担当区分：筆頭著者   掲載種別：研究論文（学術雑誌）   出版者・発行元：Japan Journal of Industrial and Applied Mathematics  

We propose a forecasting method based on a logistic curve model with missing data, which are a ubiquitous problem in social science forecasting, especially in marketing. The method completely recovers parameters of the difference equation when data are on an exact solution curve because it uses an unequal step difference equation that has an exact solution. It makes full use of data without wasting any data or generating plausible data for the missing data. It only requires regression analysis and a simple optimization technique and showed better fitting than two conventional methods for three actual datasets.

DOI： 10.1007/s13160-020-00452-w

Scopus

researchmap

その他リンク： https://link.springer.com/article/10.1007/s13160-020-00452-w/fulltext.html

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Japan Journal of Industrial and Applied Mathematics  

A property of data on the exact solution of the logistic curve model was exposed by behavior of upper limits estimated with an unsuitable model (the Gompertz curve model). The property is that the upper limits estimated with the Gompertz curve model for logistic data change with the downward convex for the data as the data size increases, i.e., time elapses. This contributes to identifying a suitable model because the behavior is independent of noise included in actual data. A suitable model is indispensable for correct forecasts. The property was proved and the proof was accomplished thanks to difference equations that have exact solutions. Moreover, we analyzed how resistant the downward convex and monotonic decrease of the estimated upper limit were to noise included in actual data sets.

DOI： 10.1007/s13160-019-00382-2

Scopus

researchmap

その他リンク： http://link.springer.com/article/10.1007/s13160-019-00382-2/fulltext.html

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Informa UK Limited  

DOI： 10.1080/25742558.2019.1660503

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Informa UK Limited  

DOI： 10.1080/25742558.2019.1596552

researchmap

その他リンク： https://www.tandfonline.com/doi/pdf/10.1080/25742558.2019.1596552

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Japan Journal of Industrial and Applied Mathematics  

The Gompertz curve and logistic curve models are often used to forecast upper limits (saturation points). To accurately estimate an upper limit, an appropriate model selection as well as accurate parameter estimation is required. We mathematically analyze how an upper limit estimated with an inappropriate model changes as the data size increases, i.e., time elapses, when the Gompertz curve model is selected for data described on the exact solution of the logistic curve model. We prove that an estimated upper limit is strictly monotonically decreasing as the historical data size increases and that the upper limit estimated with the inappropriate model converges to the upper limit estimated with the appropriate model as the data size approaches infinity. These results can help in selecting an appropriate model.

DOI： 10.1007/s13160-018-0333-9

Scopus

researchmap

その他リンク： http://link.springer.com/content/pdf/10.1007/s13160-018-0333-9.pdf

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Computer Networks  

When a disaster strikes, many people make calls to their loved ones in the affected area. As a result, telephone networks become congested, making it difficult for people to contact each other. This congestion continues in the aftermath of a large-scale disaster. The sooner the congestion is eased, the sooner and easier people can contact each other. We accomplish this by reducing communication demand without directly restricting call duration. We propose a congestion control method, called the road space rationing (RSR) method (RSR was originally designed for transportation and restricts access to congested areas on the basis of the last digit of a vehicle's license plate or license number). Our RSR method only restricts the period in which to make a call on the basis of the last digits of calling parties’ phone numbers (e.g., only people with phone numbers ending in 1 can make calls between XX:06 and XX:12). It not only avoids restricting the overall number of calling parties but also prompts people to reduce their call duration consciously despite it being unrestricted. It thus has a mechanism to change human communication behavior without directly restricting call duration. This consciously willed reduction is effective against disaster congestion because there are no redials to the same called parties. This reduction in call duration in turn decreases congestion. Experimental results revealed that the RSR method reduced call duration by 30%.

DOI： 10.1016/j.comnet.2018.01.049

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences  

The network operations center of a communication carrier play an important and critical role in the early stage of disaster response because its function is the maintenance of communication services, which includes traffic control and restoration of services. This paper describes traffic control and restoration of services affected by the Great East Japan Earthquake. This paper discusses challenges on traffic congestion and restoration for future large-scale disasters.

