Capsules are fundamental informative units that are introduced into capsule networks to manipulate the hierarchical presentation of patterns. The part-hole relationship of an entity is learned through capsule layers, using a routing-by-agreement mechanism that is approximated by a voting procedure. Nevertheless, existing routing methods are computationally inefficient. We address this issue by proposing a novel routing mechanism, namely “shortcut routing”, that directly learns to activate global capsules from local capsules. In our method, the number of operations in the routing procedure is reduced by omitting the capsules in intermediate layers, resulting in lighter routing. To further address the computational problem, we investigate an attention-based approach, and propose fuzzy coefficients, which have been found to be efficient than mixture coefficients from EM routing. Our method achieves on-par classification results on the Mnist (99.52%), smallnorb (93.91%), and affNist (89.02%) datasets. Compared to EM routing, our fuzzy-based and attention-based routing methods attain reductions of 1.42 and 2.5 in terms of the number of calculations.

This paper investigates a constrained distributed online optimization problem over strongly connected communication networks, where a local cost function of each agent varies in time due to environmental factors. We propose a distributed online projected subgradient method over unbalanced directed networks. The performance of the proposed method is evaluated by a regret which is defined by the error between the cumulative cost over time and the cost of the optimal strategy in hindsight. We show that a logarithmic regret bound can be achieved for strongly convex cost functions. We also demonstrate the validity of the proposed method through a numerical example on distributed estimation over a diffusion field.

This paper presents a distributed server allocation model with preventive start-time optimization against a single server failure. The presented model preventively determines the assignment of servers to users under each failure pattern to minimize the largest maximum delay among all failure patterns. We formulate the proposed model as an integer linear programming (ILP) problem. We prove the NP-completeness of the considered problem. As the number of users and that of servers increase, the size of ILP problem increases; the computation time to solve the ILP problem becomes excessively large. We develop a heuristic approach that applies simulated annealing and the ILP approach in a hybrid manner to obtain the solution. Numerical results reveal that the developed heuristic approach reduces the computation time by 26% compared to the ILP approach while increasing the largest maximum delay by just 3.4% in average. It reduces the largest maximum delay compared with the start-time optimization model; it avoids the instability caused by the unnecessary disconnection permitted by the run-time optimization model.

In this paper, we propose a design method for a diplexer using a surface acoustic wave (SAW) filter, a multilayer ceramic filter, chip inductors, and chip capacitors. A controllable transmission zero can be created in the stopband by designing matching circuits based on the out-of-band characteristics of the SAW filter using this method. The proposed method can achieve good attenuation performance and a compact size because it does not use an additional resonator for creating the controllable transmission zero and the matching circuits are composed of only five components. A diplexer is designed for 2.4 GHz wireless systems and a global positioning system receiver using the proposed method. It is compact (8.0 mm × 8.0 mm), and the measurement results indicate good attenuation performance with the controllable transmission zero.

This paper theoretically presents that a terahertz (THz) oscillator using a resonant tunneling diode (RTD) and a rectangular cavity, which has previously been proposed, can radiate high output power by the impedance matching between RTD and load through metal-insulator-metal (MIM) capacitors. Based on an established equivalent-circuit model, an equation for output power has been deduced. By changing MIM capacitors, a matching point can be derived for various sizes of rectangular-cavity resonator. Simulation results show that high output power is possible by long cavity. For example, a high output power of 5 mW is expected at 1 THz.

A classification function maps a set of vectors into several classes. A machine learning problem is treated as a design problem for partially defined classification functions. To realize classification functions for MNIST hand written digits, three different architectures are considered: Single-unit realization, 45-unit realization, and 45-unit ×r realization. The 45-unit realization consists of 45 ternary classifiers, 10 counters, and a max selector. Test accuracy of these architectures are compared using MNIST data set.

