Improve Detection Results Research Articles

PYRAMID CHANNEL-BASED FEATURE ATTENTION NETWORK WITH ENSEMBLE LEARNING-BASED UAV IMAGE CLASSIFICATION ON IoT-ASSISTED REMOTE SENSING ENVIRONMENT

Advances in Unmanned Aerial Vehicles (UAVs), otherwise recognized as drones, have tremendous promise in improving the wide-ranging applications of the Internet of Things (IoT). UAV image classification using deep learning (DL) is an amalgamation to modernize data analysis, collection, and decision-making in a variety of sectors. IoT devices collect information in real time, while remote sensing captures data afar without direct contact. UAVs equipped with sensors offer high-quality images for classification tasks. DL techniques, especially the convolutional neural networks (CNNs), analyze data streams, extracting complicated features for the accurate classification of objects or environmental features. This synergy enables applications including urban planning and precision agriculture, fostering smarter disaster response, decision support systems, and efficient resource management. This paper introduces a novel Pyramid Channel-based Feature Attention Network with an Ensemble Learning-based UAV Image Classification (PCFAN-ELUAVIC) technique in an assisted remote sensing environment. The PCFAN-ELUAVIC technique begins with the contrast enhancement of the UAV images using the CLAHE technique. Following that, the feature vectors are derived by the use of the PCFAN model. Meanwhile, the hyperparameter tuning procedure is executed by the inclusion of a vortex search algorithm (VSA). For image classification, the PCFAN-ELUAVIC technique comprises an ensemble of three classifiers like long short-term memory (LSTM), graph convolutional networks (GCNs), and Hermite neural network (HNN). To exhibit the improved detection results of the PCFAN-ELUAVIC system, an extensive range of experiments are carried out. The experimental values confirmed the enhanced performance of the PCFAN-ELUAVIC model when compared to other techniques.

An open dataset for individual tree detection in UAV LiDAR point clouds and RGB orthophotos in dense mixed forests

We present an open access dataset for development, evaluation, and comparison of algorithms for individual tree detection in dense mixed forests. The dataset consists of a detailed field inventory and overlapping UAV LiDAR and RGB orthophoto, which make it possible to develop algorithms that fuse multimodal data to improve detection results. Along with the dataset, we describe and implement a basic local maxima filtering baseline and an algorithm for automatically matching detection results to the ground truth trees for detection algorithm evaluation.

An Adaptive Vehicle Detection Model for Traffic Surveillance of Highway Tunnels Considering Luminance Intensity.

Vehicle detection is essential for road traffic surveillance and active safety management. Deep learning methods have recently shown robust feature extraction capabilities and achieved improved detection results. However, vehicle detection models often perform poorly under abnormal lighting conditions, especially in highway tunnels. We proposed an adaptive vehicle detection model that accounts for varying luminance intensities to address this issue. The model categorizes the image data into abnormal and normal luminance scenarios. We employ an improved CycleGAN with edge loss as the adaptive luminance adjustment module for abnormal luminance scenarios. This module adjusts the brightness of the images to a normal level through a generative network. Finally, YOLOv7 is utilized for vehicle detection. The experimental results demonstrate that our adaptive vehicle detection model effectively detects vehicles under abnormal luminance scenarios in highway tunnels. The improved CycleGAN can effectively mitigate edge generation distortion. Under abnormal luminance scenarios, our model achieved a 16.3% improvement in precision, a 1.7% improvement in recall, and a 9.8% improvement in mAP_0.5 compared to the original YOLOv7. Additionally, our adaptive luminance adjustment module is transferable and can enhance the detection accuracy of other vehicle detection models.

