Weizhi LIAO Mingtong HUANG Pan MA Yu WANG
There are many knowledge entities in sci-tech intelligence resources. Extracting these knowledge entities is of great importance for building knowledge networks, exploring the relationship between knowledge, and optimizing search engines. Many existing methods, which are mainly based on rules and traditional machine learning, require significant human involvement, but still suffer from unsatisfactory extraction accuracy. This paper proposes a novel approach for knowledge entity extraction based on BiLSTM and conditional random field (CRF).A BiLSTM neural network to obtain the context information of sentences, and CRF is then employed to integrate global label information to achieve optimal labels. This approach does not require the manual construction of features, and outperforms conventional methods. In the experiments presented in this paper, the titles and abstracts of 20,000 items in the existing sci-tech literature are processed, of which 50,243 items are used to build benchmark datasets. Based on these datasets, comparative experiments are conducted to evaluate the effectiveness of the proposed approach. Knowledge entities are extracted and corresponding knowledge networks are established with a further elaboration on the correlation of two different types of knowledge entities. The proposed research has the potential to improve the quality of sci-tech information services.
Yangshengyan LIU Fu GU Yangjian JI Yijie WU Jianfeng GUO Xinjian GU Jin ZHANG
Resource sharing is to ensure required resources available for their demanders. However, due to the lack of proper sharing model, the current sharing rate of the scientific and technological resources is low, impeding technological innovation and value chain development. Here we propose a novel method to share scientific and technological resources by storing resources as nodes and correlations as links to form a complex network. We present a few-shot relational learning model to solve the cold-start and long-tail problems that are induced by newly added resources. Experimentally, using NELL-One and Wiki-One datasets, our one-shot results outperform the baseline framework - metaR by 40.2% and 4.1% on MRR in Pre-Train setting. We also show two practical applications, a resource graph and a resource map, to demonstrate how the complex network helps resource sharing.
Radomir S. STANKOVIĆ Milena STANKOVIĆ Claudio MORAGA Jaakko T. ASTOLA
Binary bent functions have a strictly specified number of non-zero values. In the same way, ternary bent functions satisfy certain requirements on the elements of their value vectors. These requirements can be used to specify six classes of ternary bent functions. Classes are mutually related by encoding of function values. Given a basic ternary bent function, other functions in the same class can be constructed by permutation matrices having a block structure similar to that of the factor matrices appearing in the Good-Thomas decomposition of Cooley-Tukey Fast Fourier transform and related algorithms.
Masayoshi NAKAMOTO Naoyuki AIKAWA
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.
A scheme is proposed for generation of large-amplitude short pulses using a transmission line with regularly spaced series-connected tunnel diodes (TDs). In the case where the loaded TD is unique, it is established that the leading edge of the inputted pulse moves slower than the trailing edge, when the pulse amplitude exceeds the peak voltage of the loaded TD; therefore, the pulse width is autonomously reduced through propagation in the line. In this study, we find that this property is true even when the several series-connected TDs are loaded periodically. By these mechanisms, the TD line succeeds in generating large and short pulses. Herein, we clarify the design criteria of the TD line, together with both numerical and experimental validation.
This paper reviews the evolutionary process that reduced the transmission loss of silica optical fibers from the report of 20dB/km by Corning in 1970 to the current record-low loss. At an early stage, the main effort was to remove impurities especially hydroxy groups for fibers with GeO2-SiO2 core, resulting in the loss of 0.20dB/km in 1980. In order to suppress Rayleigh scattering due to composition fluctuation, pure-silica-core fibers were developed, and the loss of 0.154dB/km was achieved in 1986. As the residual main factor of the loss, Rayleigh scattering due to density fluctuation was actively investigated by utilizing IR and Raman spectroscopy in the 1990s and early 2000s. Now, ultra-low-loss fibers with the loss of 0.150dB/km are commercially available in trans-oceanic submarine cable systems.
