Online learning is a method which updates the model gradually and can modify and strengthen the previous model, so that the updated model can adapt to the new data without having to relearn all the data. However, the accuracy of the current online multiclass learning algorithm still has room for improvement, and the ability to produce sparse models is often not strong. In this paper, we propose a new Multiclass Truncated Gradient Confidence-Weighted online learning algorithm (MTGCW), which combine the Truncated Gradient algorithm and the Confidence-weighted algorithm to achieve higher learning performance. The experimental results demonstrate that the accuracy of MTGCW algorithm is always better than the original CW algorithm and other baseline methods. Based on these results, we applied our algorithm for phishing website recognition and image classification, and unexpectedly obtained encouraging experimental results. Thus, we have reasons to believe that our classification algorithm is clever at handling unstructured data which can promote the cognitive ability of computers to a certain extent.

Laser speech detection uses a non-contact Laser Doppler Vibrometry (LDV)-based acoustic sensor to obtain speech signals by precisely measuring voice-generated surface vibrations. Over long distances, however, the detected signal is very weak and full of speckle noise. To enhance the quality and intelligibility of the detected signal, we designed a two-sided Linear Prediction Coding (LPC)-based locator and interpolator to detect and replace speckle noise. We first studied the characteristics of speckle noise in detected signals and developed a binary-state statistical model for speckle noise generation. A two-sided LPC-based locator was then designed to locate the polluted samples, composed of an inverse decorrelator, nonlinear filter and threshold estimator. This greatly improves the detectability of speckle noise and avoids false/missed detection by improving the noise-to-signal-ratio (NSR). Finally, samples from both sides of the speckle noise were used to estimate the parameters of the interpolator and to code samples for replacing the polluted samples. Real-world speckle noise removal experiments and simulation-based comparative experiments were conducted and the results show that the proposed method is better able to locate speckle noise in laser detected speech and highly effective at replacing it.

Based on TLS-ESPRIT algorithm, this paper proposes a weighted spatial smoothing DOA estimation algorithm to address the problem that the conventional TLS-ESPRIT algorithm will be disabled to estimate the direction of arrival (DOA) in the scenario of coherent sources. The proposed method divides the received signal array into several subarrays with special structural feature. Then, utilizing these subarrays, this paper constructs the new weighted covariance matrix to estimate the DOA based on TLS-ESPRIT. The auto-correlation and cross-correlation information of subarrays in the proposed algorithm is extracted sufficiently, improving the orthogonality between the signal subspace and the noise subspace so that the DOA of coherent sources could be estimated accurately. The simulations show that the proposed algorithm is superior to the conventional spatial smoothing algorithms under different signal to noise ratio (SNR) and snapshot numbers with coherent sources.

SPHINCS+ is a state-of-the-art post-quantum hash-based signature that is a candidate for the NIST post-quantum cryptography standard. For a target bit security, SPHINCS+ supports many different tradeoffs between the signature size and the signing speed. SPHINCS+ provides 6 parameter sets: 3 parameter sets for size optimization and 3 parameter sets for speed optimization. We propose new parameter sets with better performance. Specifically, SPHINCS+ implementations with our parameter sets are up to 26.5% faster with slightly shorter signature sizes.

This paper proposes a change detection method for buildings based on convolutional neural networks. The proposed method detects building changes from pairs of optical aerial images and past map information concerning buildings. Using high-resolution image pair and past map information seamlessly, the proposed method can capture the building areas more precisely compared to a conventional method. Our experimental results show that the proposed method outperforms the conventional change detection method that uses optical aerial images to detect building changes.

