This letter describes the development and implementation of the lane detection system accelerated by the neuromorphic hardware. Because the neuromorphic hardware has inherently parallel nature and has constant output latency regardless the size of the knowledge, the proposed lane detection system can recognize various types of lanes quickly and efficiently. Experimental results using the road images obtained in the actual driving environments showed that white and yellow lanes could be detected with an accuracy of more than 94 percent.

Various types of classifiers and feature extraction methods for acoustic scene classification have been recently proposed in the IEEE Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 Challenge Task 1. The results of the final evaluation, however, have shown that even top 10 ranked teams, showed extremely low accuracy performance in particular class pairs with similar sounds. Due to such sound classes being difficult to distinguish even by human ears, the conventional deep learning based feature extraction methods, as used by most DCASE participating teams, are considered facing performance limitations. To address the low performance problem in similar class pair cases, this letter proposes to employ a recurrent neural network (RNN) based source separation for each class prior to the classification step. Based on the fact that the system can effectively extract trained sound components using the RNN structure, the mid-layer of the RNN can be considered to capture discriminative information of the trained class. Therefore, this letter proposes to use this mid-layer information as novel discriminative features. The proposed feature shows an average classification rate improvement of 2.3% compared to the conventional method, which uses additional classifiers for the similar class pair issue.

Multiport SRAMs are frequently installed in network and/or telecommunication VLSIs to implement smart functions. This paper presents a high speed and low-power dual-port (i.e., 1W+1R two-port) SRAM macro customized for serial access operations. To reduce the wasted power dissipation due to subthreshold leakage currents, the supply voltage for 10T memory cells is lowered to 1 V and a power switch is prepared for every 64 word drivers. The switch is activated with look-ahead decoder-segment activation logic, so there is no penalty when selecting a wordline. The data I/O circuitry with a new column-based configuration makes it possible to hide the bitline precharge operation with the sensing operation in the read cycle ahead of it; that is, we have successfully reduced the read latency by a half clock cycle, resulting in a pure two-stage pipeline. The SRAM macro installed in a 4K-entry × 33-bit FIFO memory, fabricated with a 0.3-µm fully-depleted-SOI CMOS process, achieved a 500-MHz operation in the typical conditions of 2- and 1-V power supplies, and 25°C. The power consumption during the standby time was less than 1.0 mW, and that at a practical operating frequency of 400 MHz was in a range of 47-57 mW, depending on the bit-stream data pattern.

There is increasing interest in quantum computing, because of its enormous computing potential. A small number of powerful quantum algorithms have been proposed to date; however, the development of new quantum algorithms for practical use remains essential. Parallel computing with a neural network has successfully realized certain unique functions such as learning and recognition; therefore, the introduction of certain neural computing techniques into quantum computing to enlarge the quantum computing application field is worthwhile. In this paper, a novel quantum associative memory (QuAM) is proposed, which is achieved with a quantum neural network by employing adiabatic Hamiltonian evolution. The memorization and retrieval procedures are inspired by the concept of associative memory realized with an artificial neural network. To study the detailed dynamics of our QuAM, we examine two types of Hamiltonians for pattern memorization. The first is a Hamiltonian having diagonal elements, which is known as an Ising Hamiltonian and which is similar to the cost function of a Hopfield network. The second is a Hamiltonian having non-diagonal elements, which is known as a neuro-inspired Hamiltonian and which is based on interactions between qubits. Numerical simulations indicate that the proposed methods for pattern memorization and retrieval work well with both types of Hamiltonians. Further, both Hamiltonians yield almost identical performance, although their retrieval properties differ. The QuAM exhibits new and unique features, such as a large memory capacity, which differs from a conventional neural associative memory.

