This paper presents an improved YOLOv3 network, named MSFF-YOLOv3, for precisely detecting variable surface defects of aluminum profiles in practice. First, we introduce a larger prediction scale to provide detailed information for small defect detection; second, we design an efficient attention-guided block to extract more features of defects with less overhead; third, we design a bottom-up pyramid and integrate it with the existing feature pyramid network to construct a twin-tower structure to improve the circulation and fusion of features of different layers. In addition, we employ the K-median algorithm for anchor clustering to speed up the network reasoning. Experimental results showed that the mean average precision of the proposed network MSFF-YOLOv3 is higher than all conventional networks for surface defect detection of aluminum profiles. Moreover, the number of frames processed per second for our proposed MSFF-YOLOv3 could meet real-time requirements.

Predicting the grasping point accurately and quickly is crucial for successful robotic manipulation. However, to commercially deploy a robot, such as a dishwasher robot in a commercial kitchen, we also need to consider the constraints of limited usable resources. We present a deep learning method to predict the grasp position when using a single suction gripper for picking up objects. The proposed method is based on a shallow network to enable lower training costs and efficient inference on limited resources. Costs are further reduced by collecting data in a custom-built synthetic environment. For evaluating the proposed method, we developed a system that models a commercial kitchen for a dishwasher robot to manipulate symmetric objects. We tested our method against a model-fitting method and an algorithm-based method in our developed commercial kitchen environment and found that a shallow network trained with only the synthetic data achieves high accuracy. We also demonstrate the practicality of using a shallow network in sequence with an object detector for ease of training, prediction speed, low computation cost, and easier debugging.

A method to predict lightning by machine learning analysis of atmospheric electric fields is proposed for the first time. In this study, we calculated an anomaly score with long short-term memory (LSTM), a recurrent neural network analysis method, using electric field data recorded every second on the ground. The threshold value of the anomaly score was defined, and a lightning alarm at the observation point was issued or canceled. Using this method, it was confirmed that 88.9% of lightning occurred while alarming. These results suggest that a lightning prediction system with an electric field sensor and machine learning can be developed in the future.

Although end-to-end based speech recognition research for Mandarin-English code-switching has attracted increasing interests, it remains challenging due to data scarcity. Meta-learning approach is popular with low-resource modeling using high-resource data, but it does not make full use of low-resource code-switching data. Therefore we propose a two-fold cross-validation training framework combined with meta-learning approach. Experiments on the SEAME corpus demonstrate the effects of our method.

The recurrent neural network (RNN) has been used in audio and speech processing, such as language translation and speech recognition. Although RNN-based architecture can be applied to speech synthesis, the long computing time is still the primary concern. This research proposes a fast gated recurrent neural network, a fast RNN-based architecture, for speech synthesis based on the minimal gated unit (MGU). Our architecture removes the unit state history from some equations in MGU. Our MGU-based architecture is about twice faster, with equally good sound quality than the other MGU-based architectures.

The integration of social networking concepts into the Internet of Things has led to the Social Internet of Things (SIoT) paradigm, and trust evaluation is essential to secure interaction in SIoT. In SIoT, when resource-constrained nodes respond to unexpected malicious services and malicious recommendations, the trust assessment is prone to be inaccurate, and the existing architecture has the risk of privacy leakage. An edge-cloud collaborative trust evaluation architecture in SIoT is proposed in this paper. Utilize the resource advantages of the cloud and the edge to complete the trust assessment task collaboratively. An evaluation algorithm of relationship closeness between nodes is designed to evaluate neighbor nodes' reliability in SIoT. A trust computing algorithm with enhanced sensitivity is proposed, considering the fluctuation of trust value and the conflict between trust indicators to enhance the sensitivity of identifying malicious behaviors. Simulation results show that compared with traditional methods, the proposed trust evaluation method can effectively improve the success rate of interaction and reduce the false detection rate when dealing with malicious services and malicious recommendations.

