Detection Efficiency Research Articles

Efficient Malware Detection in Android Devices to Improve Cyber Security

Efficient Malware Detection in Android Devices to Improve Cyber Security

ResRetinaFace: an efficient face detection network based on RetinaFace and residual structure

ResRetinaFace: an efficient face detection network based on RetinaFace and residual structure

An Improved YOLOv8n Used for Fish Detection in Natural Water Environments

To improve detection efficiency and reduce cost consumption in fishery surveys, target detection methods based on computer vision have become a new method for fishery resource surveys. However, the specialty and complexity of underwater photography result in low detection accuracy, limiting its use in fishery resource surveys. To solve these problems, this study proposed an accurate method named BSSFISH-YOLOv8 for fish detection in natural underwater environments. First, replacing the original convolutional module with the SPD-Conv module allows the model to lose less fine-grained information. Next, the backbone network is supplemented with a dynamic sparse attention technique, BiFormer, which enhances the model’s attention to crucial information in the input features while also optimizing detection efficiency. Finally, adding a 160 × 160 small target detection layer (STDL) improves sensitivity for smaller targets. The model scored 88.3% and 58.3% in the two indicators of mAP@50 and mAP@50:95, respectively, which is 2.0% and 3.3% higher than the YOLOv8n model. The results of this research can be applied to fishery resource surveys, reducing measurement costs, improving detection efficiency, and bringing environmental and economic benefits.

Software Installation Threat Detection Based on Attention Mechanism and Improved Convolutional Neural Network in IOT Platform

Abstract With of the Internet of Things (IoT) developing and the network technique progressing, malware attacks continue to occur, seriously endangering the information and property security of Internet of Things device users. To ensure the security of the Internet of Things platform and improve the efficiency of malware and vulnerability detection, a software installation threat detection model based on attention mechanism and improved convolutional neural network is constructed. Firstly, the enhanced dynamic symbolic execution module and forward program slicing algorithm are used to extract dynamic features, and then the improved convolutional neural network is utilized to classify malware. In the existing software of IoT devices, the inlining correlation function is studied using the inlining strategy, and the weight between the target pixel and the global pixel is calculated using the attention mechanism, through which the logic and correlation between the triples are correlated. Then, deep residual network is used to detect software vulnerabilities. This enables threat detection before and after software installation. In comparison with the current popular vulnerability detection model experiments, the accuracy, recall rate, accuracy rate and running time of the constructed model in the process of vulnerability detection are 0.975, 0.970, 0.968 and 0.02s, respectively. Compared with other models, the research design model has better performance. This shows that this built model can effectively detect software installation threats, and has high detection accuracy and operation efficiency, which can provide strong support for the Internet of Things platform’s security protection.

Multi-Scale Marine Object Detection in Side-Scan Sonar Images Based on BES-YOLO

Aiming at the problem of low accuracy of multi-scale seafloor target detection in side-scan sonar images with high noise and complex background texture, a model for multi-scale target detection using the BES-YOLO network is proposed. First, an efficient multi-scale attention (EMA) mechanism is used in the backbone of the YOLOv8 network, and a bi-directional feature pyramid network (Bifpn) is introduced to merge the information of different scales, finally, a Shape_IoU loss function is introduced to continuously optimize the model and improve its accuracy. Before training, the dataset is preprocessed using 2D discrete wavelet decomposition and reconstruction to enhance the robustness of the network. The experimental results show that 92.4% of the mean average accuracy at IoU of 0.5 (mAP@0.5) and 67.7% of the mean average accuracy at IoU of 0.5 to 0.95 (mAP@0.5:0.95) are achieved using the BES-YOLO network, which is an increase of 5.3% and 4.4% compared to the YOLOv8n model. The research results can effectively improve the detection accuracy and efficiency of multi-scale targets in side-scan sonar images, which can be applied to AUVs and other underwater platforms to implement intelligent detection of undersea targets.

