Efficient Detection Algorithm Research Articles

Hailstorm events in the Central Andes of Peru: insights from historical data and radar microphysics

Abstract. Hailstorms, while fascinating from a meteorological perspective, pose significant risks to communities, agriculture, and infrastructure. In regions such as the Central Andes of Peru, the characteristics and frequency of these extreme weather events remain largely uncharted. This study fills this gap by investigating the historical frequency and vertical structure of hailstorms in this region. We analyzed historical hailstorm records dating back to 1958 alongside 4 years of observations (2017–2021) from the Parsivel2 disdrometer and a cloud-profiling radar MIRA35c. Our findings indicate a trend of decreasing hail frequency (−0.5 events per decade). However, the p value of 0.07 suggests the need for further investigation, particularly in relation to environmental changes and reporting methods. The results show that hailstorms predominantly occur during the austral summer months, with peak frequency in December, and are most common during the afternoon and early evening hours. The analysis of radar variables such as reflectivity, radial velocity, spectral width, and linear depolarization ratio (LDR) reveals distinct vertical profiles for hail events. Two case studies highlight the diversity in the radar measurements of hailstorms, underscoring the complexity of accurate hail detection. This study suggests the need for refining the Parsivel2 algorithm and further understanding its classification of hydrometeors. Additionally, the limitations of conventional radar variables for hail detection are discussed, recommending the use of LDR and Doppler spectrum analysis for future research. Our findings lay the groundwork for the development of more efficient hail detection algorithms and improved understanding of hailstorms in the Central Andes of Peru.

Comparative Study of Machine Learning Algorithms for Traffic Sign Recognition

The increasing integration of intelligent transportation systems has brought forth a critical need for accurate and efficient traffic sign detection algorithms. In this research, we conduct a comprehensive comparative analysis of four prominent convolutional neural network (CNN) architectures—LeNet, ResNet, VGG, and a standard CNN model—for their performance in traffic sign detection. The evaluation is conducted on a diverse dataset, utilizing the German Traffic Signs Recognition Benchmark (GTSRB). Our study encompasses an in-depth examination of accuracy metrics and performance under varying conditions, such as challenging lighting, occlusion, and environmental complexities. The results demonstrate nuanced differences in accuracy and computational efficiency among the algorithms. LeNet exhibits notable improvements in real-time processing, while ResNet showcases enhanced accuracy, and VGG demonstrates robustness in challenging conditions. The findings provide valuable insights into the strengths and weaknesses of each algorithm, aiding researchers and practitioners in selecting the most suitable model for specific traffic sign detection applications. This research contributes to advancing the field of computer vision in intelligent transportation systems, with implications for enhancing road safety and efficiency. Key Words: traffic sign recognition, deep learning, Res-Net, VGG19, CNN, LeNet.

An efficient algorithm for multi-scale maritime object detection and recognition

Due to the complexity of the maritime environment and the diversity of the volume and shape of monitored objects in the maritime, existing object detection algorithms based on Convolutional Neural Networks (CNN) are challenging to balance the requirements of high accuracy and high real-time simultaneously in the field of maritime object detection. In response to the characteristics of complex backgrounds, significant differences in object size between categories, and the characteristic of having a large number of small objects in maritime surveillance videos and images, the Maritime dataset with rich scenes and object categories was self-made, and the OS-YOLOv7 algorithm was proposed based on the YOLOv7 algorithm. Firstly, a feature enhancement module named the TC-ELAN module based on the self-attention mechanism was designed, which enables the feature map used for detection to obtain enhanced semantic information fused from multiple scale features. Secondly, in order to enhance the attention to the area of dense small objects and further improve the positioning accuracy of occluded small objects, this study redesigned the SPPCSPC structure. Then, the network structure was improved to alleviate the problem of decreased object detection accuracy caused by the loss of semantic feature information. Finally, experimental results on self-made datasets and mainstream maritime object detection datasets show that OS-YOLOv7 has a better object detection effect compared to other state-of-the-art (SOTA) object detection algorithms at the cost of reasonable inference time and parameter quantity and can achieve good object detection accuracy on mainstream datasets with high real-time performance.