For the increasing demands of computation, heterogeneous multicore architecture is believed to be a promising solution to fulfill the edge computational requirement. In FPGAs, the heterogeneous multicore is realized as multiple soft processor cores with custom processing elements. Since FPGA is a resource-constrained device, sharing the hardware resources among the soft processor cores can be advantageous. A few research works have focused on the resource sharing between soft processors, but they do not study how much FPGA logic is minimized for a different pipeline processor. This paper proposes the microarchitecture of four, and five stage pipeline processors that enables the sharing of functional units for execution among the multiple cores as well as sharing the BRAM ports. We then investigate the performance and hardware resource utilization for a four-core processor. We find that sharing different functional units can save the LUT usage to 31.7% and DSP usage to 75%. We analyze the performance impact of sharing from the simulation of the Embench benchmark program. Our simulation results indicate that for some cases the sharing improves the performance and for other configurations worst-case performance drop is 16.7%.

Laser Doppler Vibrometers (LDVs) enable the acquisition of remote speech signals by measuring small-scale vibrations around a target. They are now widely used in the fields of information acquisition and national security. However, in remote speech detection, the coherent measurement signal is subject to environmental noise, making detecting and reconstructing speech signals challenging. To improve the detection distance and speech quality, this paper proposes a highly accurate real-time speech measurement method that can reconstruct speech from noisy coherent signals. First, the I/Q demodulation and arctangent phase discrimination are used to extract the phase transformation caused by the acoustic vibration from coherent signals. Then, an innovative smoothness criterion and a novel phase difference-based dynamic bilateral compensation phase unwrapping algorithm are used to remove any ambiguity caused by the arctangent phase discrimination in the previous step. This important innovation results in the highly accurate detection of phase jumps. After this, a further innovation is used to enhance the reconstructed speech by applying an improved waveform-based linear prediction coding method, together with adaptive spectral subtraction. This removes any impulsive or background noise. The accuracy and performance of the proposed method were validated by conducting extensive simulations and comparisons with existing techniques. The results show that the proposed algorithm can significantly improve the measurement of speech and the quality of reconstructed speech signals. The viability of the method was further assessed by undertaking a physical experiment, where LDV equipment was used to measure speech at a distance of 310m in an outdoor environment. The intelligibility rate for the reconstructed speech exceeded 95%, confirming the effectiveness and superiority of the method for long-distance laser speech measurement.

AONT (All-or-Nothing Transform) is a kind of (n, n)-threshold secret sharing scheme that distributes a message m into a set of n shares such that the message m can be reconstructed if and only if n shares are collected. At CRYPTO 2000, Desai proposed a simple and faster AONT based on the CTR mode of encryption (called CTRT) and proved its security in the ideal cipher model. Though AES-128, whose key length k = 128 and block length l = 128, can be used in CTRT as a block cipher, AES-256 and AES-192 cannot be used due to its intrinsic restriction of k ≤ l. In this paper, we propose an extended CTRT (for short, XCTRT) suitable for AES-256. By thoroughly evaluating all the tricky cases, we prove that XCTRT is secure in the ideal cipher model under the same CTRT security definition. Also, we discuss the security result of XCTRT in concrete parameter settings. For more flexibility of key length, we propose a variant of XCTRT dealing with l

The differential uniformity, the boomerang uniformity, and the extended Walsh spectrum etc are important parameters to evaluate the security of S (substitution)-box. In this paper, we introduce efficient formulas to compute these cryptographic parameters of permutation polynomials of the form xrh(x(2n-1)/d) over a finite field of q=2n elements, where r is a positive integer and d is a positive divisor of 2n-1. The computational cost of those formulas is proportional to d. We investigate differentially 4-uniform permutation polynomials of the form xrh(x(2n-1)/3) and compute the boomerang spectrum and the extended Walsh spectrum of them using the suggested formulas when 6≤n≤12 is even, where d=3 is the smallest nontrivial d for even n. We also investigate the differential uniformity of some permutation polynomials introduced in some recent papers for the case d=2n/2+1.