Source retrieval is the primary task of plagiarism detection. It searches the documents that may be the sources of plagiarism to a suspicious document. The state-of-the-art approaches usually rely on the classical information retrieval models, such as the probability model or vector space model, to get the plagiarism sources. However, the goal of source retrieval is to obtain the source documents that contain the plagiarism parts of the suspicious document, rather than to rank the documents relevant to the whole suspicious document. To model the “partial matching” between documents, this paper proposes a Partial Matching Convolution Neural Network (PMCNN) for source retrieval. In detail, PMCNN exploits a sequential convolution neural network to extract the plagiarism patterns of contiguous text segments. The experimental results on PAN 2013 and PAN 2014 plagiarism source retrieval corpus show that PMCNN boosts the performance of source retrieval significantly, outperforming other state-of-the-art document models.

We address analysis and design problems of aggregate demand response systems composed of various consumers based on controllability to facilitate to design automated demand response machines that are installed into consumers to automatically respond to electricity price changes. To this end, we introduce a controllability index that expresses the worst-case error between the expected total electricity consumption and the electricity supply when the best electricity price is chosen. The analysis problem using the index considers how to maximize the controllability of the whole consumer group when the consumption characteristic of each consumer is not fixed. In contrast, the design problem considers the whole consumer group when the consumption characteristics of a part of the group are fixed. By solving the analysis problem, we first clarify how the controllability, average consumption characteristics of all consumers, and the number of selectable electricity prices are related. In particular, the minimum value of the controllability index is determined by the number of selectable electricity prices. Next, we prove that the design problem can be solved by a simple linear optimization. Numerical experiments demonstrate that our results are able to increase the controllability of the overall consumer group.

As NAND flash-based storage has been settled, a flash translation layer (FTL) has been in charge of mapping data addresses on NAND flash memory. Many FTLs implemented various mapping schemes, but the amount of mapping data depends on the mapping level. However, the FTL should contemplate mapping consistency irrespective of how much mapping data dwell in the storage. Furthermore, the recovery cost by the inconsistency needs to be considered for a faster storage reboot time. This letter proposes a novel method that enhances the consistency for a page-mapping level FTL running a legacy logging policy. Moreover, the recovery cost of page mappings also decreases. The novel method is to adopt a virtually-shrunk segment and deactivate page-mapping logs by assembling and storing the segments. This segment scheme already gave embedded NAND flash-based storage enhance its response time in our previous study. In addition to that improved result, this novel plan maximizes the page-mapping consistency, therefore improves the recovery cost compared with the legacy page-mapping FTL.

This paper proposes a novel radio access scheme that uses duplicated transmission via multiple frequency channels to achieve mission critical Internet of Things (IoT) services requiring highly reliable wireless communications; the interference constraints that yield the required reliability are revealed. To achieve mission critical IoT services by wireless communication, it is necessary to improve reliability in addition to satisfying the required transmission delay time. Reliability is defined as the packet arrival rate without exceeding the desired transmission delay time. Traffic of the own system and interference from the other systems using the same frequency channel such as unlicensed bands degrades the reliability. One solution is the frequency/time diversity technique. However, these techniques may not achieve the required reliability because of the time taken to achieve the correct reception. This paper proposes a novel scheme that transmits duplicate packets utilizing multiple wireless interfaces over multiple frequency channels. It also proposes a suppressed duplicate transmission (SDT) scheme, which prevents the wastage of radio resources. The proposed scheme achieves the same reliable performance as the conventional scheme but has higher tolerance against interference than retransmission. We evaluate the relationship between the reliability and the occupation time ratio where the interference occupation time ratio is defined as the usage ratio of the frequency resources occupied by the other systems. We reveal the upper bound of the interference occupation time ratio for each frequency channel, which is needed if channel selection control is to achieve the required reliability.

Scalability of distributed DNN training can be limited by slowdown of specific processes due to unexpected hardware failures. We propose a dynamic process exclusion technique so that training throughput is maximized. Our evaluation using 32 processes with ResNet-50 shows that our proposed technique reduces slowdown by 12.5% to 50% without accuracy loss through excluding the slow processes.

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.