REDef-DETR: Real-time and Efficient DETR for industrial surface defect detection

Abstract Industrial surface defect detection is an important part of industrial production, which aims to identify and detecting various defects on the surface of product to ensure quality and meet customer requirements. With the development of deep learning and image processing technologies, the surface defect detection methods based on computer vision has become the mainstream method. However, the prevalent convolutional neural network(CNN)-based de-fect detection methods also have many problems. For example, these methods rely on post-processing of Non-Maximum Suppression (NMS) and have poor detection ability for small targets, which affects the speed and accuracy of surface defect detection in industrial scenar-ios. Therefore, we propose a novel DEtection TRansformer (DETR)-based surface defect detection method. Firstly, we propose a Multi-scale Contextual Information Dilated module and fuse it into the backbone. The module is mainly composed of large kernel convolutions, which aims to expand the receptive field of the model, thus reducing the leakage rate of the model. Moreover, we design an efficient encoder which mainly contains two important mod-ules, namely feature enhancement based on cascaded group attention module and efficient feature fusion module based on content-aware. The former module effectively enhances the high-level semantic information extracted by the backbone, thus enabling the model to better interpret features, and it can improve the problem of high computational cost of transformer encoder, thus increasing the detection speed. The latter module performs multi-scale feature fusion across the feature information of various scales, thus improving the detection accura-cy of the model for small-size defects. Experimental results show that the proposed method achieves 80.6%mAP and 80.3FPS on NEU-DET, and 98.0%mAP and 79.4FPS on PCB-DET. Our proposed method exhibits excellent detection performance and achieves real-time and efficient surface defect detection capability to meet the needs of industrial surface defect detection.

Online meta-learning approach for sensor fault diagnosis using limited data

The accurate and timely diagnosis of sensor faults plays a critical role in ensuring the reliability and performance of structural health monitoring (SHM) systems. However, the challenge is detecting, locating, and estimating sensor faults in an online manner using limited training data. To resolve this problem, a novel approach for online sensor fault diagnosis is proposed for SHM. The proposed approach is based on meta-learning, which enables superior model generalization capabilities using limited data. The detection, localization, and estimation of typical sensor faults in an online manner can be achieved efficiently by the proposed approach. First, a one-dimensional convolutional neural network (1D CNN) is designed to detect and locate faulty sensors. The initial model parameters of the 1D CNN are optimized using a model-agnostic meta-learning training strategy. This strategy allows the acquisition of transferable prior knowledge, which can speed up the learning process on new sensor fault detection and localization tasks. The meta-learning strategy also enables efficient and accurate detection and localization of potential faulty sensors with limited data. After detecting and locating the faulty sensors, an online updating algorithm based on a dual Kalman filter is used to estimate the severity of sensor faults and structural states simultaneously. The proposed approach is demonstrated with simulated sensor faults that cover a numerical example and field measurements from the Canton Tower. The results show that the proposed approach is applicable for online sensor fault diagnosis in SHM.

Application of Advanced Deep Learning Models for Efficient Apple Defect Detection and Quality Grading in Agricultural Production

In this study, a deep learning-based system for apple defect detection and quality grading was developed, integrating various advanced image-processing technologies and machine learning algorithms to enhance the automation and accuracy of apple quality monitoring. Experimental validation demonstrated the superior performance of the proposed model in handling complex image tasks. In the defect-segmentation experiments, the method achieved a precision of 93%, a recall of 90%, an accuracy of 91% and a mean Intersection over Union (mIoU) of 92%, significantly surpassing traditional deep learning models such as U-Net, SegNet, PSPNet, UNet++, DeepLabv3+ and HRNet. Similarly, in the quality-grading experiments, the method exhibited high efficiency with a precision of 91%, and both recall and accuracy reaching 90%. Additionally, ablation experiments with different loss functions confirmed the significant advantages of the Jump Loss in enhancing model performance, particularly in addressing class imbalance and improving feature learning. These results not only validate the effectiveness and reliability of the system in practical applications but also highlight its potential in automating the detection and grading processes in the apple industry. This integration of advanced technologies provides a new automated solution for quality control of agricultural products like apples, facilitating the modernization of agricultural production.