DOI： 10.1587/transfun.e98.a.1602

Scopus

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences  

We demonstrated that load balancing using actual subscriber extension numbers was practical and effective against traffic congestion after a disaster based on actual data. We investigated the ratios of the same subscriber extension numbers in each prefecture and found that most of them were located almost evenly all over the country without being concentrated in a particular area. The ratio of every number except for the fourth-last digit in the last group of four numbers in a telephone number was used almost equally and located almost evenly all over the country. Tolerance against overload in the last, second-, and third-last single digits stays close to that in the ideal situation if we assume that each session initiation protocol server has a capacity in accordance with the ratio of each number on every single digit in the last group of four numbers in Japan. Although tolerance against overload in double-, triple-, and quadruple-digit numbers does not stay close to that in the ideal situation, it still remains sufficiently high in the case of double- and triple-digit numbers. Although tolerance against overload in the quadruple-digit numbers becomes low, disaster congestion is still not likely to occur in almost half of the area of Japan (23 out of 47 prefectures).

DOI： 10.1587/transfun.e98.a.1637

Scopus

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Computer Communications  

Pre-congestion notification (PCN) gives an early warning of congestion by marking packets to protect the quality of service of inelastic flows. PCN defines two rates per link: admissible rate (AR) and supportable rate (SR), which divide the PCN traffic load into three states, "no pre-congestion," "AR pre-congestion," and "SR pre-congestion." PCN admission control and flow termination control operate in accordance with these three states. However, only two PCN encoding states, unmarked and PCN marked, can be used due to the requirement of PCN encoding to survive tunneling through a currently used IPsec tunnel. We propose a marking algorithm, which uses the two encoding states, for distinguishing the three states of PCN traffic load. We also propose new admission and flow termination controls, which are based on the proposed marking algorithm, and evaluate their performance. Markings that require fewer PCN encoding states are preferable because the remaining encoding state can be used for a newly added PCN-based control in the future. Furthermore, distinguishing more states with fewer encoding states benefits not only PCN but also general marking techniques because header fields are limited; thus, valuable. © 2013 Elsevier B.V. All rights reserved.

DOI： 10.1016/j.comcom.2013.03.004

Scopus

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings - IEEE Symposium on Computers and Communications  

Pre-congestion notification (PCN) is a packet marking mechanism for DiffServ domains to facilitate feedback-based admission control (AC) and flow termination (FT) for the Internet to achieve quality of service (QoS) for inelastic flows. While AC blocks new flows to prevent an overly high load on network links, FT removes traffic to protect the QoS of the remaining PCN-flows when traffic is rerouted due to any kind of failure. We focus on one of the PCN methods, the controlled load (CL) method, whose edge behavior is now under standardization in the PCN working group of the Internet Engineering Task Force. The CL method terminates a sufficient number of flows in one shot and seems to have accurate control. However, we discovered that more termination than was needed, which we call overtermination, occurred in the CL method. We found that the CL method causes overtermination when not all the ingress-egress pairs have the same round-trip time. A countermeasure is presented to remove this overtermination. © 2010 IEEE.

DOI： 10.1109/ISCC.2010.5546742

Scopus

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE Transactions on Communications  

We present a session initiation protocol (SIP) network design for a voice-over-IP network to prevent congestion caused by people calling friends and family after a disaster. The design increases the capacity of SIP servers in a network by using all of the SIP servers equally. It takes advantage of the fact that equipment for voice data packets is different from equipment for signaling packets in SIP networks. Furthermore, the design achieves simple routing on the basis of telephone numbers. We evaluated the performance of our design in preventing congestion through simulation. We showed that the proposed design has roughly 20 times more capacity, which is 57 times the normal load, than the conventional design if a disaster were to occur in Niigata Prefecture struck by the Chuetsu earthquake in 2004. Copyright © 2010 The Institute of Electronics, Information and Communication Engineers.

