Yukihiro TAGAMI Hayato KOBAYASHI Shingo ONO Akira TAJIMA
Modeling user activities on the Web is a key problem for various Web services, such as news article recommendation and ad click prediction. In our work-in-progress paper[1], we introduced an approach that summarizes each sequence of user Web page visits using Paragraph Vector[3], considering users and URLs as paragraphs and words, respectively. The learned user representations are used among the user-related prediction tasks in common. In this paper, on the basis of analysis of our Web page visit data, we propose Backward PV-DM, which is a modified version of Paragraph Vector. We show experimental results on two ad-related data sets based on logs from Web services of Yahoo! JAPAN. Our proposed method achieved better results than those of existing vector models.
Mohamad Sabri bin SINAL Eiji KAMIOKA
Automatic detection of heart cycle abnormalities in a long duration of ECG data is a crucial technique for diagnosing an early stage of heart diseases. Concretely, Paroxysmal stage of Atrial Fibrillation rhythms (ParAF) must be discriminated from Normal Sinus rhythms (NS). The both of waveforms in ECG data are very similar, and thus it is difficult to completely detect the Paroxysmal stage of Atrial Fibrillation rhythms. Previous studies have tried to solve this issue and some of them achieved the discrimination with a high degree of accuracy. However, the accuracies of them do not reach 100%. In addition, no research has achieved it in a long duration, e.g. 12 hours, of ECG data. In this study, a new mechanism to tackle with these issues is proposed: “Door-to-Door” algorithm is introduced to accurately and quickly detect significant peaks of heart cycle in 12 hours of ECG data and to discriminate obvious ParAF rhythms from NS rhythms. In addition, a quantitative method using Artificial Neural Network (ANN), which discriminates unobvious ParAF rhythms from NS rhythms, is investigated. As the result of Door-to-Door algorithm performance evaluation, it was revealed that Door-to-Door algorithm achieves the accuracy of 100% in detecting the significant peaks of heart cycle in 17 NS ECG data. In addition, it was verified that ANN-based method achieves the accuracy of 100% in discriminating the Paroxysmal stage of 15 Atrial Fibrillation data from 17 NS data. Furthermore, it was confirmed that the computational time to perform the proposed mechanism is less than the half of the previous study. From these achievements, it is concluded that the proposed mechanism can practically be used to diagnose early stage of heart diseases.
Yuto KUROSAKI Masayoshi OHTA Hidetaka ITO Hiroomi HIKAWA
This paper discusses the effect of pre-grouping on vector classification based on the self-organizing map (SOM). The SOM is an unsupervised learning neural network, and is used to form clusters of vectors using its topology preserving nature. The use of SOMs for practical applications, however, may pose difficulties in achieving high recognition accuracy. For example, in image recognition, the accuracy is degraded due to the variation of lighting conditions. This paper considers the effect of pre-grouping of feature vectors on such types of applications. The proposed pre-grouping functionality is also based on the SOM and introduced into a new parallel configuration of the previously proposed SOM-Hebb classifers. The overall system is implemented and applied to position identification from images obtained in indoor and outdoor settings. The system first performs the grouping of images according to the rough representation of the brightness profile of images, and then assigns each SOM-Hebb classifier in the parallel configuration to one of the groups. Recognition parameters of each classifier are tuned for the vectors belonging to its group. Comparison between the recognition systems with and without the grouping shows that the grouping can improve recognition accuracy.
Shinya MOCHIDUKI Reina WATANABE Miyuki SUGANUMA Hiroaki KUDO Noboru OHNISHI Mitsuho YAMADA
Stereoscopic vision technology is applied in a wide range of fields, from 3D movies to medical care. Stereoscopic vision makes it possible to observe images in parallax between both eyes. However, parallax images cannot be used all the time due to a situation called “occlusion”, in which an object is hidden in the depths by another object. In this case, different images are projected on the right and left retina. Here, we propose a psychology experiment to elucidate the function of parvocellular cells in the LGN of the visual cortex of the brain using occlusion perception. As a new psychology experiment to clarify whether parvocellular cells in the LGN of the visual cortex, said to process chromatic and luminance information, can detect a disagreement between the retinal images produced by each eye, we measured convergence eye movement when gazing at the rim of a column under occlusion using an equiluminance random dot pattern. When eye movement prevented the disagreement of the retinal images caused by occlusion, we thought that convergence eye movement to move both eyes in front of the rim or divergence eye movement to move them behind the rim would occur. In other words, we thought that we could clarify whether there was parvocellular system process agreement or disagreement between the right and left retinal images under equiluminance. Therefore, we examined whether a system to detect disagreement between the retinal images exists in the brain when gazing at the rim of a column onto which an equiluminance random dot texture was mapped. Results suggested that the mechanism to avoid disagreement between the retinal images of the eyes caused by occlusion occurs in the parvocellular cells, which mainly process color information, as well as in the magnocellular cells, which process binocular disparity.