SnapFISH-IMPUTE: an imputation method for multiplexed DNA FISH data

Chromatin spatial organization plays a crucial role in gene regulation. Recently developed and prospering multiplexed DNA FISH technologies enable direct visualization of chromatin conformation in the nucleus. However, incomplete data caused by limited detection efficiency can substantially complicate and impair downstream analysis. Here, we present SnapFISH-IMPUTE that imputes missing values in multiplexed DNA FISH data. Analysis on multiple published datasets shows that the proposed method preserves the distribution of pairwise distances between imaging loci, and the imputed chromatin conformations are indistinguishable from the observed conformations. Additionally, imputation greatly improves downstream analyses such as identifying enhancer-promoter loops and clustering cells into distinct cell types. SnapFISH-IMPUTE is freely available at https://github.com/hyuyu104/SnapFISH-IMPUTE.

Maximizing intrusion detection efficiency for IoT networks using extreme learning machine

Intrusion Detection Systems (IDSs) are crucial for safeguarding modern IoT communication networks against cyberattacks. IDSs must exhibit exceptional performance, low false positive rates, and significant flexibility in constructing attack patterns to efficiently identify and neutralize these attacks. This research paper discusses the use of an Extreme Learning Machine (ELM) as a new technique to enhance the performance of IDSs. The study utilizes two standard IDS-based IoT network datasets: NSL-KDD 2009 via Distilled-Kitsune 2021. Both datasets are used to assess the effectiveness of ELM in a conventional supervised learning setting. The study investigates the capacity of the ELM algorithm to handle high-dimensional and unbalanced data, indicating the potential to enhance IDS accuracy and efficiency. The research also examines the setup of ELM for both NSL_KDD and Kitsune using Python and Google COLAB to do binary and multi-class classification. The experimental evaluation revealed the proficient performance of the proposed ELM-based IDS among other implemented supervised learning-based IDSs and other state-of-the-art models in the same study area.

GEB-YOLO: a novel algorithm for enhanced and efficient detection of foreign objects in power transmission lines

Detecting foreign objects in power transmission lines is essential for mitigating safety risks and maintaining line stability. Practical detection, however, presents challenges including varied target sizes, intricate backgrounds, and large model weights. To address these issues, this study introduces an innovative GEB-YOLO model, which balances detection performance and quantification. Firstly, the algorithm features a lightweight architecture, achieved by merging the GhostConv network with the advanced YOLOv8 model. This integration considerably lowers computational demands and parameters through streamlined linear operations. Secondly, this paper proposes a novel EC2f mechanism, a groundbreaking feature that bolsters the model’s information extraction capabilities. It enhances the relationship between weights and channels via one-dimensional convolution. Lastly, the BiFPN mechanism is employed to improve the model’s processing efficiency for targets of different sizes, utilizing bidirectional connections and swift feature fusion for normalization. Experimental results indicate the model’s superiority over existing models in precision and mAP, showing improvements of 3.7 and 6.8%, respectively. Crucially, the model’s parameters and FLOPs have been reduced by 10.0 and 7.4%, leading to a model that is both lighter and more efficient. These advancements offer invaluable insights for applying laser technology in detecting foreign objects, contributing significantly to both theory and practice.

Modeling the impact of coincidence loss on count rate statistics and noise performance in counting detectors for imaging applications

Coincidence loss can have detrimental effects on the image quality provided by pixelated counting detectors, especially in dose-sensitive applications like cryoEM where the information extracted from the recorded signal needs to be maximized. In this work, we investigate the impact of coincidence loss phenomena on the recorded statistics in counting detectors producing sparse binary images. First, we derive exact analytical expressions for the mean and the variance of the recorded counts as a function of the incoming event rate. Second, we address the problem of the mean and variance of the recorded events (i.e., pixel clusters identified as individual incoming events), which also acts as a function of the incoming event rate. In this frame, we review previous studies from different disciplines on approximated two-dimensional models, and we critically reinterpret them in our context and evaluate the suitability of their adoption in the present case. The knowledge of the first two momenta of the recorded statistics allows inferring about the signal-to-noise ratio (SNR) and the detective quantum efficiency at zero frequency (DQE0). Analytical results are validated through comparison with numerical data obtained with a custom-made Monte Carlo code. We chose a realistic case study for cryoEM application consisting of a 25-µm-thick MAPS detector featuring a pixel size of 10 µm and illuminated with electrons of 300 keV energy over a wide range of incoming rate.