Ryosuke SUGIURA Yutaka KAMAMOTO Takehiro MORIYA
This paper presents extended-domain Golomb (XDG) code, an extension of Golomb code for sparse geometric sources as well as a generalization of extended-domain Golomb-Rice (XDGR) code, based on the idea of almost instantaneous fixed-to-variable length (AIFV) codes. Showing that the XDGR encoding can be interpreted as extended usage of the code proposed in the previous works, this paper discusses the following two facts: The proposed XDG code can be constructed as an AIFV code relating to Golomb code as XDGR code does to Rice code; XDG and Golomb codes are symmetric in the sense of relative redundancy. The proposed XDG code can be efficiently used for losslessly compressing geometric sources too sparse for the conventional Golomb and Rice codes. According to the symmetry, its relative redundancy is guaranteed to be as low as Golomb code compressing non-sparse geometric sources. Awing to this fact, the parameter of the proposed XDG code, which is more finely tunable than the conventional XDGR code, can be optimized for given inputs using the conventional techniques. Therefore, it is expected to be more useful for many coding applications that deal with geometric sources at low bit rates.
Yusuke HARA Xueting WANG Toshihiko YAMASAKI
Video inpainting is a task of filling missing regions in videos. In this task, it is important to efficiently use information from other frames and generate plausible results with sufficient temporal consistency. In this paper, we present a video inpainting method jointly using affine transformation and deformable convolutions for frame alignment. The former is responsible for frame-scale rough alignment and the latter performs pixel-level fine alignment. Our model does not depend on 3D convolutions, which limits the temporal window, or troublesome flow estimation. The proposed method achieves improved object removal results and better PSNR and SSIM values compared with previous learning-based methods.
Ahmed Salih AL-KHALEEFA Rosilah HASSAN Mohd Riduan AHMAD Faizan QAMAR Zheng WEN Azana Hafizah MOHD AMAN Keping YU
Machine learning is becoming an attractive topic for researchers and industrial firms in the area of computational intelligence because of its proven effectiveness and performance in resolving real-world problems. However, some challenges such as precise search, intelligent discovery and intelligent learning need to be addressed and solved. One most important challenge is the non-steady performance of various machine learning models during online learning and operation. Online learning is the ability of a machine-learning model to modernize information without retraining the scheme when new information is available. To address this challenge, we evaluate and analyze four widely used online machine learning models: Online Sequential Extreme Learning Machine (OSELM), Feature Adaptive OSELM (FA-OSELM), Knowledge Preserving OSELM (KP-OSELM), and Infinite Term Memory OSELM (ITM-OSELM). Specifically, we provide a testbed for the models by building a framework and configuring various evaluation scenarios given different factors in the topological and mathematical aspects of the models. Furthermore, we generate different characteristics of the time series to be learned. Results prove the real impact of the tested parameters and scenarios on the models. In terms of accuracy, KP-OSELM and ITM-OSELM are superior to OSELM and FA-OSELM. With regard to time efficiency related to the percentage of decreases in active features, ITM-OSELM is superior to KP-OSELM.
Keiichiro SATO Ryoichi SHINKUMA Takehiro SATO Eiji OKI Takanori IWAI Takeo ONISHI Takahiro NOBUKIYO Dai KANETOMO Kozo SATODA
Predictive spatial-monitoring, which predicts spatial information such as road traffic, has attracted much attention in the context of smart cities. Machine learning enables predictive spatial-monitoring by using a large amount of aggregated sensor data. Since the capacity of mobile networks is strictly limited, serious transmission delays occur when loads of communication traffic are heavy. If some of the data used for predictive spatial-monitoring do not arrive on time, prediction accuracy degrades because the prediction has to be done using only the received data, which implies that data for prediction are ‘delay-sensitive’. A utility-based allocation technique has suggested modeling of temporal characteristics of such delay-sensitive data for prioritized transmission. However, no study has addressed temporal model for prioritized transmission in predictive spatial-monitoring. Therefore, this paper proposes a scheme that enables the creation of a temporal model for predictive spatial-monitoring. The scheme is roughly composed of two steps: the first involves creating training data from original time-series data and a machine learning model that can use the data, while the second step involves modeling a temporal model using feature selection in the learning model. Feature selection enables the estimation of the importance of data in terms of how much the data contribute to prediction accuracy from the machine learning model. This paper considers road-traffic prediction as a scenario and shows that the temporal models created with the proposed scheme can handle real spatial datasets. A numerical study demonstrated how our temporal model works effectively in prioritized transmission for predictive spatial-monitoring in terms of prediction accuracy.
