This paper proposes and characterizes an A/D converter (ADC) based on a spiking neuron model with a rectangular threshold signal. The neuron repeats an integrate-and-fire process and outputs a superstable spike sequence. The dynamics of this system are closely related to those of rate-encoding ADCs. We propose an ADC system based on the spiking neuron model. We derive a theoretical parameter region in a limited time interval of the digital output sequence. We analyze the conversion characteristics in this region and verify that they retain the monotonic increase and rate encoding of an ADC.

Fault localization analyzes the runtime information of two classes of test cases (i.e., passing test cases and failing test cases) to identify suspicious statements potentially responsible for a failure. However, the failing test cases are always far fewer than passing test cases in reality, and the class imbalance problem will affect fault localization effectiveness. To address this issue, we propose a data augmentation approach using conditional variational auto-encoder to synthesize new failing test cases for FL. The experimental results show that our approach significantly improves six state-of-the-art fault localization techniques.

A triple loss based framework for generalized zero-shot learning is presented in this letter. The approach learns a shared latent space for image features and attributes by using aligned variational autoencoders and variants of triplet loss. Then we train a classifier in the latent space. The experimental results demonstrate that the proposed framework achieves great improvement.

The spectral envelope parameter is a significant speech parameter in the vocoder's quality. Recently, the Vector Quantized Variational AutoEncoder (VQ-VAE) is a state-of-the-art end-to-end quantization method based on the deep learning model. This paper proposed a new technique for improving the embedding space learning of VQ-VAE with the Generative Adversarial Network for quantizing the spectral envelope parameter, called VQ-VAE-EMGAN. In experiments, we designed the quantizer for the spectral envelope parameters of the WORLD vocoder extracted from the 16kHz speech waveform. As the results shown, the proposed technique reduced the Log Spectral Distortion (LSD) around 0.5dB and increased the PESQ by around 0.17 on average for four target bit operations compared to the conventional VQ-VAE.

The prediction of the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation industry. Studies have been conducted on machine learning methods that use condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques that use unsupervised learning where the anomaly pattern is unknown have attracted significant interest in the area of anomaly detection and prediction. In particular, vibration data are considered useful because they include the changes that occur in the early stages of a malfunction. However, when autoencoder-based techniques are applied for prediction purposes, in the training process it is difficult to distinguish the difference between operating and non-operating condition data, which leads to the degradation of the prediction performance. In this letter, we propose a method in which both vibration data and SCADA data are utilized to improve the prediction performance, namely, a method that uses a power curve composed of active power and wind speed. We evaluated the method's performance using vibration and SCADA data obtained from an actual wind farm.

Maximum run-length limited codes are constraint codes used in communication and data storage systems. Insertion/deletion correcting codes correct insertion or deletion errors caused in transmitted sequences and are used for combating synchronization errors. This paper investigates the maximum run-length limited single insertion/deletion correcting (RLL-SIDC) codes. More precisely, we construct efficiently encodable and decodable RLL-SIDC codes. Moreover, we present its encoding and decoding algorithms and show the redundancy of the code.

Accumulate Repeat-4 Jagged-Accumulate (AR4JA) codes, which are channel codes designed for deep-space communications, are a series of QC-LDPC codes. Structures of these codes' generator matrix can be exploited to design reconfigurable encoders. To make the decoder reconfigurable and achieve shorter convergence time, turbo-like decoding message passing (TDMP) is chosen as the hardware decoder's decoding schedule and normalized min-sum algorithm (NMSA) is used as decoding algorithm to reduce hardware complexity. In this paper, we propose a reconfigurable decoder and present its FPGA implementation results. The decoder can achieve throughput greater than 74 Mbps.

An autoencoder is trained to generate the background from the surveillance image by setting the training label as the shuffled input, instead of the input itself in a traditional autoencoder. Then the multi-scale features are extracted by a sparse autoencoder from the surveillance image and the corresponding background to detect foreground.

Crowd flow prediction in high density urban scenes is involved in a wide range of intelligent transportation and smart city applications, and it has become a significant topic in urban computing. In this letter, a CNN-based framework called Pyramidal Spatio-Temporal Network (PSTNet) for crowd flow prediction is proposed. Spatial encoding is employed for spatial representation of external factors, while prior pyramid enhances feature dependence of spatial scale distances and temporal spans, after that, post pyramid is proposed to fuse the heterogeneous spatio-temporal features of multiple scales. Experimental results based on TaxiBJ and MobileBJ demonstrate that proposed PSTNet outperforms the state-of-the-art methods.