A CNN- and Transformer-Based Dual-Branch Network for Change Detection with Cross-Layer Feature Fusion and Edge Constraints

Change detection aims to identify the difference between dual-temporal images and has garnered considerable attention over the past decade. Recently, deep learning methods have shown robust feature extraction capabilities and have achieved improved detection results; however, they exhibit limitations in preserving clear boundaries for the identified regions, which is attributed to the inadequate contextual information aggregation capabilities of feature extraction, and fail to adequately constrain the delineation of boundaries. To address this issue, a novel dual-branch feature interaction backbone network integrating the CNN and Transformer architectures to extract pixel-level change information was developed. With our method, contextual feature aggregation can be achieved by using a cross-layer feature fusion module, and a dual-branch upsampling module is employed to incorporate both spatial and channel information, enhancing the precision of the identified change areas. In addition, a boundary constraint is incorporated, leveraging an MLP module to consolidate fragmented edge information, which increases the boundary constraints within the change areas and minimizes boundary blurring effectively. Quantitative and qualitative experiments were conducted on three benchmarks, including LEVIR-CD, WHU Building, and the xBD natural disaster dataset. The comprehensive results show the superiority of the proposed method compared with previous approaches.

A Lightweight Rice Pest Detection Algorithm Using Improved Attention Mechanism and YOLOv8

Intelligent pest detection algorithms are capable of effectively detecting and recognizing agricultural pests, providing important recommendations for field pest control. However, existing recognition models have shortcomings such as poor accuracy or a large number of parameters. Therefore, this study proposes a lightweight and accurate rice pest detection algorithm based on improved YOLOv8. Firstly, a Multi-branch Convolutional Block Attention Module (M-CBAM) is constructed in the YOLOv8 network to enhance the feature extraction capability for pest targets, yielding better detection results. Secondly, the Minimum Points Distance Intersection over Union (MPDIoU) is introduced as a bounding box loss metric, enabling faster model convergence and improved detection results. Lastly, lightweight Ghost convolutional modules are utilized to significantly reduce model parameters while maintaining optimal detection performance. The experimental results demonstrate that the proposed method outperforms other detection models, with improvements observed in all evaluation metrics compared to the baseline model. On the test set, this method achieves a detection average precision of 95.8% and an F1-score of 94.6%, with a model parameter of 2.15 M, meeting the requirements of both accuracy and lightweightness. The efficacy of this approach is validated by the experimental findings, which provide specific solutions and technical references for intelligent pest detection.

A Portable Automated Microfluidic Platform for Point-of-Care Testing for Multiple Mycotoxins in Wine.

Food safety requires point-of-care testing (POCT) for mycotoxins, since their presence in wine significantly impacts the wine industry and poses a severe threat to human life. Traditional detection methods are usually limited to detecting one mycotoxin and cannot achieve high-throughput, automated, and rapid quantitative analysis of multiple mycotoxins in real samples. Here, we propose a portable automated microfluidic platform (PAMP) integrating a chemiluminescence (CL) imaging system and a microfluidic chip to realize POCT for multiple mycotoxins in real samples, simplifying complex manual operations, shortening the detection time, and improving the detection sensitivity. Specially, silicone films were used as substrates on microfluidic chips to incubate mycotoxin conjugations, and the streptavidin-biotin (SA-B) system and an indirect immunoassay were implemented on silicone films to improve the sensitivity of reaction results. Interestingly, these methods significantly improved detection results, resulting in sensitive detection of mycotoxins, including zearalenone (ZEA) ranging from 1 to 32 ng/mL, aflatoxin B1 (AFB1) ranging from 0.2 to 6.4 ng/mL, and ochratoxin A (OTA) ranging from 2 to 64 ng/mL. The recovery of samples reached 91.39-109.14%, which verified the reliability and practicability of the PAMP. This PAMP enables sensitive and rapid detection of multiple mycotoxins in markets or wineries that lack advanced laboratory facilities. Therefore, it is essential to develop a portable microfluidic platform for POCT to detect mycotoxins in real samples.

Anomaly detection in log-event sequences: A federated deep learning approach and open challenges