This paper presents an interactive locomotion controller using motion capture data and an inverted pendulum model (IPM). The motion data of a character is decomposed into those of upper and lower bodies, which are then dimension-reduced via what we call hierarchical Gaussian process dynamical model (H-GPDM). The locomotion controller receives the desired walking direction from the user. It is integrated into the IPM to determine the pose of the center of mass and the stance-foot position of the character. They are input to the H-GPDM, which interpolates the low-dimensional data to synthesise a redirected motion sequence on an uneven surface. The locomotion controller allows the upper and lower bodies to be independently controlled and helps us generate natural locomotion. It can be used in various real-time applications such as games.

The objectives of this survey are to provide an in-depth coverage of a few selected research papers that have made significant contributions to the development of Network Function Virtualization (NFV), and to provide readers insights into the key advantages and disadvantages of NFV and Software Defined Networks (SDN) when compared to traditional networks. The research papers covered are classified into four categories: NFV Infrastructure (NFVI), Network Functions (NFs), Management And Network Orchestration (MANO), and service chaining. The NFVI papers describe “framework” software that implement common functions, such as dynamic scaling and load balancing, required by NF developers. Papers on NFs are classified as offering solutions for software switches or middleboxes. MANO papers covered in this survey are primarily on resource allocation (virtual network embedding), which is an orchestrator function. Finally, service chaining papers that offer examples and extensions are reviewed. Our conclusions are that with the current level of investment in NFV from cloud and Internet service providers, the promised cost savings are likely to be realized, though many challenges remain.

We proposed the simulation method of reconstructed holographic images in considering phase distribution in the small pixels of liquid crystal spatial light modulator (LC-SLM) and clarified zero-order diffraction appeared on the reconstructed images when the phase distribution in a single pixel is non-uniform. These results are useful for design of fine LC-SLM for realizing wide-viewing-angle holographic displays.

We developed flexible liquid crystal devices using ultra-thin polyimide substrates and bonding polymer spacers, and discussed the effects of polymer spacer structure on the cell thickness uniformity of flexible LCDs. We clarified that the lattice-shaped polymer spacer is effective to stabilize the cell thickness by suppressing the flow of the liquid crystal during bending process.

The aim of this letter is to guarantee the ability of low probability of intercept (LPI) and anti-jamming (AJ) by maximizing the energy efficiency (EE) to improve wireless communication survivability and sustain wireless communication in jamming environments. We studied a scenario based on one transceiver pair with a partial-band noise jammer in a Rician fading channel and proposed an EE optimization algorithm to solve the optimization problem. With the proposed EE optimization algorithm, the LPI and AJ can be simultaneously guaranteed while satisfying the constraint of the maximum signal-to-jamming-and-noise ratio and combinatorial subchannel allocation condition, respectively. The results of the simulation indicate that the proposed algorithm is more energy-efficient than those of the baseline schemes and guarantees the LPI and AJ performance in a jamming environment.

In this letter, we propose a novel and effective haze removal method by using the structure-aware atmospheric veil. More specifically, the initial atmospheric veil is first estimated based on dark channel prior and morphological operator. Furthermore, an energy optimization function considering the structure feature of the input image is constructed to refine the initial atmospheric veil. At last, the haze-free image can be restored by inverting the atmospheric scattering model. Additionally, brightness adjustment is also performed for preventing the dehazing result too dark. Experimental results on hazy images reveal that the proposed method can effectively remove the haze and yield dehazing results with vivid color and high scene visibility.

In this paper, we propose a precise indoor localization method using visible light communication (VLC) with dual-facing cameras on a smart device (mobile phone, smartphone, or tablet device). This approach can assist the visually impaired with navigation, or provide mobile-robot control. The proposed method is different from conventional techniques in that dual-facing cameras are used to expand the localization area. The smart device is used as the receiver, and light-emitting diodes on the ceiling are used as localization landmarks. These are identified by VLC using a rolling shutter effect of complementary metal-oxide semiconductor image sensors. The front-facing camera captures the direct incident light of the landmarks, while the rear-facing camera captures mirror images of landmarks reflected from the floor face. We formulated the relationship between the poses (position and attitude) of the two cameras and the arrangement of landmarks using tilt detection by the smart device accelerometer. The equations can be analytically solved with a constant processing time, unlike conventional numerical methods, such as least-squares. We conducted a simulation and confirmed that the localization area was 75.6% using the dual-facing cameras, which was 3.8 times larger than that using only the front-facing camera. As a result of the experiment using two landmarks and a tablet device, the localization error in the horizontal direction was less than 98 mm at 90% of the measurement points. Moreover, the error estimation index can be used for appropriate route selection for pedestrians.

