Jianfeng XU Satoshi KOMORITA Kei KAWAMURA
We propose a framework for the integration of heterogeneous networks in human pose estimation (HPE) with the aim of balancing accuracy and computational complexity. Although many existing methods can improve the accuracy of HPE using multiple frames in videos, they also increase the computational complexity. The key difference here is that the proposed heterogeneous framework has various networks for different types of frames, while existing methods use the same networks for all frames. In particular, we propose to divide the video frames into two types, including key frames and non-key frames, and adopt three networks including slow networks, fast networks, and transfer networks in our heterogeneous framework. For key frames, a slow network is used that has high accuracy but high computational complexity. For non-key frames that follow a key frame, we propose to warp the heatmap of a slow network from a key frame via a transfer network and fuse it with a fast network that has low accuracy but low computational complexity. Furthermore, when extending to the usage of long-term frames where a large number of non-key frames follow a key frame, the temporal correlation decreases. Therefore, when necessary, we use an additional transfer network that warps the heatmap from a neighboring non-key frame. The experimental results on PoseTrack 2017 and PoseTrack 2018 datasets demonstrate that the proposed FSPose achieves a better balance between accuracy and computational complexity than the competitor method. Our source code is available at https://github.com/Fenax79/fspose.
Runze WANG Zehua ZHANG Yueqin ZHANG Zhongyuan JIANG Shilin SUN Guixiang MA
Recent studies in protein structure prediction such as AlphaFold have enabled deep learning to achieve great attention on the Drug-Target Affinity (DTA) task. Most works are dedicated to embed single molecular property and homogeneous information, ignoring the diverse heterogeneous information gains that are contained in the molecules and interactions. Motivated by this, we propose an end-to-end deep learning framework to perform Molecular Heterogeneous features Fusion (MolHF) for DTA prediction on heterogeneity. To address the challenges that biochemical attributes locates in different heterogeneous spaces, we design a Molecular Heterogeneous Information Learning module with multi-strategy learning. Especially, Molecular Heterogeneous Attention Fusion module is present to obtain the gains of molecular heterogeneous features. With these, the diversity of molecular structure information for drugs can be extracted. Extensive experiments on two benchmark datasets show that our method outperforms the baselines in all four metrics. Ablation studies validate the effect of attentive fusion and multi-group of drug heterogeneous features. Visual presentations demonstrate the impact of protein embedding level and the model ability of fitting data. In summary, the diverse gains brought by heterogeneous information contribute to drug-target affinity prediction.
He HE Shun KOJIMA Kazuki MARUTA Chang-Jun AHN
In mobile communication systems, the channel state information (CSI) is severely affected by the noise effect of the receiver. The adaptive subcarrier grouping (ASG) for sample matrix inversion (SMI) based minimum mean square error (MMSE) adaptive array has been previously proposed. Although it can reduce the additive noise effect by increasing samples to derive the array weight for co-channel interference suppression, it needs to know the signal-to-noise ratio (SNR) in advance to set the threshold for subcarrier grouping. This paper newly proposes adaptive zero padding (AZP) in the time domain to improve the weight accuracy of the SMI matrix. This method does not need to estimate the SNR in advance, and even if the threshold is always constant, it can adaptively identify the position of zero-padding to eliminate the noise interference of the received signal. Simulation results reveal that the proposed method can achieve superior bit error rate (BER) performance under various Rician K factors.
Kazuo TAKARAGI Takashi KUBOTA Sven WOHLGEMUTH Katsuyuki UMEZAWA Hiroki KOYANAGI
Central bank digital currencies require the implementation of eKYC to verify whether a trading customer is eligible online. When an organization issues an ID proof of a customer for eKYC, that proof is usually achieved in practice by a hierarchy of issuers. However, the customer wants to disclose only part of the issuer's chain and documents to the trading partner due to privacy concerns. In this research, delegatable anonymous credential (DAC) and zero-knowledge range proof (ZKRP) allow customers to arbitrarily change parts of the delegation chain and message body to range proofs expressed in inequalities. That way, customers can protect the privacy they need with their own control. Zero-knowledge proof is applied to prove the inequality between two time stamps by the time stamp server (signature presentation, public key revocation, or non-revocation) without disclosing the signature content and stamped time. It makes it possible to prove that the registration information of the national ID card is valid or invalid while keeping the user's personal information anonymous. This research aims to contribute to the realization of a sustainable financial system based on self-sovereign identity management with privacy-enhanced PKI.