Anomaly Detection (AD) is an important area to reliably detect malicious behavior and attacks on computer systems. Log data is a rich source of information about systems and thus provides a suitable input for AD. With the sheer amount of log data available today, for years Machine Learning (ML) and more recently Deep Learning (DL) have been applied to create models for AD. Especially when processing complex log data, DL has shown some promising results in recent research to spot anomalies. It is necessary to group these log lines into log-event sequences, to detect anomalous patterns that span over multiple log lines. This work uses a centralized approach using a Long Short-Term Memory (LSTM) model for AD as its basis which is one of the most important approaches to represent long-range temporal dependencies in log-event sequences of arbitrary length. Therefore, we use past information to predict whether future events are normal or anomalous. For the LSTM model we adapt a state of the art open source implementation called LogDeep. For the evaluation, we use a Hadoop Distributed File System (HDFS) data set, which is well studied in current research. In this paper we show that without padding, which is a commonly used preprocessing step that strongly influences the AD process and artificially improves detection results and thus accuracy in lab testing, it is not possible to achieve the same high quality of results shown in literature. With the large quantity of log data, issues arise with the transfer of log data to a central entity where model computation can be done. Federated Learning (FL) tries to overcome this problem, by learning local models simultaneously on edge devices and overcome biases due to a lack of heterogeneity in training data through exchange of model parameters and finally arrive at a converging global model. Processing log data locally takes privacy and legal concerns into account, which could improve coordination and collaboration between researchers, cyber security companies, etc., in the future. Currently, there are only few scientific publications on log-based AD which use FL. Implementing FL gives the advantage of converging models even if the log data are heterogeneously distributed among participants as our results show. Furthermore, by varying individual LSTM model parameters, the results can be greatly improved. Further scientific research will be necessary to optimize FL approaches.

Inception‐YOLO: Computational cost and accuracy improvement of the YOLOv5 model based on employing modified CSP, SPPF, and inception modules

AbstractThe demand for less complex and more accurate architectures has always been a priority since the broad usage of computer vision in everyday life, like auto‐drive cars, portable applications, augmented reality systems, medical image analysis etc. There are a lot of methods that have been developed to improve the accuracy and complexity of object detection, like the generations of R‐CNNs and YOLOs. However, these methods are not the most efficient architectures, and there is always room to improve. In this study, the 5th version of YOLO is employed and the improved architecture, Inception‐YOLO, is presented. The model significantly outperforms the SOTA YOLO family. Specifically, the improvements can be summarised as follows: impressive improvement of floating point operations (FLOPs) and number of parameters, as well as improvement in accuracy compared to the models with fewer FLOPs. All our presented approaches, like the optimized inception module, proposed structures for CSP and SPPF, and the improved loss function used in this research, work together to incrementally improve detection results, accuracy, demanded memory, and FLOPs simultaneously. For a glimpse of performance, the Inception‐YOLO‐S model hits 38.7% AP with 5.9M parameters and 11.5 BFLOPs and outperforms YOLOv5‐S with 37.4% AP, 7.2M parameters, and 16.5 BFLOPs.

Research on surface defect detection algorithm of pipeline weld based on YOLOv7

Aiming at the problems of low target detection accuracy and high leakage rate of the current traditional weld surface defect detection methods and existing detection models, an improved YOLOv7 pipeline weld surface defect detection model is proposed to improve detection results. In the improved model, a Le-HorBlock module is designed, and it is introduced into the back of fourth CBS module of the backbone network, which preserves the characteristics of high-order information by realizing second-order spatial interaction, thus enhancing the ability of the network to extract features in weld defect images. The coordinate attention (CoordAtt) block is introduced to enhance the representation ability of target features, suppress interference. The CIoU loss function in YOLOv7 network model is replaced by the SIoU, so as to optimize the loss function, reduce the freedom of the loss function, and accelerate convergence. And a new large-scale pipeline weld surface defect dataset containing 2000 images of pipeline welds with weld defects is used in the proposed model. In the experimental comparison, the improved YOLOv7 network model has greatly improved the missed detection rate compared with the original network. The experimental results show that the improved YOLOv7 network model mAP@80.5 can reach 78.6%, which is 15.9% higher than the original model, and the detection effect is better than the original network and other classical target detection networks.