Yoojin KIM Yongwoon SONG Hyukjun LEE
An accurate but energy-efficient estimation of a position is important as the number of mobile computing systems grow rapidly. A challenge is to develop a highly accurate but energy efficient estimation method. A particle filter is a key algorithm to estimate and track the position of an object which exhibits non-linear movement behavior. However, it requires high usage of computation resources and energy. In this paper, we propose a scheme which can dynamically adjust the number of particles according to the accuracy of the reference signal for positioning and reduce the energy consumption by 37% on Cortex A7.
Shaojun ZHANG Julong LAN Chao QI Penghao SUN
Distributed control plane architecture has been employed in software-defined data center networks to improve the scalability of control plane. However, since the flow space is partitioned by assigning switches to different controllers, the network topology is also partitioned and the rule setup process has to invoke multiple controllers. Besides, the control load balancing based on switch migration is heavyweight. In this paper, we propose a lightweight load partition method which decouples the flow space from the network topology. The flow space is partitioned with hosts rather than switches as carriers, which supports fine-grained and lightweight load balancing. Moreover, the switches are no longer needed to be assigned to different controllers and we keep all of them controlled by each controller, thus each flow request can be processed by exactly one controller in a centralized style. Evaluations show that our scheme reduces rule setup costs and achieves lightweight load balancing.
Chang-Hee KANG Sung-Soon PARK Young-Hwan YOU Hyoung-Kyu SONG
In wireless communication systems, OFDM technology is a communication method that can yield high data rates. However, OFDM systems suffer high PAPR values due to the use of many of subcarriers. The SLM and the PTS technique were proposed to solve the PAPR problem in OFDM systems. However, these approaches have the disadvantage of having high complexity. This paper proposes a method which has lower complexity than the conventional PTS method but has less performance degradation.
Nawfal AL-ZUBAIDI R-SMITH Lubomír BRANČÍK
Numerical inverse Laplace transform (NILT) methods are potential methods for time domain simulations, for instance the analysis of the transient phenomena in systems with lumped and/or distributed parameters. This paper proposes a numerical inverse Laplace transform method based originally on hyperbolic relations. The method is further enhanced by properly adapting several convergence acceleration techniques, namely, the epsilon algorithm of Wynn, the quotient-difference algorithm of Rutishauser and the Euler transform. The resulting accelerated models are compared as for their accuracy and computational efficiency. Moreover, an expansion to two dimensions is presented for the first time in the context of the accelerated hyperbolic NILT method, followed by the error analysis. The expansion is done by repeated application of one-dimensional partial numerical inverse Laplace transforms. A detailed static error analysis of the resulting 2D NILT is performed to prove the effectivness of the method. The work is followed by a practical application of the 2D NILT method to simulate voltage/current distributions along a transmission line. The method and application are programmed using the Matlab language.
This paper presents a self-calibrating dynamic latched comparator with a stochastic offset voltage detector that can be realized by using simple digital circuitry. An offset voltage of the comparator is compensated by using a statistical calibration scheme, and the offset voltage detector uses the uncertainty in the comparator output. Thanks to the simple offset detection technique, all the calibration circuitry can be synthesized using only standard logic cells. This paper also gives a design methodology that can provide the optimal design parameters for the detector on the basis of fundamental statistics, and the correctness of the design methodology was statistically validated through measurement. The proposed self-calibrating comparator system was fabricated in a 180 nm 1P6M CMOS process. The prototype achieved a 38 times improvement in the three-sigma of the offset voltage from 6.01 mV to 158 µV.
Sae IWATA Tomoyuki NITTA Toshinori TAKAYAMA Masao YANAGISAWA Nozomu TOGAWA
Cell phones with GPS function as well as GPS loggers are widely used and users' geographic information can be easily obtained. However, still battery consumption in these mobile devices is main concern and then obtaining GPS positioning data so frequently is not allowed. In this paper, a stayed location estimation method for sparse GPS positioning information is proposed. After generating initial clusters from a sequence of measured positions, the effective radius is set for every cluster based on positioning accuracy and the clusters are merged effectively using it. After that, short-time clusters are removed temporarily but measured positions included in them are not removed. Then the clusters are merged again, taking all the measured positions into consideration. This process is performed twice, in other words, two-stage short-time cluster removal is performed, and finally accurate stayed location estimation is realized even when the GPS positioning interval is five minutes or more. Experiments demonstrate that the total distance error between the estimated stayed location and the true stayed location is reduced by more than 33% and also the proposed method much improves F1 measure compared to conventional state-of-the-art methods.