Yaping SUN Gaoqi DOU Hao WANG Yufei ZHANG
With the advent of the Internet of Things (IoT), short packet transmissions will dominate the future wireless communication. However, traditional coherent demodulation and channel estimation schemes require large pilot overhead, which may be highly inefficient for short packets in multipath fading scenarios. This paper proposes a novel pilot-free short packet structure based on the association of modulation on conjugate-reciprocal zeros (MOCZ) and tail-biting convolutional codes (TBCC), where a noncoherent demodulation and decoding scheme is designed without the channel state information (CSI) at the transceivers. We provide a construction method of constellation sets and demodulation rule for M-ary MOCZ. By deriving low complexity log-likelihood ratios (LLR) for M-ary MOCZ, we offer a reasonable balance between energy and bandwidth efficiency for joint coding and modulation scheme. Simulation results show that our proposed scheme can attain significant performance and throughput gains compared to the pilot-based coherent modulation scheme over multipath fading channels.
Feng LIU Xianlong CHENG Conggai LI Yanli XU
This letter solves the energy efficiency optimization problem for the simultaneous wireless information and power transfer (SWIPT) systems with non-orthogonal multiple access (NOMA), multiple input single output (MISO) and power-splitting structures, where each user may have different individual quality of service (QoS) requirements about information and energy. Nonlinear energy harvesting model is used. Alternate optimization approach is adopted to find the solution, which shows a fast convergence behavior. Simulation results show the proposed scheme has higher energy efficiency than existing dual-layer iteration and throughput maximization methods.
Long LIU Gensai TEI Masahiro WATANABE
We have proposed integrated waveguide structure suitable for mid- and near- infrared light propagation using Si and CaF2 heterostructures on Si substrate. Using a fabrication process based on etching, lithography and crystal growth techniques, we have formed a slab-waveguide structure with a current injection mechanism on a SOI substrate, which would be a key component for Si/CaF2 quantum cascade lasers and other optical integrated systems. The propagation of light at a wavelength of 1.55 µm through a Si/CaF2 waveguide structure have been demonstrated for the first time using a structure with a Si/CaF2 multilayered core with 610-nm-thick, waveguide width of 970 nm, which satisfies single-mode condition in the horizontal direction within a tolerance of fabrication accuracy. The waveguide loss for transverse magnetic (TM) mode has been evaluated to be 51.4 cm-1. The cause of the loss was discussed by estimating the edge roughness scattering and free carrier absorption, which suggests further reduction of the loss would be possible.
Xiuping PENG Mingshuo SHEN Hongbin LIN Shide WANG
This letter provides a direct construction of binary even-length Z-complementary pairs. To date, the maximum zero correlation zone ratio of Type-I Z-complementary pairs has reached 6/7, but no direct construction of Z-complementary pairs can achieve the zero correlation zone ratio of 6/7. In this letter, based on Boolean function, we give a direct construction of binary even-length Z-complementary pairs with zero correlation zone ratio 6/7. The length of constructed Z-complementary pairs is 2m+3 + 2m + 2+2m+1 and the width of zero correlation zone is 2m+3 + 2m+2.
Fan LIU Zhewang MA Weihao ZHANG Masataka OHIRA Dongchun QIAO Guosheng PU Masaru ICHIKAWA
A novel compact 5-pole bandpass filter (BPF) using two different types of resonators, one is coaxial TEM-mode resonator and the other dielectric triple-mode resonator, is proposed in this paper. The coaxial resonator is a simple single-mode resonator, while the triple-mode dielectric resonator (DR) includes one TM01δ mode and two degenerate HE11 modes. An excellent spurious performance of the BPF is obtained due to the different resonant behaviors of these two types of resonators used in the BPF. The coupling scheme of the 5-pole BPF includes two cascade triplets (CTs) which produce two transmission zeros (TZs) and a sharp skirt of the passband. Behaviors of the resonances, the inter-resonance couplings, as well as their tuning methods are investigated in detail. A procedure of mapping the coupling matrix of the BPF to its physical dimensions is developed, and an optimization of these physical dimensions is implemented to achieve best performance of the filter. The designed BPF is operated at 1.84GHz with a bandwidth of 51MHz. The stopband rejection is better than 20dB up to 9.7GHz (about 5.39×f0) except 7.85GHz. Good agreement between the designed and theoretically synthesized responses of the BPF is reached, verifying well the proposed configuration of the BPF and its design method.
