著者

Farhan Shafiq Tsuyoshi Isshiki Dongju Li

出版者

一般社団法人 情報処理学会

雑誌

IPSJ Transactions on System LSI Design Methodology (ISSN:18826687)

巻号頁・発行日

vol.10, pp.13-27, 2017 (Released:2017-02-03)

参考文献数

38

---

Accurate and fast performance estimation methods for modern and future multi-core systems are the focal point of much research due to the complexity associated with such architectures. The communication architecture of such systems has a huge impact on the performance and power of the whole system. Architects need to explore many design possibilities by using performance estimation techniques at early stages of design to make design decisions earlier in the design cycle. While software developers need to develop and test applications for the target architecture and gather performance measurements as early in the design cycle as possible. Full system simulation techniques provide accurate performance values but are extremely time consuming. Static analysis techniques are fast but cannot capture the dynamic behavior associated with shared resource contention and arbitration. Moreover, synthetic traffic patterns have been used to analyze the communication architecture however, such patterns are not realistic enough. We propose a statistical based model to predict the dynamic cost of bus arbitration on the performance of a bus architecture. The proposed model uses workload trace of the actual applications and benchmarks to capture the real application traffic behavior. Statistics on the traffic patterns are collected and input to the analytical model which calculates performance values for the communication architecture under consideration. By knowing the performance measures, designers can avoid over and under-design of the communication architecture. This paper builds up on a previously developed performance estimation model. The previous work modeled single and burst bus-transfers, however only one interfering bus master at a time for each blocked bus request was considered. The proposed, improved accuracy model considers multiple interfering masters for each blocked request hence improving the estimation accuracy especially for traffic intensive applications and many PE architectures. Experiments are performed for two different architectures i.e., 4 processing elements connected via a shared bus and 8 processing elements connected via a shared bus. Results show no significant difference in accuracy compared to previously developed model, for low traffic applications SPARSE and ROBOT however notable accuracy improvement for traffic intensive applications. Maximum estimation error is reduced from 1.75% to 0.6% for FPPPP and from maximum 13.91% to 8.8% for FFT on the 4PE architecture. On the 8PE architecture, maximum estimation error is reduced from 11.8% to 2.7% for the FPPP benchmark. Moreover simulation speed-up for the proposed technique over simulation method is reported.

著者

Sayaka Akioka Yuki Ohno Midori Sugaya Tatsuo Nakajima

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.19, pp.421-429, 2011 (Released:2011-08-10)

参考文献数

24

---

This paper proposes SPLiT (Scalable Performance Library Tool) as the methodology to improve performance of applications on multicore processors through CPU and cache optimizations on the fly. SPLiT is designed to relieve the difficulty of the performance optimization of parallel applications on multicore processors. Therefore, all programmers have to do to benefit from SPLiT is to add a few library calls to let SPLiT know which part of the application should be analyzed. This simple but compelling optimization library contributes to enrich pervasive servers on a multicore processor, which is a strong candidate for an architecture of information appliances in the near future. SPLiT analyzes and predicts application behaviors based on CPU cycle counts and cache misses. According to the analysis and predictions, SPLiT tries to allocate processes and threads sharing data onto the same physical cores in order to enhance cache efficiency. SPLiT also tries to separate cache effective codes from the codes with more cache misses for the purpose of the avoidance of cache pollutions, which result in performance degradation. Empirical experiments assuming web applications validated the efficiency of SPLiT and the performance of the web application is improved by 26%.

著者

Kazuyuki Amano Shin-ichi Nakano Koichi Yamazaki

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.23, no.3, pp.252-257, 2015 (Released:2015-05-15)

参考文献数

5

被引用文献数

1

---

The anti-slide packing is a packing of a number of three dimensional pieces of same size into a larger box such that none of them can slide in any direction. In this paper, we consider the problem of how to find a sparsest anti-slide packing. We give an IP formulation of this problem, and obtain the solutions for some small cases by using an IP solver. In addition, we give the upper and lower bounds on the ratio of the volume occupied by the pieces when the size of a box approaches infinity. For the case of piece size 2 × 2 × 1, we show that a sparsest anti-slide packing occupies at least 28.8% and at most 66.7% of the total volume.