Non-enzymatic aptazyme-driven autonomous DNA circuits coupled with three-junction CHA for amplified live-cell ATP imaging

Live-cell imaging of adenosine triphosphate (ATP) is crucial for gaining insight into enzymatic activities and biological processes. However, it is still difficult to achieve sensitive and non-destructive ATP imaging due to the difficulty of amplifying molecules within cells and the complexity of intercellular environments. Herein, we present non-enzymatic ATP aptamer-based DNAzyme (Aptazyme)-driven autonomous DNA circuits for sensitive ATP imaging in living cells. The combination of dual amplifiers with aptazyme and catalysis hairpin assembly (CHA) circuits yielded a detection limit of 0.21 μM for ATP, which was 83.9 times more sensitive than the aptazyme-based probe without CHA circuits amplification. Moreover, the efficient carrier function and quenching effect of molybdenum disulfide (MoS2) made it possible to incorporate circuits components into cells without the requirement of transfection, thus allowing for efficient and non-destructive ATP detection within live cells. Therefore, the non-enzymatic aptazyme-driven autonomous DNA circuits present a promising novel approach for the sensitive detection of small molecules within live cells.

Efficient Post-Quantum Pattern Matching on Encrypted Data

Pattern matching methods are essential in various applications where users must disclose highly sensitive information. Among these applications are genomic data analysis, financial records inspection, and intrusion detection processes, all of which necessitate robust privacy protection mechanisms. Balancing the imperative of protecting the confidentiality of analyzed data with the need for efficient pattern matching presents a significant challenge. In this paper, we propose an efficient post-quantum secure construction that enables arbitrary pattern matching over encrypted data while ensuring the confidentiality of the data to be analyzed. In addition, we address scenarios where a malicious data sender, intended to send an encrypted content for pattern detection analysis, has the ability to modify the encrypted content. We adapt the data fragmentation technique to handle such a malicious sender. Our construction makes use of a well-suited Homomorphic Encryption packing method in the context of fragmented streams and combines homomorphic operations in a leveled mode (i.e. without bootstrapping) to obtain a very efficient pattern matching detection process. In contrast to the most efficient state-of-the-art scheme, our construction achieves a significant reduction in the time required for encryption, decryption, and pattern matching on encrypted data. Specifically, our approach decreases the time by factors of 1850 , 10 6 , and 245 , respectively, for matching a single pattern, and by factors of 115 , 10 5 , and 12 , respectively, for matching 2 10 patterns.

Quantitative detection and survival analysis of VBNC Salmonella Typhimurium in flour using droplet digital PCR and DNA-intercalating dyes.

Salmonella, a major foodborne pathogen, poses significant risks, particularly to vulnerable groups like infants, older people, and the immunocompromised. Accurate detection is vital for public health and food safety, given its potential to cause severe and life-threatening symptoms. Our study demonstrated digital polymerase chain reaction (ddPCR) with DNA-intercalating dyes for identifying the different physiological statuses of Salmonella. Also, the application of ddPCR with DNA-intercalating dyes offers quantification of viable cells post-disinfection as an alternative method in food. Utilizing ddPCR and DNA-intercalating dyes, we enhanced the detection of VBNC Salmonella, a form often undetectable by conventional methods. This innovative approach could significantly improve the precision and efficiency of detection for viable Salmonella. By providing deeper insights into its transmission potential, our method is a critical tool in preventing outbreaks and ensuring the safety of food products. This research contributes substantially to global efforts in controlling foodborne illnesses and safeguarding public health.

Object Detection Algorithms Based on Deep Learning: A Review

With the continuous development of deep learning, object detection algorithms based on deep learning have made significant progress in the field of computer vision, widely applied in areas such as autonomous driving, industrial inspection, agriculture, transportation, and medicine. Traditional object detection algorithms face issues such as low detection efficiency and poor robustness. However, deep learning-based object detection algorithms significantly enhance detection accuracy and generalization by learning low-level and high-level image features. This article first introduces traditional object detection algorithms and their existing problems, then elaborates on the main processes, innovations, advantages, disadvantages, and experimental results on datasets of deep learning-based object detection algorithms. It focuses on the development of Two-Stage and One-Stage object detection algorithms, and provides an outlook on the future development of object detection algorithms, discussing challenges such as the coordination of detection speed and accuracy, difficulties in detecting small objects, real-time detection tasks, and multi-modal fusion applications, and proposes possible future directions.

