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.

Novel cyber-physical collaborative detection and localization method against dynamic load altering attacks in smart energy grids

Owing to the integration of energy digitization and artificial intelligence technology,smart energy grids can realize the stable,efficient and clean operation of power systems.However,the emergence of cyber-physical attacks,such as dynamic load-altering attacks(DLAAs)has introduced great challenges to the security of smart energy grids.Thus,this study developed a novel cyber-physical collaborative security framework for DLAAs in smart energy grids.The proposed framework integrates attack prediction in the cyber layer with the detection and localization of attacks in the physical layer.First,a data-driven method was proposed to predict the DLAA sequence in the cyber layer.By designing a double radial basis function network,the influence of disturbances on attack prediction can be eliminated.Based on the prediction results,an unknown input observer-based detection and localization method was further developed for the physical layer.In addition,an adaptive threshold was designed to replace the traditional precomputed threshold and improve the detection performance of the DLAAs.Consequently,through the collaborative work of the cyber-physics layer,injected DLAAs were effectively detected and located.Compared with existing methodologies,the simulation results on IEEE 14-bus and 118-bus power systems verified the superiority of the proposed cyber-physical collaborative detection and localization against DLAAs.

Comparative Analysis of ARIMA and LSTM Model-Based Anomaly Detection for Unannotated Structural Health Monitoring Data in an Immersed Tunnel

Structural Health Monitoring(SHM)systems have become a crucial tool for the operational management of long tunnels.For immersed tunnels exposed to both traffic loads and the effects of the marine environment,efficiently identifying abnormal conditions from the extensive unannotated SHM data presents a significant challenge.This study proposed amodel-based approach for anomaly detection and conducted validation and comparative analysis of two distinct temporal predictive models using SHM data from a real immersed tunnel.Firstly,a dynamic predictive model-based anomaly detectionmethod is proposed,which utilizes a rolling time window for modeling to achieve dynamic prediction.Leveraging the assumption of temporal data similarity,an interval prediction value deviation was employed to determine the abnormality of the data.Subsequently,dynamic predictive models were constructed based on the Autoregressive Integrated Moving Average(ARIMA)and Long Short-Term Memory(LSTM)models.The hyperparameters of these models were optimized and selected using monitoring data from the immersed tunnel,yielding viable static and dynamic predictive models.Finally,the models were applied within the same segment of SHM data,to validate the effectiveness of the anomaly detection approach based on dynamic predictive modeling.A detailed comparative analysis discusses the discrepancies in temporal anomaly detection between the ARIMA-and LSTM-based models.The results demonstrated that the dynamic predictive modelbased anomaly detection approach was effective for dealing with unannotated SHM data.In a comparison between ARIMA and LSTM,it was found that ARIMA demonstrated higher modeling efficiency,rendering it suitable for short-term predictions.In contrast,the LSTM model exhibited greater capacity to capture long-term performance trends and enhanced early warning capabilities,thereby resulting in superior overall performance.

An Industrial Intrusion Detection Method Based on Hybrid Convolutional Neural Networks with Improved TCN

Network intrusion detection systems(NIDS)based on deep learning have continued to make significant advances.However,the following challenges remain:on the one hand,simply applying only Temporal Convolutional Networks(TCNs)can lead to models that ignore the impact of network traffic features at different scales on the detection performance.On the other hand,some intrusion detection methods considermulti-scale information of traffic data,but considering only forward network traffic information can lead to deficiencies in capturing multi-scale temporal features.To address both of these issues,we propose a hybrid Convolutional Neural Network that supports a multi-output strategy(BONUS)for industrial internet intrusion detection.First,we create a multiscale Temporal Convolutional Network by stacking TCN of different scales to capture the multiscale information of network traffic.Meanwhile,we propose a bi-directional structure and dynamically set the weights to fuse the forward and backward contextual information of network traffic at each scale to enhance the model’s performance in capturing the multi-scale temporal features of network traffic.In addition,we introduce a gated network for each of the two branches in the proposed method to assist the model in learning the feature representation of each branch.Extensive experiments reveal the effectiveness of the proposed approach on two publicly available traffic intrusion detection datasets named UNSW-NB15 and NSL-KDD with F1 score of 85.03% and 99.31%,respectively,which also validates the effectiveness of enhancing the model’s ability to capture multi-scale temporal features of traffic data on detection performance.

Deadlock Detection:Background,Techniques,and Future Improvements

Deadlock detection is an essential aspect of concurrency control in parallel and distributed systems,as it ensures the efficient utilization of resources and prevents indefinite delays.This paper presents a comprehensive analysis of the various deadlock detection techniques,including static and dynamic approaches.We discuss the future improvements associated with deadlock detection and provide a comparative evaluation of these techniques in terms of their accuracy,complexity,and scalability.Furthermore,we outline potential future research directions to improve deadlock detection mechanisms and enhance system performance.