Toshihisa NABETANI Masahiro SEKIYA
With the development of the IEEE 802.11 standard for wireless LANs, there has been an enormous increase in the usage of wireless LANs in factories, plants, and other industrial environments. In industrial applications, wireless LAN systems require high reliability for stable real-time communications. In this paper, we propose a multi-access-point (AP) diversity method that contributes to the realization of robust data transmissions toward realization of ultra-reliable low-latency communications (URLLC) in wireless LANs. The proposed method can obtain a diversity effect of multipaths with independent transmission errors and collisions without modification of the IEEE 802.11 standard or increasing overhead of communication resources. We evaluate the effects of the proposed method by numerical analysis, develop a prototype to demonstrate its feasibility, and perform experiments using the prototype in a factory wireless environment. These numerical evaluations and experiments show that the proposed method increases reliability and decreases transmission delay.
Xin-Ling GUO Zhe-Ming LU Yi-Jia ZHANG
Robustness of complex networks is an essential subject for improving their performance when vertices or links are removed due to potential threats. In recent years, significant advancements have been achieved in this field by many researchers. In this paper we show an overview from a novel statistic perspective. We present a brief review about complex networks at first including 2 primary network models, 12 popular attack strategies and the most convincing network robustness metrics. Then, we focus on the correlations of 12 attack strategies with each other, and the difference of the correlations from one network model to the other. We are also curious about the robustness of networks when vertices are removed according to different attack strategies and the difference of robustness from one network model to the other. Our aim is to observe the correlation mechanism of centralities for distinct network models, and compare the network robustness when different centralities are applied as attacking directors to distinct network models. What inspires us is that maybe we can find a paradigm that combines several high-destructive attack strategies to find the optimal strategy based on the deep learning framework.
Yong HE Ji LI Xuanhong ZHOU Zewei CHEN Xin LIU
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.
Takahiro MATSUDA Fumie ONO Shinsuke HARA
In wireless links between ground stations and UAVs (Unmanned Aerial Vehicles), wireless signals may be attenuated by obstructions such as buildings. A three-dimensional RSS (Received Signal Strength) map (3D-RSS map), which represents a set of RSSs at various reception points in a three-dimensional area, is a promising geographical database that can be used to design reliable ground-to-air wireless links. The construction of a 3D-RSS map requires higher computational complexity, especially for a large 3D area. In order to sequentially estimate a 3D-RSS map from partial observations of RSS values in the 3D area, we propose a graph Laplacian-based sequential smooth estimator. In the proposed estimator, the 3D area is divided into voxels, and a UAV observes the RSS values at the voxels along a predetermined path. By considering the voxels as vertices in an undirected graph, a measurement graph is dynamically constructed using vertices from which recent observations were obtained and their neighboring vertices, and the 3D-RSS map is sequentially estimated by performing graph Laplacian regularized least square estimation.
Asraa ABDULRAZAK ALI MARDAN Kenji KONO
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.