Efficient detection of p-nitrophenol via a polypyrrole flower-decorated nickel foam-based electrochemical sensor.

p-Nitrophenol (p-NP) is known as a common contaminant found in wastewater, agricultural runoff, and industrial effluents which can degrade water quality and cause potential carcinogenic and toxic effects on the human body. Its detection is essential for public health, industrial safety, environmental protection, and regulatory compliance, underscoring its broad applicability. In this study, a novel electrochemical sensor based on polypyrrole (PPy) flowers assembled via nanotubes was developed for the sensitive determination of p-NP. The nickel (Ni) foam modified with PPy flowers functioned as the working electrode and showed selectivity toward p-NP in a phosphate buffer medium at pH 7.0. Cyclic voltammetry (CV) and differential pulse voltammetry (DPV) techniques were utilized for the sensitive determination of p-NP. Under the optimum conditions, the peak currents of DPV versus the concentrations of p-NP in the range of 0.01-20 nM showed a good linear relationship (R2 = 0.9943), and the limit of detection (LOD) was calculated to be 7.18 pM (signal-to-noise ratio of 3, S/N = 3). The fabricated electrochemical p-NP sensor exhibited high sensitivity, a low detection limit, and a low response time. The recoveries of p-NP in real samples of groundwater and tap water using the PPy Fls/Ni foam electrode were in the range of 91.0-108.4% with a relative standard deviation (RSD) in the range of 6.65%. Consequently, the PPy Fls/Ni foam electrode could be applied as a rapid, precise, and sensitive electrochemical sensor platform for aqueous p-NP quantification and determination.

Triple-drug therapy with ivermectin, diethylcarbamazine and albendazole for the acceleration of lymphatic filariasis elimination in Kenya: Programmatic implementation and results of the first impact assessment.

The World Health Organization (WHO) endorsed the use of triple-drug mass drug administration (MDA) regimen with ivermectin, diethylcarbamazine (DEC) and albendazole (commonly abbreviated as IDA) to accelerate the elimination of lymphatic filariasis (LF) as a public health problem in settings where onchocerciasis is not co-endemic. The National Programme for Elimination of LF (NPELF) in Kenya was among the first adopters of the IDA-MDA and two annual rounds were provided in 2018 and 2019 to the residents of Lamu County and Jomvu sub-County in the coast region. This study documented the feasibility of successfully delivering the two rounds of IDA-MDA. An operational research study was undertaken to determine efficient sampling strategies, indicators, and the appropriate population groups that could be used for the monitoring and evaluation of LF programs using IDA-MDA for the elimination of the disease as a public health problem. Two cross-sectional surveys were conducted at baseline in 2018 before IDA-MDA and an impact assessment 17 months after the second round of IDA-MDA. The reported epidemiological treatment coverage was at least 80% in all implementation units during each round of IDA-MDA. Blood samples were tested for filarial antigenemia using commercial Filariasis Test Strips (FTS) and any individual found to be positive was tested again at night for the presence of microfilariae in finger prick blood smears using microscopy. The overall prevalence of circulating filarial antigen (CFA) was relatively low at the baseline survey with Jomvu having 1.39% (95% CI: 0.91, 2.11) and Lamu having 0.48% (95% CI: 0.21, 1.13). Significant reduction in CFA prevalence was observed during the impact assessment after two annual rounds of treatment. The overall relative reduction (%) in CFA prevalence following the two rounds of MDA with IDA was significant in both Jomvu (52.45%, Z = -2.46, P < 0.02) and Lamu (52.71%, Z = -1.97, P < 0.05). Heterogeneity, however, was observed in the CFA prevalence reduction between random and purposive clusters, as well as between adult and child populations. The results of the impact assessment survey offered strong evidence that it was safe to stop the IDA-MDA in the two EUs because transmission appears to have been interrupted. It is also important to implement a post-treatment surveillance system which would enable efficient detection of any recrudescence of LF transmission at a sub-evaluation unit level. Our findings show that IDA-MDA may be considered for acceleration of LF elimination in other settings where onchocerciasis is not co-endemic.

