In wireless networks, efficient topology improves the performance of network protocols. The previous research mainly focuses on how to construct a cost-efficient network structure from a static and connected topology. Due to lack of continuous connectivity in the underlying topology, most traditional topology control methods are not applicable to the delay or disruption tolerant networks (DTNs). In this paper, we consider the topology control problem in a predictable DTN where the dynamic topology is known a priori or can be predicted over time. First, this dynamic topology is modeled by a directed space-time graph that includes spatial and temporal information. Second, the topology control problem of the predictable DTN is formulated as building a sparse structure. For any pair devices, there is an efficient path connecting them to improve the efficiency of the generated structure. Then, a topology control strategy is proposed for this optimization problem by using a kth shortest paths algorithm. Finally, simulations are conducted on random networks and a real-world DTN tracing date. The results demonstrate that the proposed method can significantly improve the efficiency of the generated structure and reduce the total cost.

In this paper, we propose an automatic design support system for compact acoustic devices such as microspeakers inside smartphones. The proposed design support system outputs the dimensions of compact acoustic devices with the desired acoustic characteristic. This system uses a deep neural network (DNN) to obtain the relationship between the frequency characteristic of the compact acoustic device and its dimensions. The training data are generated by the acoustic finite-difference time-domain (FDTD) method so that many training data can be easily obtained. We demonstrate the effectiveness of the proposed system through some comparisons between desired and designed frequency characteristics.

The paper employed an Alexnet, which is a deep learning framework, to automatically diagnose the damages of wind power generator blade surfaces. The original images of wind power generator blade surfaces were captured by machine visions of a 4-rotor UAV (unmanned aerial vehicle). Firstly, an 8-layer Alexnet, totally including 21 functional sub-layers, is constructed and parameterized. Secondly, the Alexnet was trained with 10000 images and then was tested by 6-turn 350 images. Finally, the statistic of network tests shows that the average accuracy of damage diagnosis by Alexnet is about 99.001%. We also trained and tested a traditional BP (Back Propagation) neural network, which have 20-neuron input layer, 5-neuron hidden layer, and 1-neuron output layer, with the same image data. The average accuracy of damage diagnosis of BP neural network is 19.424% lower than that of Alexnet. The point shows that it is feasible to apply the UAV image acquisition and the deep learning classifier to diagnose the damages of wind turbine blades in service automatically.

A travel route recommendation service that recommends a sequence of points of interest for tourists traveling in an unfamiliar city is a very useful tool in the field of location-based social networks. Although there are many web services and mobile applications that can help tourists to plan their trips by providing information about sightseeing attractions, travel route recommendation services are still not widely applied. One reason could be that most of the previous studies that addressed this task were based on the orienteering problem model, which mainly focuses on the estimation of a user-location relation (for example, a user preference). This assumes that a user receives a reward by visiting a point of interest and the travel route is recommended by maximizing the total rewards from visiting those locations. However, a location-location relation, which we introduce as a transition pattern in this paper, implies useful information such as visiting order and can help to improve the quality of travel route recommendations. To this end, we propose a travel route recommendation method by combining location and transition knowledge, which assigns rewards for both locations and transitions.

For cross-corpus speech emotion recognition (SER), how to obtain effective feature representation for the discrepancy elimination of feature distributions between source and target domains is a crucial issue. In this paper, we propose a Target-adapted Subspace Learning (TaSL) method for cross-corpus SER. The TaSL method trys to find a projection subspace, where the feature regress the label more accurately and the gap of feature distributions in target and source domains is bridged effectively. Then, in order to obtain more optimal projection matrix, ℓ1 norm and ℓ2,1 norm penalty terms are added to different regularization terms, respectively. Finally, we conduct extensive experiments on three public corpuses, EmoDB, eNTERFACE and AFEW 4.0. The experimental results show that our proposed method can achieve better performance compared with the state-of-the-art methods in the cross-corpus SER tasks.

Free/libre open source software (FLOSS) are being rapidly employed in several companies and organizations, because it can be modified and used for free. Hence, the use of FLOSS could contribute to its originally intended benefits and to the competence of its users. In this study, we analyzed the effect of using FLOSS on related competences. We investigated the change in the competences through an empirical study before and after the use of FLOSS among project participants. Consequently, it was confirmed that the competences of the participants improved after utilizing FLOSS.

Indexing is one of the fields where the non-volatile memory (NVM) has the advantages of byte-addressable characteristics and fast read/write speed. The existing index structures for NVM have been developed based on the fact that the size of cache line and the atomicity guarantee unit of NVM are different and they tried to overcome the weakness of consistency from the difference. To overcome the weakness, an expensive flush operation is required which results in a lower performance than a basic B+tree index. Recent studies have shown that the I/O units of the NVM can be matched with the atomicity guarantee units under limited circumstances. In this paper, we propose a Cache line sized Atomic Write B+tree (CAWBT), which is a minimal B+tree structure that shows higher performance than a basic b+ tree and designed for NVM. CAWBT has almost same performance compared to basic B+tree without consistency guarantee and shows remarkable performance improvement compared to other B+tree indexes for NVM.

