Search

In this paper, we propose a modular security approach using a positioning security engine featuring Global Positioning System (GPS) location features that can uniquely identify the Internet of Things (IoT) user device. Our approach aims to reinforce the security and viability of IoT-centric solutions for various innovative applications, including IoT Mobile payment, Smart city heterogeneous networks, communication services, safety, and location-based services integration. To achieve our goal of securitization and viability, we target consumer IoT devices equipped with built-in location-based GPS chips, which are vulnerable to hackers where the existing cryptographic authentication-based protocols demand power and computation resources required for authentication protocols is not sufficient to carry end to end secure transaction in an IoT environment. Therefore, to compensate this lack of environment capability to carry the end-to-end secure transaction on IoT devices when emitting various radio signals, we implement a modular security approach to compensate the lack of capabilities. This leads to an optimal security facilitated by Simple Public Key Infrastructure following the Pretty Good Privacy Web of Trust approach. Moreover, our implementation on the development board Arduino succeeded in providing and extended secure capable environment for carrying secure transactions. The results show a communication success rate of 70, 80 and 90 percent between Security Engine component called modules, with 70 percent of successful Secure Sockets Layer (SSL) key exchange by every identified user in average 15 seconds simulation running time for every two by third round of simulation.

Detecting two-dimensional (2D) materials in silicon chips presents a significant challenge in the field of quantum machines due to the difficulty of data collection. Specifically, among thousands of flakes, not all flakes are useful or well-annotated, resulting in noisy and hard samples within the dataset, which challenges the deep neural network (DNN) to learn. To address this problem, we propose a novel method for identifying quantum 2D flakes even when there is a high rate of missing annotations in the input images. In particular, we first propose a new mechanism for automatically detecting false negative flakes that are missing annotations. Second, we introduce an attention-based loss function to mitigate the negative impact of these unannotated flakes on the DNNs. The experimental results demonstrate that our method outperforms previous approaches.

The optimal setting of parameters of PID controllers is a significant requirement of industrial practice. It seems intuitive, but it can be complicated, especially when there are many (often conflicting) requirements for the control process. Many regulators are then set incorrectly or inappropriately. The search for a method of identifying the parameters of the controlled system with the subsequent setting of the parameters of the PID controllers takes place from the moment it is found. Nevertheless, we decided to develop a physical controller that would be easy to use in industrial practice. The demand is that the operator set as few parameters as possible, and most of the settings should be automatic. We based the identification on the relay method, more precisely, on its modification known as the relay-shifting method. During identification, an asymmetric relay is used. The parameters of a model of the system are then calculated from three points of the frequency characteristic. This method is not as commonly utilized in current commercial controllers. The general advantages of the relay method include identifying the system in a closed control loop and performing time-saving calculations. This makes it suitable for practical use in industry. The parameters of the PID controller are calculated using either the Marchetti-Scali method or the Ackermann method from the model whose parameters were obtained by relay identification. We built the controller on a development microcontroller board, which we supplemented with the necessary peripherals. The result is a prototype of a physical PID controller with autotuning. In the article, we present not only the implemented equations but also the test results of our PID controller on one of the real devices on which its functionality was verified.

Accidents resulting from fires caused by electrical devices are frequent occurrences, inflicting substantial damage to both human lives and infrastructure in the Republic of Korea. To ascertain whether these fires stem from external or internal infrastructure factors, investigators such as the police, The National Institute of Scientific Investigation, and the National Fire Research Institute conduct fire-causing inspections. However, obtaining conclusive results in this regard is an intricate process, exacerbated by the dearth of adequate digital forensics tools and related programs. Among electrical devices, multi-socket outlets also contribute to fire incidents. This study explores the feasibility of employing CNN-based deep learning object detection models for fire-causing inspection systems targeting multi-socket outlets. Specifically, we introduce a novel image dataset comprising 6009 images of post-fire multi-socket outlets remaining, categorized into two classes: “burnt-in” and “burnt-out.” This dataset is utilized for training various models, including the YOLO-series (v5, v6, and v8), Faster-RCNN, RetinaNet, and SSD. Results from our experiments show the feasibility of six CNN models in detecting the cause of fire in post-fire sockets. Particularly, YOLOv5s surpasses other models with an accuracy of 89.1% mAP@0.5, a model size of 14.4MB, and an inference time of 44.5ms (equivalent to 22 fps) on RTX 3050. Subsequently, the trained models are implemented in an operational application for trial testing during an executive period.

Atomic Force Microscopy (AFM) has been a broadly used platform for high-resolution imaging and mechanical characterization of a wide range of samples. However, this technique can be time-consuming and heavily relies on constant human supervision and human insight for data acquisition and analysis. Recent advancement in artificial intelligence (AI) provides the potential for efficient data analysis for AFM applications. The fusion of AFM with AI for effective image analysis and classification still remains an ongoing research endeavor. In this study, we present a novel AFM image defect detection and classification framework, AFM_YOLO-ResNet, using advanced deep learning (DL) techniques. Central to our approach is a highly integrated DL model that consists of a YOLO image defect detection layer and a ResNet feature extraction and classification layer. The proposed AFM_YOLO-ResNet framework is trained with expert annotated AFM images, and prepared to assess future AFM images from similar samples. Performance of AFM_YOLO-ResNet was validated for AFM image defect detection and classification, and compared with three commonly used transfer learning and computer vision models (Googlenet, Darknet, and YOLOv8). The results with high training and validation accuracies demonstrated that the AFM_YOLO-ResNet framework greatly improves the AFM imaging analysis efficiency.

We test an approach to modelling the car driver behaviour during simulated lane changing tasks, aiming to obtain a sufficiently precise model in the simplest possible form, namely, with a small number of parameters. Various applications of such models are available in the literature. Based on a recent review of the research to date, the cybernetic single-loop transfer function models employing McRuer’s theory are applied. The purpose of the presented method is to evaluate the optimal structure of the transfer function via cross-validation as a technique known from machine learning. The experiments utilize a driving simulator with in-house developed software; this configuration facilitates acquiring the data at the desired sampling frequency and in a manner that ensures the repeatability of the test process scenarios. Using the cross-validation results, we evaluate the second-order model with a derivative state and a reaction delay component as an optimal structure for approximating the measured data, which originated from a set of measurements on 92 active drivers. Even though more complex driving tasks could require high-order models, driver’s control action during our specific experiment is described through only four parameters. The parameters are jointly determined by the current driver’s mental state and the testing conditions defined in our scenario. Since the parameters are related to his/her dynamical behaviour, they allow easier mutual comparison of the drivers than complex models with many parameters. The results are verified via establishing a relationship to the multi-loop model presented in the recent literature. The larger dataset enables evaluating the confidence intervals of the drivers’ parameters which is inconvenient with 4 to 10 drivers commonly presented in the relevant sources.

