基于改进Detection Transformer的棉花幼苗与杂草检测模型研究

基于深度学习的目标检测技术在棉花幼苗与杂草检测领域已取得一定进展。论文提出了基于改进Detection Transformer的棉花幼苗与杂草检测模型,以提高杂草目标检测的准确率和效率。首先,引入了可变形注意力模块替代原始模型中的Transformer注意力模块,提高模型对特征图目标形变的处理能力。提出新的降噪训练机制,解决了二分图匹配不稳定问题。提出混合查询选择策略,提高解码器对目标类别和位置信息的利用效率。使用Swin Transformer作为网络主干,提高模型特征提取能力。通过对比原网络,论文提出的模型方法在训练过程中表现出更快的收敛速度,并且在准确率方面提高了6.7%。

Esophageal cancer screening,early detection and treatment:Current insights and future directions

Esophageal cancer ranks among the most prevalent malignant tumors globally,primarily due to its highly aggressive nature and poor survival rates.According to the 2020 global cancer statistics,there were approximately 604000 new cases of esophageal cancer,resulting in 544000 deaths.The 5-year survival rate hovers around a mere 15%-25%.Notably,distinct variations exist in the risk factors associated with the two primary histological types,influencing their worldwide incidence and distribution.Squamous cell carcinoma displays a high incidence in specific regions,such as certain areas in China,where it meets the cost-effect-iveness criteria for widespread endoscopy-based early diagnosis within the local population.Conversely,adenocarcinoma(EAC)represents the most common histological subtype of esophageal cancer in Europe and the United States.The role of early diagnosis in cases of EAC originating from Barrett's esophagus(BE)remains a subject of controversy.The effectiveness of early detection for EAC,particularly those arising from BE,continues to be a debated topic.The variations in how early-stage esophageal carcinoma is treated in different regions are largely due to the differing rates of early-stage cancer diagnoses.In areas with higher incidences,such as China and Japan,early diagnosis is more common,which has led to the advancement of endoscopic methods as definitive treatments.These techniques have demonstrated remarkable efficacy with minimal complications while preserving esophageal functionality.Early screening,prompt diagnosis,and timely treatment are key strategies that can significantly lower both the occurrence and death rates associated with esophageal cancer.

Detection of Turbulence Anomalies Using a Symbolic Classifier Algorithm in Airborne Quick Access Record(QAR)Data Analysis

As the risks associated with air turbulence are intensified by climate change and the growth of the aviation industry,it has become imperative to monitor and mitigate these threats to ensure civil aviation safety.The eddy dissipation rate(EDR)has been established as the standard metric for quantifying turbulence in civil aviation.This study aims to explore a universally applicable symbolic classification approach based on genetic programming to detect turbulence anomalies using quick access recorder(QAR)data.The detection of atmospheric turbulence is approached as an anomaly detection problem.Comparative evaluations demonstrate that this approach performs on par with direct EDR calculation methods in identifying turbulence events.Moreover,comparisons with alternative machine learning techniques indicate that the proposed technique is the optimal methodology currently available.In summary,the use of symbolic classification via genetic programming enables accurate turbulence detection from QAR data,comparable to that with established EDR approaches and surpassing that achieved with machine learning algorithms.This finding highlights the potential of integrating symbolic classifiers into turbulence monitoring systems to enhance civil aviation safety amidst rising environmental and operational hazards.

An Underwater Target Detection Algorithm Based on Attention Mechanism and Improved YOLOv7

For underwater robots in the process of performing target detection tasks,the color distortion and the uneven quality of underwater images lead to great difficulties in the feature extraction process of the model,which is prone to issues like error detection,omission detection,and poor accuracy.Therefore,this paper proposed the CER-YOLOv7(CBAM-EIOU-RepVGG-YOLOv7)underwater target detection algorithm.To improve the algorithm’s capability to retain valid features from both spatial and channel perspectives during the feature extraction phase,we have added a Convolutional Block Attention Module(CBAM)to the backbone network.The Reparameterization Visual Geometry Group(RepVGG)module is inserted into the backbone to improve the training and inference capabilities.The Efficient Intersection over Union(EIoU)loss is also used as the localization loss function,which reduces the error detection rate and missed detection rate of the algorithm.The experimental results of the CER-YOLOv7 algorithm on the UPRC(Underwater Robot Prototype Competition)dataset show that the mAP(mean Average Precision)score of the algorithm is 86.1%,which is a 2.2%improvement compared to the YOLOv7.The feasibility and validity of the CER-YOLOv7 are proved through ablation and comparison experiments,and it is more suitable for underwater target detection.