This study investigates whether learners consider constraints while posing arithmetic word problems. Through log data from an interactive learning environment, we analyzed actions of 39 first grade elementary school students and conducted correlation analysis between the frequency of actions and validity of actions. The results show that the learners consider constraints while posing arithmetic word problems.

Extreme learning machine (ELM) has recently attracted many researchers' interest due to its very fast learning speed, good generalization ability, and ease of implementation. However, it has a linear output layer which may limit the capability of exploring the available information, since higher-order statistics of the signals are not taken into account. To address this, we propose a novel ELM architecture in which the linear output layer is replaced by a Volterra filter structure. Additionally, the principal component analysis (PCA) technique is used to reduce the number of effective signals transmitted to the output layer. This idea not only improves the processing capability of the network, but also preserves the simplicity of the training process. Then we carry out performance evaluation and application analysis for the proposed architecture in the context of supervised classification and unsupervised equalization respectively, and the obtained results either on publicly available datasets or various channels, when compared to those produced by already proposed ELM versions and a state-of-the-art algorithm: support vector machine (SVM), highlight the adequacy and the advantages of the proposed architecture and characterize it as a promising tool to deal with signal processing tasks.

This paper presents a strategy, Weighted Voting of Discriminative Regions (WVDR), to improve the face recognition performance, especially in Small Sample Size (SSS) and occlusion situations. In WVDR, we extract the discriminative regions according to facial key points and abandon the rest parts. Considering different regions of face make different contributions to recognition, we assign weights to regions for weighted voting. We construct a decision dictionary according to the recognition results of selected regions in the training phase, and this dictionary is used in a self-defined loss function to obtain weights. The final identity of test sample is the weighted voting of selected regions. In this paper, we combine the WVDR strategy with CRC and SRC separately, and extensive experiments show that our method outperforms the baseline and some representative algorithms.

Coaxial connectors are extensively used in electrical systems and the degradation of the connector can alter the signal that is being transmitted and leads to faults, which is one of the major causes of low communication quality. In this work, the failure features caused by the degraded connector contact surface were studied. The relationship between the DC resistance and decreased real contact areas was given. Considering the inductance properties and capacitive coupling at high frequencies, the impedance characteristics of the degraded connector were discussed. Based on the transmission line theory and experimental measurement, an equivalent lump circuit of the coaxial connector was developed. For the degraded contact surface, the capacitance was analyzed, and the frequency effect was investigated. According to the high frequency characteristics of the degraded connector, a fault detection and location method for coaxial connectors in RF system was developed using a neural network method. For connectors suffering from different levels of pollution, their impedance modulus varies continuously. Considering the range of the connector's impedance parameters, the fault modes were determined. Based on the scattering parameter simulation of a RF receiver front-end circuit, the S11 and S21 parameters were obtained as feature parameters and Monte Carlo simulations were conducted to generate training and testing samples. Based on the BP neural network algorithm, the fault modes were classified and the results show the diagnosis accuracy was 97.33%.