Machine learning algorithm partially reconfigured on FPGA for an image edge detection system

Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)signal.However,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or spoofing.One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images.But a high effort is required for image edge extraction.Here a support vector regression(SVR)model is proposed to reduce this computational load and processing time.The dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable region.Results show that the implementation in hardware is 68 times faster than that in software.This architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without DPR.This is also the lowest power consumption in current machine learning hardware implementations.Besides,the circuitry area is 41 times smaller.SVR with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning trajectory.This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.

Dynamic-YOLOX:复杂背景下的苹果叶片病害检测模型

针对目前苹果叶片数据集的叶片病害种类不全以及图片背景单一等问题,构建了复杂背景下包括苹果叶部六种常见病害的苹果叶片病害数据集。针对目前主流苹果叶片病害检测模型检测精度不高、模型复杂和不满足实时监测等问题,提出了一种基于YOLOX-S(you only look once X-S)改进得到的复杂背景下的苹果叶片病害自适应检测模型Dynamic-YOLOX。设计并使用ECA-SPPFCSPC模块(efficient channel attention cross-stage partial fast spatial pyramid pooling module)更换YOLOX-S模型主干网络尾部Dark5中的空间金字塔池化(SPP)以及跨阶段局部网络(CSPNet)模块来增强模型关注深层语义特征、抑制无用信息的能力,并减少硬件内存开销。设计了动态跨阶段局部网络(ODCSP)模块,并用其更换YOLOX-S模型主干网络中Dark2、Dark3、Dark4部分以及颈部网络中所有的CSPNet模块,使得模型在面对不同输入特征时有更强的自适应性,在减少模型的参数量和计算量的同时提高了模型的平均检测精度。引入Varifocal Loss更换模型中分类置信度损失的BCEWithLogits Loss来提升模型对苹果叶片中密集小目标病害的检测精度。在自制数据集上Dynamic-YOLOX相对原始YOLOX-S模型的mAP提升了4.54个百分点,达到84.63%,同时模型的参数量和计算量分别下降了11.97%和13.45%,检测速度达到44.07 FPS。对比主流苹果叶片病害检测模型,Dynamic-YOLOX具有一定优越性。

Visual SLAM in dynamic environments based on object detection

A great number of visual simultaneous localization and mapping(VSLAM)systems need to assume static features in the environment.However,moving objects can vastly impair the performance of a VSLAM system which relies on the static-world assumption.To cope with this challenging topic,a real-time and robust VSLAM system based on ORB-SLAM2 for dynamic environments was proposed.To reduce the influence of dynamic content,we incorporate the deep-learning-based object detection method in the visual odometry,then the dynamic object probability model is added to raise the efficiency of object detection deep neural network and enhance the real-time performance of our system.Experiment with both on the TUM and KITTI benchmark dataset,as well as in a real-world environment,the results clarify that our method can significantly reduce the tracking error or drift,enhance the robustness,accuracy and stability of the VSLAM system in dynamic scenes.

Dynamic evolutionary community detection algorithms based on the modularity matrix

Motivated by the relationship of the dynamic behaviors and network structure, in this paper, we present two efficient dynamic community detection algorithms. The phases of the nodes in the network can evolve according to our proposed differential equations. In each iteration, the phases of the nodes are controlled by several parameters. It is found that the phases of the nodes are ultimately clustered into several communities after a short period of evolution. They can be adopted to detect the communities successfully. The second differential equation can dynamically adjust several parameters, so it can obtain satisfactory detection results. Simulations on some test networks have verified the efficiency of the presented algorithms.

Application of Bayesian Dynamic Forecast in Anomaly Detection

A macroscopical anomaly detection method based on intrusion statistic and Bayesian dynamic forecast is presented. A large number of alert data that cannot be dealt with in time are always aggregated in control centers of large-scale intrusion detection systems. In order to improve the efficiency and veracity of intrusion analysis, the intrusion intensity values are picked from alert data and Bayesian dynamic forecast method is used to detect anomaly. The experiments show that the new method is effective on detecting macroscopical anomaly in large-scale intrusion detection systems.