In an amusement park, an attraction-visiting route considering the waiting time and traveling time improves visitors' satisfaction and experience. We focus on Ising machines to solve the problem, which are recently expected to solve combinatorial optimization problems at high speed by mapping the problems to Ising models or quadratic unconstrained binary optimization (QUBO) models. We propose a mapping of the visiting-route recommendation problem in amusement parks to a QUBO model for solving it using Ising machines. By using an actual Ising machine, we could obtain feasible solutions one order of magnitude faster with almost the same accuracy as the simulated annealing method for the visiting-route recommendation problem.

Predicting the malfunction timing of wind turbines is essential for maintaining the high profitability of the wind power generation business. Machine learning methods have been studied using condition monitoring system data, such as vibration data, and supervisory control and data acquisition (SCADA) data, to detect and predict anomalies in wind turbines automatically. Autoencoder-based techniques have attracted significant interest in the detection or prediction of anomalies through unsupervised learning, in which the anomaly pattern is unknown. Although autoencoder-based techniques have been proven to detect anomalies effectively using relatively stable SCADA data, they perform poorly in the case of deteriorated SCADA data. In this letter, we propose a power-curve filtering method, which is a preprocessing technique used before the application of an autoencoder-based technique, to mitigate the dirtiness of SCADA data and improve the prediction performance of wind turbine degradation. We have evaluated its performance using SCADA data obtained from a real wind-farm.

As an important type of science and technology service resource, energy consumption data play a vital role in the process of value chain integration between home appliance manufacturers and the state grid. Accurate electricity consumption prediction is essential for demand response programs in smart grid planning. The vast majority of existing prediction algorithms only exploit data belonging to a single domain, i.e., historical electricity load data. However, dependencies and correlations may exist among different domains, such as the regional weather condition and local residential/industrial energy consumption profiles. To take advantage of cross-domain resources, a hybrid energy consumption prediction framework is presented in this paper. This framework combines the long short-term memory model with an encoder-decoder unit (ED-LSTM) to perform sequence-to-sequence forecasting. Extensive experiments are conducted with several of the most commonly used algorithms over integrated cross-domain datasets. The results indicate that the proposed multistep forecasting framework outperforms most of the existing approaches.

Advancements in portable electrocardiographs have allowed electrocardiogram (ECG) signals to be recorded in everyday life. Machine-learning techniques, including deep learning, have been used in numerous studies to analyze ECG signals because they exhibit superior performance to conventional methods. A mobile ECG analysis device is needed so that abnormal ECG waves can be detected anywhere. Such mobile device requires a real-time performance and low power consumption, however, deep-learning based models often have too many parameters to implement on mobile hardware, its amount of hardware is too large and dissipates much power consumption. We propose a design flow to implement the outlier detector using an autoencoder on a low-end FPGA. To shorten the preparation time of ECG data used in training an autoencoder, an unsupervised learning technique is applied. Additionally, to minimize the volume of the weight parameters, a weight sparseness technique is applied, and all the parameters are converted into fixed-point values. We show that even if the parameters are reduced converted into fixed-point values, the outlier detection performance degradation is only 0.83 points. By reducing the volume of the weight parameters, all the parameters can be stored in on-chip memory. We design the architecture according to the CRS format, which is the well-known data structure of a sparse matrix, minimizing the hardware size and reducing the power consumption. We use weight sharing to further reduce the weight-parameter volumes. By using weight sharing, we could reduce the bit width of the memories by 60% while maintaining the outlier detection performance. We implemented the autoencoder on a Digilent Inc. ZedBoard and compared the results with those for the ARM mobile CPU for a built-in device. The results indicated that our FPGA implementation of the outlier detector was 12 times faster and 106 times more energy-efficient.

To find the exact items from the massive patent resources for users is a matter of great urgency. Although the recommender systems have shot this problem to a certain extent, there are still some challenging problems, such as tracking user interests and improving the recommendation quality when the rating matrix is extremely sparse. In this paper, we propose a novel method called Collaborative Filtering Auto-Encoder for the top-N recommendation. This method employs Auto-Encoders to extract the item's features, converts a high-dimensional sparse vector into a low-dimensional dense vector, and then uses the dense vector for similarity calculation. At the same time, to make the recommendation list closer to the user's recent interests, we divide the recommendation weight into time-based and recent similarity-based weights. In fact, the proposed method is an improved, item-based collaborative filtering model with more flexible components. Experimental results show that the method consistently outperforms state-of-the-art top-N recommendation methods by a significant margin on standard evaluation metrics.

