Search

Safety-critical systems such as Advanced Driving Assistance Systems and Autonomous Vehicles require redundancy to satisfy their safety requirements and to be classified as fail-operational. Introducing redundancy in a system with high data rates and processing requirements also has a great impact on architectural design decisions. The current self-driving vehicle prototypes do not use a standardized system architecture but base their design on existing vehicles and the available components. In this work, we provide a novel analysis framework that allows us to qualitatively and quantitatively evaluate an in-vehicle architecture topology and compare it with others.With this framework, we evaluate different variants of two common topologies: domain and zone-based architectures. Each topology is evaluated in terms of total cost, failure probability, total communication cable length, communication load distribution, and functional load distribution.We introduce redundancy in selected parts of the systems using our automated process provided in the framework, in a safety-oriented design process that enables the ISO26262 Automotive Safety Integrity Level decomposition technique. After every design step, the architecture is re-evaluated. The advantages and disadvantages of the different architecture variants are evaluated to guide the designer towards the choice of correct architecture, with a focus on the introduction of redundancy.

Information-Centric Networking (ICN) architecture leverages the network of caches’ idea to bring content closer to consumers to ultimately reduce the load on content servers and prevent unnecessary packet re-transmissions. Nevertheless, the performance of existing cache management schemes mainly developed for a single cache is inadequate for a network of caches. There are many factors such as data dependencies, data redundancy, the limited size of caches, poor replacement policies, and many other factors that negatively impact a network of caches. Besides, traffic correlation among different caches on the network influences the performance of the network of caches. One of the essential correlations is the edge filtering effect. In the presence of data redundancy, the edge filtering effect even becomes more severe. The cache filtering effect happens when all arriving requests inspect the first cache for data. Therefore, the subsequent caches in the network receive only those requests that could not find data (cache-miss) from the edge cache. In this paper, we propose Frozen-cache to mitigate the filtering effect. This policy repeatedly freezes content in a cache to allow subsequent caches to receive popular content. A lightweight coordinated scheme incorporated with Frozen-cache policy to cope with the data redundancy problem. Based on our experiments obtained from realistic scenarios, the Frozen-cache idea highly outperforms state of the art caching schemes. Depending on the network setup, this superiority varies from 25% to 700%.

Crowd labeling, as a new paradigm of labeling classification problems, has enabled it to create a tremendous amount of high-quality labeling datasets by harnessing extensive ordinary human comprehension at a low cost. However, existing works mainly focus on a single label scene(one instance is only associated with a single label or a category). They do not fit some real applications well where one instance can associate with multiple labels and different categories can have different budget limits. In this paper, we find that the issue can be addressed by introducing $K$ -submodlar function, which has received extensive attention recently. Moreover, we further propose a $K$ -submodlar function based incentive mechanism for crowd multi-labeling scene, satisfying the truthfulness, individual rationality, computational efficiency. Extensive simulations validate the theoretical properties of our mechanism.

Supervised learning methods have been used to calculate the stereo matching cost in a lot of literature. These methods need to learn parameters from public datasets with ground truth disparity maps. Due to the heavy workload used to label the ground truth disparities, the available training data are limited, making it difficult to apply these supervised learning methods to practical applications. The two-branch convolutional sparse representation (TCSR) model is proposed in the paper. It learns the convolutional filter bank from stereo image pairs in an unsupervised manner, which reduces the redundancy of the convolution kernels. Based on the TCSR model, an unsupervised stereo matching cost (USMC), which does not rely on the truth ground disparity maps, is designed. A feasible iterative algorithm for the TCSR model is also given and its convergence is proven. Experimental results on four popular data sets and one monocular video clip show that the USMC has higher accuracy and good generalization performance.

Hypertension is a global challenge to the public health which can easily lead to life-threatening vascular diseases unless control measures are adopted. Considering the prevalence of vascular diseases and their fatality, early detection of high-risk patients is an important problem in the present world. Heart rate variability (HRV) analysis can be an effective prognostic tool to identify the characteristics of vulnerable patients, considering its reliability in predicting sudden cardiac deaths. However, challenge lies in identifying tenuous differences in HRV between the low-risk and high-risk patients at the early stage. With this motivation, we propose a hybrid approach based on dual-tree complex wavelet packet transform (DTCWPT) and linear time domain as well as nonlinear analysis of HRV signal to extract multitudinous features. A key issue before the HRV analysis of such patients is the presence of marked amount of ectopic beats, which is addressed by using time-varying auto regressive (TVAR) technique. The features extracted from TVAR edited HRV signals are shortlisted by minimum redundancy maximum relevance algorithm for an efficient classifier modeling. Furthermore in this study, we propose to use cost-sensitive RUSBoost (CS-RUSBoost) algorithm for handling the class imbalance problem of the data. A comparative performance evaluation of CS-RUSBoost with RUSBoost, SMOTEBoost, asymmetric AdaBoost algorithm shows a superior result by CS-RUSBoost with G-mean of 0.9352 and F1 score of 0.9347.

The quad tilt rotor (QTR) has the problem of manipulation redundancy due to the helicopter and fixed-wing manipulation mechanisms. Solving the problem of manipulation redundancy and develop an effective manipulation strategy is critical for QTR during conversion flight. A novel manipulation strategy based on states of QTR is proposed in this paper to solve the problem of manipulation redundancy in conversion mode. The longitude is controlled by the tilt angle of nacelle in helicopter mode and the course is controlled by the speed error of propellers in fixed-wing mode. The Active Disturbance Rejection Control (ADRC) is adopt into the flight control law, which can observe and compensate for internal and external disturbance. The simulation and flight test are carried out to verify the proposed manipulation strategy and the results show that the proposed manipulation strategy is effective and reasonable.

In order to overcome the extremely time-consuming drawback of deep learning (DL), broad learning system (BLS) was proposed as an alternative method. This model is simple, fast, and easy to update. To ensure the fitting and generalization ability of BLS, the hidden layer neurons are often set too many, in fact, a lot of neurons are not needed. Greedy BLS (GBLS) is proposed in this paper to deal with the redundancy of the hidden layer in BLS from another perspective. Different from BLS, the structure of GBLS can be seen as a combination of unsupervised multi-layer feature representation and supervised classification or regression. It trains with a greedy learning scheme, performs principal component analysis (PCA) on the previous hidden layer to form a set of compressed nodes, which are transformed into enhancement nodes and then activated by nonlinear functions. The new hidden layer is composed of all newly generated compressed nodes and enhancement nodes, and so on. The last hidden layer of the network contains the higher-order and abstract essential features of the original data, which is connected to the output layer. Each time a new layer is added to the model, and there is no need to retrain from the beginning, only the previous layer is trained. Experimental results demonstrate that the proposed GBLS model outperforms BLS both in classification and regression.