A Motion Deblurring Network for Enhancing UAV Image Quality in Bridge Inspection

Unmanned aerial vehicles (UAVs) have been increasingly utilized for facility safety inspections due to their superior safety, cost effectiveness, and inspection accuracy compared to traditional manpower-based methods. High-resolution images captured by UAVs directly contribute to identifying and quantifying structural defects on facility exteriors, making image quality a critical factor in achieving accurate results. However, motion blur induced by external factors such as vibration, low light conditions, and wind during UAV operation significantly degrades image quality, leading to inaccurate defect detection and quantification. To address this issue, this research proposes a deblurring network using a Generative Adversarial Network (GAN) to eliminate the motion blur effect in UAV images. The GAN-based motion deblur network represents an image inpainting method that leverages generative models to correct blurry artifacts, thereby generating clear images. Unlike previous studies, this proposed approach incorporates deblur and blur learning modules to realistically generate blur images required for training the generative models. The UAV images processed using the motion deblur network are evaluated using a quality assessment method based on local blur map and other well-known image quality assessment (IQA) metrics. Moreover, in the experiment of crack detection utilizing the object detection system, improved detection results are observed when using enhanced images. Overall, this research contributes to improving the quality and accuracy of facility safety inspections conducted with UAV-based inspections by effectively addressing the challenges associated with motion blur effects in UAV-captured images.

Deep learning-based intrusion detection approach for securing industrial Internet of Things

The widespread deployment of the Internet of Things (IoT) into critical sectors such as industrial and manufacturing has resulted in the Industrial Internet of Things (IIoT). The IIoT consists of sensors, actuators, and smart devices that communicate with one another to optimize manufacturing and industrial processes. Although IIoT provides various benefits to both service providers and consumers, security and privacy remain a big challenge. An intrusion detection system (IDS) has been utilized to mitigate cyberattacks in such a connected network. However, many existing solutions for IDS in IIoT suffer from the lack of comprehensiveness of the types of attack the network is exposed to, high feature dimension, models built on out-of-date datasets, and a lack of focus on the problem of imbalanced datasets. To address the aforementioned issues, we propose an intelligent detection system for identifying cyberattacks in Industrial IoT networks. The proposed model uses the singular value decomposition (SVD) technique to reduce data features and improve detection results. We use the synthetic minority over-sampling (SMOTE) technique to avoid over-fitting and under-fitting issues that result in biased classification. Several machine learning and deep learning algorithms have been implemented to classify data for binary and multi-class classification. We evaluate the efficacy of the proposed intelligent model on ToN_IoT dataset. The proposed approach achieved an accuracy rate of 99.99% and a reduced error rate of 0.001% for binary classification, and an accuracy rate of 99.98% and a reduced error rate of 0.016% for multi-class classification.

Chameleon Swarm Algorithm with Improved Fuzzy Deep Learning for Fall Detection Approach to Aid Elderly People

Over the last few decades, the processes of mobile communications and the Internet of Things (IoT) have been established to collect human and environmental data for a variety of smart applications and services. Remote monitoring of disabled and elderly persons living in smart homes was most difficult because of possible accidents which can take place due to day-to-day work like falls. Fall signifies a major health problem for elderly people. When the condition is not alerted in time, then this causes death or impairment in the elderly which decreases the quality of life. For elderly persons, falls can be assumed to be the main cause for the demise of posttraumatic complications. Therefore, early detection of elderly persons’ falls in smart homes is required for increasing their survival chances or offering vital support. Therefore, the study presents a Chameleon Swarm Algorithm with Improved Fuzzy Deep Learning for Fall Detection (CSA-IDFLFD) technique. The CSA-IDFLFD technique helps elderly persons with the identification of fall actions and improves their quality of life. The CSA-IDFLFD technique involves two phases of operations. In the initial phase, the CSA-IDFLFD technique involves the design of the IDFL model for the identification and classification of fall events. Next, in the second phase, the parameters related to the IDFL method can be optimally selected by the design of CSA. To validate the performance of the CSA-IDFLFD technique in the fall detection (FD) process, a widespread experimental evaluation process takes place. The extensive outcome stated the improved detection results of the CSA-IDFLFD technique.

Enhancing Spam Message Classification and Detection Using Transformer-Based Embedding and Ensemble Learning.

Over the last decade, the Short Message Service (SMS) has become a primary communication channel. Nevertheless, its popularity has also given rise to the so-called SMS spam. These messages, i.e., spam, are annoying and potentially malicious by exposing SMS users to credential theft and data loss. To mitigate this persistent threat, we propose a new model for SMS spam detection based on pre-trained Transformers and Ensemble Learning. The proposed model uses a text embedding technique that builds on the recent advancements of the GPT-3 Transformer. This technique provides a high-quality representation that can improve detection results. In addition, we used an Ensemble Learning method where four machine learning models were grouped into one model that performed significantly better than its separate constituent parts. The experimental evaluation of the model was performed using the SMS Spam Collection Dataset. The obtained results showed a state-of-the-art performance that exceeded all previous works with an accuracy that reached 99.91%.