Haitong YANG Guangyou ZHOU Tingting HE Maoxi LI
The current approaches to semantic role classification usually first define a representation vector for a candidate role and feed the vector into a deep neural network to perform classification. The representation vector contains some lexicalization features like word embeddings, lemmar embeddings. From linguistics, the semantic role frame of a sentence is a joint structure with strong dependencies between arguments which is not considered in current deep SRL systems. Therefore, this paper proposes a global deep reranking model to exploit these strong dependencies. The evaluation experiments on the CoNLL 2009 shared tasks show that our system can outperforms a strong local system significantly that does not consider role dependency relations.
Akira KITAYAMA Goichi ONO Tadashi KISHIMOTO Hiroaki ITO Naohiro KOHMU
Reducing power consumption is crucial for edge devices using convolutional neural network (CNN). The zero-skipping approach for CNNs is a processing technique widely known for its relatively low power consumption and high speed. This approach stops multiplication and accumulation (MAC) when the multiplication results of the input data and weight are zero. However, this technique requires large logic circuits with around 5% overhead, and the average rate of MAC stopping is approximately 30%. In this paper, we propose a precise zero-skipping method that uses input data and simple logic circuits to stop multipliers and accumulators precisely. We also propose an active data-skipping method to further reduce power consumption by slightly degrading recognition accuracy. In this method, each multiplier and accumulator are stopped by using small values (e.g., 1, 2) as input. We implemented single shot multi-box detector 500 (SSD500) network model on a Xilinx ZU9 and applied our proposed techniques. We verified that operations were stopped at a rate of 49.1%, recognition accuracy was degraded by 0.29%, power consumption was reduced from 9.2 to 4.4 W (-52.3%), and circuit overhead was reduced from 5.1 to 2.7% (-45.9%). The proposed techniques were determined to be effective for lowering the power consumption of CNN-based edge devices such as FPGA.
A non-volatile memory (NVM) employing MTJ has a lot of strong points such as read/write performance, best endurance and operating-voltage compatibility with standard CMOS. However, it consumes a lot of energy when writing the data. This becomes an obstacle when applying to battery-operated mobile devices. To solve this problem, we propose an approach to augment the capability of the precision scaling technique for the write operation in NVM. Precision scaling is an approximate computing technique to reduce the bit width of data (i.e. precision) for energy reduction. When writing image data to NVM with the precision scaling, the write energy and the image quality are changed according to the write time and the target bit range. We propose an energy-efficient approximate storing scheme for non-volatile flip-flops and a magnetic random-access memory (MRAM) that allows us to write the data by optimizing the bit positions to split the data and the write time for each bit range. By using the statistical model, we obtained optimal values for the write time and the targeted bit range under the trade-off between the write energy reduction and image quality degradation. Simulation results have demonstrated that by using these optimal values the write energy can be reduced up to 50% while maintaining the acceptable image quality. We also investigated the relationship between the input images and the output image quality when using this approach in detail. In addition, we evaluated the energy benefits when applying our approach to nine types of image processing including linear filters and edge detectors. Results showed that the write energy is reduced by further 12.5% at the maximum.
Nuttapong ATTRAPADUNG Goichiro HANAOKA Takato HIRANO Yutaka KAWAI Yoshihiro KOSEKI Jacob C. N. SCHULDT
In this paper, we put forward the notion of a token-based multi-input functional encryption (token-based MIFE) scheme - a notion intended to give encryptors a mechanism to control the decryption of encrypted messages, by extending the encryption and decryption algorithms to additionally use tokens. The basic idea is that a decryptor must hold an appropriate decryption token in addition to his secrete key, to be able to decrypt. This type of scheme can address security concerns potentially arising in applications of functional encryption aimed at addressing the problem of privacy preserving data analysis. We firstly formalize token-based MIFE, and then provide two basic schemes; both are based on an ordinary MIFE scheme, but the first additionally makes use of a public key encryption scheme, whereas the second makes use of a pseudorandom function (PRF). Lastly, we extend the latter construction to allow decryption tokens to be restricted to specified set of encryptions, even if all encryptions have been done using the same encryption token. This is achieved by using a constrained PRF.