The onboard traction transformer is a critical equipment of high-speed trains, its running state directly affects the safety and stability of a train’s operation. Given the complexity of the running condition of the onboard traction transformer, this paper proposes a running state diagnosis algorithm based on kernel principal component analysis (KPCA) and fuzzy clustering. To fully extract the status information of the onboard traction transformer, the aging characteristics of insulating oil and main insulation are analyzed under different running mileage as the first step. Thereby, to eliminate the signal redundancy, the status feature set of the onboard traction transformer is analyzed by KPCA combined with the characteristic quantities of the traditional dissolved gas analysis (DGA), and the eigenvalues with the contribution rate of over 95% are used as new eigenvectors. Finally, a status diagnosis model is established by using fuzzy clustering analysis, considering the limitations of fault data of onboard traction transformer. The results from field collected data show that the proposed method is effective in diagnosing the running status of the onboard traction transformer.

Named Data Networking (NDN) has been recognized as a lever to the Internet of Things (IoT). One of the most founding features of NDN is in-network caching to improve data availability and reduce retrieval delays and network load. Despite the existence of several caching decision algorithms, the fetching and distribution of contents with minimum resource utilization remains a great challenge. In this article, we propose an efficient caching technique named PoolCache that augments the effective caching capacity of some defined conglomerates of nodes. This is accomplished by pooling the various caches and manage them in a way to insure zero content redundancy within any defined node conglomerate. The resulting high diversity of cached contents throughout the network tacitly amounts to much better overall performances. We conducted extensive simulations using the CCNsim simulator to evaluate the performance of PoolCache and compare it to that of some well known caching strategies. Simulations using a large Transit Stub topology show that PoolCache clearly outperforms the other caching strategies in terms of a much greater content diversity and consequently a limited number of content evictions, a much better cache hit ratio, and a much lower content retrieval delay. Simulations also showed that PoolCache benefits from any eventual content popularity.

Intra prediction is the key technology to reduce spatial redundancy in the modern video coding standard. Recently, deep learning based methods that directly generate the intra prediction by neural network achieve superior performance than traditional directional based intra prediction. However, these methods lack the ability to handle complex blocks which contain mixed directional textures or recurrent patterns since they only use the neighboring reference samples of the current one. The other intermediate information denoted as reference priors in this paper generated during the coding process is not exploited. In this paper, a Current Frame Priors assisted Neural Network (CFPNN) is presented to improve the intra prediction efficiency. Specifically, we utilize the local contextual information provided by the neighboring multiple references as the primary inference source. In addition to the neighboring references, we additionally use the other two reference priors within the current frame – the predictor searched by intra block copy (IntraBC) and the corresponding residual component. The IntraBC predictor provides useful nonlocal information to help generate more accurate prediction for complex blocks together with neighboring local information. While the residual component contains unique information that reflects the characteristics of the block to some extent is utilized to reduce the noise contained in the reconstructed reference samples. Moreover, we investigate the best way to integrate the proposed method into the codec. Experimental results demonstrate that compared to HEVC, our proposed CFPNN achieves an average of 4.1% BD-rate reduction for the luma component under the All Intra configuration.

Reliability is one of the major concerns of Time Sensitive Networking (TSN). Current systems mostly rely on static redundancy to protect functionality from permanent component failures. This greatly increases the cost of Time-Triggered (TT) flows. Instead, Software Defined Networking (SDN) enables dynamic redundancy. Disrupted traffic can be rerouted by a centralized controller to reduce the cost while maintaining reliability. This paper presents an approach to compute alternative paths at run-time and analyze their impact on reliability. We define a novel three-mode recovery scheme, which includes full functionality, reduced functionality, and emergency halt modes. Run-time recovery for TT flows is explored using Integer Linear Programming (ILP) and a heuristic algorithm. Then, a Markov chain-based design-time reliability analysis is developed to evaluate the Mean Time to Reduced Functionality Mode (MTTRF) and Mean Time to Failure (MTTF) of run-time recoverable systems. Our experiments show that run-time recovery provides better protection against multi-point failures than static redundancy. Compared with the state of the art, our proposed ILP has better routing efficiency. The proposed heuristic algorithm can perform routing and scheduling in polynomial time, but it tends to route multicast flows to longer paths than ILP. Furthermore, when applied to realistic recovery scenarios, our proposed ILP improves the MTTF by up to $2\times $ and the average execution time by up to $20\times $ than the raw ILP of the state of the art. Although less efficient with multicast flows, the heuristic algorithm achieves similar reliability as the ILP, and its worst-case recovery time is below $100ms$ on an embedded ARM processor.

Moldy peanuts are often found in harvested and stored peanuts. Aflatoxins in moldy peanuts pose a potential risk to food safety. Hyperspectral imaging techniques is often used for rapid nondestructive testing of food. However, the information redundancy of hyperspectral data has a negative effect on the processing speed and classification accuracy. In this study, a novel band selection method, namely the band influence algorithm (BIA), was proposed to extract key features and remove redundancy for the classification of moldy peanuts. Firstly, hyperspectral images of moldy, healthy and damaged peanuts were collected with 128 bands ranging from 400 nm to 1000nm. Secondly, the BIA method was used to extract feature bands according to the influence of each band subset on the accuracy of the classification model. The effectiveness of BIA method was compared with five representative band selection methods on four classification models: decision tree (DT), k-nearest neighbor (KNN), support vector machine (SVM), and ShuffleNet V2. The experimental results show that the BIA method performs superior effect and stability than other methods on all classification models. The integration of BIA and ShuffleNet V2 achieved the best classification effect. Especially when using 10 feature bands on ShuffleNet V2, the average accuracy, F1 score, and kappa coefficient of BIA reached 97.66%, 0.977, and 0.963 respectively.

With the proliferation of frequency-using devices and the advent of the era of big data, spectrum management and control are faced with challenges of effectiveness and accuracy. Modulation classification technology is the foundation and key part of spectrum management and control. Therefore, the effectiveness of modulation classification technology in big data scenario is very important. In this paper, we consider not only the validity of the classification model under the background of big data, but also the dynamics of noise in the complex electromagnetic environment. So we construct a big dataset containing different signals under different MSNR, and use the big data to drive the deep learning model, and finally get the classification result. The proposed method can realize modulation classification only by training one model, which avoids the redundancy of model training in previous algorithms. The simulation results demonstrate the effectiveness and reliability of the proposed method.

An aircraft is made up of a number of complicated systems which work in harmony to ensure safe and trouble-free flight. In order to maintain such a platform, many diagnostic and prognostic techniques have been suggested, mostly aimed at components but some at the system level. Together these form a patchwork approach to the overall problem of efficiently informing aircraft maintenance to the Original Equipment Manufacturers, the operators /airlines, and the Maintenance, Repair, and Overhaul organisations. It involves these organisations having to support several different approaches to aircraft health management, and is therefore inefficient and costly. In the current work, a streamlined methodology is put forward. This is based on OSA-CBM (Open System Architecture for Condition Based Maintenance) and can be applied to any aircraft system. Integral with this is the use of mRMR (minimum redundancy maximum relevance) for feature selection, the resulting symptom vector being used for fault diagnosis. This approach is demonstrated on three test cases: the engine, the environmental control system, and the fuel system. In each case, the digital twin setup, simulation conditions for healthy and faulty scenarios, a methodology based on OSA-CBM up to diagnostics are detailed. Diagnostics is carried out for each system in turn, using four machine learning supervised algorithms. The best performing algorithm for each system will then subsequently be used in a vehicle level reasoner called FAVER (A Framework for Aerospace Vehicle Reasoning), which requires these system diagnoses as a starting point for vehicle reasoning and fault ambiguity resolution.

