• Title/Summary/Keyword: heuristic method

Search Result 1,080, Processing Time 0.024 seconds

Weighted Finite State Transducer-Based Endpoint Detection Using Probabilistic Decision Logic

  • Chung, Hoon;Lee, Sung Joo;Lee, Yun Keun
    • ETRI Journal
    • /
    • v.36 no.5
    • /
    • pp.714-720
    • /
    • 2014
  • In this paper, we propose the use of data-driven probabilistic utterance-level decision logic to improve Weighted Finite State Transducer (WFST)-based endpoint detection. In general, endpoint detection is dealt with using two cascaded decision processes. The first process is frame-level speech/non-speech classification based on statistical hypothesis testing, and the second process is a heuristic-knowledge-based utterance-level speech boundary decision. To handle these two processes within a unified framework, we propose a WFST-based approach. However, a WFST-based approach has the same limitations as conventional approaches in that the utterance-level decision is based on heuristic knowledge and the decision parameters are tuned sequentially. Therefore, to obtain decision knowledge from a speech corpus and optimize the parameters at the same time, we propose the use of data-driven probabilistic utterance-level decision logic. The proposed method reduces the average detection failure rate by about 14% for various noisy-speech corpora collected for an endpoint detection evaluation.

Solving Facility Rearrangement Problem Using a Genetic Algorithm and a Heuristic Local Search

  • Suzuki, Atsushi;Yamamoto, Hisashi
    • Industrial Engineering and Management Systems
    • /
    • v.11 no.2
    • /
    • pp.170-175
    • /
    • 2012
  • In this paper, a procedure using a genetic algorithm (GA) and a heuristic local search (HLS) is proposed for solving facility rearrangement problem (FRP). FRP is a decision problem for stopping/running of facilities and integration of stopped facilities to running facilities to maximize the production capacity of running facilities under the cost constraint. FRP is formulated as an integer programming model for maximizing the total production capacity under the constraint of the total facility operating cost. In the cases of 90 percent of cost constraint and more than 20 facilities, the previous solving method was not effective. To find effective alternatives, this solving procedure using a GA and a HLS is developed. Stopping/running of facilities are searched by GA. The shifting the production operation of stopped facilities into running facilities is searched by HLS, and this local search is executed for one individual in this GA procedure. The effectiveness of the proposed procedure using a GA and HLS is demonstrated by numerical experiment.

Usability Evaluation and Improvements of Mobile Travel Apps

  • Kim, Yeonsuk;Kim, Heesun
    • International Journal of Internet, Broadcasting and Communication
    • /
    • v.12 no.1
    • /
    • pp.27-36
    • /
    • 2020
  • The popularization of smartphones allows people to instantly get the information that they want, through mobile apps, including financial services, movies and public transportation reservations, games and shopping. Furthermore, leisure activities through overseas travel are increasing due to the improvement of the living standards of people. These increases in overseas travel and the use of mobile apps lead to the increased use of mobile travel apps when booking tour packages. Although there are many studies on the usability assessment and user interface improvement for mobile apps, studies on the usability assessment for mobile travel apps are limited. We tested the usability for mobile travel apps to present some suggestions for improvements so that anyone can purchase travel packages easily and simply. We selected the top three mobile travel apps on Rankey.com that have different UIs. The heuristic method was used to evaluate usability. We present a better UI to allow users to use the app functions more easily by analyzing user interaction, ease of learning, readability, efficiency, and satisfaction for the entire use.

Actor-Critic Algorithm with Transition Cost Estimation

  • Sergey, Denisov;Lee, Jee-Hyong
    • International Journal of Fuzzy Logic and Intelligent Systems
    • /
    • v.16 no.4
    • /
    • pp.270-275
    • /
    • 2016
  • We present an approach for acceleration actor-critic algorithm for reinforcement learning with continuous action space. Actor-critic algorithm has already proved its robustness to the infinitely large action spaces in various high dimensional environments. Despite that success, the main problem of the actor-critic algorithm remains the same-speed of convergence to the optimal policy. In high dimensional state and action space, a searching for the correct action in each state takes enormously long time. Therefore, in this paper we suggest a search accelerating function that allows to leverage speed of algorithm convergence and reach optimal policy faster. In our method, we assume that actions may have their own distribution of preference, that independent on the state. Since in the beginning of learning agent act randomly in the environment, it would be more efficient if actions were taken according to the some heuristic function. We demonstrate that heuristically-accelerated actor-critic algorithm learns optimal policy faster, using Educational Process Mining dataset with records of students' course learning process and their grades.

