Ke XU Rujun LIU Yuan SUN Keju ZOU Yan HUANG Xinfang ZHANG
In tutoring systems, students are more likely to utilize hints to assist their decisions about difficult or confusing problems. In the meanwhile, students with weaker knowledge mastery tend to choose more hints than others with stronger knowledge mastery. Hints are important assistances to help students deal with questions. Students can learn from hints and enhance their knowledge about questions. In this paper we firstly use hints alone to build a model named Hints-Model to predict student performance. In addition, matrix factorization (MF) has been prevalent in educational fields to predict student performance, which is derived from their success in collaborative filtering (CF) for recommender systems (RS). While there is another factorization method named non-negative matrix factorization (NMF) which has been developed over one decade, and has additional non-negative constrains on the factorization matrices. Considering the sparseness of the original matrix and the efficiency, we can utilize an element-based matrix factorization called regularized single-element-based NMF (RSNMF). We compared the results of different factorization methods to their combination with Hints-Model. From the experiment results on two datasets, we can find the combination of RSNMF with Hints-Model has achieved significant improvement and obtains the best result. We have also compared the Hints-Model with the pioneer approach performance factor analysis (PFA), and the outcomes show that the former method exceeds the later one.
Yasufumi TAKAMA Wataru SASAKI Takafumi OKUMURA Chi-Chih YU Lieu-Hen CHEN Hiroshi ISHIKAWA
This paper proposes a walking route recommender system aiming at continuously supporting a user to take a walk as means for health promotion. In recent years, taking a walk becomes popular with not only the elderly, but also those from all ages as one of the easiest ways for health promotion. From the viewpoint of health promotion, it is desirable to take a walk as daily exercise. However, walking is very simple activity, which makes it difficult for people to maintain their motivation. Although using an activity monitor is expected to improve the motivation for taking a walk as daily exercise, it forces users to manage their activities by themselves. The proposed system solves such a problem by recommending a walking route that can consume target calories. When a system is to be used for long period of time for supporting user's daily exercise, it should consider the case when a user will not follow the recommended route. It would cause a gap between consumed and target calories. We think this problem becomes serious when a user gradually gets bored with taking a walk during a long period of time. In order to solve the problem, the proposed method implicitly manages calories on monthly basis and recommends walking routes that could keep a user from getting bored. The effectiveness of the recommendation algorithm is evaluated with agent simulation. As another important factor for walking support, this paper also proposes a navigation interface that presents direction to the next visiting point without using a map. As users do not have to continuously focus on the interface, it is not only useful for their safety, but also gives them room to enjoy the landscape. The interface is evaluated by an experiment with test participants.
Nobuaki MINEMATSU Ibuki NAKAMURA Masayuki SUZUKI Hiroko HIRANO Chieko NAKAGAWA Noriko NAKAMURA Yukinori TAGAWA Keikichi HIROSE Hiroya HASHIMOTO
This paper develops an online and freely available framework to aid teaching and learning the prosodic control of Tokyo Japanese: how to generate its adequate word accent and phrase intonation. This framework is called OJAD (Online Japanese Accent Dictionary) [1] and it provides three features. 1) Visual, auditory, systematic, and comprehensive illustration of patterns of accent change (accent sandhi) of verbs and adjectives. Here only the changes caused by twelve fundamental conjugations are focused upon. 2) Visual illustration of the accent pattern of a given verbal expression, which is a combination of a verb and its postpositional auxiliary words. 3) Visual illustration of the pitch pattern of any given sentence and the expected positions of accent nuclei in the sentence. The third feature is technically implemented by using an accent change prediction module that we developed for Japanese Text-To-Speech (TTS) synthesis [2],[3]. Experiments show that accent nucleus assignment to given texts by the proposed framework is much more accurate than that by native speakers. Subjective assessment and objective assessment done by teachers and learners show extremely high pedagogical effectiveness of the developed framework.
Masayuki SUZUKI Ryo KUROIWA Keisuke INNAMI Shumpei KOBAYASHI Shinya SHIMIZU Nobuaki MINEMATSU Keikichi HIROSE
When synthesizing speech from Japanese text, correct assignment of accent nuclei for input text with arbitrary contents is indispensable in obtaining naturally-sounding synthetic speech. A phenomenon called accent sandhi occurs in utterances of Japanese; when a word is uttered in a sentence, its accent nucleus may change depending on the contexts of preceding/succeeding words. This paper describes a statistical method for automatically predicting the accent nucleus changes due to accent sandhi. First, as the basis of the research, a database of Japanese text was constructed with labels of accent phrase boundaries and accent nucleus positions when uttered in sentences. A single native speaker of Tokyo dialect Japanese annotated all the labels for 6,344 Japanese sentences. Then, using this database, a conditional-random-field-based method was developed using this database to predict accent phrase boundaries and accent nuclei. The proposed method predicted accent nucleus positions for accent phrases with 94.66% accuracy, clearly surpassing the 87.48% accuracy obtained using our rule-based method. A listening experiment was also conducted on synthetic speech obtained using the proposed method and that obtained using the rule-based method. The results show that our method significantly improved the naturalness of synthetic speech.