The authentication process plays a crucial role in ensuring accurate and high-level security in various applications, particularly in the face of emerging technologies and the growing threat of unauthorized access. Through a comprehensive review of previous studies on brain-computer interface (BCI)-based authentication, we have identified it as a secure and promising solution, harnessing the unique characteristics of brainwaves. The main objective of this research is to systematically categorized the literature based on modality, authentication type, BCI paradigm, stimuli and signals types, computational and machine learning methods, databases, and BCI devices. We used the preferred reporting items for systematic reviews and meta-analyses (PRISMA2020) model in conducting this review. We extracted detailed information from previous studies to gain a deeper understanding of the advancements, challenges, potential applications BCI-based authentication systems. We classified the challenges encountered by BCI systems into three categories: technological, user related, and implementation and suggested the future research directions for each of them. In this study, we presented a systematic literature review the field of BCI-based authentication to provide researchers and practitioners with a comprehensive overview of the advancements, trends, challenges, and future directions in this area.

In today’s digitally interconnected landscape, confirming the genuine associations between entities—whether they are items, devices, or individuals—and specific groups is critical. This paper introduces a new group membership verification method while ensuring minimal information loss, coupled with privacy-preservation and discrimination priors. Instead of verifying based on a similarity score in the original data space, we use a min-max functional measure in a transformed space. This method comprises two stages: (i) generating candidate nonlinear transform representations, and (ii) evaluating the min-max measure over these representations for both group assignment and transform selection. We simultaneously determine group membership and pick the appropriate representation from the candidate set based on the evaluation score. To solve within this framework, we employ an iterative alternating algorithm that both learns the parameters of candidate transforms and assigns group membership. Our method’s efficacy is assessed on public datasets across various verification and identification scenarios and further tested on real-world image databases, CFP and LFW.

The parameter identification technique for a fractional-order Wiener system with time delay is proposed using the Haar wavelet operational matrices. The method is applicable to lower and higher-order Wiener systems, where the order could be an integer or fractional value. The proposed method accomplishes identification in two stages, whereby a special input signal is utilized to separate the identification of the nonlinearity from the linear dynamics. The graphical method is applied to the step responses to compute the static nonlinearity. Subsequently, the sinusoidal response is utilized along with the obtained nonlinearity parameters to identify the linear subsystem. The lower-order models of both subsystems are utilized for identification to reduce complexity. This operational matrix-based algebraic approach is simple yet accurate, and it is applicable to noisy data. Moreover, the proposed approach does not demand prior knowledge about the fractional order or time delay. This method is simulated and validated in MATLAB for various Wiener systems. Numerical results and comparisons with the existing methods illustrate the efficiency of the proposed method.

Over the past two decades, Electrocardiography (ECG) has gained significant momentum in the field of biometrics, offering a compelling alternative for person identity recognition based on physical/biological traits. Its inherent difficulty to be circumvent and its ability to enable liveness detection make it particularly appealing compared to other popular identifiers such as face, fingerprint, and iris. As a result, ECG has garnered attention from the computer vision community working on biometrics applications. We present a novel biometric method for personal recognition that leverages I-lead signals acquired off-the-person. Through fine-tuning a pre-trained Vision Transformer (ViT) model, we achieve remarkable results in recognizing individuals based on a single 2D image of their ECG recording obtained from as little as three heartbeats. Extensive evaluation on the CYBHi database, with enrollment and testing phases separated by a three-month time window, simulating a real-world, long-term identification scenario, demonstrates the robustness of our multiclass approach. Specifically, our system achieves a remarkable single sample-based identification accuracy of over 70% with a pool of 63 individuals, along with an equal error rate of only 0.48% in the 1-vs-1 authentication task. Additionally, we evaluated our approach on the very recent Heartprint database to assess the robustness of our approach with more subjects, larger separation time windows, and continuous training settings, obtaining again remarkable performance with respect to the state-of-the-art. While the promising capabilities of ECG-based biometrics are evident, given various security challenges, using such methods as standalone authentication could raise caution among users. To address this concern and enhance the system’s dependability, we introduce a confidence-based rejection rule. Integrating this mechanism improves both identification and authentication performances, while it could also enable the system to detect out-of-database individuals.

The identification and activity monitoring of Antarctic subglacial lakes contribute to the analysis of the mass balance and sea level change. Remote sensing techniques, especially satellite altimetry, are ideal ways for identifying active subglacial lakes and indirectly monitoring their hydrological activity. Based on ICESat-2 altimetry data, we propose two methods to generate the rates of ice surface elevation changes for identifying active subglacial lakes in Antarctica. We identify 15 new active subglacial lakes and provide denser and more precise outline detail for known subglacial lakes in the Mercer and Whillans Ice Streams and Slessor Glacier regions. Then, we use ICESat-2 and earlier CryoSat-2 data to get the time series of ice surface elevation changes for subglacial lakes to further understand their hydrological processes. Results show that subglacial lakes have exhibited periodic activity and at least two fill–drain cycles in the Mercer and Whillans Ice Streams region. Owing to data limitations, the time series shows less periodic lake activity in the Slessor Glacier region. However, subglacial water movements are similarly active and have various activity patterns.