A Systematic Review of the Application of Machine Learning in CpG Island (CGI) Detection and Methylation Prediction

Background: CpG island (CGI) detection and methylation prediction play important roles in studying the complex mechanisms of CGIs involved in genome regulation. In recent years, machine learning (ML) has been gradually applied to CGI detection and CGI methylation prediction algorithms in order to improve the accuracy of traditional methods. However, there are a few systematic reviews on the application of ML in CGI detection and CGI methylation prediction. Therefore, this systematic review aims to provide an overview of the application of ML in CGI detection and methylation prediction. Methods: The review was carried out using the PRISMA guideline. The search strategy was applied to articles published on PubMed from 2000 to July 10, 2022. Two independent researchers screened the articles based on the retrieval strategies and identified a total of 54 articles. After that, we developed quality assessment questions to assess study quality and obtained 46 articles that met the eligibility criteria. Based on these articles, we first summarized the applications of ML methods in CGI detection and methylation prediction, and then identified the strengths and limitations of these studies. Result: Finally, we have discussed the challenges and future research directions. Conclusion: This systematic review will contribute to the selection of algorithms and the future development of more efficient algorithms for CGI detection and methylation prediction

Detection and location of high impedance faults in delta 13.8kV distribution networks

This article presents the main results obtained in the project “Automated System of Classification, Detection, and Location of High Impedance Faults in Distribution Networks”, carried out for Brazilian utility COPEL, between 2019 and 2021, as part of ANEEL's R&D program. The project developed an automated system with efficient and robust algorithms for the real-time detection, classification, and location of high impedance faults in the distribution networks. The system consisted of computational tools to automatic high impedance faults detection and location in 13.8 kV delta-connected grid. Field tests carried out in a real feeder turned possible the development of a simple and reliable algorithm, related to the amplitude and phase shift of the zero-sequence current monitored in the substation. The fault location was determined by consulting undervoltage at automatic reclosers, and smart energy meters installed along the feeder. A computational tool was developed to provide relevant information to the utility Operation Center to initiate an emergency maintenance.

Efficient genetic algorithm for spam mail detection and classification

E-mail is the quickest tool to convey information from one to others. Individual users and organizations have become more reliant on e-mails as technology advances. At the moment, all email inboxes are swamped with spam and these cause significant and diverse difficulties, such as the loss of crucial information and the theft of the recipient’s identity. Organizations may suffer significant losses. As a result, users cannot avoid spam emails, which come in various formats such as advertisements and messages. Spam filtering removes spam messages and prevents them from being accessed. This paper focuses on categorization of e-mails by using genetic algorithm. The proposed approach uses entropy to evaluate information gain, which is subsequently employed by the genetic algorithm classifier to choose important features from the spam database. The model performance is then assessed by using the testing dataset with all 57 features, a crossover probability of 0.3, and a mutation probability of 1.0 and obtained good accuracy.

Phase sensitive detection for embedded sensors

The measurement of some physical properties requires detection of both amplitude and phase of an applied test signal. In portable sensors, this needs to be performed locally with integrated analog circuits or digital processing. Wireless sensor network allows the measurements over wide areas but raises a challenge of using efficient algorithm for phase sensitive detection (PSD) in nodes with constrained processing capacity. It is not straightforward to compare different PSD methods because their performance is closely related to the fine tuning of their parameters such as filter order and cut-off frequency. We propose a methodology to compare several PSD methods subjected to the same response time to assess its ability to provide accurate estimation in the presence of noise. We also determine the computational complexity of the investigated methods in terms of the number of operations required. We investigate both continuous and windowed operation. The methods were tested through simulations and verified using a dedicated embedded system. Our findings demonstrate that Goertzel algorithm rendered the best results, with smaller estimation error and less computation complexity.