Code division multiple access (CDMA) based on direct sequence (DS) spread spectrum modulation using spreading codes is one of standard technologies for multiple access communications. In asynchronous DS/CDMA communications, spreading codes with appropriate negative auto-correlation can reduce bit error rate (BER) compared with uncorrelated sequences. In this letter, we design new binary functions for generating chaotic binary sequences with negative auto-correlation using Bernoulli chaotic map. Such binary functions can be applied to the generation of spreading codes with negative auto-correlation based on existing spreading codes (e.g., shift register sequences).
Xuemeng ZHAI Mingda WANG Hangyu HU Guangmin HU
Identifying IDC (Internet Data Center) IP addresses and analyzing the connection relationship of IDC could reflect the IDC network resource allocation and network layout which is helpful for IDC resource allocation optimization. Recent research mainly focuses on minimizing electricity consumption and optimizing network resource allocation based on IDC traffic behavior analysis. However, the lack of network-wide IP information from network operators has led to problems like management difficulties and unbalanced resource allocation of IDC, which are still unsolved today. In this paper, we propose a method for the IP identification and connection relationship analysis of IDC based on the flow connection behavior analysis. In our method, the frequent IP are extracted and aggregated in backbone communication network based on the traffic characteristics of IDC. After that, the connection graph of frequent IP (CGFIP) are built by analyzing the behavior of the users who visit the IDC servers, and IDC IP blocks are thus identified using CGFIP. Furthermore, the connection behavior characteristics of IDC are analyzed based on the connection graphs of IDC (CGIDC). Our findings show that the method can accurately identify the IDC IP addresses and is also capable of reflecting the relationships among IDCs effectively.
Kwang-Yul KIM Seung-Woo LEE Yu-Min HWANG Jae-Seang LEE Yong-Sin KIM Jin-Young KIM Yoan SHIN
A chirp spread spectrum (CSS) system uses a chirp signal which changes the instantaneous frequency according to time for spreading a transmission bandwidth. In the CSS system, the transmission performance can be simply improved by increasing the time-bandwidth product which is known as the processing gain. However, increasing the transmission bandwidth is limited because of the spectrum regulation. In this letter, we propose a correlation-based chirp rate allocation method to improve the transmission performance by analyzing the cross-correlation coefficient in the same time-bandwidth product. In order to analyze the transmission performance of the proposed method, we analytically derive the cross-correlation coefficient according to the time-bandwidth separation product and simulate the transmission performance. The simulation results show that the proposed method can analytically allocate the optimal chirp rate and improve the transmission performance.
Li Juan DENG Ping WEI Yan Shen DU Wan Chun LI Ying Xiang LI Hong Shu LIAO
Target determination based on Doppler frequency shift (DFS) measurements is a nontrivial problem because of the nonlinear relation between the position space and the measurements. The conventional methods such as numerical iterative algorithm and grid searching are used to obtain the solution, while the former requires an initial position estimate and the latter needs huge amount of calculations. In this letter, to avoid the problems appearing in those conventional methods, an effective solution is proposed, in which two best linear unbiased estimators (BULEs) are employed to obtain an explicit solution of the proximate target position. Subsequently, this obtained explicit solution is used to initialize the problem of original maximum likelihood estimation (MLE), which can provide a more accurate estimate.
Mi-Young NAM Jung-Hyun KIM Hong-Yeop SONG
In this paper, we examine the locality property of the original Fractional Repetition (FR) codes and propose two constructions for FR codes with better locality. For this, we first derive the capacity of the FR codes with locality 2, that is the maximum size of the file that can be stored. Construction 1 generates an FR code with repetition degree 2 and locality 2. This code is optimal in the sense of achieving the capacity we derived. Construction 2 generates an FR code with repetition degree 3 and locality 2 based on 4-regular graphs with girth g. This code is also optimal in the same sense.