Overlapping Community Detection in Dynamic Networks

Due to the increasingly large size and changing nature of social networks, algorithms for dynamic networks have become an important part of modern day community detection. In this paper, we use a well-known static community detection algorithm and modify it to discover communities in dynamic networks. We have developed a dynamic community detection algorithm based on Speaker-Listener Label Propagation Algorithm (SLPA) called SLPA Dynamic (SLPAD). This algorithm, tested on two real dynamic networks, cuts down on the time that it would take SLPA to run, as well as produces similar, and in some cases better, communities. We compared SLPAD to SLPA, LabelRankT, and another algorithm we developed, Dynamic Structural Clustering Algorithm for Networks Overlapping (DSCAN-O), to further test its validity and ability to detect overlapping communities when compared to other community detection algorithms. SLPAD proves to be faster than all of these algorithms, as well as produces communities with just as high modularity for each network.

Hierarchical adaptive stereo matching algorithm for obstacle detection with dynamic programming

An adaptive weighted stereo matching algorithm with multilevel and bidirectional dynamic programming based on ground control points （GCPs） is presented. To decrease time complexity without losing matching precision, using a multilevel search scheme, the coarse matching is processed in typical disparity space image, while the fine matching is processed in disparity-offset space image. In the upper level, GCPs are obtained by enhanced volumetric iterative algorithm enforcing the mutual constraint and the threshold constraint. Under the supervision of the highly reliable GCPs, bidirectional dynamic programming framework is employed to solve the inconsistency in the optimization path. In the lower level, to reduce running time, disparity-offset space is proposed to efficiently achieve the dense disparity image. In addition, an adaptive dual support-weight strategy is presented to aggregate matching cost, which considers photometric and geometric information. Further, post-processing algorithm can ameliorate disparity results in areas with depth discontinuities and related by occlusions using dual threshold algorithm, where missing stereo information is substituted from surrounding regions. To demonstrate the effectiveness of the algorithm, we present the two groups of experimental results for four widely used standard stereo data sets, including discussion on performance and comparison with other methods, which show that the algorithm has not only a fast speed, but also significantly improves the efficiency of holistic optimization.

A High-level Architecture for Intrusion Detection on Heterogeneous Wireless Sensor Networks: Hierarchical, Scalable and Dynamic Reconfigurable

Networks protection against different types of attacks is one of most important posed issue into the network and information security domains. This problem on Wireless Sensor Networks (WSNs), in attention to their special properties, has more importance. Now, there are some of proposed solutions to protect Wireless Sensor Networks (WSNs) against different types of intrusions;but no one of them has a comprehensive view to this problem and they are usually designed in single-purpose;but, the proposed design in this paper has been a comprehensive view to this issue by presenting a complete Intrusion Detection Architecture (IDA). The main contribution of this architecture is its hierarchical structure;i.e. it is designed and applicable, in one, two or three levels, consistent to the application domain and its required security level. Focus of this paper is on the clustering WSNs, designing and deploying Sensor-based Intrusion Detection System (SIDS) on sensor nodes, Cluster-based Intrusion Detection System (CIDS) on cluster-heads and Wireless Sensor Network wide level Intrusion Detection System (WSNIDS) on the central server. Suppositions of the WSN and Intrusion Detection Architecture (IDA) are: static and heterogeneous network, hierarchical, distributed and clustering structure along with clusters' overlapping. Finally, this paper has been designed a questionnaire to verify the proposed idea;then it analyzed and evaluated the acquired results from the questionnaires.

Three-dimensional coordinates test method with uncertain projectile proximity explosion position based on dynamic seven photoelectric detection screen

To objectively obtain the three-dimensional coordinates of the projectile fuze proximity explosion when projectile intersects the head of missile target, we propose a dynamic seven photoelectric detection screen test method, which is made up of six plane detection screens and a flash photoelectric dynamic detection screen. The three-dimensional coordinates calculation model of the projectile proximity explosion position based on seven plane detection screens with dynamic characteristics is established.According to the relation of the dynamic seven photoelectric detection screen planes and the time values,the analytical function of the projectile proximity explosion position parameters under non-linear motion is derived. The projectile signal filtering method based on discrete wavelet transform is explored in this work. Additionally, the projectile signal recognition algorithm using an improved particle swarm is proposed. Based on the characteristics of the time duration and the signal peak error for the projectile passing through the detection screen, the signals attribution of the same projectile passing through six detection screens are analyzed for obtaining precise time values of the same projectile passing through the detection screens. On the basis of the projectile fuze proximity explosion test, the linear motion model and the proposed non-linear motion model are used to calculate and compare the same group of projectiles proximity explosion position parameters. The comparison of test results verifies that the proposed test method and calculation model in this work accurately obtain the actual projectile proximity explosion position parameters.