Biometric-based personal identification models are generally considered to be accurate and secure because biological signals are too complex and person-specific to be fabricated, and EMG signals, in particular, have been used as biological identification tokens due to their high dimension and non-linearity. We investigate the possibility of effectively attacking EMG-based identification models with adversarial biological input via a novel EMG signal individual-style transformer based on a generative adversarial network and tiny leaked data segments. Since two same EMG segments do not exist in nature; the leaked data can’t be used to attack the model directly or it will be easily detected. Therefore, it is necessary to extract the style with the leaked personal signals and generate the attack signals with different contents. With our proposed method and tiny leaked personal EMG fragments, numerous EMG signals with different content can be generated in that person’s style. EMG hand gesture data from eighteen subjects and three well-recognized deep EMG classifiers were used to demonstrate the effectiveness of the proposed attack methods. The proposed methods achieved an average of 99.41% success rate on confusing identification models and an average of 91.51% success rate on manipulating identification models. These results demonstrate that EMG classifiers based on deep neural networks can be vulnerable to synthetic data attacks. The proof-of-concept results reveal that synthetic EMG biological signals must be considered in biological identification system design across a vast array of relevant biometric systems to ensure personal identification security for individuals and institutions.

The radio frequency fingerprint (RFF)-based device identification is a promising physical layer authentication technique. However, the wireless channel significantly affects the RFF features of the wideband wireless devices. In this paper, we extensively investigate the impact of channel variation on RFF identification using 20 MHz IEEE 802.11 signal. A time domain least mean square (LMS) equalization-based feature extraction method has been proposed. This method progressively restores the transmitted signal and preserves more details of RFF features than the classical frequency domain equalization (FDE) method. Moreover, a hybrid identifier is proposed to take advantage of both LMS-based and FDE-based methods. With the equalized samples, a four-layer convolutional neural network is designed for device identification. An experimental system has been set up to capture the waveform of 68 802.11 devices at different positions. The experimental results show that the LMS-based method outperforms others when the acquisition positions of the training dataset are the same as those of the testing dataset. On the other hand, the FDE-based method is shown to be more effective when the acquisition positions of the training dataset do not fully include those of the testing dataset. Moreover, the hybrid identifier achieves an improvement of 2% for overall identification accuracy.

Ferroresonance is a non-linear and dangerous resonance phenomenon that can affect power networks and damage electrical equipment. The ferroresonance phenomenon is examined by dividing it into classes, with chaotic ferroresonance being the most dangerous type that causes overvoltage’s. Detecting chaotic ferroresonance in a short period of time is of great importance in terms of taking measures and reducing equipment damage. In this study, we explored the application of deep convolutional neural networks (DCNNs) for the identification and classification of chaotic ferroresonance phenomena. Two pre-trained AlexNet models were adapted using transfer learning to perform these tasks. The first model was utilized to identify chaotic ferroresonance, while the second was employed to distinguish between different subtypes of chaotic ferroresonance by dividing voltage curve graphs into different periods and shapes. The training and testing of both DCNN models were conducted using snapshot images extracted from the voltage curves of all phase voltages. The results of the experiments showed high accuracy in both the identification and classification of chaotic ferroresonance phenomena.

A large number of electric vehicles (EVs) are connected to the grid, increasing the risk of power quality deterioration. Meanwhile, power quality disturbances (PQDs) directly affect EV charging safety. Intelligent identification of complex PQDs is the basis for solving the power quality problem, which is very meaningful for improving EV charging quality. This paper proposes an automatic recognition framework for complex PQDs based on ensemble convolution neural network (ECNN). Firstly, a multifusion structure on account of the time and frequency domain feature of PQDs signals is introduced. In addition, a composite convolution is proposed to reduce network complexity, which is using the standard convolution and depthwise separable convolution. Then, we design an adaptive-context mechanism to extend the versatility of ECNN. At the same time, the need to use batch normalization to accelerate training convergence and prevent training overfitting is verified. Furthermore, some visualization methods are performed to analyze the inner mode and illustrate the working mechanism of ECNN. Finally, we apply various experiments to prove the effectiveness of ECNN. Compared to other advanced deep neural networks and traditional methods, ECNN has better noise resistance, higher accuracy, and lower training cost.

In today’s leaf disease detection, the accuracy of recognition has never been of such importance as it is now. In this aspect, leaf disease recognition method based on machine learning relies heavily on the size of the region of interest and the dispersion of lesions. Professional instrument for leaf disease detection remains a challenging task in accuracy and convenience. A new lightweight model based on advanced residual network and attention mechanism for extracting more accurate region of interest and the lesion, SE-VRNet, was proposed. The proposed SE-VRNet incorporated deep variant residual network (VRNet) and a squeeze-and-excitation (SE) module with attention mechanism, in order to solve the problem that the feature extraction was difficult due to the dispersed location of the leaf disease. The accuracy of top-1 and top-3 obtained by the model SE-VRNet on NewData is 99.73% and 99.98%, respectively, and the accuracy of top-1 and top-3 obtained by the model on SelfData is 95.71% and 99.89%, respectively. The experimental results on the datasets of PlantVillage, OriData, NewData and SelfData were better than other state-of-the-art methods, demonstrating the effectiveness and feasibility of the proposed SE-VRNet in identifying leaf diseases with mobile devices.

In order to improve the ability to detect and identify topological errors and measurement errors, and further enhance the rapidity and reliability of substation state estimation, this paper proposes a three-phase linear state estimation method for substations based on zero impedance model. Firstly, for the shortcomings of the traditional regularized weighted residual method with many cycles and slow calculation speed, improvements are made to improve the rapidity of state estimation while suppressing the residual flooding phenomenon. Based on this, the zero-impedance model of the substation makes full use of the three-phase telemetry and telecommunication state data to establish the power measurement equation for zero-impedance initial power state estimation, and proposes a discrimination method to identify measurement errors and topological errors and to determine the state of the switching circuit breakers. Based on the secondary power state estimation, a voltage measurement equation is established based on the voltage measurement information to estimate the substation voltage state. The simulation results show that the method can accurately identify and locate the simultaneous measurement errors and topology errors, and can also identify individual measurement errors, thus improving the estimation accuracy of state estimation.