In this letter, a ray tracing (RT) acceleration method based on rank minimization is proposed. RT is a general tool used to simulate wireless communication environments. However, the simulation is time consuming because of the large number of ray calculations. This letter focuses on radio map interpolation as an acceleration approach. In the conventional methods cannot appropriately estimate short-span variation caused by multipath fading. To overcome the shortage of the conventional methods, we adopt rank minimization based interpolation. A computational simulation using commercial RT software revealed that the interpolation accuracy of the proposed method was higher than those of other radio map interpolation methods and that RT simulation can be accelerated approximate five times faster with the missing rate of 0.8.

To solve the problem of metamerism in the color reproduction process, various spectral reflectance reconstruction methods combined with neural network have been proposed in recent years. However, these methods are generally sensitive to initial values and can easily converge to local optimal solutions, especially on small data sets. In this paper, we propose a spectral reflectance reconstruction algorithm based on the Back Propagation Neural Network (BPNN) and an improved Sparrow Search Algorithm (SSA). In this algorithm, to solve the problem that BPNN is sensitive to initial values, we propose to use SSA to initialize BPNN, and we use the sine chaotic mapping to further improve the stability of the algorithm. In the experiment, we tested the proposed algorithm on the X-Rite ColorChecker Classic Mini Chart which contains 24 colors, the results show that the proposed algorithm has significantly better performance compared to other algorithms and moreover it can meet the needs of spectral reflectance reconstruction on small data sets. Code is avaible at https://github.com/LuraZhang/spectral-reflectance-reconsctuction.

Person re-identification (Re-ID) aims to match the same pedestrain identity images across different camera views. Because pedestrians will change clothes frequently for a relatively long time, while many current methods rely heavily on color appearance information or only focus on the person biometric features, these methods make the performance dropped apparently when it is applied to Clohting-Changing. To relieve this dilemma, we proposed a novel Multi Feature Fusion Attention Network (MFFAN), which learns the fine-grained local features. Then we introduced a Clothing Adaptive Attention (CAA) module, which can integrate multiple granularity features to guide model to learn pedestrain's biometric feature. Meanwhile, in order to fully verify the performance of our method on clothing-changing Re-ID problem, we designed a Clothing Generation Network (CGN), which can generate multiple pictures of the same identity wearing different clothes. Finally, experimental results show that our method exceeds the current best method by over 5% and 6% on the VCcloth and PRCC datasets respectively.

The application of compressed sensing (CS) theory to non-orthogonal multiple access (NOMA) systems has been investigated recently. As described in this paper, we propose a quality-of-service (QoS)-aware, low-complexity, CS-based user selection and power allocation scheme with adaptive resource block selection for downlink NOMA systems, where the tolerable interference threshold is designed mathematically to achieve a given QoS requirement by being relaxed to a constrained l1 norm optimization problem. The proposed scheme adopts two adaptive resource block (RB) selection algorithms that assign proper RB to user pairs, i.e. max-min channel assignment and two-step opportunistic channel assignment. Simulation results show that the proposed scheme is more effective at improving the user rate than other reference schemes while reducing the required complexity. The QoS requirement is approximately satisfied as long as the required QoS value is feasible.

This paper proposes constant voltage design based on K-inverter for cooperative inductive power transfer (IPT) where a nearby receiver picks up power and simultaneously cooperates in relaying the signal toward another distant receiver. In a cooperative IPT system, wireless power is fundamentally transferred to the nearby receiver via one K-inverter and to the distant receiver via two K-inverters. By adding one more K-inverter to the nearby receiver, our design is among the simplest methods as it delivers constant output voltage to each receiver via two K-inverters only. Experimental results verify that the proposed cooperative IPT system can stabilize two output voltages against the load variations while attaining high RF-RF efficiency of 90%.

Noninvasive recognition is an important trend in diabetes recognition. Unfortunately, the accuracy obtained from the conventional noninvasive recognition methods is low. This paper proposes a novel Diabetes Noninvasive Recognition method via the plantar pressure image and improved Capsule Network (DNR-CapsNet). The input of the proposed method is a plantar pressure image, and the output is the recognition result: healthy or possibly diabetes. The ResNet18 is used as the backbone of the convolutional layers to convert pixel intensities to local features in the proposed DNR-CapsNet. Then, the PrimaryCaps layer, SecondaryCaps layer, and DiabetesCaps layer are developed to achieve the diabetes recognition. The semantic fusion and locality-constrained dynamic routing are also developed to further improve the recognition accuracy in our method. The experimental results indicate that the proposed method has a better performance on diabetes noninvasive recognition than the state-of-the-art methods.