An efficient unused integrated circuits detection algorithm for parallel scan architecture

In recent days, many integrated circuits (ICs) are operated parallelly to increase switching operations in on-chip static random access memory (SRAM) array, due to more complex tasks and parallel operations being executed in many digital systems. Hence, it is important to efficiently identify the long-duration unused ICs in the on-chip SRAM memory array layout and to effectively distribute the task to unused ICs in SRAM memory array. In the present globalization, semiconductor supply chain detection of unused SRAM in large memory arrays is a very difficult task. This also results in reduced lifetime and more power dissipation. To overcome the above-mentioned drawbacks, an efficient unused integrated circuits detection algorithm (ICDA) for parallel scan architecture is proposed to differentiate the ‘0’ and ‘1’ in a larger SRAM memory array. The proposed architecture avoids the unbalancing of ‘0’ and ‘1’ concentrations in the on-chip SRAM memory array and also optimizes the area required for the memory array. As per simulation results, the proposed method is more efficient in terms of reliability, the detection rate in both used and unused ICs and reduction of power dissipation in comparison to conventional methods such as backscattering side-channel analysis (BSCA) and network attached storage (NAS) algorithm.

Efficient Long-Time Coherent Integration and Detection Algorithm for Radar High-Speed Target Based on the Azimuth Resampling Technology

Efficient Long-Time Coherent Integration and Detection Algorithm for Radar High-Speed Target Based on the Azimuth Resampling Technology

Anti-Theft System for Library

Object detection and tracking could be an immense, vivacious however inconclusive and trending area of computer vision.Due to its immense use in official surveillances, tracking modules applied in security and lots of other’s applications havemade researchers to devise a lot of optimized and specialized methods. For validation purpose live input video will be taken for the same where book will be getting detected and it can be simulated same for real-time through external hardware added. External Hardware will be having RFID integrated to detect if book is issue or not. In the end we see the proper optimized and efficient algorithm for object detection and alert for security. Object Detection is computer vision technique used to detect object and identify its localization. This technique is not only used to identify the location but also to identify which type of object it is. This CV technique is used to detect objects in real time while maintaining the level of accuracy. By bringing some advancement in it, this system can be very helpful for people to keep track of their precious things or devices which are very expensive and need to be protected. Open CV (Open-Source Computer Vision Library) is a library of programming functions mainly aimed at real- time computer vision

YOLOvT: CSPNet-based attention for a lightweight textile defect detection model

Fabric inspection is a crucial process in the textile industry's quality control. Due to the varying structures, textures, geometric features, and spatial distributions of fabric defects, manual fabric inspection is costly and inefficient. Existing fabric defect detection algorithms struggle to strike a balance among efficiency, accuracy, applicability, and deployment costs. In this model, an efficient lightweight fabric defect detection and classification algorithm based on deep convolutional neural networks is proposed. First, the algorithm performs cluster analysis on the fabric defect dataset to ensure that prior boxes better recall objects with fabric defect geometries and spatial characteristics. Next is fusing the convolutional block attention module attention mechanism and Swin Transformer module with the CSPNet structure. This fusion enhances the model's focus on local features and its ability to capture global contextual information without sacrificing the model's inference speed. Moreover, WIoU or Wise-IoU is used as the bounding box loss function of the model, which improves the convergence speed of the bounding box loss and enhances the positioning ability of the model. Finally, the performance of the improved model was validated on a public dataset, showing varying degrees of improvement compared to the baseline model and other state-of-the-art algorithms, meeting the requirements of modern textile processes.

Efficient Cross-Modality Insulator Augmentation for Multi-Domain Insulator Defect Detection in UAV Images.

Regular inspection of the insulator operating status is essential to ensure the safe and stable operation of the power system. Unmanned aerial vehicle (UAV) inspection has played an important role in transmission line inspection, replacing former manual inspection. With the development of deep learning technologies, deep learning-based insulator defect detection methods have drawn more and more attention and gained great improvement. However, former insulator defect detection methods mostly focus on designing complex refined network architecture, which will increase inference complexity in real applications. In this paper, we propose a novel efficient cross-modality insulator augmentation algorithm for multi-domain insulator defect detection to mimic real complex scenarios. It also alleviates the overfitting problem without adding the inference resources. The high-resolution insulator cross-modality translation (HICT) module is designed to generate multi-modality insulator images with rich texture information to eliminate the adverse effects of existing modality discrepancy. We propose the multi-domain insulator multi-scale spatial augmentation (MMA) module to simultaneously augment multi-domain insulator images with different spatial scales and leverage these fused images and location information to help the target model locate defects with various scales more accurately. Experimental results prove that the proposed cross-modality insulator augmentation algorithm can achieve superior performance in public UPID and SFID insulator defect datasets. Moreover, the proposed algorithm also gives a new perspective for improving insulator defect detection precision without adding inference resources, which is of great significance for advancing the detection of transmission lines.