With the development of the Internet of Vehicles, License plate detection technology is widely used, e.g., smart city and edge senor monitor. However, traditional license plate detection methods are based on the license plate edge detection, only suitable for limited situation, such as, wealthy light and favorable camera's angle. Fortunately, deep learning networks represented by YOLOv3 can solve the problem, relying on strict condition. Although YOLOv3 make it better to detect large targets, its low performance in detecting small targets and lack of the real-time interactively. Motivated by this, we present a faster and lightweight YOLOv3 model for multi-vehicle or under-illuminated images scenario. Generally, our model can serves as a guideline for optimizing neural network in multi-vehicle scenario.

With the development of cameras and sensors and the spread of cloud computing, life logs can be easily acquired and stored in general households for the various services that utilize the logs. However, it is difficult to analyze moving images that are acquired by home sensors in real time using machine learning because the data size is too large and the computational complexity is too high. Moreover, collecting and accumulating in the cloud moving images that are captured at home and can be used to identify individuals may invade the privacy of application users. We propose a method of distributed processing over the edge and cloud that addresses the processing latency and the privacy concerns. On the edge (sensor) side, we extract feature vectors of human key points from moving images using OpenPose, which is a pose estimation library. On the cloud side, we recognize actions by machine learning using only the feature vectors. In this study, we compare the action recognition accuracies of multiple machine learning methods. In addition, we measure the analysis processing time at the sensor and the cloud to investigate the feasibility of recognizing actions in real time. Then, we evaluate the proposed system by comparing it with the 3D ResNet model in recognition experiments. The experimental results demonstrate that the action recognition accuracy is the highest when using LSTM and that the introduction of dropout in action recognition using 100 categories alleviates overfitting because the models can learn more generic human actions by increasing the variety of actions. In addition, it is demonstrated that preprocessing using OpenPose on the sensor side can substantially reduce the transfer quantity from the sensor to the cloud.

Emerging byte-addressable non-volatile memory devices attract much attention. A non-volatile main memory (NVMM) built on them enables larger memory size and lower power consumption than a traditional DRAM main memory. To fully utilize an NVMM, both software and hardware must be cooperatively optimized. Simultaneously, even focusing on a memory module, its micro architecture is still being developed though real non-volatile memory modules, such as Intel Optane DC persistent memory (DCPMM), have been on the market. Looking at existing NVMM evaluation environments, software simulators can evaluate various micro architectures with their long simulation time. Emulators can evaluate the whole system fast with less flexibility in their configuration than simulators. Thus, an NVMM emulator that can realize flexible and fast system evaluation still has an important role to explore the optimal system. In this paper, we introduce an NVMM emulator for embedded systems and explore a direction of optimization techniques for NVMMs by using it. It is implemented on an SoC-FPGA board employing three NVMM behaviour models: coarse-grain, fine-grain and DCPMM-based. The coarse and fine models enable NVMM performance evaluations based on extensions of traditional DRAM behaviour. The DCPMM-based model emulates the behaviour of a real DCPMM. Whole evaluation environment is also provided including Linux kernel modifications and several runtime functions. We first validate the developed emulator with an existing NVMM emulator, a cycle-accurate NVMM simulator and a real DCPMM. Then, the program behavior differences among three models are evaluated with SPEC CPU programs. As a result, the fine-grain model reveals the program execution time is affected by the frequency of NVMM memory requests rather than the cache hit ratio. Comparing with the fine-grain model and the coarse-grain model under the condition of the former's longer total write latency than the latter's, the former shows lower execution time for four of fourteen programs than the latter because of the bank-level parallelism and the row-buffer access locality exploited by the former model.