Ziwei DENG Yilin HOU Xina CHENG Takeshi IKENAGA
3D ball tracking is of great significance in ping-pong game analysis, which can be utilized to applications such as TV contents and tactic analysis, with some of them requiring real-time implementation. This paper proposes a CPU-GPU platform based Particle Filter for multi-view ball tracking including 4 proposals. The multi-peak estimation and the ball-like observation model are proposed in the algorithm design. The multi-peak estimation aims at obtaining a precise ball position in case the particles' likelihood distribution has multiple peaks under complex circumstances. The ball-like observation model with 4 different likelihood evaluation, utilizes the ball's unique features to evaluate the particle's similarity with the target. In the GPU implementation, the double-queue structure and the vectorized data combination are proposed. The double-queue structure aims at achieving task parallelism between some data-independent tasks. The vectorized data combination reduces the time cost in memory access by combining 3 different image data to 1 vector data. Experiments are based on ping-pong videos recorded in an official match taken by 4 cameras located in 4 corners of the court. The tracking success rate reaches 99.59% on CPU. With the GPU acceleration, the time consumption is 8.8 ms/frame, which is sped up by a factor of 98 compared with its CPU version.
Ikuo KESHI Yu SUZUKI Koichiro YOSHINO Satoshi NAKAMURA
The problem with distributed representations generated by neural networks is that the meaning of the features is difficult to understand. We propose a new method that gives a specific meaning to each node of a hidden layer by introducing a manually created word semantic vector dictionary into the initial weights and by using paragraph vector models. We conducted experiments to test the hypotheses using a single domain benchmark for Japanese Twitter sentiment analysis and then evaluated the expandability of the method using a diverse and large-scale benchmark. Moreover, we tested the domain-independence of the method using a Wikipedia corpus. Our experimental results demonstrated that the learned vector is better than the performance of the existing paragraph vector in the evaluation of the Twitter sentiment analysis task using the single domain benchmark. Also, we determined the readability of document embeddings, which means distributed representations of documents, in a user test. The definition of readability in this paper is that people can understand the meaning of large weighted features of distributed representations. A total of 52.4% of the top five weighted hidden nodes were related to tweets where one of the paragraph vector models learned the document embeddings. For the expandability evaluation of the method, we improved the dictionary based on the results of the hypothesis test and examined the relationship of the readability of learned word vectors and the task accuracy of Twitter sentiment analysis using the diverse and large-scale benchmark. We also conducted a word similarity task using the Wikipedia corpus to test the domain-independence of the method. We found the expandability results of the method are better than or comparable to the performance of the paragraph vector. Also, the objective and subjective evaluation support each hidden node maintaining a specific meaning. Thus, the proposed method succeeded in improving readability.
Takatsugu FUKUSHIMA Naobumi MICHISHITA Hisashi MORISHITA Naoya FUJIMOTO
This paper improves radiation patterns and impedance matching of a broadband sleeve dipole antenna. A broadband sleeve dipole antenna is designed and the effect of the structure parameters on the |S11| characteristics is calculated. Current distributions of the resonance frequencies are calculated. A broadband sleeve dipole antenna with plate element is proposed. Better impedance matching is obtained by adjusting the size of the plate element. The nulls of the radiation patterns are reduced at high frequencies and the gain in the horizontal direction is improved.
Recently, the join processing of large-scale datasets in MapReduce environments has become an important issue. However, the existing MapReduce-based join algorithms suffer from too much overhead for constructing and updating the data index. Moreover, the similarity computation cost is high because the existing algorithms partition data without considering the data distribution. In this paper, we propose two grid-based join algorithms for MapReduce. First, we propose a similarity join algorithm that evenly distributes join candidates using a dynamic grid index, which partitions data considering data density and similarity threshold. We use a bottom-up approach by merging initial grid cells into partitions and assigning them to MapReduce jobs. Second, we propose a k-NN join query processing algorithm for MapReduce. To reduce the data transmission cost, we determine an optimal grid cell size by considering the data distribution of randomly selected samples. Then, we perform kNN join by assigning the only related join data to a reducer. From performance analysis, we show that our similarity join query processing algorithm and our k-NN join algorithm outperform existing algorithms by up to 10 times, in terms of query processing time.