著者

Sebastian Böcker

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.23, no.3, pp.258-264, 2015 (Released:2015-05-15)

参考文献数

13

---

We consider the following simple game: We are given a table with ten slots indexed one to ten. In each of the ten rounds of the game, three dice are rolled and the numbers are added. We then put this number into any free slot. For each slot, we multiply the slot index with the number in this slot, and add up the products. The goal of the game is to maximize this score. In more detail, we play the game many times, and try to maximize the sum of scores or, equivalently, the expected score. We present a strategy to optimally play this game with respect to the expected score. We then modify our strategy so that we need only polynomial time and space. Finally, we show that knowing all ten rolls in advance, results in a relatively small increase in score. Although the game has a random component and requires a non-trivial strategy to be solved optimally, this strategy needs only polynomial time and space.

著者

Yuichi Nakamura Yoshiki Sameshima Toshihiro Yamauchi

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.23, no.5, pp.664-672, 2015 (Released:2015-09-15)

参考文献数

31

被引用文献数

3

---

Security-Enhanced Linux (SELinux) is a useful countermeasure for resisting security threats to embedded systems, because of its effectiveness against zero-day attacks. Furthermore, it can generally mitigate attacks without the application of security patches. However, the combined resource requirements of the SELinux kernel, userland, and the security policy reduce the performance of resource-constrained embedded systems. SELinux requires tuning, and modified code should be provided to the open-source software (OSS) community to receive value from its ecosystem. In this paper, we propose an embedded SELinux with reduced resource requirements, using code modifications that are acceptable to the OSS community. Resource usage is reduced by employing three techniques. First, the Linux kernel is tuned to reduce CPU overhead and memory usage. Second, unnecessary code is removed from userland libraries and commands. Third, security policy size is reduced with a policy-writing tool. To facilitate acceptance by the OSS community, build flags can be used to bypass modified code, such that it will not affect existing features; moreover, side effects of the modified code are carefully measured. Embedded SELinux is evaluated using an evaluation board targeted for M2M gateway, and benchmark results show that its read/write overhead is almost negligible. SELinux's file space requirements are approximately 200Kbytes, and memory usage is approximately 500Kbytes; these account for approximately 1% of the evaluation board's respective flash ROM and RAM capacity . Moreover, the modifications did not result in any adverse side effects. The modified code was submitted to the OSS community along with the evaluation results, and was successfully merged into the community code.

著者

Keisuke Yanagisawa Takashi Ishida Yutaka Akiyama

出版者

一般社団法人 情報処理学会

雑誌

IPSJ Transactions on Bioinformatics (ISSN:18826679)

巻号頁・発行日

vol.8, pp.21-27, 2015 (Released:2015-08-19)

参考文献数

21

---

It is necessary to confirm that a new drug can be appropriately cleared from the human body. However, checking the clearance pathway of a drug in the human body requires clinical trials, and therefore requires large cost. Thus, computational methods for drug clearance pathway prediction have been studied. The proposed prediction methods developed previously were based on a supervised learning algorithm, which requires clearance pathway information for all drugs in a training set as input labels. However, these data are often insufficient in its numbers because of the high cost of their acquisition. In this paper, we propose a new drug clearance pathway prediction method based on semi-supervised learning, which can use not only labeled data but also unlabeled data. We evaluated the effectiveness of our method, focusing on the cytochrome P450 2C19 enzyme, which is involved in one of the major clearance pathways.

著者

Nobuaki Yasuo Masakazu Sekijima

出版者

一般社団法人 情報処理学会

雑誌

IPSJ Transactions on Bioinformatics (ISSN:18826679)

巻号頁・発行日

vol.8, pp.9-13, 2015 (Released:2015-07-08)

参考文献数

25

被引用文献数

1

---

We developed a new application to quantitatively evaluate the sequence conservation of ligand-binding sites by integrating information pertaining to protein structures, ligand-binding sites, and amino acid sequences. These data are visualized onto protein structures via a Jmol or PyMOL interface. The visualization is very important for structure-based drug design (SBDD). Key features of this application are the visualization of slight differences in specific ligand-binding sites and ConservationScore comparable among ligand-binding sites. Furthermore, we conducted an experiment to visualize the calculation and comparison of the ConservationScore of four viral proteins as well as an experiment to visualize the differences between proteins belonging to the human β adrenergic receptor family. This application is available at http://www.bio.gsic.titech.ac.jp/visco.html.