Multimodal Social Media Fake News Detection Based on Similarity Inference and Adversarial Networks

As social networks become increasingly complex, contemporary fake news often includes textual descriptionsof events accompanied by corresponding images or videos. Fake news in multiple modalities is more likely tocreate a misleading perception among users. While early research primarily focused on text-based features forfake news detection mechanisms, there has been relatively limited exploration of learning shared representationsin multimodal (text and visual) contexts. To address these limitations, this paper introduces a multimodal modelfor detecting fake news, which relies on similarity reasoning and adversarial networks. The model employsBidirectional Encoder Representation from Transformers (BERT) and Text Convolutional Neural Network (Text-CNN) for extracting textual features while utilizing the pre-trained Visual Geometry Group 19-layer (VGG-19) toextract visual features. Subsequently, the model establishes similarity representations between the textual featuresextracted by Text-CNN and visual features through similarity learning and reasoning. Finally, these features arefused to enhance the accuracy of fake news detection, and adversarial networks have been employed to investigatethe relationship between fake news and events. This paper validates the proposed model using publicly availablemultimodal datasets from Weibo and Twitter. Experimental results demonstrate that our proposed approachachieves superior performance on Twitter, with an accuracy of 86%, surpassing traditional unimodalmodalmodelsand existing multimodal models. In contrast, the overall better performance of our model on the Weibo datasetsurpasses the benchmark models across multiple metrics. The application of similarity reasoning and adversarialnetworks in multimodal fake news detection significantly enhances detection effectiveness in this paper. However,current research is limited to the fusion of only text and image modalities. Future research directions should aimto further integrate features fromadditionalmodalities to comprehensively represent themultifaceted informationof fake news.

Real-time Rescue Target Detection Based on UAV Imagery for Flood Emergency Response

Timely acquisition of rescue target information is critical for emergency response after a flood disaster.Unmanned Aerial Vehicles(UAVs)equipped with remote sensing capabilities offer distinct advantages,including high-resolution imagery and exceptional mobility,making them well suited for monitoring flood extent and identifying rescue targets during floods.However,there are some challenges in interpreting rescue information in real time from flood images captured by UAVs,such as the complexity of the scenarios of UAV images,the lack of flood rescue target detection datasets and the limited real-time processing capabilities of the airborne on-board platform.Thus,we propose a real-time rescue target detection method for UAVs that is capable of efficiently delineating flood extent and identifying rescue targets(i.e.,pedestrians and vehicles trapped by floods).The proposed method achieves real-time rescue information extraction for UAV platforms by lightweight processing and fusion of flood extent extraction model and target detection model.The flood inundation range is extracted by the proposed method in real time and detects targets such as people and vehicles to be rescued based on this layer.Our experimental results demonstrate that the Intersection over Union(IoU)for flood water extraction reaches an impressive 80%,and the IoU for real-time flood water extraction stands at a commendable 76.4%.The information on flood stricken targets extracted by this method in real time can be used for flood emergency rescue.

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models

BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.

