sparse autoencoder (DSAE) with differential evolution (DE) on data before feature selection and classification. The efficiency of the transformation methods is evaluated with recursive Pearson correlation‐based feature selection and graphical convolution neural network (G‐CNN) methods.

Visualization and analysis of electrical parameter design based on digital sensors

Abstract This paper provides an in-depth study on the application of digital sensor technology in electrical fire detection. It firstly focuses on the design of electrical parameters to improve the accuracy of fire detection. Based on the research results of recurrent neural networks, the article combines the Long Short-Term Memory (LSTM) network and the Gated Recurrent Unit (GRU) neural network. It innovatively proposes an electrical fire feature recognition method based on the LSTMGRU network. The study also incorporates fuzzy inference techniques to optimize the fire alarm decision-making process, which achieves a hierarchical output for electrical fire detection recognition and alarm decision-making. The experimental results show that the LSTM-GRU network achieves an accuracy of 98.83% in electrical fire classification and recognition, significantly better than the results of using LSTM network or GRU network alone. Regarding electrical fire distance recognition, the relative error of the method only ranges from 0.32% to 2.10%, and its output of fire alarm decision is entirely correct. The study not only verifies the high accuracy and reasonableness of the electrical fire feature recognition method based on digital sensing technology, but also provides a brand new idea for recognizing electrical fire detection and alarm decision-making.

Verification of Quasi-Linear Convective Systems Predicted by the Warn-on-Forecast System (WoFS)

Abstract Quasi-linear convective systems (QLCSs) can produce multiple hazards (e.g., straight-line winds, flash flooding, and mesovortex tornadoes) that pose a significant threat to life and property, and are often difficult to accurately forecast. The NSSL Warn-on-Forecast System (WoFS) is a convection-allowing ensemble system developed to provide short-term, probabilistic forecasting guidance for severe convective events. Examination of WoFS’s capability to predict QLCSs has yet to be systematically assessed across a large number of cases for 0–6-h forecast times. In this study, the quality of WoFS QLCS forecasts for 50 QLCS days occurring between 2017 and 2020 is evaluated using object-based verification techniques. First, a storm mode identification and classification algorithm is tuned to identify high-reflectivity, linear convective structures. The algorithm is used to identify convective line objects in WoFS forecasts and Multi-Radar Multi-Sensor system (MRMS) gridded observations. WoFS QLCS objects are matched with MRMS observed objects to generate bulk verification statistics. Results suggest WoFS’s QLCS forecasts are skillful with the 3- and 6-h forecasts having similar probability of detection and false alarm ratio values near 0.59 and 0.34, respectively. The WoFS objects are larger, more intense, and less eccentric than those in MRMS. A novel centerline analysis is performed to evaluate orientation, length, and tortuosity (i.e., curvature) differences, and spatial displacements between observed and predicted convective lines. While no systematic propagation biases are found, WoFS typically has centerlines that are more tortuous and displaced to the northwest of MRMS centerlines, suggesting WoFS may be overforecasting the intensity of the QLCS’s rear-inflow jet and northern bookend vortex. Significance Statement Quasi-linear convective systems (QLCSs), also known as squall lines, can be very destructive to life and property as they produce multiple hazards such as hail, severe straight-line winds, flash flooding, and tornadoes that typically form quickly and may be difficult to observe on radar. These storms can occur year-round and have the propensity to develop overnight or into the early morning hours, potentially catching the public off-guard. An ensemble prediction system called the Warn-on-Forecast System (WoFS), created by the National Severe Storms Laboratory, has shown promise in accurately forecasting a variety of severe weather events. This research evaluates the quality of the WoFS’s QLCS forecasts. Results show WoFS can accurately predict these systems for forecast times out to 6 h.