A Mach-Zehnder optical modulator with the tunable multimode interference coupler was fabricated using Ti-diffused LiNbO3. The modulation extinction ratio could be voltage controlled to maximize up to 50 dB by tuning the coupler. Optical single-sideband modulation was also achieved with a sideband suppression ratio of more than 30 dB.

This paper presents the design, implementation, and verification of a blockchain-based online electronic voting system that ensures accuracy and reliability in electronic voting and its application to various types of voting using blockchain technologies, such as distributed ledgers and smart contracts. Specifically, in this study, the connection between the electronic voting system and blockchain nodes is simplified using the REST API design, and the voting opening and counting information is designed to store the latest values in the distributed ledger in JSON format, using a smart contract that cannot be falsified. The developed electronic voting system can provide blockchain authentication, secret voting, forgery prevention, ballot verification, and push notification functions, all of which are currently not supported in existing services. Furthermore, the developed system demonstrates excellence on all evaluation items, including 101 transactions per second (TPS) of blockchain online authentication, 57.6 TPS of secret voting services, 250 TPS of forgery prevention cases, 547 TPS of read transaction processing, and 149 TPS of write transaction processing, along with 100% ballot verification service, secret ballot authentication, and encryption accuracy. Functional and performance verifications were obtained through an external test certification agency in South Korea. Our design allows for blockchain authentication, non-forgery of ballot counting data, and secret voting through blockchain-based distributed ledger technology. In addition, we demonstrate how existing electronic voting systems can be easily converted to blockchain-based electronic voting systems by applying a blockchain-linked REST API. This study greatly contributes to enabling electronic voting using blockchain technology through cost reductions, information restoration, prevention of misrepresentation, and transparency enhancement for a variety of different forms of voting.

Feature selection based on particle swarm optimization is often employed for promoting the performance of artificial intelligence algorithms. However, its interpretability has been lacking of concrete research. Improving the stability of the feature selection method is a way to effectively improve its interpretability. A novel feature selection approach named Interpretable Particle Swarm Optimization is developed in this paper. It uses four data perturbation ways and three filter feature selection methods to obtain stable feature subsets, and adopts Fuch map to convert them to initial particles. Besides, it employs similarity mutation strategy, which applies Tanimoto distance to choose the nearest 1/3 individuals to the previous particles to implement mutation. Eleven representative algorithms and four typical datasets are taken to make a comprehensive comparison with our proposed approach. Accuracy, F1, precision and recall rate indicators are used as classification measures, and extension of Kuncheva indicator is employed as the stability measure. Experiments show that our method has a better interpretability than the compared evolutionary algorithms. Furthermore, the results of classification measures demonstrate that the proposed approach has an excellent comprehensive classification performance.

As a kind of marine vehicles, Unmanned Surface Vehicles (USV) are widely used in military and civilian fields because of their low cost, good concealment, strong mobility and high speed. High-precision detection of obstacles plays an important role in USV autonomous navigation, which ensures its subsequent path planning. In order to further improve obstacle detection performance, we propose an encoder-decoder architecture named Fusion Refinement Network (FRN). The encoder part with a deeper network structure enables it to extract more rich visual features. In particular, a dilated convolution layer is used in the encoder for obtaining a large range of obstacle features in complex marine environment. The decoder part achieves the multiple path feature fusion. Attention Refinement Modules (ARM) are added to optimize features, and a learnable fusion algorithm called Feature Fusion Module (FFM) is used to fuse visual information. Experimental validation results on three different datasets with real marine images show that FRN is superior to state-of-the-art semantic segmentation networks in performance evaluation. And the MIoU and MPA of the FRN can peak at 97.01% and 98.37% respectively. Moreover, FRN could maintain a high accuracy with only 27.67M parameters, which is much smaller than the latest obstacle detection network (WaSR) for USV.