Towards tackling the phenomenon of textual information overload that is exponentially pumping with redundancy over the Internet, this paper investigates a solution depending on the Automatic Text Summarization (ATS) method. The idea of ATS is to assist, e.g., online readers, in getting a simplified version of texts for preserving their time/effort required to skim a given large body of text. However, ATS is deemed as one of the most complex NLP applications, particularly for the Arabic language that has not been intelligently developed like the other Indo-European languages. Thus, we present an extractive-based summarizer (ArDBertSum) for text written in Arabic, relying on the DistilBERT model. Besides, we propose a domain-specific sentence-clauses segmentater (SCSAR) to support our ArDBertSum in further shortening long/complex sentences. The results of our experiments illustrate that our ArDBertSum yields the best performance, compared with non-heuristic Arabic summarizers, in producing an acceptable quality of candidate summaries. These experiments have been conducted on EASC-dataset (along with our proposed dataset) to report on (1) a statistical evaluation utilizing ROUGE metrics and (2) a specific human-based evaluation. The human evaluation results revealed promising perceptions; however, further works are needed to ameliorate the coherence and punctuation of the automatic summaries.

Audio steganography aims to exploit the human auditory redundancy to embed the secret message into cover audio, without raising suspicion when hearing it. However, recent studies have shown that the existing audio steganography can be easily exposed with the deep learning based steganalyzers by extracting high-dimensional features of stego audio for classification. The existing GAN-based steganography approaches mainly studied in images cover, less work is conducted on audio cover. In addition, though a few GAN-based audio steganography methods have been proposed, they still have room for improvements in perceptual quality and undetectability. In this work, we propose an audio steganography framework that could automatically learn to generate superior steganographic cover audio for message embedding. Specifically, the training framework of the proposed framework consists of three components, namely, generator, discriminator and trained deep learning based steganalyzer. Then the traditional message embedding algorithm LSBM, is employed to embed the secret message into the steganographic cover audio to obtain stego audio, which is delivered to the trained steganalyzer for misclassifying as cover audio. Once the adversarial training is completed among these three parties, one can obtain a well-trained generator, which could generate steganographic cover audio for subsequent message embedding. In the practice of our proposed method, the stego audio is produced by embedding the secret message into the steganographic cover audio using a traditional steganography method. Experimental results demonstrate that our proposed audio steganography can yield steganographic cover audio that preserves a quite high perception quality for message embedding. We have compared the detection accuracies with the existing audio steganography schemes as presented in our experiment, the proposed method exhibits lower detection accuracies against the state-of-the-art deep learning based steganalyzers, under various embedding rates. Codes are publicly available at https://github.com/Chenlang2018/Audio-Steganography-using-GAN.

To overcome the problems of coverage blind areas and coverage redundancy when sensor nodes are deployed randomly in heterogeneous wireless sensor networks (HWSNs). An optimal coverage method for HWSNs based on an improved social spider optimization (SSO) algorithm is proposed, which can reduce the energy consumption and improve the network coverage. First, a mathematical model of HWSN coverage is established, which is a complex combinatorial optimization problem. To improve the global convergence speed of the proposed algorithm, a chaotic initialization method is used to generate the initial population. In addition, the SSO algorithm has a poor convergence speed and search ability, which is enhanced by improving the neighborhood search, global search, and matching radius. In the iterative optimization process, the optimal solution is ultimately obtained by simulating the movement law of the spider colony, i.e., according to the cooperation, mutual attraction, and mating process of female and male spiders. An improved SSO algorithm based on chaos, namely the CSSO algorithm, is proposed to apply to the optimal deployment of sensory nodes in HWSNs. On this basis, the optimization goals are to improve the network coverage and reduce network costs. The optimal deployment plan of nodes is searched via the proposed CSSO algorithm, which effectively prevents coverage blind spots and coverage redundancy in the network.

Compared to the injection of a transient fault, time synchronization and accuracy are not required for the injection process of a persistent fault. However, the known persistent fault analyses (PFAs) do not work on SM4 implementations because the linear transformation layer hides the position where an error occurs during the encryption process. We present the first persistent fault analysis against SM4 implemented with an S-box by combining the inverse linear transformation with differential techniques. In addition, we propose a locating algorithm to figure out not only where an error occurs during the encryption process but also where a fault is inserted in the lookup table. Consequently, the locating algorithm helps break SM4 implemented with a T-table. We validate our PFA on two open-source implementations of SM4 – Crypto++(v8.3) and GMSSL(v1.0.0). The experiments are performed on a PC and the analysis codes are written in C language. The experimental data shows that the probability of successfully recovering the encryption key approximates 1 when the number of normal-and-faulty-ciphertext pairs is 3000 on average. Namely, PFA can break the encryption system of SM4 in practice once valid faults are inserted. Finally, we apply the attack to protected SM4 implementations and prove that the E-and-D mode of the dual modular temporal redundancy (DMTR) can defeat our PFA.

A fast Coding Unit (CU) partition decision strategy based on Human Visual System (HVS) perception quality is proposed in this paper. Considering that it is difficult for existing fast algorithms to further improve compression efficiency, perceptual coding technology has been tried to remove visual redundancy for achieving the purpose of reducing the bit rate on the basis of maintaining subjective visual quality. However, the existing perceptual coding model is still insufficient to reflect the characteristics of the HVS, which has limited improvement in coding efficiency, especially in fast algorithms. In this method, the characteristics of the limited human capacity for spatial-temporal resolution and the visual sensory memory are used to improve coding performance. First, the color complexity is used as a control factor to optimize the Just Noticeable Difference (JND) model to remove visual redundancy in a way that is more in line with the characteristics of visual perception. Second, a classification model of motion patterns based on human visual saliency is designed to provide a basis for CU classification, which effectively improves the coding accuracy. Finally, an offline Decision Tree (DT) classifier is designed based on the above model, and texture features are incorporated into the classifier as another key attribute to further reduce the computational complexity. The results of performance evaluation confirm that the proposed method achieves significantly improved coding performance compared with original Versatile Test Model (VTM). Compared with existing algorithms, our method not only improves coding efficiency, but also improves subjective visual quality.