ECABLE (External Catheter Flexible) innovation of catheter external products for women

The increasing age of humans leads to reduced strength and muscle mass. Increasing age can also cause a decrease in the function of other organs, such as the urinary tract so that some elderly people have difficulty moving places to urinate and need to use diapers. The types of urinary catheters on the market are intermittent catheters, suprapubic catheters, and external catheters. The purpose of this study was to design a special external catheter for women with the name Ecable. Ecable is designed according to the needs of users both the elderly themselves and people who care for the elderly. The method used in this design is design thinking. ecable consists of five major components: a urine bag, an alarm, a hose, special underwear, and a urine funnel. The advantages offered by this product are easy to install and remove, comfortable to use, minimize unpleasant odors, there is a full urine bag detection alarm, minimize the cause of irritation, and are cost-effective because they can be used repeatedly. This catheter is expected to help the elderly and caregivers to overcome existing needs.

A First-Out Alarm Detection Method via Association Rule Mining and Correlation Analysis.

Alarm systems are commonly deployed in complex industries to monitor the operation status of the production process in real time. Actual alarm systems generally have alarm overloading problems. One of the major factors leading to excessive alarms is the presence of many correlated or redundant alarms. Analyzing alarm correlations will not only be beneficial to the detection of and reduction in redundant alarm configurations, but also help to track the propagation of abnormalities among alarm variables. As a special problem in correlated alarm detection, the research on first-out alarm detection is very scarce. A first-out alarm is known as the first alarm that occurs in a series of alarms. Detection of first-out alarms aims at identifying the first alarm occurrence from a large number of alarms, thus ignoring the subsequent correlated alarms to effectively reduce the number of alarms and prevent alarm overloading. Accordingly, this paper proposes a new first-out alarm detection method based on association rule mining and correlation analysis. The contributions lie in the following aspects: (1) An association rule mining approach is presented to extract alarm association rules from historical sequences based on the FP-Growth algorithm and J-Measure; (2) a first-out alarm determination strategy is proposed to determine the first-out alarms and subsequent alarms through correlation analysis in the form of a hypothesis test on conditional probability; and (3) first-out rule screening criteria are proposed to judge whether the rules are redundant or not and then consolidated results of first-out rules are obtained. The effectiveness of the proposed method is tested based on the alarm data generated by a public simulation platform.

A locational false data injection attack detection method in smart grid based on adversarial variational autoencoders

Stealthy FDIA (False Data Injection Attack) is a serious cyber threat that can modify state estimation of smart grid through maliciously altering the measurement data, but can’t be detected by traditional bad data detection system in smart grid. There exist two weakpoints for numerous deep neural networks (DNNs) based data-driven schemes against FDIA. First, they mainly focus on detecting the presence of FDIA, but fail to localize the specific bus/nodes affected. Second, their performance is not sufficiently desirable under small attack, i.e., anomalies caused by the attack closely resemble normal data. To address the above issues, this paper proposes an effective locational FDIA detection framework based on data reconstruction, AT-GVAE, which seamlessly integrates the variational autoencoders (VAEs) and generative adversarial network paradigm. Specifically, our contributions are threefold. First, the proposed AT-GVAE framework is novelly composed of two main modules: the generative VAE_G and discriminative VAE_D that both play dual roles: reconstruct data from jointly learning distributions of data and latent feature space, and meanwhile play Minmax game with adversarial way. Second, multiple-layer gated recurrent units (GRUs) are utilized as the basic structure of the encoder and decoders in both VAEs, to characterize the temporal correlations of measurement data sequence. Additionally, the self-attention mechanism is used to enhance the expressive ability of GRU based VAEs. Then, the anomaly score for each busbar in the smart grid is determined by comparing the residual between the observed measurement and the outputs of VAE_G and VAE_D, enabling the localization of FDIA. Finally, thorough experiments on multiple power systems with series data of total 3456 measurements demonstrate that, in terms of multiple typical metrics, including false alarm rate vs. detection probability, AUC-ROC, and AUC-PR, our proposed framework outperforms the state-of-the-art GRU, VAE and adversarial training based FDIA detection schemes.