A temporal-spectral value and shape change detection method integrating thematic index information and spectral band information.

Satellite imagery time series change detection methods are effective in avoiding pseudochange due to vegetation phenology to a certain extent. Traditional time series change detection methods use thematic indexes (e.g., NDVI, RVI) to obtain time series information for corresponding change detection. However, change detection methods using several thematic index time series may not make full use of other spectral band information in remotely sensed images and may still suffer from over- and under-detections. To address this challenge, a temporal-spectral value and shape change detection method integrating thematic index information and spectral band information (TISB) is proposed. Possible clouds and cloud shadowing phenomena are removed according to the changes in the spectral values of the remotely sensed images to avoid the generation of pseudochanges in clouds. The spectral and time series information is used to obtain change information from the value perspective, and then, further possible enhanced change regions from a shape perspective to obtain the final change detection results through the expectation-maximization (EM) method. Experiments with Landsat images have shown that the TISB method improves detection results by approximately 1-4% compared to the comparison method.

FT-TDR: Frequency-Guided Transformer and Top-Down Refinement Network for Blind Face Inpainting

Blind face inpainting refers to the task of reconstructing visual contents without explicitly indicating the corrupted regions in a face image. Inherently, this task faces two challenges: (1) how to detect various mask patterns of different shapes and contents; (2) how to restore visually plausible and pleasing contents in the masked regions. In this paper, we propose a novel two-stage blind face inpainting method named Frequency-guided Transformer and Top-Down Refinement Network (FT-TDR) to tackle these challenges. Specifically, we first use a transformer-based network to detect the corrupted regions to be inpainted as masks by modeling the relation among different patches. For improved detection results, we also exploit the frequency modality as complementary information and capture the local contextual incoherence to enhance boundary consistency. Then a top-down refinement network is proposed to hierarchically restore features at different levels and generate contents that are semantically consistent with the unmasked face regions. Extensive experiments demonstrate that our method outperforms current state-of-the-art blind and non-blind face inpainting methods qualitatively and quantitatively.

Securing 6G-enabled IoT/IoV networks by machine learning and data fusion

The rapid growth of Internet of Things (IoT) and Internet of Vehicles (IoV) are rapidly moving to the 6G networks, which leads to dramatically raised security issues. Using machine learning, including deep learning, to find out malicious network traffic is one of practical ways. Though much work has been done in this direction, we found little investigating the effect of using fused network conversation datasets to train and test models. Thus, this work proposes to check conversation dataset characteristics and find suitable ones to fuse into one dataset in order to improve the capability of malicious traffic and malware detection performance. The experiments using real data show that conditioned combination of datasets can be used to enhance algorithm performance and improve detection results. For this reason, it is recommended to profile datasets and conduct conditional fusion of network conversation datasets before using machine learning or deep learning. As the characterization is done using general statistical calculation, it is promising to be used for other domains too.

Insulator-Defect Detection Algorithm Based on Improved YOLOv7.

Existing detection methods face a huge challenge in identifying insulators with minor defects when targeting transmission line images with complex backgrounds. To ensure the safe operation of transmission lines, an improved YOLOv7 model is proposed to improve detection results. Firstly, the target boxes of the insulator dataset are clustered based on K-means++ to generate more suitable anchor boxes for detecting insulator-defect targets. Secondly, the Coordinate Attention (CoordAtt) module and HorBlock module are added to the network. Then, in the channel and spatial domains, the network can enhance the effective features of the feature-extraction process and weaken the ineffective features. Finally, the SCYLLA-IoU (SIoU) and focal loss functions are used to accelerate the convergence of the model and solve the imbalance of positive and negative samples. Furthermore, to optimize the overall performance of the model, the method of non-maximum suppression (NMS) is improved to reduce accidental deletion and false detection of defect targets. The experimental results show that the mean average precision of our model is 93.8%, higher than the Faster R-CNN model, the YOLOv7 model, and YOLOv5s model by 7.6%, 3.7%, and 4%, respectively. The proposed YOLOv7 model can effectively realize the accurate detection of small objects in complex backgrounds.