Existing methods in predicting short-term photovoltaic (PV) power have low accuracy and cannot satisfy actual demand. Thus, a prediction model based on similar days and seagull optimization algorithm (SOA) is proposed to optimize a deep belief network (DBN). Fast correlation-based filter (FCBF) method is used to select a meteorological feature set with the best correlation with PV output and avoid redundancy among meteorological factors affecting PV output. In addition, a comprehensive similarity index combining European distance and gray correlation degree is proposed to select the similar day. Then, SOA is used to optimize the number of neurons and the learning rate parameters in DBN. Based on the nonuniform mutation and opposition-based learning method, an improved seagull optimization algorithm (ISOA) with higher optimization accuracy is proposed. Finally, the ISOA-DBN prediction model is established, and the experimental analysis is conducted using the actual data of PV power stations in Australia. Results show that compared with DBN, support vector machine (SVM), extreme learning machine (ELM), radial basis function (RBF), Elman, and back propagation (BP), the mean absolute percentage error indicator of ISOA-DBN is only 1.512% on a sunny day, 5.975 on a rainy day, 3.359 on a cloudy to sunny day, and 1.911% on a sunny to cloudy day. Therefore, the good accuracy of the proposed model is verified.

Humans learn adaptively and efficiently throughout their lives. However, incrementally learning tasks causes artificial neural networks to overwrite relevant information learned about older tasks, resulting in 'Catastrophic Forgetting'. Efforts to overcome this phenomenon often utilize resources poorly, for instance, by growing the network architecture or needing to save parametric importance scores, or violate data privacy between tasks. To tackle this, we propose SPACE, an algorithm that enables a network to learn continually and efficiently by partitioning the learnt space into a Core space, that serves as the condensed knowledge base over previously learned tasks, and a Residual space, which is akin to a scratch space for learning the current task. After learning each task, the Residual is analyzed for redundancy, both within itself and with the learnt Core space. A minimal number of extra dimensions required to explain the current task are added to the Core space and the remaining Residual is freed up for learning the next task. We evaluate our algorithm on P-MNIST, CIFAR and a sequence of 8 different datasets, and achieve comparable accuracy to the state-of-the-art methods while overcoming catastrophic forgetting. Additionally, our algorithm is well suited for practical use. The partitioning algorithm analyzes all layers in one shot, ensuring scalability to deeper networks. Moreover, the analysis of dimensions translates to filter-level sparsity, and the structured nature of the resulting architecture gives us up to 5x improvement in energy efficiency during task inference over the current state-of-the-art., The first two authors contributed equally to this paper

Deep neural networks (DNNs) have been successfully deployed in widespread domains, including healthcare applications. DenseNet201 is a new DNN architecture used in healthcare systems (i.e., presence detection of the surgical tool). Specialized accelerators such as GPUs have been used to speed up the execution of DNNs. Nevertheless, GPUs are prone to transient effects and other reliability threats, which can impact DNN models’ reliability. Safety-critical systems, such as healthcare applications, must be highly reliable because minor errors might lead to severe injury or death. In this paper, we propose a selective mitigation technique that relies on in-depth analysis. First, we inject the DenseNet201 model implemented on a GPU via NVIDIA’s SASSIFI fault injector. Second, we perform a comprehensive analysis from the perspective of kernel and layer to identify the most vulnerable portions of the injected model. Finally, we validate our technique by applying it to the top-vulnerable kernels to selectively protect the only sensitive portions of the model to avoid unnecessary overheads. Our experiments demonstrate that our mitigation technique achieves a significant reduction in the percentage of errors that cause malfunction (errors that lead to misclassification) from 6.463% to 0.21%. Moreover, the performance overhead (the execution time) of our technique is compared with the well-known protection techniques: Algorithm-Based Fault Tolerance (ABFT), Double Modular Redundancy (DMR), and Triple Modular Redundancy (TMR). The proposed solution shows only 0.3035% overhead compared to these techniques while correcting up 84.8% of the SDC errors in DenseNet201, remarkably improving the healthcare domain’s model reliability.

As semiconductor technology scales, modern microprocessors are more vulnerable to transient faults. Software-level fault tolerance schemes are promising because they can improve reliability effectively without extra hardware. Redundant Multi-threading (RMT) uses off-the-shelf cores as redundancy to achieve error resilience. Latest software RMT fault-tolerance models do not effectively cope with transient faults occurring on multiple components during the application execution, resulting in a large number of silent data corruptions (SDC). To address this challenge, we propose FERNANDO, a software-level RMT runtime fault tolerance scheme which provides enhanced error detection and comprehensive error recovery by Triple-Modular Redundancy (TMR). On an ARM Cortex-A57 like simulated microprocessor, we performed probability model transient fault injection experiments in different components of all cores. The results demonstrate that, compared to the state-of-the-art technique, FERNANDO can reduce the SDC rate by about 86.67 percent and optimize the execution time overhead by about 19.64 percent.

Due to the popularity of short-range communications and the ultra-dense deployment of the Internet of Things (IoT), the occurrence of severe signal collision in crowded nodes is becoming increasingly critical. We propose a scheme called anti-collision voting based on Bluetooth low energy improvement for the ultra-dense edge, in which one topic can be identified and separated from the others to enable intensive voting. The scheme alleviates the exponential growth of advertising collisions and achieves efficient consensus between the devices and humans by localized the message advertising. The previous proposals focused on enhancing the hardware and optimizing the parameters to establish a connection for interaction. Considering the limitation of connective devices, our scheme adopts a novel advertising model in which the nodes can promptly exit the advertising state by actively responding. In addition, the scheme merges active responses into a group to notify the advertising nodes and randomly chooses a channel to reduce redundancy and save energy. The simulations demonstrate that the scheme can reduce the collisions by more than 90% and channel occupancy by half, while doubling the capacity and efficiently supporting intensive voting within edge networks.

As research into technology for autonomous vehicles becomes ever more intensive, the need for redundant system designs, as a solution for fail-operational functionality, has also increased. Redundant systems are those involved in maintaining normal operation even when one or more components fails. In particular, in electric power steering (EPS) systems, redundancy is achieved by applying dual-winding (DW), permanent magnet synchronous motors (PMSMs) and dual electronic control units (ECUs). In this study, the torque and efficiency of DW-PMSMs is analysed based on the manner in which the currents in each winding mechanism are combined. It was found that the PMSMs have maximum torque and efficiency when the current ratio was the same between DWs. A diagnostic strategy is proposed whereby the phase current ratio of dual lanes is not matched. The proposed diagnostic process includes the selection of the optimal fault threshold of the current difference between two ECUs and a method for distinguishing which of these was a failure for disagreement. In addition, depending on whether or not failure detection has occurred, a current compensation control method is proposed for reverting to normal operation or for failure operations. The dual-lane system was fabricated and the proposed solutions were experimentally verified.