Human intrusion detection for high-speed railway perimeter under all-weather condition

Purpose – The paper aims to solve the problem of personnel intrusion identification within the limits of highspeed railways. It adopts the fusion method of millimeter wave radar and camera to improve the accuracy ofobject recognition in dark and harsh weather conditions.Design/methodology/approach – This paper adopts the fusion strategy of radar and camera linkage toachieve focus amplification of long-distance targets and solves the problem of low illumination by laser lightfilling of the focus point. In order to improve the recognition effect, this paper adopts the YOLOv8 algorithm formulti-scale target recognition. In addition, for the image distortion caused by bad weather, this paper proposesa linkage and tracking fusion strategy to output the correct alarm results.Findings – Simulated intrusion tests show that the proposed method can effectively detect human intrusionwithin 0–200 m during the day and night in sunny weather and can achieve more than 80% recognitionaccuracy for extreme severe weather conditions.Originality/value – (1) The authors propose a personnel intrusion monitoring scheme based on the fusion ofmillimeter wave radar and camera, achieving all-weather intrusion monitoring;(2) The authors propose a newmulti-level fusion algorithm based on linkage and tracking to achieve intrusion target monitoring underadverse weather conditions;(3) The authors have conducted a large number of innovative simulationexperiments to verify the effectiveness of the method proposed in this article.

A dual-RPA based lateral flow strip for sensitive,on-site detection of CP4-EPSPS and Cry1Ab/Ac genes in genetically modified crops

Traditional transgenic detection methods require high test conditions and struggle to be both sensitive and efficient.In this study,a one-tube dual recombinase polymerase amplification(RPA)reaction system for CP4-EPSPS and Cry1Ab/Ac was proposed and combined with a lateral flow immunochromatographic assay,named“Dual-RPA-LFD”,to visualize the dual detection of genetically modified(GM)crops.In which,the herbicide tolerance gene CP4-EPSPS and the insect resistance gene Cry1Ab/Ac were selected as targets taking into account the current status of the most widespread application of insect resistance and herbicide tolerance traits and their stacked traits.Gradient diluted plasmids,transgenic standards,and actual samples were used as templates to conduct sensitivity,specificity,and practicality assays,respectively.The constructed method achieved the visual detection of plasmid at levels as low as 100 copies,demonstrating its high sensitivity.In addition,good applicability to transgenic samples was observed,with no cross-interference between two test lines and no influence from other genes.In conclusion,this strategy achieved the expected purpose of simultaneous detection of the two popular targets in GM crops within 20 min at 37°C in a rapid,equipmentfree field manner,providing a new alternative for rapid screening for transgenic assays in the field.

YOLO-MFD:Remote Sensing Image Object Detection with Multi-Scale Fusion Dynamic Head

Remote sensing imagery,due to its high altitude,presents inherent challenges characterized by multiple scales,limited target areas,and intricate backgrounds.These inherent traits often lead to increased miss and false detection rates when applying object recognition algorithms tailored for remote sensing imagery.Additionally,these complexities contribute to inaccuracies in target localization and hinder precise target categorization.This paper addresses these challenges by proposing a solution:The YOLO-MFD model(YOLO-MFD:Remote Sensing Image Object Detection withMulti-scale Fusion Dynamic Head).Before presenting our method,we delve into the prevalent issues faced in remote sensing imagery analysis.Specifically,we emphasize the struggles of existing object recognition algorithms in comprehensively capturing critical image features amidst varying scales and complex backgrounds.To resolve these issues,we introduce a novel approach.First,we propose the implementation of a lightweight multi-scale module called CEF.This module significantly improves the model’s ability to comprehensively capture important image features by merging multi-scale feature information.It effectively addresses the issues of missed detection and mistaken alarms that are common in remote sensing imagery.Second,an additional layer of small target detection heads is added,and a residual link is established with the higher-level feature extraction module in the backbone section.This allows the model to incorporate shallower information,significantly improving the accuracy of target localization in remotely sensed images.Finally,a dynamic head attentionmechanism is introduced.This allows themodel to exhibit greater flexibility and accuracy in recognizing shapes and targets of different sizes.Consequently,the precision of object detection is significantly improved.The trial results show that the YOLO-MFD model shows improvements of 6.3%,3.5%,and 2.5%over the original YOLOv8 model in Precision,map@0.5 and map@0.5:0.95,separately.These results illustrate the clear advantages of the method.