Motion detection in moving camera videos using background modeling and FlowNet

Real-time moving object detection is challenging for moving cameras due to the moving background. Many studies use homography matrix to compensate for global motion by warping the background model to the current frame. Then, the pixel difference between the current frame and the background model is used for background subtraction. Moving pixels are extracted by applying adaptive threshold and some post-processing techniques. On the other hand, deep learning-based dense optical flow can be efficient enough to extract the moving pixels, but it increases computational cost. This study proposes a method to enhance a classical background modeling method with deep learning-based dense optical flow. The main contribution of this paper is to propose a fusing algorithm for dense optical flow and background modeling approach. The background modeling methods are error-prone, especially with continuous camera movement, while the optical flow method alone may not always be efficient. Our hybrid method fuses both techniques to improve the detection accuracy. We propose a software architecture to run background modeling and dense optical flow methods in parallel processes. The proposed implementation approach significantly increases the method’s working speed, while the proposed fusion and combining strategy improve detection results. The experimental results show that the proposed method can run at high speed and has satisfying performance against the methods in the literature.

Combined head accelerometry and EEG improves the detection of respiratory-related cortical activity during inspiratory loading in healthy participants.

Mechanical ventilation is a highly utilized life‐saving tool, particularly in the current era. The use of EEG in a brain–ventilator interface (BVI) to detect respiratory discomfort (due to sub‐optimal ventilator settings) would improve treatment in mechanically ventilated patients. This concept has been realized via development of an EEG covariance‐based classifier that detects respiratory‐related cortical activity associated with respiratory discomfort. The aim of this study was to determine if head movement, detected by an accelerometer, can detect and/or improve the detection of respiratory‐related cortical activity compared to EEG alone. In 25 healthy participants, EEG and acceleration of the head were recorded during loaded and quiet breathing in the seated and lying postures. Detection of respiratory‐related cortical activity using an EEG covariance‐based classifier was improved by inclusion of data from an Accelerometer‐based classifier, i.e. classifier ‘Fusion’. In addition, ‘smoothed’ data over 50s, rather than one 5 s window of EEG/Accelerometer signals, improved detection. Waveform averages of EEG and head acceleration showed the incidence of pre‐inspiratory potentials did not differ between loaded and quiet breathing, but head movement was greater in loaded breathing. This study confirms that compared to event‐related analysis with >5 min of signal acquisition, an EEG‐based classifier is a clinically valuable tool with rapid processing, detection times, and accuracy. Data smoothing would introduce a small delay (<1 min) but improves detection results. As head acceleration improved detection compared to EEG alone, the number of EEG signals required to detect respiratory discomfort with future BVIs could be reduced if head acceleration is included.

A Fingerprint-Based Verification Framework Using Harris and SURF Feature Detection Algorithms

Amongst all biometric-based personal authentication systems, a fingerprint that gives each person a unique identity is the most commonly used parameter for personal identification. In this paper, we present an automatic fingerprint-based authentication framework by means of fingerprint enhancement, feature extraction, and matching techniques. Initially, a variant of adaptive histogram equalization called CLAHE (contrast limited adaptive histogram equalization) along with a combination of FFT (fast Fourier transform), and Gabor filters are applied to enhance the contrast of fingerprint images. The fingerprint is then authenticated by picking a small amount of information from some local interest points called minutiae point features. These features are extracted from the thinned binary fingerprint image with a hybrid combination of Harris and SURF feature detectors to render significantly improved detection results. For fingerprint matching, the Euclidean distance between the corresponding Harris-SURF feature vectors of two feature points is used as a feature matching similarity measure of two fingerprint images. Moreover, an iterative algorithm called RANSAC (RANdom SAmple Consensus) is applied for fine matching and to automatically eliminate false matches and incorrect match points. Quantitative experimental results achieved on FVC2002 DB1 and FVC2000 DB1 public domain fingerprint databases demonstrate the good performance and feasibility of the proposed framework in terms of achieving average recognition rates of 95% and 92.5% for FVC2002 DB1 and FVC2000 DB1 databases, respectively.