The frequency of uterine peristalsis is closely related to the success rate of pregnancy. An ultrasonic imaging is almost always employed for the measure of the frequency. The physician subjectively evaluates the frequency from the ultrasound image by the naked eyes. This paper aims to measure the frequency of uterine peristalsis from the ultrasound image. The ultrasound image consists of relative amounts in the brightness, and the contour of the uterine is not clear. It was not possible to measure the frequency by using the inter-frame difference and optical flow, which are the representative methods of motion detection, since uterine peristaltic movement is too small to apply them. This paper proposes a measurement method of the frequency of the uterine peristalsis from the ultrasound image in the implantation phase. First, traces of uterine peristalsis are semi-automatically done from the images with location-axis and time-axis. Second, frequency analysis of the uterine peristalsis is done by Fourier transform for 3 minutes. As a result, the frequency of uterine peristalsis was known as the frequency with the dominant frequency ingredient with maximum value among the frequency spectrums. Thereby, we evaluate the number of the frequency of uterine peristalsis quantitatively from the ultrasound image. Finally, the success rate of pregnancy is calculated from the frequency based on Fuzzy logic. This enabled us to evaluate the success rate of pregnancy by measuring the uterine peristalsis from the ultrasound image.

Speech recognition is a technique that recognizes words and sentences in audio form and converts them into text sentences. Currently, with the advancement of deep learning technologies, speech recognition has achieved very satisfactory results close to human abilities. However, there are still limitations in identification results such as lack of punctuation, capitalization, and standardized numerical data. Vietnamese also contains local words, homonyms, etc, which make it difficult to read and understand the identification results for users as well as to perform the next tasks in Natural Language Processing (NLP). In this paper, we propose to combine the transformer decoder with conditional random field (CRF) to restore punctuation and capitalization for the Vietnamese automatic speech recognition (ASR) output. By chunking input sentences and merging output sequences, it is possible to handle longer strings with greater accuracy. Experiments show that the method proposed in the Vietnamese post-speech recognition dataset delivers the best results.

As scientific and technological resources are experiencing information overload, it is quite expensive to find resources that users are interested in exactly. The personalized recommendation system is a good candidate to solve this problem, but data sparseness and the cold starting problem still prevent the application of the recommendation system. Sparse data affects the quality of the similarity measurement and consequently the quality of the recommender system. In this paper, we propose a matrix factorization recommendation algorithm based on similarity calculation(SCMF), which introduces potential similarity relationships to solve the problem of data sparseness. A penalty factor is adopted in the latent item similarity matrix calculation to capture more real relationships furthermore. We compared our approach with other 6 recommendation algorithms and conducted experiments on 5 public data sets. According to the experimental results, the recommendation precision can improve by 2% to 9% versus the traditional best algorithm. As for sparse data sets, the prediction accuracy can also improve by 0.17% to 18%. Besides, our approach was applied to patent resource exploitation provided by the wanfang patents retrieval system. Experimental results show that our method performs better than commonly used algorithms, especially under the cold starting condition.

Likelihood ratios (LRs), which are commonly used for probabilistic data processing, are often estimated based on the frequency counts of individual elements obtained from samples. In natural language processing, an element can be a continuous sequence of N items, called an N-gram, in which each item is a word, letter, etc. In this paper, we attempt to estimate LRs based on N-gram frequency information. A naive estimation approach that uses only N-gram frequencies is sensitive to low-frequency (rare) N-grams and not applicable to zero-frequency (unobserved) N-grams; these are known as the low- and zero-frequency problems, respectively. To address these problems, we propose a method for decomposing N-grams into item units and then applying their frequencies along with the original N-gram frequencies. Our method can obtain the estimates of unobserved N-grams by using the unit frequencies. Although using only unit frequencies ignores dependencies between items, our method takes advantage of the fact that certain items often co-occur in practice and therefore maintains their dependencies by using the relevant N-gram frequencies. We also introduce a regularization to achieve robust estimation for rare N-grams. Our experimental results demonstrate that our method is effective at solving both problems and can effectively control dependencies.