This paper demonstrates latent word recurrent neural network language models (LW-RNN-LMs) for enhancing automatic speech recognition (ASR). LW-RNN-LMs are constructed so as to pick up advantages in both recurrent neural network language models (RNN-LMs) and latent word language models (LW-LMs). The RNN-LMs can capture long-range context information and offer strong performance, and the LW-LMs are robust for out-of-domain tasks based on the latent word space modeling. However, the RNN-LMs cannot explicitly capture hidden relationships behind observed words since a concept of a latent variable space is not present. In addition, the LW-LMs cannot take into account long-range relationships between latent words. Our idea is to combine RNN-LM and LW-LM so as to compensate individual disadvantages. The LW-RNN-LMs can support both a latent variable space modeling as well as LW-LMs and a long-range relationship modeling as well as RNN-LMs at the same time. From the viewpoint of RNN-LMs, LW-RNN-LM can be considered as a soft class RNN-LM with a vast latent variable space. In contrast, from the viewpoint of LW-LMs, LW-RNN-LM can be considered as an LW-LM that uses the RNN structure for latent variable modeling instead of an n-gram structure. This paper also details a parameter inference method and two kinds of implementation methods, an n-gram approximation and a Viterbi approximation, for introducing the LW-LM to ASR. Our experiments show effectiveness of LW-RNN-LMs on a perplexity evaluation for the Penn Treebank corpus and an ASR evaluation for Japanese spontaneous speech tasks.

Recently, social relation analysis receives an increasing amount of attention from text to image data. However, social relation analysis from video is an important problem, which is lacking in the current literature. There are still some challenges: 1) it is hard to learn a satisfactory mapping function from low-level pixels to high-level social relation space; 2) how to efficiently select the most relevant information from noisy and unsegmented video. In this paper, we present an Attentive Sequences Recurrent Network model, called ASRN, to deal with the above challenges. First, in order to explore multiple clues, we design a Multiple Feature Attention (MFA) mechanism to fuse multiple visual features (i.e. image, motion, body, and face). Through this manner, we can generate an appropriate mapping function from low-level video pixels to high-level social relation space. Second, we design a sequence recurrent network based on Global and Local Attention (GLA) mechanism. Specially, an attention mechanism is used in GLA to integrate global feature with local sequence feature to select more relevant sequences for the recognition task. Therefore, the GLA module can better deal with noisy and unsegmented video. At last, extensive experiments on the SRIV dataset demonstrate the performance of our ASRN model.

The aim of this paper is to propose effective attentional regions for fine-grained visual recognition. Based on the Spatial Transformers' capability of spatial manipulation within networks, we propose an extension model, the Attention-Guided Spatial Transformer Networks (AG-STNs). This model can guide the Spatial Transformers with hard-coded attentional regions at first. Then such guidance can be turned off, and the network model will adjust the region learning in terms of the location and scale. Such adjustment is conditioned to the classification loss so that it is actually optimized for better recognition results. With this model, we are able to successfully capture detailed attentional information. Also, the AG-STNs are able to capture attentional information in multiple levels, and different levels of attentional information are complementary to each other in our experiments. A fusion of them brings better results.

In-class species classification based on animal sounds is a highly challenging task even with the latest deep learning technique applied. The difficulty of distinguishing the species is further compounded when the number of species is large within the same class. This paper presents a novel approach for fine categorization of animal species based on their sounds by using pre-trained CNNs and a new self-attention module well-suited for acoustic signals The proposed method is shown effective as it achieves average species accuracy of 98.37% and the minimum species accuracy of 94.38%, the highest among the competing baselines, which include CNN's without self-attention and CNN's with CBAM, FAM, and CFAM but without pre-training.

Sensor-data gathering using multi-hop connections in a wireless sensor network is being widely used, and a tree topology for data gathering is considered promising because it eases data aggregation. Therefore, many sensor-tree-creation algorithms have been proposed. The sensors in a tree, however, generally run on batteries, so long tree lifetime is one of the most important factors in collecting sensor data from a tree over a long period. It has been proven that creating the longest-lifetime tree is a non-deterministic-polynomial complete problem; thus, all previously proposed sensor-tree-creation algorithms are heuristic. To evaluate a heuristic algorithm, the time complexity of the algorithm is very important, as well as the quantitative evaluation of the lifetimes of the created trees and algorithm speed. This paper proposes an algorithm called assured switching with accurate graph optimization (ASAGAO) that can create a sensor tree with a much longer lifetime much faster than other sensor-tree-creation algorithms. In addition, it has much smaller time complexity.