Zhenyu SONG Shangce GAO Yang YU Jian SUN Yuki TODO
This paper proposes a novel multiple chaos embedded gravitational search algorithm (MCGSA) that simultaneously utilizes multiple different chaotic maps with a manner of local search. The embedded chaotic local search can exploit a small region to refine solutions obtained by the canonical gravitational search algorithm (GSA) due to its inherent local exploitation ability. Meanwhile it also has a chance to explore a huge search space by taking advantages of the ergodicity of chaos. To fully utilize the dynamic properties of chaos, we propose three kinds of embedding strategies. The multiple chaotic maps are randomly, parallelly, or memory-selectively incorporated into GSA, respectively. To evaluate the effectiveness and efficiency of the proposed MCGSA, we compare it with GSA and twelve variants of chaotic GSA which use only a certain chaotic map on a set of 48 benchmark optimization functions. Experimental results show that MCGSA performs better than its competitors in terms of convergence speed and solution accuracy. In addition, statistical analysis based on Friedman test indicates that the parallelly embedding strategy is the most effective for improving the performance of GSA.
Kyung-Jin YOU Ha-Eun JEON Hyun-Chool SHIN
In this paper, we proposed a method for radar modulation identification based on the measurement of inequality in the frequency domain. Gini's coefficient was used to exploit the inequality in the powers of spectral components. The maximum likelihood classifier was used to classify the detected radar signal into four types of modulations: unmodulated signal (UM), linear frequency modulation (LFM), non-linear frequency modulation (NLFM), and frequency shift keying (FSK). The simulation results demonstrated that the proposed method achieves an overall identification accuracy of 98.61% at a signal-to-noise ratio (SNR) of -6dB without a priori information such as carrier frequency, pulse arrival times or pulse width.
Changbeom SHIM Wooil KIM Wan HEO Sungmin YI Yon Dohn CHUNG
The development of smart devices has led to the growth of Location-Based Social Networking Services (LBSNSs). In this paper, we introduce an l-Close Range Friends query that finds all l-hop friends of a user within a specified range. We also propose a query processing method on Social Grid Index (SGI). Using real datasets, the performance of our method is evaluated.
Junlin TANG Guangrong YUE Lei CHEN Shaoqian LI
Nowadays, with the extensive use of smart devices, the amount of mobile data is experiencing an exponential growth. As a result, accommodating the large amount of traffic is important for the future 5G mobile communication. Millimeter-wave band, which has a lot of spectrum resources to meet the demand brought by the growth of mobile data, is becoming an important part of 5G technology. In order to mitigate the high path loss brought by the high frequency band, beamforming is often used to enhance the gain of a link. In this paper, we propose an iteration-based beamforming method for planar phased array. When compared to a linear array, a planar phased array points a smaller area which ensures a better link performance. We deduce that different paths of millimeter-wave channel are approximately orthogonal when the antenna array is large, which forms the basis of our iterative approach. We also discuss the development of the important millimeter-wave device-phase shifter, and its effect on the performance of the proposed beamforming method. From the simulation, we prove that our method has a performance close to the singular vector decomposition (SVD) method and is superior to the method in IEEE802.15.3c. Moreover, the channel capacity of the proposed method is at most 0.41bps/Hz less than the SVD method. We also show that the convergence of the proposed method could be achieved within 4 iterations and a 3-bit phase shifter is enough for practical implementation.
The quality of codebook is very important in visual image classification. In order to boost the classification performance, a scheme of codebook generation for scene image recognition based on parallel key SIFT analysis (PKSA) is presented in this paper. The method iteratively applies classical k-means clustering algorithm and similarity analysis to evaluate key SIFT descriptors (KSDs) from the input images, and generates the codebook by a relaxed k-means algorithm according to the set of KSDs. With the purpose of evaluating the performance of the PKSA scheme, the image feature vector is calculated by sparse code with Spatial Pyramid Matching (ScSPM) after the codebook is constructed. The PKSA-based ScSPM method is tested and compared on three public scene image datasets. The experimental results show the proposed scheme of PKSA can significantly save computational time and enhance categorization rate.
Hui-Seon GANG Shaikhul Islam CHOWDHURY Chun-Su PARK Goo-Rak KWON Jae-Young PYUN
Video quality generally suffers from packet losses caused by an unreliable channel when video is transmitted over an error-prone wireless channel. This quality degradation is the main reason that a video compression encoder uses error-resilient coding to deal with the high packet-loss probability. The use of adequate error resilience can mitigate the effects of channel errors, but the coding efficiency for bit reduction will be decreased. On the other hand, H.264/AVC uses multiple reference frame (MRF) motion compensation for a higher coding efficiency. However, an increase in the number of reference frames in the H.264/AVC encoder has been recently observed, making the received video quality worse in the presence of transmission errors if the cyclic intra-refresh is used as the error-resilience method. This is because the reference-block selection in the MRF chooses blocks on the basis of the rate distortion optimization, irrespective of the intra-refresh coding. In this paper, a new error-resilient reference selection method is proposed to provide error resilience for MRF based motion compensation. The proposed error-resilient reference selection method achieves an average PSNR enhancement up to 0.5 to 2dB in 10% packet-loss-ratio environments. Therefore, the proposed method can be valuable in most MRF-based interactive video encoding system, which can be used for video broadcasting and mobile video conferencing over an erroneous network.