An Efficient and Accurate Surface Defect Detection Method for Wood Based on Improved YOLOv8

Accurate detection of wood surface defects plays a pivotal role in enhancing wood grade sorting precision, maintaining high standards in wood processing quality, and safeguarding forest resources. This paper introduces an efficient and precise approach to detecting wood surface defects, building upon enhancements to the YOLOv8 model, which demonstrates significant performance enhancements in handling multi-scale and small-target defects commonly found in wood. The proposed method incorporates the dilation-wise residual (DWR) module in the trunk and the deformable large kernel attention (DLKA) module in the neck of the YOLOv8 architecture to enhance the network’s capability in extracting and fusing multi-scale defective features. To further improve the detection accuracy of small-target defects, the model replaces all the detector heads of YOLOv8 with dynamic heads and adds an additional small-target dynamic detector head in the shallower layers. Additionally, to facilitate faster and more-efficient regression, the original complete intersection over union (CIoU) loss function of YOLOv8 is replaced with the IoU with minimum points distance (MPDIoU) loss function. Experimental results indicate that compared with the YOLOv8n baseline model, the proposed method improves the mean average precision (mAP) by 5.5%, with enhanced detection accuracy across all seven defect types tested. These findings suggest that the proposed model exhibits a superior ability to detect wood surface defects accurately.

Clinical application of plasma P-tau217 to assess eligibility for amyloid-lowering immunotherapy in memory clinic patients with early Alzheimer’s disease

BackgroundWith the approval of disease-modifying treatments (DMTs) for early Alzheimer’s disease (AD), there is an increased need for efficient and non-invasive detection methods for cerebral amyloid-β (Aβ) pathology. Current methods, including positron emission tomography (PET) and cerebrospinal fluid (CSF) analysis, are costly and invasive methods that may limit access to new treatments. Plasma tau phosphorylated at threonine-217 (P-tau217) presents a promising alternative, yet optimal cutoffs for treatment eligibility with DMTs like aducanumab require further investigation. This study evaluates the efficacy of one- and two-cutoff strategies for determining DMT eligibility at the Butler Hospital Memory & Aging Program (MAP).MethodsIn this retrospective, cross-sectional diagnostic cohort study, we first developed P-tau217 cutoffs using site-specific and BioFINDER-2 training data, which were then tested in potential DMT candidates from Butler MAP (total n = 150). ROC analysis was used to calculate the area under the curve (AUC) and accuracy of P-tau217 interpretation strategies, using Aβ-PET/CSF testing as the standard of truth.ResultsPotential DMT candidates at Butler MAP (n = 50), primarily diagnosed with mild cognitive impairment (n = 29 [58%]) or mild dementia (21 [42%]), were predominantly Aβ-positive (38 [76%]), and half (25 [50%]) were subsequently treated with aducanumab. Elevated P-tau217 predicted cerebral Aβ positivity in potential DMT candidates (AUC = 0.97 [0.92–1]), with diagnostic accuracy ranging from 0.88 (0.76–0.95, p = 0.028) to 0.96 (0.86–1, p < .001). When using site-specific cutoffs, a subset of DMT candidates (10%) exhibited borderline P-tau217 (between 0.273 and 0.399 pg/mL) that would have potentially required confirmatory testing.ConclusionsThis study, which included participants treated with aducanumab, confirms the utility of one- and two-cutoff strategies for interpreting plasma P-tau217 in assessing DMT eligibility. Using P-tau217 could potentially replace more invasive diagnostic methods, and all aducanumab-treated participants would have been deemed eligible based on P-tau217. However, false positives remain a concern, particularly when applying externally derived cutoffs that exhibited lower specificity which could have led to inappropriate treatment of Aβ-negative participants. Future research should focus on prospective validation of P-tau217 cutoffs to enhance their generalizability and inform standardized treatment decision-making across diverse populations.