In order to better characterize the performance degradation trend of rolling bearings, a new performance degradation evaluation method based on principal component analysis (PCA), phase space reconstruction (PSR) and kernel extreme learning machine (KELM), namely PAPRKM is proposed to evaluate the performance degradation of rolling bearings in this paper. In the PAPRKM method, the time-domain and frequency-domain features of the vibration signal are extracted to construct the high-dimension feature matrix. Then the PCA is used to reduce the dimension of the feature matrix in order to represent the running state and the declining trend of rolling bearings, so as to eliminate the redundancy and information conflict among these features. Nextly, the PSR is adopted to obtain more relevant information from the time series. By determining the delay time and embedding dimension, the time series are reconstructed to obtain a new performance degradation index, which is regarded as the input data to input into KELM, and the degradation trend prediction model is established to realize the performance degradation trend prediction. Finally, the actual vibration signals of rolling bearings are applied to prove the effectiveness of the PAPRKM. The obtained experimental results show that the PAPRKM method can effectively predict the performance degradation trend of rolling bearings. The predicted results are more accurate than the other compared methods.

The importance of image security in the field of medical imaging is challenging. Several research works have been conducted to secure medical healthcare images. Encryption, not risking loss of data, is the right solution for image confidentiality. Due to data size limitations, redundancy, and capacity, traditional encryption techniques cannot be applied directly to e-health data, especially when patient data are transferred over the open channels. Therefore, patients may lose the privacy of data contents since images are different from the text because of their two particular factors of loss of data and confidentiality. Researchers have identified such security threats and have proposed several image encryption techniques to mitigate the security problem. However, the study has found that the existing proposed techniques still face application-specific several security problems. Therefore, this paper presents an efficient, lightweight encryption algorithm to develop a secure image encryption technique for the healthcare industry. The proposed lightweight encryption technique employs two permutation techniques to secure medical images. The proposed technique is analyzed, evaluated, and then compared to conventionally encrypted ones in security and execution time. Numerous test images have been used to determine the performance of the proposed algorithm. Several experiments show that the proposed algorithm for image cryptosystems provides better efficiency than conventional techniques.

Advanced capacity and density of memory have resulted in an increase in the probability of memory faults. The in-memory Error Correction Code (ECC), which solves this problem, is a widely used technology to improve the yield of highly integrated memory. However, the use of in-memory ECC causes problems that have not been considered in memory repair algorithms. Redundancy analysis is effective for repairing memory with redundant memory and in-memory ECC. In this paper, an ECC-aware fast and reliable pattern matching redundancy analysis algorithm for memory using both spare memory and in-memory ECC is proposed. This algorithm simplifies large-scale fault groups using in-memory ECC and includes an early termination method that can determine whether a memory that cannot be repaired with line spares can be repaired considering in-memory ECC. Experimental results show that the proposed pattern matching redundancy analysis algorithm achieves a similar yield but 14.6% less RA time and 8.6 times higher reliability compared to the existing redundancy analysis algorithms.

Future generation Internet of Things (IoT) communication infrastructure is expected to pave the path for innovative applications like smart cities, smart grids, smart industries, and smart healthcare. To support these diverse applications, the communication protocols are required to be adaptive and intelligent. At the network layer, an efficient and lightweight algorithm known as trickle-timer is designed to perform the route updates and it utilizes control messages to share the updated route information between IoT nodes. Trickle-timer tends to generate higher control overhead ratio and achieves lower reliability. Therefore, this article aims to propose an RL-based Intelligent Adaptive Trickle-Timer Algorithm (RIATA). The proposed algorithm performs three-fold optimization of the trickle-timer algorithm. Firstly, the RIATA assigns higher probability to control message transmission to nodes that have received an inconsistent control message in the past intervals. Secondly, the RIATA utilizes RL to learn the optimal policy to transmit or suppress a control message in the current network environment. Lastly, the RIATA selects an adaptive redundancy constant value to avoid unnecessary transmissions of control messages. Simulation results show that RIATA outperforms the other state-of-the-art mechanisms in terms of reducing control overhead ratio by an average of 21%, decreasing the average total power consumption by 10%, and increasing the packet delivery ratio by 4% on an average.

A 12-bit 80 MS/s hybrid type analog-to-digital converter (ADC) for high sampling speed and low power applications is presented in this paper. It has a subranging architecture with a front end of 6-bit Flash ADC with five channels of 6-bit time interleaved synchronous Successive Approximation Register (SAR) ADC. The proposed architecture with a shared 6-bit Flash ADC and time interleaved SAR ADC provides a power and area efficient high speed ADC. The proposed Time-skew calibration is implemented to minimize the discrepancy between the output of Flash ADC and SAR ADC’s channels. To rectify the decision error of the Flash ADC and extract the time-skew information, 1-bit redundancy is included in the CDAC of the SAR conversion. The decision error between the Flash ADC and the SAR ADC is covered with designed redundancy and the mismatch between the ADCs is covered with the time-skew calibration. To reduce the offset mismatch between Flash and SAR ADC and within SAR ADCs, all comparators are calibrated to minimize their absolute offset by utilizing background offset calibration. The modified dynamic strong ARM comparator is used for flash ADC and dynamic latched comparator is used for SAR ADCs. For fine offset calibration and low power consumption, the comparator’s offset calibration circuit is implemented. To reduce the kickback noise and enhance the overall energy efficiency for fast operation of SAR ADCs, rail-to-rail dynamic latch comparator with modified adaptive power control (APC) is implemented. The proposed ADC structure has been implemented in 130 nm CMOS process. The ADC has an effective number of bit (ENOB) of 10.97 bits while consuming 7.08 mW current consumption from the 1.2 V supply voltage.

Modern Data Center Networks (DCNs) are commonly based on Clos topologies with a large number of equal-cost multiple paths to provide high bisection bandwidth. The existing Random Packet Spraying (RPS) scheme spreads each flow of packets to all available parallel paths in order to achieve good load balancing under symmetric topologies. However, under asymmetric topologies caused by traffic dynamics or link failures, RPS potentially suffers from serious out-of-order problem. Therefore, to avoid packet reordering, we propose a Coding-based Distributed Congestion-aware Packet Spraying mechanism called CDCPS. At the sender end, CDCPS encodes packets using forward error correction (FEC) technology and adaptively adjusts the coding redundancy according to the asymmetric degree of multiple equal-cost paths. To make full use of link bandwidth, CDCPS randomly spreads encoded packets to all available paths at the switches. The original packets can be recovered immediately once enough encoded packets from uncongested paths arrive at the receiver, even if some encoded packets are blocked on congested paths. The test results of NS2 simulation showed that CDCPS eliminates out-of-order packets completely and effectively reduces the average and $99^{th}$ flow completion time by up to 73% and 78% over the state-of-the-art load balancing scheme.