The mechanical parameters, including the Coulomb and viscous friction coefficients together with the moment of inertia, are of great interest for the performance optimization and condition evaluation of surface-mounted permanent magnet synchronous motor (SPMSM) drives. This article contributes a speed-controller-independent mechanical parameter identification scheme using open-loop speed response due to signal injection, which has not been reported in existing works. It is designed based on the premise that the viscous friction torque is disproportional to the rotor speed, which is a new progress toward estimating the mechanical parameters with high precision. Moreover, as a practical full-participation-type solution, this scheme involves a new electrical parameter estimation technique based on differential algebra to assist in identifying the mechanical parameters. This auxiliary technique attains the current-controller-free estimation of the electrical parameters with the inverter nonlinearity eliminated, thereby addressing the current controller self-commissioning and serving to acquire the accurate electromagnetic torque. The experimental evaluations on two prototype SPMSM drive systems validate the feasibility of this suggested scheme. [ABSTRACT FROM AUTHOR]

To construct a more effective model with good generalization performance for inter-site autism spectrum disorder (ASD) diagnosis, domain adaptation based ASD diagnostic models are proposed to alleviate the inter-site heterogeneity. However, most existing methods only reduce the marginal distribution difference without considering class discriminative information, and are difficult to achieve satisfactory results. In this paper, we propose a low rank and class discriminative representation (LRCDR) based multi-source unsupervised domain adaptation method to reduce the marginal and conditional distribution differences synchronously for improving ASD identification. Specifically, LRCDR adopts low rank representation to alleviate the marginal distribution difference between domains by aligning the global structure of the projected multi-site data. To reduce the conditional distribution difference of data from all sites, LRCDR learns the class discriminative representation of data from multiple source domains and the target domain to enhance the intra-class compactness and inter-class separability of the projected data. For inter-site prediction on all ABIDE I data (1102 subjects from 17 sites), LRCDR obtains the mean accuracy of 73.1%, superior to the results of the compared state-of-the-art domain adaptation methods and multi-site ASD identification methods. In addition, we locate some meaningful biomarkers: Most of the top important biomarkers are inter-network resting-state functional connectivities (RSFCs). The proposed LRCDR method can effectively improve the identification of ASD, and has great potential as a clinical diagnostic tool. [ABSTRACT FROM AUTHOR]

A novel online multiparameter identification method is proposed for interior permanent magnet (IPM) machines considering cross-coupling magnetic saturation. The identification method is based on the combination of small-signal impedance model and fundamental frequency signal model under dq-axes. To analyze the nonlinearity of IPM machines, cross-coupling magnetic saturation effect is introduced into online multiparameter identification for the first time. Based on this model, a phase compensation strategy and orthogonal decomposition in phasor domain is proposed to decouple the complicated mathematical model into four linear equations. By injecting voltage small-signals into dq-axes, multiparameter of IPM machine including adjusted apparent inductance, incremental self-inductance, incremental mutual-inductance can be identified online in a wide operation region. During this process, no additional computing equipment is required. The proposed method is carried out on a tested IPM machine and verified by the finite-element analysis. [ABSTRACT FROM AUTHOR]

Contact operations of free-floating satellite robots are difficult and risky and therefore, they must be thoroughly tested and verified by ground-based facilities. A hardware-in-the-loop (HIL) simulation system with industrial robots is commonly used for simulating space robotic operations. However, a great challenge is to handle simulation divergence due to intrinsic time delay between the measured forces and the simulation driven reaction of the robot. This paper presents a novel hybrid force/velocity control method for compensating the time delay of a HIL simulation. A real-time identification method for contact stiffness and damping is proposed based on the adaptive Kalman filter. Then, an energy observer is designed to monitor the energy flow and an energy controller (EC) is established. The EC acts a variable damping and thus the contact damping is amended. Therefore, a compensation strategy based on parameter identification and damping amendment is proposed to eliminate the effects of time delays. Finally, numerical simulations and experimental results show that the simulation divergence due to time delay can be prevented. Moreover, space robotic operations with high fidelity of both contact force and contact velocity are reproduced by the proposed method.

Gastric cancer (GC) is one of the most common cancers in the world. In cancer detection, liquid biopsy, as a noninvasive and rapid method, is growing in importance. Different from traditional liquid biopsy using a single biomarker, this study integrated a variety of blood biochemical indices and established an identification system by means of deep learning under the H2O framework method. Based on data from 2951 samples, 58 routine blood biochemical indices, age and gender were collected as comprehensive indices to establish the identification model. Then, the number of indices was reduced to simplify the model, and 33 indices were utilized to build the final identification tool. A tenfold cross-validation technique was used to evaluate the performance of the proposed method. The sensitivity, specificity, accuracy, and area under the ROC curve on the cross-validation set were 85.44%, 83.82%, 84.54% and 0.9165, respectively. The identification tool is built free online at https://www.cppdd.cn/GC2. The proposed system provides a new approach to identify GC with advantages of being efficient, noninvasive and economical. The deep learning of the integration of these blood biochemical indices will bring insights into the comprehensive understanding of GC pathology, as well as the prevention, screening, diagnosis, and prognosis of GC.

Electroencephalogram signals (EEG) have provided biometric identification systems with great capabilities. Several studies have shown that EEG introduces unique and universal features besides specific strength against spoofing attacks. Essentially, EEG is a graphic recording of the brain’s electrical activity calculated by sensors (electrodes) on the scalp at different spots, but their best locations are uncertain. In this paper, the EEG channel selection problem is formulated as a binary optimization problem, where a binary version of the Grey Wolf Optimizer (BGWO) is used to find an optimal solution for such an NP-hard optimization problem. Further, a Support Vector Machine classifier with a Radial Basis Function kernel (SVM-RBF) is then considered for EEG-based biometric person identification. For feature extraction purposes, we examine three different auto-regressive coefficients. A standard EEG motor imagery dataset is employed to evaluate the proposed method, including four criteria: (i) Accuracy, (ii) F-Score, (iii) Recall, and (v) Specificity. In the experimental results, the proposed method (named BGWO-SVM) obtained 94.13% accuracy using only 23 sensors with 5 auto-regressive coefficients. Besides, BGWO-SVM finds electrodes not too close to each other to capture relevant information all over the head. As concluding remarks, BGWO-SVM achieved the best results concerning the number of selected channels and competitive classification accuracies against other meta-heuristics algorithms.