著者

Ryoichi Ishikawa Bo Zheng Takeshi Oishi Katsushi Ikeuchi

出版者

一般社団法人 情報処理学会

雑誌

IPSJ Transactions on Computer Vision and Applications (ISSN:18826695)

巻号頁・発行日

vol.7, pp.89-93, 2015 (Released:2015-07-27)

参考文献数

12

---

The aerial 3D laser scanner is needed for scanning the areas that cannot be observed from the ground. Since the laser scanning takes time, the obtained range data is distorted due to the sensor motion while scanning. This paper presents a rectification method for the distorted range data by aligning each scan line to the 3D data obtained from the ground. To avoid the instability and ambiguity of the line-based alignment, the parameters to be optimized are selected alternately, and the smoothness constraint is introduced by assuming that the sensor motion is smooth. The experimental results show that the proposed method has the good accuracy simulation and actual data.

著者

Yoshifumi Manabe Tatsuaki Okamoto

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.20, no.3, pp.686-693, 2012 (Released:2012-07-15)

参考文献数

18

被引用文献数

1

---

This paper discusses cake-cutting protocols when the cake is a heterogeneous good, represented by an interval on the real line. We propose a new desirable property, the meta-envy-freeness of cake-cutting, which has not been formally considered before. Meta-envy-free means there is no envy on role assignments, that is, no party wants to exchange his/her role in the protocol with the one of any other party. If there is an envy on role assignments, the protocol cannot be actually executed because there is no settlement on which party plays which role in the protocol. A similar definition, envy-freeness, is widely discussed. Envy-free means that no player wants to exchange his/her part of the cake with that of any other player's. Though envy-freeness was considered to be one of the most important desirable properties, envy-freeness does not prevent envy about role assignment in the protocols. We define meta-envy-freeness to formalize this kind of envy. We propose that simultaneously achieving meta-envy-free and envy-free is desirable in cake-cutting. We show that current envy-free cake-cutting protocols do not satisfy meta-envy-freeness. Formerly proposed properties such as strong envy-free, exact, and equitable do not directly consider this type of envy and these properties are very difficult to realize. This paper then shows cake-cutting protocols for two and three party cases that simultaneously achieves envy-free and meta-envy-free. Last, we show meta-envy-free pie-cutting protocols.

著者

Nobuharu Kami Teruyuki Baba Satoshi Ikeda Takashi Yoshikawa Hiroyuki Morikawa

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.20, no.3, pp.757-766, 2012 (Released:2012-07-15)

参考文献数

19

---

We present a fast algorithm for probabilistically extracting significant locations from raw GPS data based on data point density. Extracting significant locations from raw GPS data is the first essential step of algorithms designed for location-aware applications. Most current algorithms compare spatial/temporal variables with given fixed thresholds to extract significant locations. However, the appropriate threshold values are not clearly known in priori, and algorithms with fixed thresholds are inherently error-prone, especially under high noise levels. Moreover, they do not often scale in response to increase in system size since direct distance computation is required. We developed a fast algorithm for selective data point sampling around significant locations based on density information by constructing random histograms using locality-sensitive hashing. Theoretical analysis and evaluations show that significant locations are accurately detected with a loose parameter setting even under high noise levels.

著者

Shin'ichi Shiraishi

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.21, no.1, pp.34-45, 2013 (Released:2013-01-15)

参考文献数

21

被引用文献数

1 1

---

This paper presents two different model-based approaches that use multiple architecture description languages (ADLs) for automotive system development. One approach is based on AADL (Architecture Analysis & Design Language), and the other is a collaborative approach using multiple languages: SysML (Systems Modeling Language) and MARTE (Modeling and Analysis of Real-Time and Embedded systems). In this paper, the detailed modeling steps for both approaches are explained through a real-world automotive development example: a cruise control system. Moreover, discussion of the modeling steps offers a qualitative comparison of the two approaches, and then clarifies the characteristics of the different types of ADLs.