Bing DENG Zhengbo SUN Le YANG Dexiu HU
A linear-correction method is developed for source position and velocity estimation using time difference of arrival (TDOA) and frequency difference of arrival (FDOA) measurements. The proposed technique first obtains an initial source location estimate using the first-step processing of an existing algebraic algorithm. It then refines the initial localization result by estimating via weighted least-squares (WLS) optimization and subtracting out its estimation error. The new solution is shown to be able to achieve the Cramer-Rao lower bound (CRLB) accuracy and it has better accuracy over several benchmark methods at relatively high noise levels.
When haze exists in an image of an outdoor scene, the visibility of objects in the image is deteriorated. In recent years, to improve the visibility of objects in such images, many dehazing methods have been investigated. Most of the methods are based on the atmospheric scattering model. In such methods, the transmittance and global atmospheric light are estimated from an input image and a dehazed image is obtained by substituting them into the model. To estimate the transmittance and global atmospheric light, the dark channel prior is a major and powerful concept that is employed in many dehazing methods. In this paper, we propose a new dehazing method in which the degree of haze removal can be adjusted by changing its parameters. Our method is also based on the atmospheric scattering model and employs the dark channel prior. In our method, the estimated transmittance is adjusted to a more suitable value by a transform function. By choosing appropriate parameter values for each input image, good haze removal results can be obtained by our method. In addition, a quantitative index for evaluating the quality of a dehazed image is proposed in this paper. It can be considered that haze removal is a type of saturation enhancement. On the other hand, an output image obtained using the atmospheric scattering model is generally darker than the input image. Therefore, we evaluate the quality of dehazed images by considering the balance between the brightness and saturation of the input and output images. The validity of the proposed index is examined using our dehazing method. Then a comparison between several dehazing methods is carried out using the index. Through these experiments, the effectiveness of our dehazing method and the quantitative index is confirmed.
Haibo DAI Chunguo LI Luxi YANG
In this letter, we focus on the subcarrier allocation problem for device-to-device (D2D) communication in cellular networks to improve the cellular energy efficiency (EE). Our goal is to maximize the weighted cellular EE and its solution is obtained by using a game-theoretic learning approach. Specifically, we propose a lower bound instead of the original optimization objective on the basis of the proven property that the gap goes to zero as the number of transmitting antennas increases. Moreover, we prove that an exact potential game applies to the subcarrier allocation problem and it exists the best Nash equilibrium (NE) which is the optimal solution to optimize the lower bound. To find the best NE point, a distributed learning algorithm is proposed and then is proved that it can converge to the best NE. Finally, numerical results verify the effectiveness of the proposed scheme.
Abu Nowshed CHY Md Zia ULLAH Masaki AONO
Microblog, especially twitter, has become an integral part of our daily life for searching latest news and events information. Due to the short length characteristics of tweets and frequent use of unconventional abbreviations, content-relevance based search cannot satisfy user's information need. Recent research has shown that considering temporal and contextual aspects in this regard has improved the retrieval performance significantly. In this paper, we focus on microblog retrieval, emphasizing the alleviation of the vocabulary mismatch, and the leverage of the temporal (e.g., recency and burst nature) and contextual characteristics of tweets. To address the temporal and contextual aspect of tweets, we propose new features based on query-tweet time, word embedding, and query-tweet sentiment correlation. We also introduce some popularity features to estimate the importance of a tweet. A three-stage query expansion technique is applied to improve the relevancy of tweets. Moreover, to determine the temporal and sentiment sensitivity of a query, we introduce query type determination techniques. After supervised feature selection, we apply random forest as a feature ranking method to estimate the importance of selected features. Then, we make use of ensemble of learning to rank (L2R) framework to estimate the relevance of query-tweet pair. We conducted experiments on TREC Microblog 2011 and 2012 test collections over the TREC Tweets2011 corpus. Experimental results demonstrate the effectiveness of our method over the baseline and known related works in terms of precision at 30 (P@30), mean average precision (MAP), normalized discounted cumulative gain at 30 (NDCG@30), and R-precision (R-Prec) metrics.
In this paper, robust stability of nonlinear feedback systems with unknown disturbance is considered by using the operator-based right coprime factorization method. For dealing with the unknown disturbance, a new design scheme and a nonlinear controller are given. That is, robust stability of the nonlinear systems with unknown disturbance is guaranteed by combining right coprime factorization with the proposed controller. Simultaneously, adverse effects resulting from the disturbance are removed by using the proposed nonlinear operator controller. Finally, a simulation example is given to show the effectiveness of the proposed design scheme of this paper.