This paper describes a novel 4K 120fps (frames per second) real-time HEVC (High Efficiency Video Coding) encoder for high-frame-rate video encoding and transmission. Motion portrayal problems such as motion blur and jerkiness may occur in video scenes containing fast-moving objects or quick camera panning. A high-frame-rate solves such problems and provides a more immersive viewing experience that can express even the fast-moving scenes without discomfort. It can also be used in remote operation for scenes with high motion, such as VAR (Video Assistant Referee) systems in sports. Real-time encoding of high-frame-rate videos with low latency and temporal scalability is required for providing such high-frame-rate video services. The proposed encoder achieves full 4K/120fps real-time encoding, which is twice the current 4K service frame rate of 60fps, by multichip configuration with two encoder LSI. Exchange of reference picture data near a spatially divided slice boundary provides cross-chip motion estimation, and maintains the coding efficiency. The encoder supports temporal-scalable coding mode, in which it output stream with temporal scalability transmitted over one or two transmission paths. The encoder also supports the other mode, low-delay coding mode, in which it achieves 21.8msec low-latency processing through motion vector restriction. Evaluation of the proposed encoder's multichip configuration shows that the BD-bitrate (the average rate of bitrate increase), compared to simple slice division without inter-chip transfer, is -2.86% at minimum and -2.41% on average in temporal-scalable coding mode. The proposed encoder system will open the door to the next generation of high-frame-rate UHDTV (ultra-high-definition television) services.

The development of deep learning and neural networks has brought broad prospects to computer vision and natural language processing. The image captioning task combines cutting-edge methods in two fields. By building an end-to-end encoder-decoder model, its description performance can be greatly improved. In this paper, the multi-branch deep convolutional neural network is used as the encoder to extract image features, and the recurrent neural network is used to generate descriptive text that matches the input image. We conducted experiments on Flickr8k, Flickr30k and MSCOCO datasets. According to the analysis of the experimental results on evaluation metrics, the model proposed in this paper can effectively achieve image caption, and its performance is better than classic image captioning models such as neural image annotation models.

To date, many studies have employed clustering for the classification of unlabeled data. Deep separate clustering applies several deep learning models to conventional clustering algorithms to more clearly separate the distribution of the clusters. In this paper, we employ a convolutional autoencoder to learn the features of input images. Following this, k-means clustering is conducted using the encoded layer features learned by the convolutional autoencoder. A center loss function is then added to aggregate the data points into clusters to increase the intra-cluster homogeneity. Finally, we calculate and increase the inter-cluster separability. We combine all loss functions into a single global objective function. Our new deep clustering method surpasses the performance of existing clustering approaches when compared in experiments under the same conditions.

Ising machines have attracted attention as they are expected to solve combinatorial optimization problems at high speed with Ising models corresponding to those problems. An induced subgraph isomorphism problem is one of the decision problems, which determines whether a specific graph structure is included in a whole graph or not. The problem can be represented by equality constraints in the words of combinatorial optimization problem. By using the penalty functions corresponding to the equality constraints, we can utilize an Ising machine to the induced subgraph isomorphism problem. The induced subgraph isomorphism problem can be seen in many practical problems, for example, finding out a particular malicious circuit in a device or particular network structure of chemical bonds in a compound. However, due to the limitation of the number of spin variables in the current Ising machines, reducing the number of spin variables is a major concern. Here, we propose an efficient Ising model mapping method to solve the induced subgraph isomorphism problem by Ising machines. Our proposed method theoretically solves the induced subgraph isomorphism problem. Furthermore, the number of spin variables in the Ising model generated by our proposed method is theoretically smaller than that of the conventional method. Experimental results demonstrate that our proposed method can successfully solve the induced subgraph isomorphism problem by using the Ising-model based simulated annealing and a real Ising machine.

In this letter, we consider the incorrigible sets of binary linear codes. First, we show that the incorrigible set enumerator of a binary linear code is tantamount to the Tutte polynomial of the vector matroid induced by the parity-check matrix of the code. A direct consequence is that determining the incorrigible set enumerator of binary linear codes is #P-hard. Then for a cycle code, we express its incorrigible set enumerator via the Tutte polynomial of the graph describing the code. Furthermore, we provide the explicit formula of incorrigible set enumerators of cycle codes constructed from complete graphs.

Ising machines have attracted attention, which is expected to obtain better solutions of various combinatorial optimization problems at high speed by mapping the problems to natural phenomena. A slot-placement problem is one of the combinatorial optimization problems, regarded as a quadratic assignment problem, which relates to the optimal logic-block placement in a digital circuit as well as optimal delivery planning. Here, we propose a mapping to the Ising model for solving a slot-placement problem with additional constraints, called a constrained slot-placement problem, where several item pairs must be placed within a given distance. Since the behavior of Ising machines is stochastic and we map the problem to the Ising model which uses the penalty method, the obtained solution does not always satisfy the slot-placement constraint, which is different from the conventional methods such as the conventional simulated annealing. To resolve the problem, we propose an interpretation method in which a feasible solution is generated by post-processing procedures. We measured the execution time of an Ising machine and compared the execution time of the simulated annealing in which solutions with almost the same accuracy are obtained. As a result, we found that the Ising machine is faster than the simulated annealing that we implemented.