DOI： 10.1587/transcom.e93.b.2273

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEE Communications Surveys and Tutorials  

Pre-congestion notification (PCN) provides feedback about load conditions in a network to its boundary nodes. The PCN working group of the IETF discusses the use of PCN to implement admission control (AC) and flow termination (FT) for prioritized realtime traffic in a DiffServ domain. Admission control (AC) is a well-known flow control function that blocks admission requests of new flows when they need to be carried over a link whose admitted PCN rate already exceeds an admissible rate. Flow termination (FT) is a new flow control function that terminates some already admitted flows when they are carried over a link whose admitted PCN rate exceeds a supportable rate. The latter condition can occur in spite of AC, e.g., when traffic is rerouted due to network failures. This survey gives an introduction to PCN and is a primer for this new technology. It presents and discusses the multitude of architectural design options in an early stage of the standardization process in a comprehensive and streamlined way before only a subset of them is standardized by the IETF. It brings PCN from the IETF to the research community and serves as historical record. © 2005 IEEE.

DOI： 10.1109/surv.2010.040710.00078

Scopus

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Conference on Communications  

We present a session initiation protocol (SIP) network design for a voice-over-IP (VoIP) network to prevent congestion caused by people calling friends and family after a disaster. The design increases the capacity of SIP servers in a network by using all the SIP servers equally. The design uses a property that SIP network elements do not carry voice data packets but signaling packets instead. Furthermore, the design achieves simple routing based on telephone numbers. We evaluate the performance of preventing congestion through simulation. We show that the proposed design has roughly 20 times more capacity, which is 57 times of the normal load, than the conventional design if a disaster were to occur in Niigata Prefecture. ©2009 IEEE.

DOI： 10.1109/ICC.2009.5199461

Scopus

出版者・発行元：IEEE International Conference on Communications  

The topology of a network seriously affects its cost, reliability, throughput, and traffic pattern, etc, so we need to simultaneously consider these multiple criteria, which have different units, when evaluating network topologies. Moreover, we need to reflect the relative importance of each criterion when evaluating the network topology. However, ordinary methods of network topology design consider only a single criterion. In this paper, we apply AHP (analytic hierarchy process), which has been widely used when making a rational decision with multiple criteria, to network topology design. AHP enables us to reflect the relative importance of each criterion on the results. In network topology design, we need to consider a huge number of candidates, and the differences in the weights among candidates are small. Therefore, the optimum topologies will be determined by just the weighted criteria, and other criteria will not be considered. Therefore, to emphasize the difference of the weights, we propose to use a linear-transformed value of each criterion when constructing weights in AHP. ©2008 IEEE.

DOI： 10.1109/ICC.2008.393

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：International Journal of Communication Systems  

The paper introduces two new unicast active end-to-end measurement techniques, called the single-double unicast probing (SDUP) and the delay-based unicast probing (DUP), to estimate the rate of losses which occurs on the shared network path of two flows. A comprehensive performance evaluation and a comparison between these two techniques and an existing one having the same objective, the striped unicast probing (SUP) (Proceedings of the INFOCOM 2001-The IEEE Conference on Computer Communications, No. 2, Anchorage, Alaska, U.S.A., 2001; 915-923), were carried out. We demonstrate that our proposed SDUP technique provides even better estimation accuracy compared to that of the SUP while it requires only one piece of measurement equipment at only one receiver instead of deploying units to both receivers. Furthermore, with only one sender and receiver pair we can measure not only one shared path, but any partial path that begins at the sender and is located on the sender-receiver path. We also show that while the DUP have the same accuracy as the SUP in the case of Drop-Tail buffer management, the DUP is capable of measuring loss rates of RED buffers, which the other techniques do not work with. The SDUP and the DUP are less intrusive and cause less bursty traffic compared to the SUP. Finally, the adaptation of these techniques into passive measurements is also considered. Copyright © 2006 John Wiley & Sons, Ltd.

DOI： 10.1002/dac.839

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings of the Third IASTED International Conference on Communications, Internet, and Information Technology  

In this paper we present a new method for the detection of bottleneck link(s) in the networks. The proposed method is based on the variance-per-mean ratio of the flow's throughput crossing the link which can be calculated from the data trace information provided by passive traffic monitoring. This new indicator of bottleneck links is found to be effective and robust against the offered link loads, bottleneck bandwidth, and the traffic composition. The results are verified using both simulation and real measurement analysis.