Target Detection Algorithm in Foggy Scenes Based on Dual Subnets

Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the image by the universal detection network.Thus,a dual subnet based on multi-task collaborative training(DSMCT)is proposed in this paper.Firstly,in the training phase,the Gated Context Aggregation Network(GCANet)is used as the supervisory network of YOLOX to promote the extraction of clean information in foggy scenes.In the test phase,only the YOLOX branch needs to be activated to ensure the detection speed of the model.Secondly,the deformable convolution module is used to improve GCANet to enhance the model’s ability to capture details of non-homogeneous fog.Finally,the Coordinate Attention mechanism is introduced into the Vision Transformer and the backbone network of YOLOX is redesigned.In this way,the feature extraction ability of the network for deep-level information can be enhanced.The experimental results on artificial fog data set FOG_VOC and real fog data set RTTS show that the map value of DSMCT reached 86.56%and 62.39%,respectively,which was 2.27%and 4.41%higher than the current most advanced detection model.The DSMCT network has high practicality and effectiveness for target detection in real foggy scenes.

A Hybrid Feature Fusion Traffic Sign Detection Algorithm Based on YOLOv7

Autonomous driving technology has entered a period of rapid development,and traffic sign detection is one of the important tasks.Existing target detection networks are difficult to adapt to scenarios where target sizes are seriously imbalanced,and traffic sign targets are small and have unclear features,which makes detection more difficult.Therefore,we propose aHybrid Feature Fusion Traffic Sign detection algorithmbased onYOLOv7(HFFTYOLO).First,a self-attention mechanism is incorporated at the end of the backbone network to calculate feature interactions within scales;Secondly,the cross-scale fusion part of the neck introduces a bottom-up multi-path fusion method.Design reuse paths at the end of the neck,paying particular attention to cross-scale fusion of highlevel features.In addition,we found the appropriate channel width through a lot of experiments and reduced the superfluous parameters.In terms of training,a newregression lossCMPDIoUis proposed,which not only considers the problem of loss degradation when the aspect ratio is the same but the width and height are different,but also enables the penalty term to dynamically change at different scales.Finally,our proposed improved method shows excellent results on the TT100K dataset.Compared with the baseline model,without increasing the number of parameters and computational complexity,AP0.5 and AP increased by 2.2%and 2.7%,respectively,reaching 92.9%and 58.1%.

Artificial Immune Detection for Network Intrusion Data Based on Quantitative Matching Method

Artificial immune detection can be used to detect network intrusions in an adaptive approach and proper matching methods can improve the accuracy of immune detection methods.This paper proposes an artificial immune detection model for network intrusion data based on a quantitative matching method.The proposed model defines the detection process by using network data and decimal values to express features and artificial immune mechanisms are simulated to define immune elements.Then,to improve the accuracy of similarity calculation,a quantitative matching method is proposed.The model uses mathematical methods to train and evolve immune elements,increasing the diversity of immune recognition and allowing for the successful detection of unknown intrusions.The proposed model’s objective is to accurately identify known intrusions and expand the identification of unknown intrusions through signature detection and immune detection,overcoming the disadvantages of traditional methods.The experiment results show that the proposed model can detect intrusions effectively.It has a detection rate of more than 99.6%on average and a false alarm rate of 0.0264%.It outperforms existing immune intrusion detection methods in terms of comprehensive detection performance.

SDH-FCOS:An Efficient Neural Network for Defect Detection in Urban Underground Pipelines

Urban underground pipelines are an important infrastructure in cities,and timely investigation of problems in underground pipelines can help ensure the normal operation of cities.Owing to the growing demand for defect detection in urban underground pipelines,this study developed an improved defect detection method for urban underground pipelines based on fully convolutional one-stage object detector(FCOS),called spatial pyramid pooling-fast(SPPF)feature fusion and dual detection heads based on FCOS(SDH-FCOS)model.This study improved the feature fusion component of the model network based on FCOS,introduced an SPPF network structure behind the last output feature layer of the backbone network,fused the local and global features,added a top-down path to accelerate the circulation of shallowinformation,and enriched the semantic information acquired by shallow features.The ability of the model to detect objects with multiple morphologies was strengthened by introducing dual detection heads.The experimental results using an open dataset of underground pipes show that the proposed SDH-FCOS model can recognize underground pipe defects more accurately;the average accuracy was improved by 2.7% compared with the original FCOS model,reducing the leakage rate to a large extent and achieving real-time detection.Also,our model achieved a good trade-off between accuracy and speed compared with other mainstream methods.This proved the effectiveness of the proposed model.