Feature selection is a critical step in the data preprocessing phase in the field of pattern recognition and machine learning. The core of feature selection is to analyze and quantify the relevance, irrelevance, and redundancy between features and class labels. While existing feature selection methods give multiple explanations for these relationships, they ignore the multi-value bias of class-independent features and the redundancy of class dependent features. Therefore, a feature selection method (Maximal independent classification information and minimal redundancy, MICIMR) is proposed in this paper. Firstly, the relevance and redundancy terms of class independent characteristics are calculated respectively based on the symmetric uncertainty coefficient. Secondly, it calculates the relevance and redundancy terms of class-dependent features according to the independent classification information criterion. Finally, the selection criteria for these two characteristics are combined. To verify the effectiveness of the MICIMR algorithm, five feature selection methods are compared with the MICIMR algorithm on fifteen real datasets. The experimental results demonstrate that the MICIMR algorithm outperforms the other feature selection algorithms in terms of redundancy rate as well as classification accuracy (Gmean_macro and F1_macro).

Fining effective and informative biomarker genes form microarray is very challenging. In order to develop an hybrid gene selection algorithm, numerous filter feature selection algorithms have been previously reported. This research paper aims to identify the filter method that will improve the performance of our previously proposed FF-SVM algorithm to find the minimum number of accurate genes that achieves high accuracy performance. Therefore, an experiment was conducted using four different filter methods: Maximum Relevance Minimum Redundancy (mRMR), Joint Mutual Information (JMI), F-score, and Double Input Symmetrical Relevance (DISR). This experiment was undertaken in two phases: the first phase was filter to SVM, to identify the minimum number of features (genes) which served to maximize the SVM classifier; the second phase was filter to FF-SVM, to ascertain the best suite filter method to our previously proposed FF-SVM algorithm. The result of this experiment would be the most suited filter method to the FF-SVM. In conclusion, we found that the f-score method outperformed other filter methods when combined with FF-SVM.

This study proposes a control method for the maneuvering control of an aircraft system equipped with a cable-driven gripper. The UAV chosen for the study is a hex-rotor due to its durability and redundancy. The reason for opting for the cable-driven robotic arm is because of its extended range as compared to a fixed robotic arm. The aircraft system also contains an Ultra HD camera which helps to locate and identify the target object. Since the UAV grabs the object, the extra weight introduces some instability in the system. To help stabilize the dynamic behavior of the gripper and reduce external wind disturbance, we need an effective and robust control mechanism. To tackle these issues, this paper designs a control method based on the Model Reference Adaptive Control with an integrator (MRACI) with reference dynamics like an observer. On one hand, first, verify the performance of the proposed controller using computer-based simulations. On the other hand, it also applies the designed method to hardware-based results. The simulations and experimental results show that the designed controller works as intended and the errors are within an acceptable range.

The distribution grid is undergoing profound changes nowadays, and state estimator has become an essential part in the control room to enable future smart grid. The newly deployed micro phase measurement units ( $\mu $ PMU) and advanced metering infrastructure (AMI) devices make the real-time state estimation possible for distribution system. Therefore, this paper studies the incorporation and process of the multi-source measurements and proposes a fast three-phase state estimation based on the hybrid measurements scheme. By the process of $\mu $ PMU measurements, pseudo voltage measurements are added, which significantly increases the estimation redundancy. For AMI measurements, the harmonic components model is used to overcome the asynchronicity problem. An improved sequential state estimation based on the changed measurements is proposed to enable a fast estimation. IEEE 13-node and 390-node systems are simulated to verify the efficacy and efficiency of the proposed method.

Recent discriminative trackers especially based on Correlation Filters (CFs) have shown dominant performance for visual tracking. This kind of trackers benefit from multi-resolution deep features a lot, taking the expressive power of deep Convolutional Neural Networks (CNN). However, distractors in complex scenarios, such as similar targets, occlusion, and deformation, lead to model drift. Meanwhile, learning deep features results in feature redundancy that the increasing number of learning parameters introduces the risk of over-fitting. In this paper, we propose a discriminative CFs based visual tracking method, called dimension adaption correlation filters (DACF). First, the framework adopts the multi-channel deep CNN features to obtain a discriminative sample appearance model, resisting the background clutters. Moreover, a dimension adaption operation is introduced to reduce relatively irrelevant parameters as possible, which tackles the issue of over-fitting and promotes the model effectively adapting to different tracking scenes. Furthermore, the DACF formulation optimization can be efficiently performed on the basis of implementing the alternating direction method of multipliers (ADMM). Extensive evaluations are conducted on benchmarks, including OTB2013, OTB2015, VOT2016, and UAV123. The experiments results show that our tracker gains remarkable performance. Especially, DACF obtains an AUC score of 0.698 on OTB2015.

In most of the existing work for activity recognition, 3D ConvNets show promising performance for learning spatiotemporal features of videos. However, most methods sample fixed-length frames from the original video, which are cropped to a fixed size and fed into the model for training. In this manner, two problems limit the model performance for recognition. First, the cropped video clips are incomplete or even distorted in appearance, resulting in a large gap between the feature representation and semantics of human activity. Second, the useful features of longer video frame sequences are weakened by the repeated stacking of 3D convolution over deep networks due to the limitations of GPU memory and computing ability. This article proposes a method based on a 3D backbone network for multi scale spatial feature representation, which uses a pyramid pooling layer to allow the input of video frames at different scales, and then aggregates short-term spatial–temporal features into a long-term video-level representation. Objection detection is used as a component of model testing to explore the improvement of activity recognition considering the large amount of space–time redundancy in real life videos. An experiment is performed on the principal video dataset, UCF101, and the proposed method presents a competitive performance.

Reliability block diagram (RBD) is a well-known, high-level abstract modeling method for calculating systems reliability. Increasing redundancy is the most important way for increasing Fault-tolerance and reliability of dependable systems. K-out-of-N (KooN) is one of the known redundancy models. The redundancy causes repeated events and increases the complexity of the computing system’s reliability, and researchers use techniques like factorization to overcome it. Current methods lead to the cumbersome formula that needs a lot of simplification to change in the form of Sum of the Products (SoP) in terms of reliabilities of its constituting components. In This paper, a technique for extracting simple formula for calculating the KooN system’s reliability in SoP form using the Venn diagram is presented. Then, the shortcoming of using the Venn diagram that is masking some joints events in the case of a large number of independent components is explained. We proposed the replacement of Lattice instead of Venn diagrams to overcome this weakness. Then, the Lattice of reliabilities that is dual of power set Lattice of components is introduced. Using the basic properties of Lattice of reliabilities and their inclusion relationships, we propose an algorithm for driving a general formula of the KooN system’s reliability in SoP form. The proposed algorithm gives the SoP formula coefficients by computing elements of the main diagonal and elements below it in a squared matrix. The computational and space complexity of the proposed algorithm is $\theta (\left ({n-k }\right)^{2}/2)$ that $n$ is the number of different components and $k$ denotes the number of functioning components. A lemma and a theorem are defined and proved as a basis of the proposed general formula for computing coefficients of the SoP formula of the KooN system. Computational and space complexity of computing all of the coefficients of reliability formula of KooN system using this formula reduced to $\theta (n-k)$ . The proposed formula is simple and is in the form of SoP, and its computation is less error-prone.