Community Detection in Dynamic Social Networks

There are many community detection algorithms for discovering communities in networks, but very few deal with networks that change structure. The SCAN (Structural Clustering Algorithm for Networks) algorithm is one of these algorithms that detect communities in static networks. To make SCAN more effective for the dynamic social networks that are continually changing their structure, we propose the algorithm DSCAN (Dynamic SCAN) which improves SCAN to allow it to update a local structure in less time than it would to run SCAN on the entire network. We also improve SCAN by removing the need for parameter tuning. DSCAN, tested on real world dynamic networks, performs faster and comparably to SCAN from one timestamp to another, relative to the size of the change. We also devised an approach to genetic algorithms for detecting communities in dynamic social networks, which performs well in speed and modularity.

Extraordinary tunable dynamic range of electrochemical aptasensor for accurate detection of ochratoxin A in food samples

We report the design of a sensitive,electrochemical aptasensor for detection of ochratoxin A(OTA)with an extraordinary tunable dynamic sensing range.This electrochemical aptasensor is constructed based on the target induced aptamer-folding detection mechanism and the recognition between OTA and its aptamers results in the conformational change of the aptamer probe and thus signal changes for measurement.The dynamic sensing range of the electrochemical aptasensor is successfully tuned by introduction of free assistant aptamer probes in the sensing system.Our electrochemical aptasensor shows an extraordinary dynamic sensing range of 11-order magnitude of OTA concentration from 10^−8 to 10^2 ng/g.Of great significance,the signal response in all OTA concentration ranges is at the same current scale,demonstrating that our sensing protocol in this research could be applied for accurate detections of OTA in a broad range without using any complicated treatment of signal amplification.Finally,OTA spiked red wine and maize samples in different dynamic sensing ranges are determined with the electrochemical aptasensor under optimized sensing conditions.This tuning strategy of dynamic sensing range may offer a promising platform for electrochemical aptasensor optimizations in practical applications.

A Nonparametric Approach to Foreground Detection in Dynamic Backgrounds

Foreground detection is a fundamental step in visual surveillance.However,accurate foreground detection is still a challenging task especially in dynamic backgrounds.In this paper,we present a nonparametric approach to foreground detection in dynamic backgrounds.It uses a history of recently pixel values to estimate background model.Besides,the adaptive threshold and spatial coherence are introduced to enhance robustness against false detections.Experimental results indicate that our approach achieves better performance in dynamic backgrounds compared with several approaches.

Dynamic Simulation of Cracked Buildings for Damage Detection

A dynamic simulation method for cracked structures is implemented to determine their dynamic response with the purpose of evaluating their structural behavior.The procedure makes possible the si mulation of three-dimensional cracked structures.The excitation force is randomly generated to simulate wind gusts.It is assumed the structure remains in the elastic range,which allows for each mode that contributes to its dynamic response to be decoupled.The results indicate that the presence of damage causes changes in the modals parameters of the structure as accurate as other similar methods proposed for simpler structures.Therefore,it is concluded that the proposed method is a reliable way to evaluate the dynamic behavior of three-dimensi onal cracked building structures.

Loss-of-Main Monitoring and Detection for Distributed Generations Using Dynamic Principal Component Analysis

In this paper, our previous work on Principal Component Analysis (PCA) based fault detection method is extended to the dynamic monitoring and detection of loss-of-main in power systems using wide-area synchrophasor measurements. In the previous work, a static PCA model was built and verified to be capable of detecting and extracting system faulty events;however the false alarm rate is high. To address this problem, this paper uses a well-known ‘time lag shift’ method to include dynamic behavior of the PCA model based on the synchronized measurements from Phasor Measurement Units (PMU), which is named as the Dynamic Principal Component Analysis (DPCA). Compared with the static PCA approach as well as the traditional passive mechanisms of loss-of-main detection, the proposed DPCA procedure describes how the synchrophasors are linearly auto- and cross-correlated, based on conducting the singular value decomposition on the augmented time lagged synchrophasor matrix. Similar to the static PCA method, two statistics, namely T2 and Q with confidence limits are calculated to form intuitive charts for engineers or operators to monitor the loss-of-main situation in real time. The effectiveness of the proposed methodology is evaluated on the loss-of-main monitoring of a real system, where the historic data are recorded from PMUs installed in several locations in the UK/Ireland power system.

Wide dynamic detection range of methane gas based on enhanced cavity absorption spectroscopy

Integrated cavity output spectroscopy(ICOS) is an effective technique in trace gase detection.The strong absorption due to the long optical path of this method makes it challenging in the application scenes that have large gas concentration fluctuation,especially when the gas concentration is high.In this paper,we demonstrate an extension of the dynamic range of ICOS by using a detuned laser combined with an off-axis integrating cavity.With this,we improve the upper limit of the dynamic detection range from 0.1%(1000 ppm) to 20% of the gas concentration.This method provides a way of using ICOS in the applications with unpredictable gas concentrations such as gas leak detection,ocean acidification,carbon sequestration,etc.