Recent trends in designing filters involve development of sparse filters with coefficients that not only have real but also zero values. These sparse filters can achieve a high performance through optimizing the selection of the zero coefficients and computing the real (non-zero) coefficients. Designing an infinite impulse response (IIR) sparse filter is more challenging than designing a finite impulse response (FIR) sparse filter. Therefore, studies on the design of IIR sparse filters have been rare. In this study, we consider IIR filters whose coefficients involve zero value, called sparse IIR filter. First, we formulate the design problem as a linear programing problem without imposing any stability condition. Subsequently, we reformulate the design problem by altering the error function and prepare several possible denominator polynomials with stable poles. Finally, by incorporating these methods into successive thinning algorithms, we develop a new design algorithm for the filters. To demonstrate the effectiveness of the proposed method, its performance is compared with that of other existing methods.

6DoF pose estimation from a monocular RGB image is a challenging but fundamental task. The methods based on unit direction vector-field representation and Hough voting strategy achieved state-of-the-art performance. Nevertheless, they apply the smooth l1 loss to learn the two elements of the unit vector separately, resulting in which is not taken into account that the prior distance between the pixel and the keypoint. While the positioning error is significantly affected by the prior distance. In this work, we propose a Prior Distance Augmented Loss (PDAL) to exploit the prior distance for more accurate vector-field representation. Furthermore, we propose a lightweight channel-level attention module for adaptive feature fusion. Embedding this Adaptive Fusion Attention Module (AFAM) into the U-Net, we build an Attention Voting Network to further improve the performance of our method. We conduct extensive experiments to demonstrate the effectiveness and performance improvement of our methods on the LINEMOD, OCCLUSION and YCB-Video datasets. Our experiments show that the proposed methods bring significant performance gains and outperform state-of-the-art RGB-based methods without any post-refinement.

Containers offer a lightweight alternative over virtual machines and become a preferable choice for application consolidation in the clouds. However, the sharing of kernel components can violate the I/O performance and isolation in containers. It is widely recognized that file system journaling has terrible performance side effects in containers, especially when consolidating database management systems (DBMSs). The sharing of journaling modules among containers causes performance dependency among them. This dependency violates resource consumption enforced by the resource controller, and degrades I/O performance due to the contention of the journaling module. The operating system developers have been working on novel designs of file systems or new journaling mechanisms to solve the journaling problems. This paper shows that it is possible to overcome journaling problems without re-designing file systems or implementing a new journaling method. A careful configuration of containers in existing file systems can gracefully solve the problems. Our recommended configuration consists of 1) per-container journaling by presenting each container with a virtual block device to have its own journaling module, and 2) accounting journaling I/Os separately for each container. Our experimental results show that our configuration resolves journaling-related problems, improves MySQL performance by 3.4x, and achieves reasonable performance isolation among containers.

For the first stage of the multi-sensitive bucketization (MSB) method, the l-diversity grouping for multiple sensitive attributes is incomplete, causing more information loss. To solve this problem, we give the definitions of the l-diversity avoidance set for multiple sensitive attributes and the avoiding of a multiple dimensional bucket, and propose a complete l-diversity grouping (CLDG) algorithm for multiple sensitive attributes. Then, we improve the first stages of the MSB algorithms by applying the CLDG algorithm to them. The experimental results show that the grouping ratio of the improved first stages of the MSB algorithms is significantly higher than that of the original first stages of the MSB algorithms, decreasing the information loss of the published microdata.

In this paper, we propose a robust parameters estimation algorithm for channel coded systems based on the low-density parity-check (LDPC) code over fading channels with impulse noise. The estimated parameters are then used to generate bit log-likelihood ratios (LLRs) for a soft-inputLDPC decoder. The expectation-maximization (EM) algorithm is used to estimate the parameters, including the channel gain and the parameters of the Bernoulli-Gaussian (B-G) impulse noise model. The parameters can be estimated accurately and the average number of iterations of the proposed algorithm is acceptable. Simulation results show that over a wide range of impulse noise power, the proposed algorithm approaches the optimal performance under different Rician channel factors and even under Middleton class-A (M-CA) impulse noise models.