Jun WANG Yuanyun WANG Chengzhi DENG Shengqian WANG Yong QIN
Developing a robust appearance model is a challenging task due to appearance variations of objects such as partial occlusion, illumination variation, rotation and background clutter. Existing tracking algorithms employ linear combinations of target templates to represent target appearances, which are not accurate enough to deal with appearance variations. The underlying relationship between target candidates and the target templates is highly nonlinear because of complicated appearance variations. To address this, this paper presents a regularized kernel representation for visual tracking. Namely, the feature vectors of target appearances are mapped into higher dimensional features, in which a target candidate is approximately represented by a nonlinear combination of target templates in a dimensional space. The kernel based appearance model takes advantage of considering the non-linear relationship and capturing the nonlinear similarity between target candidates and target templates. l2-regularization on coding coefficients makes the approximate solution of target representations more stable. Comprehensive experiments demonstrate the superior performances in comparison with state-of-the-art trackers.
Seitaro KOYAMA Shunsuke AOKI Toshimichi SAITO
A dynamic neural network has ternary connection parameters and can generate various binary periodic orbits. In order to analyze the dynamics, we present two feature quantities which characterize stability and transient phenomenon of a periodic orbit. Calculating the feature quantities, we investigate influence of connection sparsity on stability of a target periodic orbit corresponding to a circuit control signal. As the sparsity increases, at first, stability of a target periodic orbit tends to be stronger. In the next, the stability tends to be weakened and various transient phenomena exist. In the most sparse case, the network has many periodic orbits without transient phenomenon.
Tran Sy BANG Virach SORNLERTLAMVANICH
This paper presents a supervised method to classify a document at the sub-sentence level. Traditionally, sentiment analysis often classifies sentence polarity based on word features, syllable features, or N-gram features. A sentence, as a whole, may contain several phrases and words which carry their own specific sentiment. However, classifying a sentence based on phrases and words can sometimes be incoherent because they are ungrammatically formed. In order to overcome this problem, we need to arrange words and phrase in a dependency form to capture their semantic scope of sentiment. Thus, we transform a sentence into a dependency tree structure. A dependency tree is composed of subtrees, and each subtree allocates words and syllables in a grammatical order. Moreover, a sentence dependency tree structure can mitigate word sense ambiguity or solve the inherent polysemy of words by determining their word sense. In our experiment, we provide the details of the proposed subtree polarity classification for sub-opinion analysis. To conclude our discussion, we also elaborate on the effectiveness of the analysis result.
With the recent explosion of geographic data generated by smartphones, sensors, and satellites, a data storage that can handle the massive volume of data and support high-computational spatial queries is becoming essential. Although key-value stores efficiently handle large-scale data, they are not equipped with effective functions for supporting geographic data. To solve this problem, in this paper, we present G-HBase, a high-performance geographical database based on HBase, a standard key-value store. To index geographic data, we first use Geohash as the rowkey in HBase. Then, we present a novel partitioning method, namely binary Geohash rectangle partitioning, to support spatial queries. Our extensive experiments on real datasets have demonstrated an improved performance with k nearest neighbors and range query in G-HBase when compared with SpatialHadoop, a state-of-the-art framework with native support for spatial data. We also observed that performance of spatial join in G-HBase is on par with SpatialHadoop and outperforms SJMR algorithm in HBase.
Jinguang HAO Gang WANG Lili WANG Honggang WANG
In this paper, an optimal method is proposed to design sparse-coefficient notch filters with principal basic vectors in the column space of a matrix constituted with frequency samples. The proposed scheme can perform in two stages. At the first stage, the principal vectors can be determined in the least-squares sense. At the second stage, with some components of the principal vectors, the notch filter design is formulated as a linear optimization problem according to the desired specifications. Optimal results can form sparse coefficients of the notch filter by solving the linear optimization problem. The simulation results show that the proposed scheme can achieve better performance in designing a sparse-coefficient notch filter of small order compared with other methods such as the equiripple method, the orthogonal matching pursuit based scheme and the L1-norm based method.
Haruki MARUOKA Masashi HIFUMI Jun FURUTA Kazutoshi KOBAYASHI
We propose a radiation-hardened Flip-Flop (FF) with stacked transistors based on the Adaptive Coupling Flip-Flop (ACFF) with low power consumption in a 65 nm FDSOI process. The slave latch in ACFF is much weaker against soft errors than the master latch. We design several FFs with stacked transistors in the master or slave latches to mitigate soft errors. We investigate radiation hardness of the proposed FFs by α particle and neutron irradiation tests. The proposed FFs have higher radiation hardness than a conventional DFF and ACFF. Neutron irradiation and α particle tests revealed no error in the proposed AC Slave-Stacked FF (AC_SS FF) which has stacked transistors only in the slave latch. We also investigate radiation hardness of the proposed FFs by heavy ion irradiation. The proposed FFs maintain higher radiation hardness up to 40 MeV-cm2/mg than the conventional DFF. Stacked inverters become more sensitive to soft errors by increasing tilt angles. AC_SS FF achieves higher radiation hardness than ACFF with the performance equivalent to that of ACFF.