Stance detection in twitter aims at mining user stances expressed in a tweet towards a single or multiple target entities. Detecting and analyzing user stances from massive opinion-oriented twitter posts provide enormous opportunities to journalists, governments, companies, and other organizations. Most of the prior studies have explored the traditional deep learning models, e.g., long short-term memory (LSTM) and gated recurrent unit (GRU) for detecting stance in tweets. However, compared to these traditional approaches, recently proposed densely connected bidirectional LSTM and nested LSTMs architectures effectively address the vanishing-gradient and overfitting problems as well as dealing with long-term dependencies. In this paper, we propose a neural network model that adopts the strengths of these two LSTM variants to learn better long-term dependencies, where each module coupled with an attention mechanism that amplifies the contribution of important elements in the final representation. We also employ a multi-kernel convolution on top of them to extract the higher-level tweet representations. Results of extensive experiments on single and multi-target benchmark stance detection datasets show that our proposed method achieves substantial improvement over the current state-of-the-art deep learning based methods.

Semi-bent functions have important applications in cryptography and coding theory. 2-rotation symmetric semi-bent functions are a class of semi-bent functions with the simplicity for efficient computation because of their invariance under 2-cyclic shift. However, no construction of 2-rotation symmetric semi-bent functions with algebraic degree bigger than 2 has been presented in the literature. In this paper, we introduce four classes of 2m-variable 2-rotation symmetric semi-bent functions including balanced ones. Two classes of 2-rotation symmetric semi-bent functions have algebraic degree from 3 to m for odd m≥3, and the other two classes have algebraic degree from 3 to m/2 for even m≥6 with m/2 being odd.

This paper deals with the problem of minimizing roundoff noise and pole sensitivity simultaneously subject to l2-scaling constraints for state-space digital filters. A novel measure for evaluating roundoff noise and pole sensitivity is proposed, and an efficient technique for minimizing this measure by jointly optimizing state-space realization and error feedback is explored, namely, the constrained optimization problem at hand is converted into an unconstrained problem and then the resultant problem is solved by employing a quasi-Newton algorithm. A numerical example is presented to demonstrate the validity and effectiveness of the proposed technique.

In conventional video streaming systems, various kind of video streams are delivered from a dedicated server (e.g., edge server) to the subscribers so that a video stream of higher quality level is encoded with a higher bitrate. In this paper, we consider the problem of delivering those video streams with the assistance of Peer-to-Peer (P2P) technology with as small server cost as possible while keeping the performance of video streaming in terms of the throughput and the latency. The basic idea of the proposed method is to divide a given video stream into several sub-streams called stripes as evenly as possible and to deliver those stripes to the subscribers through different tree-structured overlays. Such a stripe-based approach could average the load of peers, and could effectively resolve the overloading of the overlay for high quality video streams. The performance of the proposed method is evaluated numerically. The result of evaluations indicates that the proposed method significantly reduces the server cost necessary to guarantee a designated delivery hops, compared with a naive tree-based scheme.

Interference alignment (IA) in temporal domain is important in the case of single-antenna vehicle communications. In this paper, perfect cyclic IA based on propagation delay is extended to the K×2 X channels with two receivers and arbitrary transmitters K≥2, which achieves the maximal multiplexing gain by obtaining the theoretical degree of freedom of 2K/(K+1). We deduce the alignment and separability conditions, and propose a general scheme which is flexible in setting the index of time-slot for IA at the receiver side. Furthermore, the feasibility of the proposed scheme in the two-/three- Euclidean space is analyzed and demonstrated.

Optical orthogonal signature pattern codes (OOSPCs) have attracted great attention due to their important application in the spatial code-division multiple-access network for image transmission. In this paper, we give a construction for OOSPCs based on cyclic codes over Fp. Applying this construction with the Reed-Solomon codes and the generalized Berlekamp-Justesen codes, we obtain two classes of asymptotically optimal OOSPCs.

This paper proposes a deep neural network (DNN) based framework to address the problem of vector quantization (VQ) for high-dimensional data. The main challenge of applying DNN to VQ is how to reduce the binary coding error of the auto-encoder when the distribution of the coding units is far from binary. To address this problem, three fine-tuning methods have been adopted: 1) adding Gaussian noise to the input of the coding layer, 2) forcing the output of the coding layer to be binary, 3) adding a non-binary penalty term to the loss function. These fine-tuning methods have been extensively evaluated on quantizing speech magnitude spectra. The results demonstrated that each of the methods is useful for improving the coding performance. When implemented for quantizing 968-dimensional speech spectra using only 18-bit, the DNN-based VQ framework achieved an averaged PESQ of about 2.09, which is far beyond the capability of conventional VQ methods.

In this paper, a new transceiver system for the in-vehicle communication system is proposed to enhance data transmission rate and timing accuracy in TDM-based application. The proposed system utilizes point-to-point (P2P) channel, a closed-loop clock forwarding path, and a transceiver with a repeater and clock delay adjuster. The proposed system with 4 ECU (Electronic Computing Unit) nodes is implemented in 180nm CMOS technology and, when compared with conventional bus-based system, achieved more than 125 times faster data transmission. The maximum data rate was 2.5Gbps at 1.8V power supply and the worst peak-to-peak jitter for the data and clock signals over 5000 data symbols were about 49.6ps and 9.8ps respectively.