Accurate obstacle detection and proper behavior planning are key factors in the success of transmission line inspection robots. To achieve the autonomous location and identification of line obstacles in the operation of transmission line inspection robots, we propose a method in which information from various sensors is used to control a robot such that it can reliably and stably approach, locate, and identify obstacles. The accuracy and real-time requirements of obstacle information in the autonomous operation of the inspection robot are analyzed, a multi-sensor integrated structure for line obstacle location and identification is proposed, and an obstacle location and identification algorithm is designed for each stage. The principle of monocular vision ranging is used to control the robot such that it approaches obstacles and enters the short-range location stage, where the reliable location of obstacles is achieved via collision-encoder-current sensor data fusion. Obstacles are identified and the identification results are combined with those of the approaching rolling phase. The robot state vector is constructed according to the obstacle detection information and information measured by the robot sensors. Based on the current state vector, combined with the robot obstacle surmounting process, an obstacle surmounting behavior planning method based on multi-sensor fusion is implemented. Experiments were conducted using laboratory-simulated lines to verify the effectiveness of the proposed method for obstacle detection and behavior planning during transmission line inspection.

To address the problem of the sparrow search algorithm (SSA) has poor global search ability, weak local development ability, and easily falls into the local optimal solution, a multi-strategy improved evolutionary sparrow search algorithm (MSSA) is proposed. The introduction of the tent chaotic map improves the diversity of the initialization population, accelerates algorithm convergence, and improves convergence accuracy. Endow sparrow finders with a random search ability to coordinate the balance between global search and local development. To discover dangerous sparrow individuals, the mutation evolution operation is completed, and a greedy strategy is combined to improve the processing ability of the algorithm for local optimal solutions and make full use of each sparrow individual. Six benchmark functions were used to comprehensively verify the feasibility of the proposed algorithm based on four aspects: optimization ability, robustness, convergence ability, and optimization trajectory. These results indicate that the proposed algorithm is superior. Finally, through the comparison and analysis of the parameter identification and control strategies of the two servo systems in practical application, on the one hand, the advantages of the proposed algorithm in practical engineering applications are illustrated. In addition, a fuzzy PID control strategy based on MSSA is proposed. By adding step, sinusoidal, triangular wave and disturbance signals, simulation experiments show that the control strategy can significantly improve the dynamic and steady performance of the servo system.

The robot kinematic error model may include redundant parameters, which require removal prior to the identification of kinematic parameters to ensure the accuracy and stability of such. Traditionally, the redundant parameters are determined by the numerical analysis. This paper presents an analytical method to determine the identifiable kinematic parameters for serial-robot calibration under various identification conditions. Among various kinematic models of robots, the DH (Denavit-Hartenberg) model is the most commonly used, so the analysis of redundant parameters is based on the DH error model. The correlation between the columns of the Jacobian matrix is analyzed by theoretical methods, resulting in the linear relationship between these columns. The redundant error parameters and the linear independent parameters after removing redundancies from robots with different measurement conditions and different configurations are clearly given. Thus, the redundant parameters can be easily determined based on the values of kinematic parameters, which facilitates the determination of the non-redundant kinematic calibration model. In addition, the physical meanings of redundant parameters are also elaborated, which can reveal the inherent principle of the error parameters’ linear correlation. Finally, the parameter identification simulation experiment shows that the identification results, after removing the redundant parameters, all converge to the true values when the random noise is not considered, which verifies the correctness of the parameter redundancy analysis results. In the case of considering random noise, the non-redundant parameter identification has better convergence than the full parameter identification. This study can provide theoretical and application references for robot kinematic calibration.

This paper proposes a system identification framework based on eigensystem realization to accurately model power electronic converters. The proposed framework affords an energy-based optimal reduction method to precisely identify the dynamics of power electronic converters from simulated or actual raw data measured at the converter's ports. This method does not require any prior knowledge of the topology or internal parameters of the converter to derive the system modal information. The accuracy and feasibility of the proposed method are exhaustively evaluated via simulations and practical tests on a software-simulated and hardware-implemented dual active bridge (DAB) converter under steady-state and transient conditions. After various comparisons with the Fourier series-based generalized average model, switching model, and experimental measurements, the proposed method attains a root mean square error (RMSE) of less than 1% with respect to the actual raw data. Moreover, the computational effort is reduced to 1/8.6 of the Fourier series-based model.

Multi-motor drive systems (MMDS) combine several drives that work together to fulfill one task. Compared to conventional single-motor drive systems modular product concepts can be realized with MMDS thanks to additional degrees of freedom. Because of their mechanical structure consisting of several shafts, clutches, and gear pairings, complex deflection shapes arise which lead to unintended torque oscillations.To compensate for these torque oscillations a data-driven adaptive multiple-input single-output scheme based on two cascaded recursive least squares estimators is proposed. Here, weights (manipulable amplitudes) for each order (multiple of a fundamental frequency) to be compensated are multiplied with unit amplitude harmonic signals of a reference oscillator and added as reference torques to the torque controllers of the MMDS’s drives. These weights are continually adapted by an online identification of transfer paths and disturbances. Furthermore, the torque contribution of the individual drives concerning the compensation task can be changed at runtime utilizing a weighting matrix as tuning parameter by analytically solving a quadratic program with a linear equality constraint. Hence, the proposed algorithm is suitable for automatic self-commissioning requiring only marginal expert intervention. Experimental investigations prove the compensation capability of the approach whereby a reduction of the output torque’s total harmonic distortion (THD) of up to $80\%$ from $26.8\%$ to $5.4\%$ for a representative operation point is achieved.

Decentralization is essential when trust and performance must not depend on a single organization. Distributed Ledger Technologies (DLTs) and Decentralized Hash Tables (DHTs) are examples where the DLT is useful for transactional events, and the DHT is useful for large-scale data storage. The combination of these two technologies can meet many challenges. The blockchain is a DLT with immutable history protected by cryptographic signatures in data blocks. Identification is an essential issue traditionally provided by centralized trust anchors. Self-sovereign identities (SSIs) are proposed decentralized models where users can control and manage their identities with the help of DHT. However, slowness is a challenge among decentralized identification systems because of many connections and requests among participants. In this article, we focus on decentralized identification by DLT and DHT, where users can control their information and store biometrics. We survey some existing alternatives and address the performance challenge by comparing different decentralized identification technologies based on execution time and throughput. We show that the DHT and machine learning model (BioIPFS) performs better than other solutions such as uPort, ShoCard, and BBID.