Modeling alarm detection in noise for normal and hearing-impaired listeners: the effect of elevated thresholds and enlarged auditory filters

ABSTRACT A model was developed to assess how elevated absolute thresholds and enlarged auditory filters can impede the ability to detect alarms in a noisy background, such alarms being of paramount importance to ensure the safety of workers. Based on previously measured masked thresholds of 80 listeners in five groups (normal hearing to strongly impaired), the model was derived from signal detection theory (SDT) applied to Glasberg and Moore’s excitation pattern model. The model can describe the influence of absolute thresholds and enlarged auditory filters together or separately on the detection ability for normal hearing and hearing-impaired listeners with various hearing profiles. Furthermore, it suggests that enlarged auditory filters alone can explain all of the impairment in this specific alarm detection task. Finally, the possibility of further development of the model into an alarm detection model is discussed.

A Survey: Fire Detection Alarm System Using OpenCV

The Fire Detection Alarm System using OpenCV is a computer vision-based solution designed to provide early detection of fires in real-time video streams. Fires pose substantial threats to both human safety and property, underscoring the importance of timely intervention. This system leverages OpenCV, a powerful computer vision library, to identify flames and smoke patterns in video frames, triggering alerts upon detection. So, we propose a smoke and fire detection method based on YOLOv5 network as a solution to address this problem.

Evaluated bird swarm optimization based on deep belief network (EBSO-DBN) classification technique for IOT network intrusion detection

Because of the recent development of various intrusion detection systems (IDS), which defend computer networks from security as well as privacy threats. The confidentiality, integrity and also availability of data may be compromised in the case that IDS prevention efforts fail. The amount of private, delicate and crucial data travelling over the worldwide network has expanded tremendously as a result of the recent development of Internet of Things (IoT) devices. Developing a better edge-based feature selection strategy, a deep learning technique for identifying and blocking malicious traffic, is the goal of intrusion detection. The classification method Evaluated Bird Swarm Optimization based Deep Belief Network (EBSO-DBN) has shown to be the most successful in this study. A variation of performance criteria have been used to critically assess deep learning techniques for IDS (accuracy, precision, recall, f-1 score, false alarm rate and detection rate). To ascertain the optimal performance of IDS models, this study focuses on building an ensemble classifier utilizing the suggested EBSO-DBN classification algorithm with 98.7% of accuracy, 99.4% of precision and 98.8% of recall.

Joint detection algorithm for multiple cognitive users in spectrum sensing

Spectrum sensing technology is a crucial aspect of modern communication technology, serving as one of the essential techniques for efficiently utilizing scarce information resources in tight frequency bands. This paper first introduces three common logical circuit decision criteria in hard decisions and analyzes their decision rigor. Building upon hard decisions, the paper further introduces a method for multi-user spectrum sensing based on soft decisions. Then the paper simulates the false alarm probability and detection probability curves corresponding to the three criteria. The simulated results of multi-user collaborative sensing indicate that the simulation process significantly reduces false alarm probability and enhances detection probability. This approach effectively detects spectrum resources unoccupied during idle periods, leveraging the concept of time-division multiplexing and rationalizing the redistribution of information resources. The entire computation process relies on the calculation principles of power spectral density in communication theory, involving threshold decision detection for noise power and the sum of noise and signal power. It provides a secondary decision detection, reflecting the perceptual decision performance of logical detection methods with relative accuracy.