An Optimized Approach to Deep Learning for Botnet Detection and Classification for Cybersecurity in Internet of Things Environment

The recent development of the Internet of Things(IoTs)resulted in the growth of IoT-based DDoS attacks.The detection of Botnet in IoT systems implements advanced cybersecurity measures to detect and reduce malevolent botnets in interconnected devices.Anomaly detection models evaluate transmission patterns,network traffic,and device behaviour to detect deviations from usual activities.Machine learning(ML)techniques detect patterns signalling botnet activity,namely sudden traffic increase,unusual command and control patterns,or irregular device behaviour.In addition,intrusion detection systems(IDSs)and signature-based techniques are applied to recognize known malware signatures related to botnets.Various ML and deep learning(DL)techniques have been developed to detect botnet attacks in IoT systems.To overcome security issues in an IoT environment,this article designs a gorilla troops optimizer with DL-enabled botnet attack detection and classification(GTODL-BADC)technique.The GTODL-BADC technique follows feature selection(FS)with optimal DL-based classification for accomplishing security in an IoT environment.For data preprocessing,the min-max data normalization approach is primarily used.The GTODL-BADC technique uses the GTO algorithm to select features and elect optimal feature subsets.Moreover,the multi-head attention-based long short-term memory(MHA-LSTM)technique was applied for botnet detection.Finally,the tree seed algorithm(TSA)was used to select the optimum hyperparameter for the MHA-LSTM method.The experimental validation of the GTODL-BADC technique can be tested on a benchmark dataset.The simulation results highlighted that the GTODL-BADC technique demonstrates promising performance in the botnet detection process.

A self-organization formation configuration based assignment probability and collision detection

The formation control of multiple unmanned aerial vehicles(multi-UAVs)has always been a research hotspot.Based on the straight line trajectory,a multi-UAVs target point assignment algorithm based on the assignment probability is proposed to achieve the shortest overall formation path of multi-UAVs with low complexity and reduce the energy consumption.In order to avoid the collision between UAVs in the formation process,the concept of safety ball is introduced,and the collision detection based on continuous motion of two time slots and the lane occupation detection after motion is proposed to avoid collision between UAVs.Based on the idea of game theory,a method of UAV motion form setting based on the maximization of interests is proposed,including the maximization of self-interest and the maximization of formation interest is proposed,so that multi-UAVs can complete the formation task quickly and reasonably with the linear trajectory assigned in advance.Finally,through simulation verification,the multi-UAVs target assignment algorithm based on the assignment probability proposed in this paper can effectively reduce the total path length,and the UAV motion selection method based on the maximization interests can effectively complete the task formation.

Establishment and performance analysis of a new multiplex detection method for influenza an and B virus antigen

BACKGROUND Influenza A and B virus detection is pivotal in epidemiological surveillance and disease management.Rapid and accurate diagnostic techniques are crucial for timely clinical intervention and outbreak prevention.Quantum dot-encoded microspheres have been widely used in immunodetection.The integration of quantum dot-encoded microspheres with flow cytometry is a well-established technique that enables rapid analysis.Thus,establishing a multiplex detection method for influenza A and B virus antigens based on flow cytometry quantum dot microspheres will help in disease diagnosis.AIM To establish a codetection method of influenza A and B virus antigens based on flow cytometry quantum dot-encoded microsphere technology,which forms the foundation for the assays of multiple respiratory virus biomarkers.METHODS Different quantum dot-encoded microspheres were used to couple the monoclonal antibodies against influenza A and B.The known influenza A and B antigens were detected both separately and simultaneously on a flow cytometer,and the detection conditions were optimized to establish the influenza A and B antigen codetection method,which was utilized for their detection in clinical samples.The results were compared with the fluorescence quantitative polymerase chain reaction(PCR)method to validate the clinical performance of this method.RESULTS The limits of detection of this method were 26.1 and 10.7 pg/mL for influenza A and B antigens,respectively,which both ranged from 15.6 to 250000 pg/mL.In the clinical sample evaluation,the proposed method well correlated with the fluorescent quantitative PCR method,with positive,negative,and overall compliance rates of 57.4%,100%,and 71.6%,respectively.CONCLUSION A multiplex assay for quantitative detection of influenza A and B virus antigens has been established,which is characterized by high sensitivity,good specificity,and a wide detection range and is promising for clinical applications.