Smart home IoT devices lack proper security, raising safety and privacy concerns. One-size-fits-all network administration is ineffective because of the diverse QoS requirements of IoT devices. Device classification can improve IoT administration and security. It identifies vulnerable and rogue items and automates network administration by device type or function. Considering this, a promising research topic focusing on Machine Learning (ML)-based traffic analysis has emerged in order to demystify hidden patterns in IoT traffic and enable automatic device classification. This study analyzes these approaches to understand their potential and limitations. It starts by describing a generic workflow for IoT device classification. It then looks at the methods and solutions for each stage of the workflow. This mainly consists of i) an analysis of IoT traffic data acquisition methodologies and scenarios, as well as a classification of public datasets, ii) a literature evaluation of IoT traffic feature extraction, categorizing and comparing popular features, as well as describing open-source feature extraction tools, and iii) a comparison of ML approaches for IoT device classification and how they have been evaluated. The findings of the analysis are presented in taxonomies with statistics showing literature trends. This study also explores and suggests undiscovered or understudied research directions.

Full-polarimetric ground penetrating radar (FP-GPR) can measure the ability of an object to change the polarization of electromagnetic waves. Compared to the traditional GPR, it has a stronger capability to identify underground objects. In recent years, a series of polarization decomposition methods have been applied to the FP-GPR data processing to obtain the polarimetric attributes and enhance the capability of targets identification. Different polarimetric attributes characterize different features of a target but there is still no effective way to integrate these attributes and take their respective advantages for target classification. In this article, we propose a particle center AdaBoost (PCAD) method and achieve the multiparameter adaptive target identification. The experimental results indicate that the PCAD method can automatically select suitable parameters during the training process for different targets. Compared to the single-parameter classification and the AdaBoost methods based on the traditional average and Bagging method, the PCAD method presents higher correct rates in classification. Finally, the proposed method is applied to landmine detection. The results demonstrate that the landmine is a composite scatterer that can generate surface scattering signals on its surface and dipole and volume scattering signals from its interior; based on the color-coded two-dimensional image by PCAD, we can distinguish landmines from other targets.

This article proposes an improved position sensorless drive method for interior permanent magnet synchronous machines (IPMSM) in medium- and high-speed regions, which relies on the fully discretized extended back-electromotive force (EEMF) model and online inductance identification. First, the fully discretized EEMF model is developed for constructing position observers, which overcomes the accuracy deterioration of the conventional Euler-discretized model with the speed increasing. And then, an online inductance identification method for IPMSM, which utilizes the inherent pulsewidth modulation (PWM) current ripple of the voltage source inverter (VSI), is proposed to improve the position estimation accuracy. Compared with the traditional parameter identification method, the proposed method does not require the additional signal injection, therefore, the undesirable torque fluctuation and additional voltage occupancy due to signal injection are avoided. Benefiting from the fully discretized EEMF model and the estimated inductances, the improved rotor position estimation of IPMSM can be achieved. Finally, the proposed method is verified by simulations and experiments. [ABSTRACT FROM AUTHOR]

As the core of the attitude determination system, the star sensor working in "lost in space" scenarios requires the star identification algorithm to be robust and fast with limited computing and memory resources. Nevertheless, previous algorithms are not satisfactory in robustness and identification speed. Hence, motivated by the fact that the one-dimensional convolutional neural network (1D-CNN) is suitable for sequential data, this article proposes a robust and efficient star identification algorithm, where 1D-CNN is used to process mixed initial features from star points. Moreover, this article proposes a combined star points selection strategy technique and a mixed initial features extraction technique to further improve the performance of 1D-CNN-based algorithm. Experimental results show that, compared with the state-of-the-art algorithm, the proposed algorithm can improve the average identification accuracy by 0.76%, the identification speed by 1.86× with the comparable memory consumption. [ABSTRACT FROM AUTHOR]

This paper proposes a systematic method for the identification of the load circuit parameters (say the $\boldsymbol{R}$ , $\boldsymbol{L}$ , and $\boldsymbol{C}$ elements) based only on the information of the instantaneous voltage and current measured at the point of common coupling (pcc). Geometric Algebra (GA) and concepts of differential geometry are used to produce a rigorous mathematical framework. The identification is formulated as a multidimensional geometrical problem that is solved conveniently by means of GA. Once the passive elements of the load have been identified, the active and reactive powers can be computed from first electromagnetic principles (Maxwell Equations). The theory is general and is verified with linear and nonlinear circuits. The paper shows single-phase circuits but the theory can be extended to three-phase circuits. The method is easy to program and has shown to be very robust for all tested cases. Because of its generality, the method presented will find applications beyond electric circuits. [ABSTRACT FROM AUTHOR]

Tuning the receiver to match the resonant frequency with the working frequency plays an important role in improving the efficiency. One of the crucial steps in tuning is to determine the value or degree of detuning. In order to obtain the receiver reactance used to determine the detuning value, this article proposes a pulse density modulation (PDM)-based receiver reactance identification method. The parameter identification is performed as follows: implementing PDM technology on the active single-phase rectifier (ASPR) to bring in interharmonics and through Fast Fourier Transformation and least-square approximation, values of inductor and capacitor of the receiver can be identified. This estimation method only requires the magnitudes of voltage and current into ASPR for estimation. No extra hardware, no need to synchronize with the transmitter. In the experimental verification, four cases of resonant, inductive, and capacitive receivers are designed. Results show the maximum relative errors for estimation are within 5%, based on which the ASPR can tune the receiver as resonant. The situation that parameter deviates from the nominal value is also considered, even with deviations of mutual inductance and transmitter-side reactance, the estimation accuracy of receiver-side reactance is still at an average level. [ABSTRACT FROM AUTHOR]

Identifying competitors is an essential first step in creating a competitive advantage to generate superior business performance. Diverse methods for competitor identification have been introduced in the literature, but financial transactions are overlooked in these models even though such transactions among firms, as the basic economic unit of interfirm business activities, contain critical information. This article proposes a novel method for the identification of firm-level competitors using a network constructed from financial transactions among firms. To identify competitors by the intensity of interfirm competition, the proposed method is based on two dimensions of pairs of firms, resource similarity and market commonality, which are represented in a data-driven approach using a transaction network. We propose network-theoretic similarity measures to quantify the resource similarity and market commonality between firms by considering both direct and indirect transactions in a transaction network. Then, based on the two dimensions, three types of competitors are identified with respect to a focal firm: direct, potential, and indirect competitors. The proposed method is applied to toy network data and a real-world case that includes the financial transactions of firms in Korea in 2014. [ABSTRACT FROM AUTHOR]