Ultrahigh moisture resistance, highly sensitive and flame retardancy wearable strain sensor for agile water rescue, fire alarm and human motion detection

Smart fabrics provide considerable inspiration for the construction of wearable electronic devices due to their excellent skin affinity and breathability. However, the limited tolerance to high humidity environments and the flammable nature of fabrics impedes broader practical applications. In this paper, by an advanced and effective method, phytic acid doped (PA-) polyaniline (PANI) was polymerized in-situ on cotton fabric deposited by carbon black (CB), and then modified by non-fluorine hydrophobic particles, a flexible breathable fabric-based strain sensor (HPCF) with ultrahigh moisture resistance, flame retardancy and environmental resistance was successfully prepared. The obtained sensor shows high sensitivity (16.14 kPa−1) in the detection range of 0–2 kPa, fast response/recovery time (82/40 ms) and high cycle stability (>10,000 cycles). Thanks to its excellent hydrophobicity (WCA = 153°) and flame retardancy properties, the material enables the detection of human movement (such as finger/wrist/elbow/knee/foot movement) under a variety of harsh conditions (extremely high temperatures, underwater, acid, alkali, salt and blown sand environments). More importantly, it can be further applied to remote detection of potentially dangerous scenarios. HPCF can successfully transmit the Morse code signals of “SOS” and “HELP” sent by drowning people, and realize water rescue. In case of fire, it serves as a fire warning sensor to realize agile (1 s) fire alarming. The highly sensitive and versatile HPCF fabric sensor enables physical condition monitoring for fire and rescue personnel working in high temperature and humidity environments, which is of great value for all human activities carried out in harsh environments.

Passive-seismic sensor placement optimization for geologic carbon storage

The implementation of passive-seismic monitoring is essential for the geological carbon storage projects. For secure and continuous observing of induced passive-seismic events by CO2 injecting, a ground geophone network would be required. By determining the ideal number of seismic stations within a regular network, recent research has enhanced monitoring capabilities while also accommodating budgetary limitations. The primary objective of the optimal placement strategy for the surface geophone network is to create a cost-effective monitoring system. Given the cost limitations, a restricted quantity of sensors can be deployed at each location to maximize monitoring performance. To address this challenge, our approach involves the P-median stochastic programming formulation. The formulation aims to minimize the expected value of a monitoring target metric, which ultimately results in the optimal placement of detectors exhibiting superior expected behaviors. Our methodology is designed to choose the arrangement of detectors with best performance to improve both the early alarm detection time and localization capabilities of the sensor network. We utilize site-specific passive-seismic scenarios that capture the uncertainty in the characteristics of carbon leakage. The sensor grids provided by the optimization method invariably improve the capacity to detect passive-seismic events in comparison to sensors positioned in a regular grid configuration. We test the effectiveness of our approach on synthetic data based on a carbon storage site named Kimberlina. In conclusion, our approach provides a cost-effective solution for the optimal placement of sensors to achieve superior monitoring performance for the detection of passive-seismic events. The incorporation of site-specific scenarios with stochastic uncertainty coverage allows for more accurate and reliable results, leading to better decision-making for long-term geological carbon storage.

GPU-Accelerated Signal Processing for Passive Bistatic Radar

Passive bistatic radar is a novel radar technology that passively detects targets without actively emitting signals. Since passive bistatic radar entails larger data volumes and computations compared to traditional active radiation radar, the development of hardware and software platforms capable of efficiently processing signals from passive bistatic radar has emerged as a research focus in this field. This research investigates the signal processing flow of passive bistatic radar based on its characteristics and devises a parallel signal processing scheme under graphic processing unit (GPU) architecture for computation-intensive tasks. The proposed scheme utilizes high-computing-power GPU as the hardware platform and compute unified device architecture (CUDA) as the software platform and optimizes the extensive cancellation algorithm batches (ECA-B), range Doppler and constant false alarm detection algorithms. The detection and tracking of a single target are realized on the passive bistatic radar dataset of natural scenarios, and experiments show that the design of this algorithm can achieve a maximum acceleration ratio of 113.13. Comparative experiments conducted with varying data volumes revealed that this method significantly enhances the signal processing rate for passive bistatic radar.