Scopus

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語   掲載種別：研究論文（学術雑誌）  

DOI： 10.15807/jorsj.46.372

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：日本語  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：学位論文（博士）  

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Japan Journal of Industrial and Applied Mathematics  

We describe software reliability growth models that yield accurate parameter estimates in spite of a small amount of input data in an actual software testing. These models are based on discrete analogs of a logistic curve model. The models are described with two difference equations, one each proposed by Morishita and Hirota. The difference equations have exact solutions. The equations tend to a differential equation on which the logistic curve model is defined when the time interval tends to zero. The exact solutions also tend to the exact solution of the differential equation when the time interval tends to zero. The discrete models conserve the characteristics of the logistic model because the difference equations have exact solutions. Therefore, the proposed models provide accurate parameter estimates, making it possible to predict in the early development phase when software can be released.

DOI： 10.1007/bf03167447

Scopus

researchmap

その他リンク： http://link.springer.com/article/10.1007/BF03167447/fulltext.html

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Computer Communications  

This paper reports our measurements and analysis of traffic characteristics in an Internet backbone ATM network. In order to utilize network resource efficiently while satisfying the quality of service requirement, it is important to understand the traffic characteristics. We therefore monitored the traffic from the flow or application level to the cell level on a link between NTT's Open Computer Network (OCN) and the Science Information Network (SINET), which are two of the largest Internet backbone ATM-based networks in Japan. Using the monitored traffic, we also evaluated the performance of the aggregate traffic by real-time simulation. Results show that the performance (cell loss ratio) greatly depended not only on link utilization but also on the number of flows, flow size, and traffic composition in terms of applications. We also found that the degree of self-similarity in the Internet backbone was not large. In addition, we clarified that more statistical multiplexing gain could be obtained in the Internet backbone when more flows were multiplexed onto a link. © 2001 Elsevier Science B.V. All rights reserved.

DOI： 10.1016/s0140-3664(01)00309-7

Scopus

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Journal of the Operations Research Society of Japan  

A discrete Bass model, which is a discrete analog of the Bass model, is proposed. This discrete Bass model is defined as a difference equation that has an exact solution. The difference equation and the solution respectively tend to the differential equation which the Bass model is defined as and the solution when the time interval tends to zero. The discrete Bass model conserves the characteristics of the Bass model because the difference equation has an exact solution. Therefore, the discrete Bass model enables us to forecast the innovation diffusion of products and services without a continuous-time Bass model. The parameter estimations of the discrete Bass model are very simple and precise. The difference equation itself can be used for the ordinary least squares procedure. Parameter estimation using the ordinary least squares procedure is equal to that using the nonlinear least squares procedure in the discrete Bass model. The ordinary least squares procedures in the discrete Bass model overcome the three shortcomings of the ordinary least squares procedure in the continuous Bass model: the time-interval bias, standard error, and multicollinearity.

DOI： 10.15807/jorsj.44.1

Scopus

researchmap

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE Transactions on Communications  

We have developed a new traffic measuring tool and applied it to the real-time simulation of a network. It monitors IP traffic on an ATM link and continuously transfers the length and timestamp of each IP packet to a post-processing system. The post-processing system receives the data, estimates the cell's arrival epoch at the transmission queue of the ATM link, and simulates the queueing behavior on-line if conditions differ from those of the actual system. The measuring tool and real-time simulation represent a new approach to traffic engineering. A new estimation problem, the arrival sequence estimation, is shown and some algorithms are proposed and evaluated. Also, a new dimensioning algorithm called the queue decay parameter method, which is expected to be robust and applicable to real-time control, is proposed and evaluated.