Phenotypic Detection of Enterobacterales Strains Susceptible of Producing OXA-48 Carbapenemase

Background: Nowadays, emergence of Carbapenemase-Producing Enterobacterales (CPE) throughout the world has become a public health problem, especially in countries with limited resources. In recent years, CPE of type OXA-48 (Ambler class D) have been identified in Dakar. The aim of this study was to evaluate the phenotypic detection of OXA-48 CPE using a temocillin disc (30 μg). Methodology: A retrospective study was carried out at Medical Biology Laboratory of Pasteur Institute in Dakar on Ertapenem-Resistant Enterobacterales (ERE) strains isolated from 2015 to 2017. These strains were then tested with a 30 μg temocillin disc. Any strain resistant to temocillin (inhibition diameter Results: Forty-one ERE isolated during the study period were tested, of which 34 (82.9%) were OXA-48 based on phenotypic detection using temocillin disc and confirmed by PCR (100%). OXA-48 CPE strains detected were composed of Klebsiella pneumoniae (n = 14;41.2%), Enterobacter cloacae (n = 8;23.5%), Escherichia coli (n = 7, 20.5%), Citrobacter freundii (n = 3;8.8%), Cronobacter sakazakii (n = 1;3%) and Morganella morganii (n = 1;3%). Conclusion: Temocillin resistance has a good positive predictive value for detecting OXA-48 CPE by phenotypic method, confirmed by PCR. Temocillin is therefore a good marker for detection of OXA-48 CPE except Hafnia alvei.

Automated Vulnerability Detection of Blockchain Smart Contacts Based on BERT Artificial Intelligent Model

The widespread adoption of blockchain technology has led to the exploration of its numerous applications in various fields.Cryptographic algorithms and smart contracts are critical components of blockchain security.Despite the benefits of virtual currency,vulnerabilities in smart contracts have resulted in substantial losses to users.While researchers have identified these vulnerabilities and developed tools for detecting them,the accuracy of these tools is still far from satisfactory,with high false positive and false negative rates.In this paper,we propose a new method for detecting vulnerabilities in smart contracts using the BERT pre-training model,which can quickly and effectively process and detect smart contracts.More specifically,we preprocess and make symbol substitution in the contract,which can make the pre-training model better obtain contract features.We evaluate our method on four datasets and compare its performance with other deep learning models and vulnerability detection tools,demonstrating its superior accuracy.

Strengthening Network Security: Deep Learning Models for Intrusion Detectionwith Optimized Feature Subset and Effective Imbalance Handling

In recent years,frequent network attacks have highlighted the importance of efficient detection methods for ensuring cyberspace security.This paper presents a novel intrusion detection system consisting of a data prepro-cessing stage and a deep learning model for accurately identifying network attacks.We have proposed four deep neural network models,which are constructed using architectures such as Convolutional Neural Networks(CNN),Bi-directional Long Short-Term Memory(BiLSTM),Bidirectional Gate Recurrent Unit(BiGRU),and Attention mechanism.These models have been evaluated for their detection performance on the NSL-KDD dataset.To enhance the compatibility between the data and the models,we apply various preprocessing techniques and employ the particle swarm optimization algorithm to perform feature selection on the NSL-KDD dataset,resulting in an optimized feature subset.Moreover,we address class imbalance in the dataset using focal loss.Finally,we employ the BO-TPE algorithm to optimize the hyperparameters of the four models,maximizing their detection performance.The test results demonstrate that the proposed model is capable of extracting the spatiotemporal features of network traffic data effectively.In binary and multiclass experiments,it achieved accuracy rates of 0.999158 and 0.999091,respectively,surpassing other state-of-the-art methods.