Cloud bursting temporarily expands the capacity of a cloud-based service hosted in a private data center by renting public data center capacity when the demand for capacity spikes. To determine the optimal resources of a business-critical web system deployed over private and public data centers, this paper presents a cloud bursting approach based on long- and short-term predictions of requests to the system. In a private data center, a dedicated pool of virtual machines (VMs) is assigned to the web system on the basis of one-week predictions. Moreover, in both private and public data centers, VMs are activated on the basis of one-hour predictions. We formulate a problem that includes the total cost and response time constraints and conduct numerical simulations. The results indicate that our approach is tolerant of prediction errors and only slightly dependent on the processing power of a single VM. Even if the website receives bursty requests and one-hour predictions include a mean absolute percentage error (MAPE) of 0.2, the total cost decreases to half the existing cost of provisioning in the private date center alone. At the same time, 95% of response time is kept below 0.15s.

Recent Network on Chip (NoC) design must take the thermal issue into consideration due to its great impact on the network performance and reliability, especially for 3D NoC. In this work, we design a virtual channel based fully adaptive routing algorithm for the runtime 3D NoC thermal-aware management. To improve the network throughput and latency, we use two virtual channels for each horizontal direction and design a routing function which can not only avoid deadlock and livelock, but also ensure high adaptivity and routability in the throttled network. For path selection, we design a strategy that takes priority to the distance, but also considers path diversity and traffic state. For throttling information collection, instead of transmitting the topology information of the whole network, we use a 12 bits register to reserve the router state for one hop away, which saves the hardware cost largely and decreases the network latency. In the experiments, we test our proposed routing algorithm in different states with different sizes, and the proposed algorithm shows better network latency and throughput with low power compared with traditional algorithms.

Microwave imaging techniques, in particular, synthetic aperture radar (SAR), are promising tools for terrain surface measurement, irrespective of weather conditions. The coherent change detection (CCD) method is being widely applied to detect surface changes by comparing multiple complex SAR images captured from the same scanning orbit. However, in the case of a general damage assessment after a natural disaster such as an earthquake or mudslide, additional about surface change, such as surface height change, is strongly required. Given this background, the current study proposes a novel height change estimation method using a CCD model based on the Pauli decomposition of fully polarimetric SAR images. The notable feature of this method is that it can offer accurate height change beyond the assumed wavelength, by introducing the frequency band-divided approach, and so is significantly better than InSAR based approaches. Experiments in an anechoic chamber on a 1/100 scaled model of the X-band SAR system, show that our proposed method outputs more accurate height change estimates than a similar method that uses single polarimetric data, even if the height change amount is over the assumed wavelength.

We study the budgeted multi-armed bandit problem with stochastic action costs. In this problem, a player not only receives a reward but also pays a cost for an action of his/her choice. The goal of the player is to maximize the cumulative reward he/she receives before the total cost exceeds the budget. In the classical multi-armed bandit problem, a policy called KL-UCB is known to perform well. We propose KL-UCB-SC, an extension of this policy for the budgeted bandit problem. We prove that KL-UCB-SC is asymptotically optimal for the case of Bernoulli costs and rewards. To the best of our knowledge, this is the first result that shows asymptotic optimality in the study of the budgeted bandit problem. In fact, our regret upper bound is at least four times better than that of BTS, the best known upper bound for the budgeted bandit problem. Moreover, an empirical simulation we conducted shows that the performance of a tuned variant of KL-UCB-SC is comparable to that of state-of-the-art policies such as PD-BwK and BTS.

This paper presents convex filter networks that are obtained from extensions of morphological filters. The proposed filter network consists of a convex and concave filter that are extensions of the dilation and erosion of mathematical morphology with the maxout activation function. Maxout can approximate arbitrary convex functions as piecewise linear functions, including the max function. The class of the convex function hence includes the morphological dilation and can be trained for specific image processing tasks. In this paper, the closing filter is extended to a convex-concave filter network with maxout. The convex-concave filter is trained by the stochastic gradient method for noise and mask removal. The examples of noise and mask removal show that the convex-concave filter can obtain a recovered image, whose quality is comparable to inpainting by using the total variation minimization with reduced computational cost without mask information of the corrupted pixels.