Sixia LI Shogo OKADA Jianwu DANG
Zero-shot slot filling is a domain adaptation approach to handle unseen slots in new domains without training instances. Previous studies implemented zero-shot slot filling by predicting both slot entities and slot types. Because of the lack of knowledge about new domains, the existing methods often fail to predict slot entities for new domains as well as cannot effectively predict unseen slot types even when slot entities are correctly identified. Moreover, for some seen slot types, those methods may suffer from the domain shift problem, because the unseen context in new domains may change the explanations of the slots. In this study, we propose intrinsic representations to alleviate the domain shift problems above. Specifically, we propose a multi-relation-based representation to capture both the general and specific characteristics of slot entities, and an ontology-based representation to provide complementary knowledge on the relationships between slots and values across domains, for handling both unseen slot types and unseen contexts. We constructed a two-step pipeline model using the proposed representations to solve the domain shift problem. Experimental results in terms of the F1 score on three large datasets—Snips, SGD, and MultiWOZ 2.3—showed that our model outperformed state-of-the-art baselines by 29.62, 10.38, and 3.89, respectively. The detailed analysis with the average slot F1 score showed that our model improved the prediction by 25.82 for unseen slot types and by 10.51 for seen slot types. The results demonstrated that the proposed intrinsic representations can effectively alleviate the domain shift problem for both unseen slot types and seen slot types with unseen contexts.
In this paper, we propose an online probabilistic activation/deactivation control method for base stations (BSs) in heterogeneous networks based on the temporal system throughput and activation states of neighbor BSs (cells). The conventional method iteratively updates the activation/deactivation states in a probabilistic manner at each BS based on the change in the observed system throughput and activation/deactivation states of that BS between past multiple consecutive discrete times. Since BS activation control increases the system throughput by improving the tradeoff between the reduction in inter-cell interference and the traffic off-loading effect, the activation of a BS whose neighbor BSs are deactivated is likely to result in improved system performance and vice versa. The proposed method newly introduces a metric, which represents the effective ratio of the activated neighbor BSs considering their transmission power and distance to the BS of interest, to the update control of the activation probability. This improves both the convergence rate of the iterative algorithm and throughput performance after convergence. Computer simulation results, in which the mobility of the user terminals is taken into account, show the effectiveness of the proposed method.
An asymmetric zero correlation zone (A-ZCZ) sequence set can be regarded as a special type of ZCZ sequence set, which consists of multiple sequence subsets. Each subset is a ZCZ sequence set, and have a common zero cross-correlation zone (ZCCZ) between sequences from different subsets. This paper supplements an existing construction of A-ZCZ sequence sets and further improves the research results. Besides, a new construction of A-ZCZ sequence sets is proposed by matrices transformation. The obtained sequence sets are optimal with respect to theoretical bound, and the parameters can be chosen more flexibly, such as the number of subsets and the lengths of ZCCZ between sequences from different subsets. Moreover, as the diversity of the orthogonal matrices and the flexibility of initial matrix, more A-ZCZ sequence sets can be obtained. The resultant sequence sets presented in this paper can be applied to multi-cell quasi-synchronous code-division multiple-access (QS-CDMA) systems, to eliminate the interference not only from the same cell but also from adjacent cells.
Stance prediction on social media aims to infer the stances of users towards a specific topic or event, which are not expressed explicitly. It is of great significance for public opinion analysis to extract and determine users' stances using user-generated content on social media. Existing research makes use of various signals, ranging from text content to online network connections of users on these platforms. However, it lacks joint modeling of the heterogeneous information for stance prediction. In this paper, we propose a self-supervised heterogeneous graph contrastive learning framework for stance prediction in online debate forums. Firstly, we perform data augmentation on the original heterogeneous information network to generate an augmented view. The original view and augmented view are learned from a meta-path based graph encoder respectively. Then, the contrastive learning among the two views is conducted to obtain high-quality representations of users and issues. Finally, the stance prediction is accomplished by matrix factorization between users and issues. The experimental results on an online debate forum dataset show that our model outperforms other competitive baseline methods significantly.
In recent years, Graph Neural Networks has received enormous attention from academia for its huge potential of modeling the network traits such as macrostructure and single node attributes. However, prior mainstream works mainly focus on homogeneous network and lack the capacity to characterize the network heterogeneous property. Besides, most previous literature cannot the model latent influence link under microscope vision, making it infeasible to model the joint relation between the heterogeneity and mutual interaction within multiple relation type. In this letter, we propose a latent influence based self-attention framework to address the difficulties mentioned above. To model the heterogeneity and mutual interactions, we redesign the attention mechanism with latent influence factor on single-type relation level, which learns the importance coefficient from its adjacent neighbors under the same meta-path based patterns. To incorporate the heterogeneous meta-path in a unified dimension, we developed a novel self-attention based framework for meta-path relation fusion according to the learned meta-path coefficient. Our experimental results demonstrate that our framework not only achieves higher results than current state-of-the-art baselines, but also shows promising vision on depicting heterogeneous interactive relations under complicated network structure.