Nano crystalline zinc oxide (ZnO) is deposited by room temperature atomic layer deposition (RT-ALD) using dimethylzinc and a plasma excited humidified Ar without thermal treatments. The TEM observation indicated that the deposited ZnO films were crystallized with grain sizes of ∼20 nm on Si in the course of the RT-ALD process. The crystalline ZnO exhibited semiconducting characteristics in a thin film transistor, where the field-effect mobility was recorded at 1.29×10-3cm2/V·s. It is confirmed that the RT deposited ZnO film has an anticorrosion to hot water. The water vapor transmission rate of 8.4×10-3g·m-2·day-1 was measured from a 20 nm thick ZnO capped 40 nm thick Al2O3 on a polyethylene naphthalate film. In this paper, we discuss the crystallization of ZnO in the RT ALD process and its applicability to flexible electronics.

A novel direction of arrival (DOA) estimation method for the coherent signal is presented in this paper. The proposed method applies the eigenvector associated with max eigenvalue, which contains the DOAs of all signals, to form a Toeplitz matrix, yielding an unconstrained optimization problem. Then, the DOA is obtained by peak searching of the pseudo power spectrum without the knowledge of signal number. It is illustrated that the method has a great performance and low computation complexity for the coherent signal. Simulation results verify the usefulness of the method.

Traffic categorization aims to classify network traffic into major service types. A modern deep neural network based on temporal sequence modeling is proposed for encrypted traffic categorization. The contemporary techniques such as dilated convolution and residual connection are adopted as the basic building block. The raw traffic files are pre-processed to generate 1-dimensional flow byte sequences and are feed into our specially-devised network. The proposed approach outperforms other existing methods greatly on a public traffic dataset.

In network function virtualization (NFV) environments, service chaining is an emerging technology that enables network operators to provide network service dynamically and flexibly by using virtual network function (VNF). In the service chaining, a service chain is expected to be constructed based on VNF performances such as dependences among VNFs and traffic changing effects in VNFs. For achieving optimal data transmission services in NFV environments, we focus on the optimal service chain construction based on VNF performances so that both the maximum amount of traffic on links and the total number of VNF instances are decreased. In this paper, at first, an optimization problem is formulated for determining placements of VNFs and a route for each service chain. The service chains can be constructed by solving this optimization problem with an optimization software or meta-heuristic algorithm. Then, for the optimization problem, we propose a heuristic service chain construction algorithm. By using our proposed algorithm, the service chains can be constructed appropriately more quickly. We evaluate the performance of the proposed heuristic algorithm with simulation, and we investigate the effectiveness of the heuristic algorithm from the performance comparison. From some numerical examples, we show that the proposed heuristic algorithm is effective to decrease the amount of traffic and the number of VNF instances. Moreover, it is shown that our proposed heuristic algorithm can construct service chains quickly.

This paper studies a harvested power-oriented simultaneous wireless information and power transfer (SWIPT) scheme over multiple-input multiple-output (MIMO) interference channels in which energy harvesting (EH) circuits exhibit nonlinearity. To maximize the power harvested by all receivers, we propose an algorithm to jointly optimize the transmit beamforming vectors, power splitting (PS) ratios and the receive decoding vectors. As all variables are coupled to some extent, the problem is non-convex and hard to solve. To deal with this non-convex problem, an iterative optimization method is proposed. When two variables are fixed, the third variable is optimized. Specifically, when the transmit beamforming vectors are optimized, the transferred objective function is the sum of several fractional functions. Non-linear sum-of-ratios programming is used to solve the transferred objective function. The convergence and advantage of our proposed scheme compared with traditional EH circuits are validated by simulation results.