Enhancing elderly care: Efficient and reliable real-time fall detection algorithm.

Falls pose a significant risk to public health, especially for the elderly population, and could potentially result in severe injuries or even death. A reliable fall detection system is urgently needed to recognise and promptly alert to falls effectively. A vision-based fall detection system has the advantage of being non-invasive and affordable compared with another popular approach using wearable sensors. Nevertheless, the present challenge lies in the algorithm's limited on-device operating speed due to extremely high computational demands, and the high computational demands are usually essential to improve the performance for the complex scene. Therefore, it is crucial to address the above challenge in computational power and complex scenes. This article presents the implementation of a real-time fall detection algorithm with low computational costs using a single webcam. The suggested method optimises precision and efficiency by synthesising the strengths of background subtraction and the human pose estimation model BlazePose. The biomechanical features, derived from body key points identified by BlazePose, are utilised in a random forest model for classifying fall events. The proposed algorithm achieves 89.99% accuracy and 29.7 FPS with a laptop CPU on the UR Fall Detection dataset and the Le2i Fall Detection dataset. The algorithm shows great generalisation and robustness in different scenarios. Due to the low computational power of the system, the findings also suggest the potential for implementing the system in small-scale medical monitoring equipment, which maximises its practical value in digital health.

IL-YOLO: An Efficient Detection Algorithm for Insulator Defects in Complex Backgrounds of Transmission Lines

IL-YOLO: An Efficient Detection Algorithm for Insulator Defects in Complex Backgrounds of Transmission Lines

P-Bifurcation Analysis of a Quarter-Car Model With Inerter-Based Pendulum Vibration Absorber: A Wiener Path Integration Approach

Abstract In this theoretical study, a recently developed inerter-based pendulum vibration absorber (IPVA) coupled with energy harvesting capabilities is applied to the quarter car model with class C road conditions (ISO 8608). The impact of varying the pendulum length parameter on power harvesting, ride comfort (sprung mass acceleration), and road handling is investigated. It is discovered that P-bifurcation of the probability density function (PDF), can simultaneously occur with enhanced output power (40% improvements), low sprung mass acceleration (60% improvements), and better road handling (60% improvements) when compared with the linear benchmark system. To predict this bifurcation, a Wiener path integration (WPI) method coupled with curvature checking is developed for the PDF. An efficient bifurcation detection algorithm is developed which leads to the prediction of monomodal, bimodal, and rotation PDF regions in the noise intensity-electrical damping plane. Using Monte Carlo simulations (MCS), the performance metrics were then compared against the optimal linear benchmark for varying driving speed on a class F road while varying the electrical damping so that the system is at or near P-bifurcation. Energy transfer into the electrical domain and power harvested are shown to be up to 43% and 20% higher than for the optimized linear system, respectively. Electrical efficiency considerations show that generator selection is also a factor. Ride comfort and road handling still saw improvements of at least 59%. Finally, the new algorithm effectively reduces an exhaustive MCS for various parameter configurations when qualitative changes in the PDF are linked to performance.

An efficient feature selection and explainable classification method for EEG-based epileptic seizure detection

Epilepsy is a prevalent neurological disorder that poses life-threatening emergencies. Early electroencephalogram (EEG) seizure detection can mitigate the risks and aid in the treatment of patients with epilepsy. EEG based epileptic seizure (ES) detection has significant applications in epilepsy treatment and medical diagnosis. Therefore, this paper presents an innovative framework for efficient ES detection, providing coefficient and distance correlation feature selection algorithms, a Bagged Tree-based classifer (BTBC), and Explainable Artificial Intelligence (XAI). Initially, the Butterworth filter is employed to eliminate various artifacts, and the discrete wavelet transform (DWT) is used to decompose the EEG signals and extract various eigenvalue features of the statistical time domain (STD) as linear and Fractal dimension-based non-linear (FD-NL). The optimal features are then identified through correlation coefficients with P-value and distance correlation analysis.These features are subsequently utilized by the Bagged Tree-based classifer (BTBC). The proposed model provides best performance in mitigating overfitting issues and improves the average accuracy by 2% using (CD, E), (AB, CD, E), and (A, B) experimental types as compared to other machine learning (ML) models using well-known Bonn and UCI-EEG benchmark datasets. Finally, SHapley additive exPlanation (SHAP) was used to interpret and explain the decision-making process of the proposed model. The results highlight the framework’s capability to accurately classify ES, thereby improving the diagnosis process in patients with brain dysfunctions.