著者

Tomoyuki Kawamura Kenichi Takano

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.22, no.4, pp.689-700, 2014 (Released:2014-10-15)

参考文献数

58

被引用文献数

1 3

---

Researchers have found that about 70% of information systems (IS) development projects in Japan have failed, thus increasing the demand for solutions that will increase expected project success rates. In this study, we seek to explore such a solution by identifying factors that affect the degree to which Japanese IS development projects succeed or fail. We accomplish this by using an Internet-based questionnaire and statistical analysis. The questionnaire, which was primarily comprised of questions related to CMMI, yielded responses from 650 project managers who work for Japanese IT vendors. Multivariate analyses and structure equation modeling techniques demonstrated that seven factors, “Ordering Company's Skill and Requirement, ” “Project Planning, ” “Detailed Planning and Product Quality in Each Phase, ” “Project Monitoring and Control, ” “Change Requirement Management, ” “Skill and Teamwork of Project Members, ” and “Schedule Progress in Each Phase” influence project performance. Results also showed that these factors covary.

著者

Masahide Kawai Tomoyori Iwao Daisuke Mima Akinobu Maejima Shigeo Morishima

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.22, no.2, pp.401-409, 2014 (Released:2014-04-15)

参考文献数

27

被引用文献数

2 10

---

Speech animation synthesis is still a challenging topic in the field of computer graphics. Despite many challenges, representing detailed appearance of inner mouth such as nipping tongue's tip with teeth and tongue's back hasn't been achieved in the resulting animation. To solve this problem, we propose a method of data-driven speech animation synthesis especially when focusing on the inside of the mouth. First, we classify inner mouth into teeth labeling opening distance of the teeth and a tongue according to phoneme information. We then insert them into existing speech animation based on opening distance of the teeth and phoneme information. Finally, we apply patch-based texture synthesis technique with a 2,213 images database created from 7 subjects to the resulting animation. By using the proposed method, we can automatically generate a speech animation with the realistic inner mouth from the existing speech animation created by previous methods.

著者

Chuzo Iwamoto

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.22, no.1, pp.40-43, 2014 (Released:2014-01-15)

参考文献数

20

被引用文献数

2 15

---

Yosenabe is one of Nikoli's pencil puzzles, which is played on a rectangular grid of cells. Some of the cells are colored gray, and two gray cells are considered connected if they are adjacent vertically or horizontally. A set of connected gray cells is called a gray area. Some of the gray areas are labeled by numbers, and some of the non-gray cells contain circles with numbers. The object of the puzzle is to draw arrows, vertically or horizontally, from all circles to gray areas so that (i) the arrows do not bend, and do not cross other circles or lines of other arrows, (ii) the number in a gray area is equal to the total of the numbers of the circles which enter the gray area, and (iii) gray areas with no numbers may have any sum total, but at least one circle must enter each gray area. It is shown that deciding whether a Yosenabe puzzle has a solution is NP-complete.

著者

Marat Zhanikeev

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.22, no.2, pp.253-262, 2014 (Released:2014-04-15)

参考文献数

15

被引用文献数

2

---

Smart Cities are supposed to be the next generation of not only city infrastructure but also citizenship. Improving citizens' quality of life - referred to as social utility in this paper - should be one of the main targets of a smart city. Electric Vehicles (EVs) offer several new venues in this area. While today citizens are basically on their own when they buy a car while residing in a city, EVs in a smart city is a different topic entirely. Citizens shrink from purchasing EVs today mainly because of high cost and low availability of battery charging. With alternative battery ownership model and Vehicle-To-Home (V2H) systems, citizens can get much more from owning an EV in terms of social utility. This paper shows that high social utility depends on the infrastructure provided by the city. While the battery replacement model presented in this paper greatly increases charging availability, it still heavily depends on battery replacement stations. This paper presents a realistic model for a city-wide EV service infrastructure. The model is based on the real road map of Tokyo. The model evaluates quality of life of citizens, represented by two social utility metrics. Recommendations to battery replacement service providers are made based on simulation results.

著者

Toshiyuki Hagiya Tsuneo Kato

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.22, no.2, pp.410-416, 2014 (Released:2014-04-15)

参考文献数

25

被引用文献数

1

---

To provide an accurate and user-adaptable software keyboard for touchscreens, we propose a probabilistic flick keyboard based on hidden Markov models (HMMs). Touch and flick operations for each character are modeled by HMMs. This keyboard reduces input errors by taking the trajectory of the actual touch position into consideration and by user adaptation. We evaluated the performance of an HMM-based flick keyboard and maximum-likelihood linear regression (MLLR) adaptation. Experimental results showed that a user-dependent model reduced the error rate by 28.3%. In a practical setting, the MLLR adaptation to a specific user with only 10 words reduced the error rate by 16.6% and increased the typing speed by 11.9%.