Fault tolerant control systems can be used in the process machines such as Internal Combustion (IC) engines to achieve greater reliability and stability in the fault conditions. Thus, costly loss of production due to the unusual and unexpected shutdown of these machines can be avoided. The Air Fuel Ratio (AFR) control system is an important system in IC engines and faults in the sensors of this system will cause its shutdown creating costly production loss, therefore, fault tolerance is necessary for them. In this paper, an Active Fault Tolerant Control System (AFTCS) based on Artificial Neural Networks (ANN) has been proposed for the AFR control system of a Spark Ignition (SI) IC engine to increase its reliability. In the proposed AFTCS, a nonlinear ANN-based observer is used in the Fault Detection and Isolation (FDI) unit for the highly nonlinear sensors of the AFR system for analytical redundancy. The Lyapunov stability analysis has been utilized to design a stable system in normal and faulty conditions. The system has been implemented in MATLAB/Simulink environment to test its performance. The simulation experimental results demonstrate that the suggested system stays reliable maintaining the stability well in the fault conditions of sensors with little degradation in AFR. A comparison with the existing works demonstrates the superior performance of the proposed AFTCS for the highly nonlinear sensors of the AFR control system. The technique suggested is very effective in terms of fault robustness and is more specifically based on the nonlinear behavior of the MAP sensor compared to the existing works.

Multivariate time series (MTS) is a kind of matrix data, typically consisting of multiple variables measured at multiple time points. Due to the high dimensionality of MTS data, many methods for MTS classification have been proposed within the literature to reduce the redundancy in time or variable mode, but there is relatively little work on exploring the redundancy in both modes concurrently. In this paper we propose a new method for MTS classification based on bidirectional linear discriminant analysis (BLDA). The advantage is that BLDA can utilize label information in reducing the redundancy in time and variable modes simultaneously. Moreover, the existing procedures for BLDA suffer from two problems: (i) BLDA cannot be performed when one of the within-class matrices is singular; (ii) the computational burden could be very heavy when one of the data dimensionality is high. A new procedure for BLDA based on pseudo-inverse (PBLDA) and an efficient algorithm for PBLDA are proposed in this paper to overcome the two problems. The performance of our proposed method is illustrated through the experiments on a number of real MTS datasets.

Many complex systems in physics, biology and engineering are modeled as dynamical networks and described using multivariate time series analysis. Recent developments have shown that the emergent dynamics of a network system are significantly affected by interactions involving multiple network nodes which cannot be described using pairwise links. While these higher-order interactions can be probed using information-theoretic measures, a rigorous framework to describe them in the frequency domain is still lacking. This work presents an approach for the spectral decomposition of multivariate information measures, capable of identifying higher-order synergistic and redundant interactions between oscillatory processes. We show theoretically that synergy and redundancy can coexist at different frequencies among the output signals of a network system and can be detected only using the proposed spectral method. To demonstrate the broad applicability of the framework, we provide parametric and non-parametric data-efficient estimators for the spectral information measures, and employ them to describe multivariate interactions in three complex systems producing rich oscillatory dynamics, namely the human brain, a ring of electronic oscillators, and the global climate system. In these systems, we show that the use of our framework for the spectral decomposition of information measures reveals multivariate and higher-order interactions not detectable in the time domain. Our results are exemplary of how the frequency-specific analysis of multivariate dynamics can aid the implementation of assessment and control strategies in real-world network systems.

Effective intelligent fault diagnosis of rotating machinery using its vibrational signals has a considerable influence on certain analysis factors such as the reliability, performance, and productivity of a variety of modern manufacturing machines. Traditional intelligent approaches lack generalization schemes and add the burden of extracting features from data-driven cases. On the other hand, the Deep Learning (DL) studies have reported capabilities higher than the expectations of the researchers’ objectives. In this context, this paper proposes a new deep architecture based on Stacked Variant Autoencoders for multi-fault machinery identification with imbalanced samples. The proposed model starts with a Variational Autoencoder (VAE) for facilitating data augmentation of small and imbalanced data samples using Gaussian distribution. After the preparation of suitable samples based on quality and size, the preprocessed vibration signals obtained are injected into the deep framework. The proposed deep architecture contains two subsequent unsupervised Sparse Autoencoders (SAE) with a penalty term that helps in acquiring more abstract and essential features as well as avoiding redundancy. The output of the second SAE is integrated on a supervised Logistic Regression (LR) with 10 classes. This is utilized for the proposed classifier training to achieve accurate fault identification. Experimental results show the efficiency of the proposed model which achieved an accuracy of 93.2%. In addition, for extensive comparative analysis issue, the Generative Adversarial Network (GAN) and triNetwork Generative Adversarial Network (tnGAN) were both implemented on the vibrational signal data, where the proposed method reported better results in terms of training and testing time and overall accuracy.

The memory cell density and memory capacity have been increased for obtaining larger and faster memory. However, this threatens the memory reliability by increasing the probability of faulty cell generation. In this paper, a fast and small-area built-in redundancy analysis (RA) for the post-bond repair process in 3D memory is proposed. Spare line allocation is the structure for memory repair which the most widely used. However, the spare line structure that replaces the entire line which contains faults in each memory layer occurs inefficiency in repairing a small number of faults, including single faults, and it is difficult to share spares between layers. The proposed idea is to use spare line to repair line faults according to the characteristics of it, and to complement the structural limitations by proposing a new redundant spare. This is base common spare located on the base die, and it can be shared across all layers. The proposed BIRA improves the efficiency of spare lines with two complementary spare resource structures, achieving a short repair time and high repair rate. The proposed BIRA achieves 100% repair rate when there are at least 2 times more faults than the previous works with the same hardware overhead. In addition, it takes only at most 80% of the analysis time compared to the previous works, and as the number of faults increases, the analysis time reduction becomes greater compared to the previous works.

Advanced Television Systems Committee (ATSC) 3.0 is a more innovative standardization including Ultra High Definition (UHD) broadcasting and mobile High-Definition (HD) broadcasting. It also includes the deployment of a disaster information alarm function as well as the adoption of All-Internet Protocol (IP) based transmission in terrestrial broadcasting networks. Thus, ATSC enables additional technologies such as hybrid broadcasting services by interworking terrestrial broadcasting and internet networks for bidirectional customized services. In addition, there is a growing interest in wider viewing contents, which provide more immersive contents than existing UHD broadcasting mediums. Wider viewing contents can be acquired by using large field of view (FoV) lenses such as fish-eye lenses or by stitching several sub-images. The images captured by large FoV lenses have heavily curved surface distortions, while the distortion of the stitching-based wider viewing contents caused by the synthesizing process on overlapping regions is lower. Provision of wider viewing contents over the traditional broadcasting service has limitations in terms of bandwidth. However, they can be overcome by using hybrid broadcasting platforms such as ATSC 3.0, which transmits a video sequence over an RF channel and other viewing-angle video sequences through the Internet network, where signalling among those video sequences is required. Therefore, this paper proposes a hybrid broadcasting platform for transmitting multiple video sequences over broadcasting and Internet networks, and stitching them for wider viewing.