In order to erase data including confidential information stored in storage devices, an unrelated and random sequence is usually overwritten, which prevents the data from being restored. The problem of minimizing the cost for information erasure when the amount of information leakage of the confidential information should be less than or equal to a constant asymptotically has been introduced by T. Matsuta and T. Uyematsu. Whereas the minimum cost for overwriting has been given for general sources, a single-letter characterization for stationary memoryless sources is not easily derived. In this paper, we give single-letter characterizations for stationary memoryless sources under two types of restrictions: one requires the output distribution of the encoder to be independent and identically distributed (i.i.d.) and the other requires it to be memoryless but not necessarily i.i.d. asymptotically. The characterizations indicate the relation among the amount of information leakage, the minimum cost for information erasure and the rate of the size of uniformly distributed sequences. The obtained results show that the minimum costs are different between these restrictions.

In a network topology design problem, it is important to analyze the reliability and construction cost of complex network systems. This paper addresses a topological optimization problem of minimizing the total cost of a network system with separate subsystems under a reliability constraint. To solve this problem, we develop three algorithms. The first algorithm finds an exact solution. The second one finds an exact solution, specialized for a system with identical subsystems. The third one is a heuristic algorithm, which finds an approximate solution when a network system has several identical subsystems. We also conduct numerical experiments and demonstrate the efficacy and efficiency of the developed algorithms.

Because solar energy is intermittent and a ship's power-system load fluctuates and changes abruptly, in this work, the solar radiation parameters were adjusted according to the latitude and longitude of the ship and the change of the sea environment. An objective function was constructed that accounted for the cost and service life simultaneously to optimize the configuration of the marine diesel engine hybrid energy system. Finally, the improved artificial bee colony algorithm was used to optimize and obtain the optimal system configuration. The feasibility of the method was verified by ship navigation tests. This method exhibited better configuration performance optimization than the traditional methods.

In this letter, a two-stage QR decomposition scheme based on Givens rotation with novel modified real-value decomposition (RVD) is presented. With the modified RVD applied to the result from complex Givens rotation at first stage, the number of non-zero terms needed to be eliminated by real Givens rotation at second stage decreases greatly and the computational complexity is thereby reduced significantly compared to the decomposition scheme with the conventional RVD. Besides, the proposed scheme is suitable for the hardware design of QR decomposition. Evaluation shows that the proposed QR decomposition scheme is superior to the related works in terms of computational complexity.

A modified whale optimization algorithm (MWOA) with dynamic leader selection mechanism and novel population updating procedure is introduced for pattern synthesis of linear antenna array. The current best solution is dynamic changed for each whale agent to overcome premature with local optima in iteration. A hybrid crossover operator is embedded in original algorithm to improve the convergence accuracy of solution. Moreover, the flow of population updating is optimized to balance the exploitation and exploration ability. The modified algorithm is tested on a 28 elements uniform linear antenna array to reduce its side lobe lever and null depth lever. The simulation results show that MWOA algorithm can improve the performance of WOA obviously compared with other algorithms.

The Software-defined network (SDN) uses a centralized SDN controller to store flow entries in the flow table of each SDN switch; the entries in the switch control packet flows. When a multicast service is provided in an SDN, the SDN controller stores a multicast entry dedicated for a multicast group in each SDN switch. Due to the limited capacity of each flow table, the number of flow entries required to set up a multicast tree must be suppressed. A conventional multicast routing scheme suppresses the number of multicast entries in one multicast tree by replacing some of them with unicast entries. However, since the conventional scheme individually determines a multicast tree for each request, unicast entries dedicated to the same receiver are distributed to various SDN switches if there are multiple multicast service requests. Therefore, further reduction in the number of flow entries is still possible. In this paper, we propose a multicast routing model for multiple multicast requests that minimizes the number of flow entries. This model determines multiple multicast trees simultaneously so that a unicast entry dedicated to the same receiver and stored in the same SDN switch is shared by multicast trees. We formulate the proposed model as an integer linear programming (ILP) problem. In addition, we develop a heuristic algorithm which can be used when the ILP problem cannot be solved in practical time. Numerical results show that the proposed model reduces the required number of flow entries compared to two benchmark models; the maximum reduction ratio is 49.3% when the number of multicast requests is 40.