Comparative analysis of gridded rainfall datasets over the Bagmati river basin, India

Abstract In this study, three high-resolution gridded rainfall datasets, viz., Integrated Multi-Satellite Retrievals for Global Precipitation Measurement (IMERG), Modern-Era Retrospective Analysis for Research and Applications 2 (MERRA-2), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks (PERSIANN) have been collected, analyzed, and compared against the ground-based observed rain gauge datasets of Indian Meteorological Department (IMD) of the Bagmati river basin from 2001 to 2014 in the Bihar State of India. Comparison analyses were performed at daily, monthly, seasonal, and annual time scales. Various statistical parameters, contingency tests, trend analysis, and rainfall anomaly index were used for comparison of datasets. Though MERRA-2 had the highest probability of detection (POD) and lowest false alarm ratio (FAR), analysis showed that IMERG data were closely matching with the observed data, whereas MERRA-2 and PERSIANN underestimated the extreme values. For the monthly scale, again IMERG had the most optimal Coefficient of Determination (R2) and Nash-Sutcliffe Efficiency (NSE) values. IMERG also performed well in detecting rainfall trends and identifying wet and dry years. Overall, IMERG was the most suitable dataset at all time scales for future studies in the basin.

Mapping property redevelopment via GeoAI: Integrating computer vision and socioenvironmental patterns and processes

Domain knowledge of social and environmental sciences is generally derived from less structured small data and/or small models. The integration of deep learning with socioenvironmental and geographical patterns and processes is still in an early phase. This study proposes a flexible framework that synthesizes computer vision with patterns and processes of geographical phenomena (e.g., urban redevelopment) via deep convolutional neural networks and spatiotemporal neighborhoods, respectively. Meanwhile, undesirable visual cues (e.g., temporary objects such as cars) cause false alarms in urban change detection. Thus, a masked deep pyramid similarity model (i.e., the computer vision model) is proposed to minimize the negative impact of nonbuilding changes. This pipeline has robustness against obfuscation of undesirable street scene changes and elasticity of geographical knowledge representations in mapping property redevelopment. This model is reproducible and adaptable due to the wide availability of SVI and flexibility of the framework. The results suggest that the domain-driven rules and nonbuilding change masking mechanism can significantly increase the accuracy of a computer vision model. We also find that urban redevelopment should be understood as a locally tuned back-to-the-city process with weak replicability. Hybrid gentrification (i.e., the combination of “seesaw” gentrification and continuous gentrification) is observed globally with local variations. Takeaway for practiceFirst, the population of those affected should be carefully identified and the benefits of gentrification need to be redistributed on a larger scale. For Auckland, decision-makers should not divert attention away from low-income tenants in outer suburbs that slipped below the radar of local government and scholars. Second, more attention should be given to less resourcing neighborhoods in constantly gentrifying neighborhoods when governments formulate and implement housing subsidy policies. Locally, incessant redevelopment in Auckland CBD, New Market and Remuera, etc., should be contained.

An Underestimated Cybersecurity Problem: Quick-Impact Time Synchronization Attacks and a Fast-Triggered Detection Method

For cybersecurity concerns in smart girds, this paper has focused on the vulnerability analysis and defense technique against the Time Synchronization Attack (TSA). This kind of attack can spoof satellite-signal-based time synchronization processes that are widely utilized in modern power systems. A quick-impact TSA experiment is presented in this paper, based on live satellite signals and a commercial time server used in current smart grids. Experiment results are alarming. Intolerable timing errors have been imposed on the server within a few tens of seconds, and it hasn’t reported any alarms. So a new cybersecurity concern for distributed power systems is revealed: stealthy TSAs must be detected at the early stage due to their quick impacts, yet current studies have underestimated this problem. In response to this potential threat, a fast-triggered detection method is proposed in this paper. It is named the Rapid Detection of Signal Distortions (RDSD) and can detect early stage signal distortions caused by TSAs at the beginning. Apart from this ability, we have also verified, via simulations and real-world comparative experiments, that the proposed method can provide improved detection and false alarm rejection capacity compared with existing methods of this type. Overall, this paper can raise attention to the cybersecurity problem caused by TSAs and facilitate the defense against them in modern smart grids.