Fall detection has become a hot issue in the field of video surveillance recently. Different from most traditional vision-based methods relying on hand-crafted features, fall detection methods based on deep learning technology can automatically mine features to detect fall events due to the powerful ability of deep learning in data analysis, and hence have received much more attention in recent years. However, information loss has become a problem that cannot be ignored, especially for the neural networks with deep layers, because loss of information will affect representativeness of features and further influence the performance of fall detection. To solve the abovementioned problem, we propose a fall detection method based on dense block with a multi-channel convolutional fusion (MCCF) strategy. In this method, MCCF-DenseBlock, a densely connected network structure, is proposed to fully extract information with its densely connected layers, and to avoid network overloading by breaking dense connections appropriately, and especially to reduce data redundancy and numerous parameters in the network via the MCCF strategy fusing its grouped features. Besides, an improved transition layer is presented to further lessen data accumulation by using a multi-level downsampling structure. Experimental results demonstrate that, the proposed method can provide accurate fall detection results (satisfactory F-score of 0.973 on the UR Fall Dataset) and outperforms several state-of-the-art methods.

The two translational degrees-of-freedom (DOF) and one rotational DOF (2T1R) planar parallel mechanisms (PMs) have the characteristics of simple structures, simple kinematic and dynamic models, and ease of control and allow for a variety of application prospects. This paper concentrates on the derivations of the 5-DOF hybrid manipulators based on the synthesized mechanisms. To understand the effect of the constraint on the motion of a rigid body clearly, the method of reciprocal product between the wrench screw (constraint) and the twist screw (motion) is used and the relationships between the constraint and the motion of a rigid body are analyzed as well. The results are extended to the relationships between the limb constraint and the axes of limb joints. Then, limbs are divided into planar motion and spatial motion limbs in view of their motion characteristics, and some common limbs with constraint are listed. After that, based on the type synthesis method, a class of 2T1R planar PMs with common limbs is carried out. Meanwhile, some typical planar closed chains with two same limbs are obtained in the process of type synthesis. Finally, a 2T1R kinematically redundancy planar PM and two 2R1T spatial PMs are derived by making simple changes to the obtained mechanisms, and detailed derivations of three 5-DOF hybrid manipulators with the ability of processing spatial complex surface are given. Proved by the test parts, the accomplishment of deriving novel robot configurations with regard to expectant motion are quite valuable and practical.

A test pattern generator generates a pseudorandom test pattern that can be weighted to reduce the fault coverage in a built-in self-test. The objective of this paper is to propose a new weighted TPG for a scan-based BIST architecture. The motivation of this work is to generate efficient weighted patterns for enabling scan chains with reduced power consumption and area. Additionally, the pseudo-primary seed of TPG is maximized to obtain a considerable length in the weighted pseudorandom patterns. The maximum-length weighted patterns are executed by assigning separate weights to the specific scan chains using a weight-enabled clock. This approach reduces the hardware overhead and achieves a low power consumption of 26.7 nW. Moreover, the proposed weighted TPG is applied in two different test-per-scan BIST architectures and achieves accurate results. The weighted patterns are also generated with fewer switching transitions and higher fault coverages of 98.81% and 97.35% in two different BIST architectures. This process is observed with six other circuits under test as their scan chains. The simulation results are tested with a SilTerra $0.13~\mu \text{m}$ process on the Mentor Graphics IC design platform. Furthermore, the proposed weighted TPG is enlarged to a higher bit TPG, which is compared to accomplish the performance strategies. The experimental results of the proposed TPG design are compared and tabulated with existing potential TPG designs.

Feature selection plays a key role in many machine learning problems. Especially as an important data preprocessing method, robust and pragmatic feature selection methods can be applied to extract meaningful features and eliminate redundant ones. As we all known, many feature selection methods select features by using some certain feature evaluation criteria to obtain the corresponding score for every feature, such that we can select high score features. Unfortunately, correlated features usually connect with each other, which may result in large correlations between top ranked features, such that the redundancy among the selected features is brought about. To solve this problem, we introduce the redundancy matrix A in the AGRM (a novel auto-weighted feature selection framework via global redundancy minimization) framework. Meanwhile, we introduce the adaptive redundancy matrix S and treat the redundancy matrix S as an optimizing variable, rather than setting the redundant matrix S as a prior. In addition, we propose a robust algorithm to efficiently address the constrained optimization problem. Finally, extensive experiments on six datasets show the superiority of our proposed method.

In this study, an adaptive fuzzy-neural-network-imitating sliding-mode control (AFNNISMC) is developed for a parallel-inverter system in an islanded micro-grid (MG) via a master-slave current sharing strategy. For ensuring the system-level stability, an entire dynamic model is constructed by viewing the parallel-inverter system as a whole. First, a total sliding-mode control (TSMC) scheme, and the TSMC plus an adaptive observer to form an adaptive TSMC (ATSMC) framework are designed for the parallel-inverter system. Then, a four-layer fuzzy neural network (FNN) is investigated to imitate the TSMC law to improve the system robustness, overcome the drawback of the dependence on detailed system dynamics, and deal with the chattering phenomena caused by the TSMC. According to the Lyapunov stability theorem and the projection algorithm, network parameters in the FNN are regulated online by employing the approximation error between the FNN and the TSMC law to ensure the convergence of the network and the stability of the control system. Thereby, the performance of high power quality and high-precision current sharing between inverters can be guaranteed even if system uncertainties exist. Moreover, the proposed AFNNISMC system can achieve the seamless disconnection and re-connection of slave inverters from and into an energized parallel-inverter system, which improves the redundancy and operation flexibility. In addition, numerical simulations and experimental results are given to demonstrate the feasibility and effectiveness of the proposed AFNNISMC scheme. Furthermore, performance comparisons with the ATSMC strategy and a conventional proportional-integral control (PIC) framework are provided to verify the superiority of the proposed scheme.

This paper proposes an energy management system (EMS) architecture based on the Kubernetes container cluster to solve the problem of traditional EMSs being unable to simultaneously achieve high reliability and high resource utilization. Container cluster technology is used to encapsulate, isolate and deploy applications, which solves the problem of low system reliability caused by interlocking failures. Discrete Markov theory is applied to propose a dynamic Pod fault-tolerant EMS model. The results of the solution model are used to adjust the Pod redundancy in real-time to achieve the highest reliability to satisfy physical resource constraints. The results of the performance analysis show that the reliability of the proposed architecture is 99.9999504%. Compared with the EMS of the service-oriented architecture (SOA), the annual failure time is reduced from 3.83 minutes to 0.26 minutes. The comprehensive utilization of hardware resources increases by approximately 20%, and performance indicators such as the peak access success rate improve significantly. The proposed architecture is implemented in a real-power system, with good operating results and broad application prospects.