Scopus

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings of the International Symposium on Software Reliability Engineering, ISSRE  

We propose a criterion to determine a more appropriate software reliability growth model in the early development phase. The criterion with a discrete software reliability growth model determines the absolute worth of a model because the discrete software reliability growth model perfectly reproduces the parameter estimates when the data are used as an exact solution of the equation. The values of the proposed criterion of a discrete software reliability growth model are smaller than those of another software reliability growth model in all periods during the test phase with actual data sets. The discrete software reliability growth models are described with difference equations which have exact solutions. The models yield accurate parameter estimates in spite of a small amount of input data in an actual software testing. Therefore, the criterion and discrete software reliability growth models enable us to predict in the early development phase when software can be released.

DOI： 10.1109/ISSRE.2001.989471

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Conference on Communications  

We have developed a real-time simulator that is connected to the network on-line and continuously uses the monitored IP traffic on AAL5/ATM. The simulator is software running on a real-time OS in a PC containing ATM network interface cards, which can use the information provided by the timestamp, VPI/VCI, IP address, protocol number, and port number of the monitored packets for the simulation. The simulator provides a simulation model of a multiplexer whose output link speed, buffer size, and queueing discipline can be changed by the user. In addition, we propose a simulation server that makes a simulation platform easily available. The simulator enables us to identify the appropriate amount of network resources, such as link speed and buffer size, and the effectiveness of various queueing disciplines. Numerical examples using the simulator in a real network are also shown.

Scopus

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE Transactions on Information and Systems  

I describe a software reliability growth model that yields accurate parameter estimates even with a small amount of input data. The model is based on a proposed discrete analog of a Gompertz equation that has an exact solution. The difference equation tends to a differential equation on which the Gompertz curve model is defined, when the time interval tends to zero. The exact solution also tends to the exact solution of the differential equation when the time interval tends to zero. The discrete model conserves the characteristics of the Gompertz model because the difference equation has an exact solution. Therefore, the proposed model provides accurate parameter estimates, making it possible to predict in the early test phase when software can be released.

Scopus

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEICE Transactions on Information and Systems  

I describe a software reliability growth model that yields accurate parameter estimates even with a small amount of input data. The model is based on a proposed discrete analog of a Gompertz equation that has an exact solution. The difference equation tends to a differential equation on which the Gompertz curve model is defined, when the time interval tends to zero. The exact solution also tends to the exact solution of the differential equation when the time interval tends to zero. The discrete model conserves the characteristics of the Gompertz model because the difference equation has an exact solution. Therefore, the proposed model provides accurate parameter estimates, making it possible to predict in the early test phase when software can be released.

Scopus

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

researchmap

担当区分：筆頭著者   記述言語：英語  

researchmap

担当区分：筆頭著者   記述言語：英語  

researchmap

担当区分：筆頭著者   記述言語：日本語   掲載種別：記事・総説・解説・論説等（商業誌、新聞、ウェブメディア）  

researchmap

担当区分：筆頭著者   記述言語：日本語   掲載種別：速報，短報，研究ノート等（大学，研究機関紀要）  

researchmap

担当区分：筆頭著者   記述言語：英語   掲載種別：機関テクニカルレポート，技術報告書，プレプリント等   出版者・発行元：NTT Review  

The ATM probe is a system intended for measuring traffic and QoS at each of the ATM, IP the TCP/UDP layers. The functions of this probe are realized by software in the PC. The probe has no effect on communication that is actually taking place. It also permits measurement without imposing a load on the network equipment.

Scopus

記述言語：日本語   掲載種別：機関テクニカルレポート，技術報告書，プレプリント等  

researchmap

担当区分：筆頭著者   記述言語：日本語   掲載種別：機関テクニカルレポート，技術報告書，プレプリント等  

researchmap

記述言語：日本語   掲載種別：機関テクニカルレポート，技術報告書，プレプリント等   出版者・発行元：NTT R and D  

With networks like the Internet becoming increasingly utilized by businesses, network service providers are being asked to guarantee high QoS by making service level agreements with their users. To provide high QoS, they need to be able to measure network conditions in order to manage bandwidth and quality. In this paper, we introduce a monitoring system called "ATM probe", which measures traffic and QoS of IP-over-ATM packets.

Scopus

記述言語：英語   会議種別：口頭発表（一般）  

researchmap

researchmap

researchmap

researchmap