Ding LI Chunxiang GU Yuefei ZHU
Website Fingerprinting (WF) enables a passive attacker to identify which website a user is visiting over an encrypted tunnel. Current WF attacks have two strong assumptions: (i) specific tunnel, i.e., the attacker can train on traffic samples collected in a simulated tunnel with the same tunnel settings as the user, and (ii) pseudo-open-world, where the attacker has access to training samples of unmonitored sites and treats them as a separate class. These assumptions, while experimentally feasible, render WF attacks less usable in practice. In this paper, we present Gene Fingerprinting (GF), a new WF attack that achieves cross-tunnel transferability by generating fingerprints that reflect the intrinsic profile of a website. The attack leverages Zero-shot Learning — a machine learning technique not requiring training samples to identify a given class — to reduce the effort to collect data from different tunnels and achieve a real open-world. We demonstrate the attack performance using three popular tunneling tools: OpenSSH, Shadowsocks, and OpenVPN. The GF attack attains over 94% accuracy on each tunnel, far better than existing CUMUL, DF, and DDTW attacks. In the more realistic open-world scenario, the attack still obtains 88% TPR and 9% FPR, outperforming the state-of-the-art attacks. These results highlight the danger of our attack in various scenarios where gathering and training on a tunnel-specific dataset would be impractical.
Yaying SHEN Qun LI Ding XU Ziyi ZHANG Rui YANG
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.
Toru NAKANISHI Hiromi YOSHINO Tomoki MURAKAMI Guru-Vamsi POLICHARLA
To prove the graph relations such as the connectivity and isolation for a certified graph, a system of a graph signature and proofs has been proposed. In this system, an issuer generates a signature certifying the topology of an undirected graph, and issues the signature to a prover. The prover can prove the knowledge of the signature and the graph in the zero-knowledge, i.e., the signature and the signed graph are hidden. In addition, the prover can prove relations on the certified graph such as the connectivity and isolation between two vertexes. In the previous system, using integer commitments on RSA modulus, the graph relations are proved. However, the RSA modulus needs a longer size for each element. Furthermore, the proof size and verification cost depend on the total numbers of vertexes and edges. In this paper, we propose a graph signature and proof system, where these are computed on bilinear groups without the RSA modulus. Moreover, using a bilinear map accumulator, the prover can prove the connectivity and isolation on a graph, where the proof size and verification cost become independent from the total numbers of vertexes and edges.
The effect of provision of “Neither-Good-Nor-Bad” (NGNB) information on the perceived trustworthiness of agents has been investigated in previous studies. The experimental results have revealed several conditions under which the provision of NGNB information works effectively to make users perceive greater trust of agents. However, the experiments in question were carried out in a situation in which a user is able to choose, with the agent's advice, one of a limited number of options. In practical problems, we are often at a loss as to which to choose because there are too many possible options and it is not easy to narrow them down. Furthermore, in the above-mentioned previous studies, it was easy to predict the size of profits that a user would obtain because its pattern was also limited. This prompted us, in this paper, to investigate the effect of provision of NGNB information on the users' trust of agents under conditions where it appears to the users that numerous options are available. Our experimental results reveal that an agent that reliably provides NGNB information tends to gain greater user trust in a situation where it appears to the users that there are numerous options and their consequences, and it is not easy to predict the size of profits. However, in contradiction to the previous study, the results in this paper also reveal that stable provision of NGNB information in the context of numerous options is less effective in a situation where it is harder to obtain larger profits.
Tetsunao MATSUTA Tomohiko UYEMATSU
We consider the coding problem for lossy source coding with side information at the decoder, which is known as the Wyner-Ziv source coding problem. The goal of the coding problem is to find the minimum rate such that the probability of exceeding a given distortion threshold is less than the desired level. We give an equivalent expression of the minimum rate by using the chromatic number and notions of covering of a set. This allows us to analyze the coding problem in terms of graph coloring and covering.
Hiroki NISHIKAWA Kana SHIMADA Ittetsu TANIGUCHI Hiroyuki TOMIYAMA
With the demand for energy-efficient and high- performance computing, multicore architecture has become more appealing than ever. Multicore task scheduling is one of domains in parallel computing which exploits the parallelism of multicore. Unlike traditional scheduling, multicore task scheduling has recently been studied on the assumption that tasks have inherent parallelism and can be split into multiple sub-tasks in data parallel fashion. However, it is still challenging to properly determine the degree of parallelism of tasks and mapping on multicores. Our proposed scheduling techniques determine the degree of parallelism of tasks, and sub-tasks are decided which type of cores to be assigned to heterogeneous multicores. In addition, two approaches to hardware/software codesign for heterogeneous multicore systems are proposed. The works optimize the types of cores organized in the architecture simultaneously with scheduling of the tasks such that the overall energy consumption is minimized under a deadline constraint, a warm start approach is also presented to effectively solve the problem. The experimental results show the simultaneous scheduling and core-type optimization technique remarkably reduces the energy consumption.