Real Time FPGA Implementation of an Efficient High Speed Harris Corner Detection Algorithm Based on High-Level Synthesis

Computer vision systems use corner detection to identify features in an image. In applications such as motion detection, tracking, picture registration, and object recognition, corner detection is often one of the initial steps. In this paper, a real-time image processing system based on Harris corner detection was designed and implemented using Zynq architecture and model-based design tools. The system was based on a development board containing the Zynq-7000 chip, which consists of a combination of FPGA and microprocessor, and the image taken with a high-resolution camera was processed in real-time by applying color conversion and Harris corner detection. The filter hardware designs used in the system were made using the HDL Coder tool in Matlab/Simulink without writing HDL code. The hardware that receives images from the camera was designed on a model-based basis with the Xilinx Vivado 2020. The HDL code that was implemented on the Xilinx ZedBoard using Vivado software was then validated to ensure real-time operation with the incoming video stream. The results achieved exhibited superiority compared to prior implementations in terms of area efficiency (reduced number of gates on the target FPGA) and speed performance on an identical target card. Using the rapid prototyping approach, two alternative hardware accelerator designs were created using various high-level synthesis tools. This design used less than 50% of the host FPGA's logic resources and was at least 30% faster than current implementations.

An efficient reconfigurable optimal source detection and beam allocation algorithm for signal subspace factorization

<span lang="EN-US">Now a <span>days, huge amount of data is communicated through channels in wireless network. It requires an efficient parallel operation for the optimal utilization of frequency, time allocation and coding model for signal subspace factorization in smart antenna. In view of this requirement, an efficient reconfigurable optimal source detection and beam allocation algorithm (RoSDBA) is proposed. The proposed algorithm is able to allocate desired signal to the user space to reduce the noise and also for efficient allocation of subspace to remove disturbance in all directions. The proposed method efficiently utilizes the antenna array elements by accurate identification and allocation of antenna array elements such as individual radiators, radiation beam, signal strength, and disturbance factor. With respect to simulation analysis, the proposed method shows better performance for the resolution, radiation beam allocations, identification bias, distribution factor and time taken for the detection of various</span> array arrangements and source numbers.</span>

An acceleration and optimization method of edge computing using filter level pruning

In order to reduce the complexity of the network and the amount of floating-point computation, this paper proposes an efficient target detection algorithm. Firstly, we use the feature of deep separable convolution to reduce the amount of calculation and design a target detection network structure. Based on the new network structure, the filter is pruned by using the size of the L1 norm value as the threshold to further compress the network model. Then it is deployed on the embedded GPU platform of the edge device for verification, and excellent algorithm performance is achieved. The combination of deep separable convolution and filter-level pruning greatly improves the computational performance of the target detection algorithm on the edge device.

AFCMiner: Finding Absolute Fair Cliques From Attributed Social Networks for Responsible Computational Social Systems

Cohesive subgraph mining on attributed social networks is attracting much attention in the realm of graph mining and analysis. Most existing studies on cohesive subgraph mining over attributed social networks neglect the fairness of attributes, which lead to difficulties in deploying responsible applications. Toward this end, this article formulates a new problem by introducing fairness into cliques model to mine the absolute fair cliques from attributed social networks. Specifically, this article adopts formal concept analysis (FCA) methodology to represent the given attributed social network, and extracts a set of special attributed equiconcepts to further return the absolute fair maximal cliques. Then, we develop an efficient absolute fair cliques detection algorithm AFCMiner for the cases of single-dimensional attributed social networks, multivalued attributed social networks, as well as multidimensional attributed social networks. Extensive experiments are conducted for demonstrating that the proposed AFCMiner algorithm can significantly reduce the time for finding absolute fair cliques with the correctness guarantee. Finally, a case study is also presented for uncovering the usefulness of our model.