著者

Hisamitsu Akiba Y-h. Taguchi

出版者

一般社団法人 情報処理学会

雑誌

IPSJ Transactions on Bioinformatics (ISSN:18826679)

巻号頁・発行日

vol.1, pp.35-41, 2008 (Released:2008-11-28)

参考文献数

12

---

The Barcode of Life (BOL) project aims to identify species with no other information than DNA sequence. We assume that BOL includes information on higher taxa. In the present study, we compute nonmetric distance from BOL barcodes by using rank order of pairwise distance for 3 distinct examples, namely, Ant Diversity in Northern Madagascar, Survey of Chelicerates, and Birds of North America. This enables us to recognize higher taxa, i.e., genus, family, and order, more easily. For example, the ratio of mean inner taxa nonmetric distance to the intertaxa distance is smaller than that for raw (metric) distance. Furthermore, for most pairs of higher taxa, the mean intertaxa distance is more than twice larger than intrataxa distances. The nonmetric multidimensional scaling method enables to discriminate higher taxa compared to tree construction by the neighbor-joining method or the maximum parsimony method with raw distance measure, when each species is embedded into more than 40 dimensional space with an accuracy of 90% even after leave-one-out-cross-validation.

著者

Masaaki Ohnishi Masugi Inoue Hiroaki Harai

出版者

一般社団法人 情報処理学会

雑誌

Journal of Information Processing (ISSN:18826652)

巻号頁・発行日

vol.21, no.2, pp.216-224, 2013 (Released:2013-04-15)

参考文献数

11

被引用文献数

3

---

In wide-area disaster situations, wireless mesh networks lose data communication reachability among arbitrary pairs of base stations due to the loss of routing information propagation and synchronization. This paper uses a Delaunay overlay approach to propose a distributed networking method in which detour overlay paths are incrementally added to a wireless mesh network in wide-area disaster situations. For this purpose, the following functions are added to each base station for wireless multi-hop communication: obtaining the spatial location, exchanging spatial location messages between base stations, transferring data based on spatial locations of base stations. The proposed method always constructs a Delaunay overlay network with detour paths on the condition that a set of wireless links provides a connected graph even if it does not initially provide reachability among arbitrary base stations in the connected graph. This is different from the previous method that assumes a connected graph and reachability. This paper therefore also shows a new convergence principle and implementation guidelines that do not interfere with the existing convergence principle. A simulation is then used to evaluate the detour length and table size of the proposed method. It shows that the proposed method has scalability. This scalability provides adaptable low-link quality and increases the number of nodes in wide-area disaster situations.

著者

Jun Kitazono Toshiaki Omori Toru Aonishi Masato Okada

出版者

一般社団法人 情報処理学会

雑誌

IPSJ Online Transactions (ISSN:18826660)

巻号頁・発行日

vol.5, pp.186-191, 2012 (Released:2012-10-03)

参考文献数

22

被引用文献数

1 3

---

With developments in optical imaging over the past decade, statistical methods for estimating dendritic membrane resistance from observed noisy signals have been proposed. In most of previous studies, membrane resistance over a dendritic tree was assumed to be constant, or membrane resistance at a point rather than that over a dendrite was investigated. Membrane resistance, however, is actually not constant over a dendrite. In a previous study, a method was proposed in which membrane resistance value is expressed as a non-constant function of position on dendrite, and parameters of the function are estimated. Although this method is effective, it is applicable only when the appropriate function is known. We propose a statistical method, which does not express membrane resistance as a function of position on dendrite, for estimating membrane resistance over a dendrite from observed membrane potentials. We use the Markov random field (MRF) as a prior distribution of the membrane resistance. In the MRF, membrane resistance is not expressed as a function of position on dendrite, but is assumed to be smoothly varying along a dendrite. We apply our method to synthetic data to evaluate its efficacy, and show that even when we do not know the appropriate function, our method can accurately estimate the membrane resistance.