Transformer-customer relationship identification refers to the determination of the physical connection relationship of electricity end-customers and their corresponding transformers. Such connection relationship is critical for distribution utilities to maintain their end-customer profiles. However, management of transformer-customer relationship becomes one of the most emerging challenges due to large number of end-customers and lack of measurement devices in low-voltage distribution systems. To address the above issue, this paper proposes an end-customer data-driven method to identify transformer-customer relationship in low-voltage distribution grid by utilizing the customer field data obtained from advanced metering infrastructure. Specifically, the incidence convolution identification method is proposed to build up the unique mapping relationship between end-customers and their transformers based on the principle of energy conservation. Then the voltage correlation maximization model based on Markov Random Field is proposed, where the voltage correlation matrix is exacted and combined with the adjacency matrix to establish an optimization model to correct the potential abnormal transformer-customer relationship. Finally, the effectiveness of the proposed method is verified by using practical utility tests. [ABSTRACT FROM AUTHOR]

This letter introduces a novel Fourier-based data augmentation strategy for visible-thermal person re-identification (VT-ReID). Different from some existing methods which are proposed from the perspective of network structure and loss functions, our method aims to fully consider the semantic information from the perspective of data preprocessing. The main hypothesis is that the phase component in the Fourier domain contains high-level semantic information and the amplitude component contains low-level modality awareness information. In order to make the model pay more attention to semantic information learning, we design a simple but effective Fourier-based semantic augmentation (FSA) module, which can be inserted seamlessly into any existing models. Extensive experiments on RegDB and SYSU-MM01 datasets have shown that our proposed method can improve the VT-ReID performance significantly and achieve state-of-the-art performance. [ABSTRACT FROM AUTHOR]

A new method for the stability assessment of inverter-based microgrids is presented in this paper. Directly determining stability boundaries by searching the multidimensional space of inverters’ droop gains is a computationally prohibitive task. Instead, we build a certified stability region by utilizing a generalized Laplacian matrix eigenvalues, which are a measure of proximity to stability boundary. We establish an upper threshold for the eigenvalues that determines the stability boundary of the entire system and demonstrate that this value depends only on the network’s R/X ratio but does not depend on the grid topology. We also provide a conservative upper threshold of the eigenvalues that are universal for any systems within a reasonable range of R/X ratios. We then construct approximate certified stability regions representing convex sets in the multidimensional space of droop gains that could be utilized for gains optimization. We show how the certified stability region can be maximized by properly choosing droop gains, and we provide closed-form analytic expressions for the certified stability regions. The computational complexity of our method is almost independent of the number of inverters. The proposed methodology has been tested using IEEE 123 node test system with 10 inverters. [ABSTRACT FROM AUTHOR]

Unsupervised person re-identification (re-ID) has attracted increasing research interests because of its scalability and possibility for real-world applications. State-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy, which generates pseudo labels by clustering and maintains a memory to store instance features and represent the centroid of the clusters for contrastive learning. This approach suffers two problems. First, the centroid generated by unsupervised learning may not be a perfect prototype. Forcing images to get closer to the centroid emphasizes the result of clustering, which could accumulate clustering errors during iterations. Second, previous instance memory based methods utilize features updated at different training iterations to represent one centroid, these features are inconsistent due to the change of encoder. To this end, we propose an unsupervised re-ID approach with a stochastic learning strategy. Specifically, we adopt a stochastic updated memory, where a random instance from a cluster is used to update the cluster-level memory for contrastive learning. In this way, the relationship between randomly selected pair of images are learned to avoid the training bias caused by unreliable pseudo labels. By picking a sole last seen sample to directly update each cluster center, the stochastic memory is also always up-to-date for classifying to keep the consistency. Besides, to relieve the issue of camera variance, a unified distance matrix is proposed during clustering, where the distance bias from different camera domains is reduced and the variances of identities are emphasized. Our proposed method outperforms the state-of-the-arts in all the common unsupervised and UDA re-ID tasks. The code will be available at https://github.com/lithium770/Unsupervised-Person-re-ID-with-Stochastic-Training-Strategy. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation (UDA) for person re-identification is challenging because of the huge gap between the source and target domain. A typical self-training method is to use pseudo-labels generated by clustering algorithms to iteratively optimize the model on the target domain. However, a drawback to this is that noisy pseudo-labels generally cause trouble in learning. To address this problem, a mutual learning method by dual networks has been developed to produce reliable soft labels. However, as the two neural networks gradually converge, their complementarity is weakened and they likely become biased towards the same kind of noise. This paper proposes a novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels. Specifically, we first introduce a parameter-free module, the WaveBlock, which creates a difference between features learned by two networks by waving blocks of feature maps differently. Then, an attention mechanism is leveraged to enlarge the difference created and discover more complementary features. Furthermore, two kinds of combination strategies, i.e. pre-attention and post-attention, are explored. Experiments demonstrate that the proposed method achieves state-of-the-art performance with significant improvements on multiple UDA person re-identification tasks. We also prove the generality of the proposed method by applying it to vehicle re-identification and image classification tasks. Our codes and models are available at: AWB. [ABSTRACT FROM AUTHOR]

Gesture recognition is the central enabler of human-computer interaction (HCI). In addition to the semantic information contained in gestures, gesture-based user identification can effortlessly enhance HCI system security. Recently, the Wi-Fi-integrated sensing and communication (ISAC) technology has shown great potential in a field hitherto occupied by computer vision and radar sensing. In this work, leveraging Wi-Fi sensing, we propose a system called WiGesID that achieves joint gesture recognition and human identification (JGRHI). The basic idea behind WiGesID is to identify personalized spatiotemporal dynamic patterns from the gestures of different users. Moreover, we develop an effective approach to recognize new categories of gestures and users by computing relation scores between the features of the new category samples and the support samples. To evaluate the performance, we implemented WiGesID and conducted extensive experiments. The results demonstrate that our system outperforms the state-of-the-art method for cross-domain sensing and accurately recognizes new categories, which promotes the use of this application of Wi-Fi sensing in HCI. [ABSTRACT FROM AUTHOR]

Capturing long-range dependencies during feature extraction is crucial for video-based person re-identification (re-id) since it would help to tackle many challenging problems such as occlusion and dramatic pose variation. Moreover, capturing subtle differences, such as bags and glasses, is indispensable to distinguish similar pedestrians. In this paper, we propose a novel and efficacious Statistic Attention (SA) block which can capture both the long-range dependencies and subtle differences. SA block leverages high-order statistics of feature maps, which contain both long-range and high-order information. By modeling relations with these statistics, SA block can explicitly capture long-range dependencies with less time complexity. In addition, high-order statistics usually concentrate on details of feature maps and can perceive the subtle differences between pedestrians. In this way, SA block is capable of discriminating pedestrians with subtle differences. Furthermore, this lightweight block can be conveniently inserted into existing deep neural networks at any depth to form Statistic Attention Network (SANet). To evaluate its performance, we conduct extensive experiments on two challenging video re-id datasets, showing that our SANet outperforms the state-of-the-art methods. Furthermore, to show the generalizability of SANet, we evaluate it on three image re-id datasets and two more general image classification datasets, including ImageNet. The source code is available at http://vipl.ict.ac.cn/resources/codes/code/SANet_code.zip. [ABSTRACT FROM AUTHOR]

In a photovoltaic (PV) DC integration system, a DC line-to-line short-circuit fault will cause all converters to be quickly locked. This can result in the sustained outage of the system. In this study, to address this problem, a protection method based on incipient fault identification is proposed to quickly identify and isolate the faulty branch, and to prevent the incipient fault from developing into a short-circuit fault. By analyzing the frequency characteristics of the incipient fault current, a disturbance injection start criterion is formed. Then, by using the converter to inject small disturbance signals to form obvious fault characteristics, the location and isolation of the faulty area can be achieved in time. The loop simulation results based on real-time digital simulator (RTDS) hardware demonstrate that the proposed method accurately recognizes the incipient fault without affecting the system power quality, and can simultaneously isolate the incipient fault. These factors provide guarantees for the safe and efficient operation of PV DC integration systems. [ABSTRACT FROM AUTHOR]

The Non-local self-attention mechanism can significantly improve the capability of feature representation with long-range dependencies at the cost of high computational complexity. To address the issue, the self-attention-based autoregressive axial transformer has been proposed to apply attention along a single axis of the feature maps instead of the whole ones with large receptive fields. It performs axial-attention twice along the height- and width-axis respectively in the spatial dimension of the feature maps for the image data. However, there is still room for improvement. We can convert the 2D spatial feature map into a 1D feature sequence and just perform axial-attention once along it to save more computing resources. Motivated by the insight, we propose an Efficient Axial-Attention Network (EAAN) for video-based person re-identification (Re-ID) to reduce computation and improve accuracy by serializing feature maps with multi-granularity and reducing the number of axial-attention runs. We also introduce a deserialization approach that can restore the shape of the feature maps. Moreover, we expand the CTN (Channel Transformer Network) to a wider range of uses. Additionally, we verify that the serialized feature sequence can enhance expressiveness in our EAAN with lower complexity. Experiments on MARS and DukeMTMC-VideoReID (DukeV) datasets show outstanding performance in computation efficiency and accuracy. It not only outperforms the state-of-the-art method on MARS by 0.3% in both Rank-1 and mAP, and surpasses that on DukeV by 0.1% in Rank-1 with equal mAP, but also reduces parameters and GFLOPS (Giga Floating-point Operations Per Second) by 16.9% and 6.6% respectively compared to another axial-attention-based method. [ABSTRACT FROM AUTHOR]

Cough, a symptom associated with many prevalent respiratory diseases, can serve as a potential biomarker for diagnosis and disease progression. Consequently, the development of cough monitoring systems and, in particular, automatic cough detection algorithms have been studied since the early 2000s. Recently, there has been an increased focus on the efficiency of such algorithms, as implementation on consumer-centric devices such as smartphones would provide a scalable and affordable solution for monitoring cough with contact-free sensors. Current algorithms, however, are incapable of discerning between coughs of different individuals and, thus, cannot function reliably in situations where potentially multiple individuals have to be monitored in shared environments. Therefore, we propose a weakly supervised metric learning approach for cougher recognition based on smartphone audio recordings of coughs. Our approach involves a triplet network architecture, which employs convolutional neural networks (CNNs). The CNNs of the triplet network learn an embedding function, which maps Mel spectrograms of cough recordings to an embedding space where they are more easily distinguishable. Using audio recordings of nocturnal coughs from asthmatic patients captured with a smartphone, our approach achieved a mean accuracyof 88 $\%$ ($\pm$ 10 $\%$ SD) on two-way identification tests with 12 enrollment samples and accuracy of 80 $\%$ and an equal error rate (EER) of 20 $\%$ on verification tests. Furthermore, our approach outperformed human raters with regard to verification tests on average by 8% in accuracy, 4% in false acceptance rate (FAR), and 12% in false rejection rate (FRR). Our code and models are publicly available. [ABSTRACT FROM AUTHOR]

To improve the topology observability in power distribution networks (PDNs), a two-stage topology identification framework is proposed to recognize the mixed topologies in a large set of historical data and predict the real-time topology based on the nodal measurements. A split expectation-maximization (split-EM) method is proposed considering the measurement errors to deal with the topology identification problem on the historical batch data, in which the number of topology categories does not need to be given in advance. Based on the topology identification results of historical data, the number of topology categories is reduced. Then, feasible classifiers are trained using machine learning methods to predict the real-time topology efficiently. An error-correcting mechanism is proposed for the real-time identification involving the credibility analysis and the reidentification based on the Bayesian recursion model. Finally, via a practical example, the effectiveness of the proposed models is verified by efficiently identifying the PDN's topologies in both the historical batch data with mixed topologies and real-time measurements. In addition, the partition-based extension application solution of the topology identification models for large-scale PDNs is proposed without extra measurements to relieve the calculation burden and reduce the identification time notably while maintaining the accuracy as the non-partitioned scheme. [ABSTRACT FROM AUTHOR]