The Solution of Vehicle Scheduling Problems with Multiple Objectives in a Probabilistic Environment

  • Park, Yang-Byung
    • Journal of Korean Institute of Industrial Engineers
    • /
    • v.14 no.1
    • /
    • pp.119-131
    • /
    • 1988
  • Vehicle Scheduling Problem (VSP) is a generic name given to a whole class of problems involving the visiting of "stations" by "vehicles," where a time is associated with each activity. The studies performed to date have the common feature of a single objective while satisfying a set of restrictions and known customer supplies or demands. However, VSPs may involve relevant multiple objectives and probabilistic supplies or demands at stations, creating multicriteria stochastic VSPs. This paper proposes a heuristic algorithm based on goal programming approach to schedule the most satisfactory vehicle routes of a bicriteria VSP with probabilistic supplies at stations. The two relevant objectives are the minimization of the expected travel distance of vehicles and the minimization of the due time violation for collection service at stations by vehicles. The algorithm developed consists of three major stages. In the first stage, an artificial capacity of vehicle is determined, on the basis of decision maker's subjective estimates. The second one clusters a set of stations into subsets by applying an efficient cluster method developed. In the third one, the stations in each subset are scheduled by applying an iterative goal programming heuristic procedure to each cluster.

  • PDF

Aesthetical-ethical Paradigm of Care Ethics in Nursing (돌봄의 윤리를 위한 미감적 - 윤리적 패러다임)

  • 공병혜
    • Journal of Korean Academy of Nursing
    • /
    • v.32 no.3
    • /
    • pp.364-372
    • /
    • 2002
  • The purposes of this study was to find aesthetical-ethical paradigm of care ethics by understanding the unique moral character of care as an art and to suggest the optimal direction of nursing ethics. Method: This study used meaning-heuristic and -interpretive methods of hermeneutics based on philosophical aesthetic theory; Baumgarten's aesthetics, Schiller's theory of aesthetical education and Kant's theory of aesthetical judgement. Result: The concept of care implied aesthetical and ethical character; caring as an art was related to moral feeling based on human dignity und emotional communication in interpersonal-relationship. Caring as an art was interpreted as a moral ideal for the promotion of the humanity und the interaction in personal-relationship according to nursing theories. Philosophical aesthetics could provide the theoretical base for the interpretation of caring as an art. The proper paradigm of care ethics in nursing could be found in character-trait ethics and communication ethics according to the philosophical aesthetics. Conclusion: This study could show aesthetical-ethical paradigm of care ethics in nursing by the heuristic interpretation of caring as an art according to the philosophical aesthetics

A Heuristic Method for Channel Allocation and Scheduling in an OFDMA System

  • Hwang, Sung-Ho;Park, Joon-Goo;Jang, Youn-Seon;Cho, Ho-Shin
    • ETRI Journal
    • /
    • v.30 no.5
    • /
    • pp.741-743
    • /
    • 2008
  • In this letter, a heuristic channel allocation and scheduling scheme is proposed. By comparing the size of the alternative-factor assessment, which is obtained by simple calculation, we can easily find the most appropriate channel for each user for overall throughput enhancement. Numerical results show that the downlink throughput of the proposed scheme is higher than that of proportional fairness and is almost the same as that of the maximum C/I scheme, while user fairness remains better than that of the maximum C/I scheme.

  • PDF

Machine-part Group Formation Methodology for Flexible Manufacturing Systems (유연생산시스템(FMS)에서의 기계-부품그룹 형성기법)

  • Ro, In-Kyu;Kwon, Hyuck-Chun
    • Journal of Korean Institute of Industrial Engineers
    • /
    • v.17 no.1
    • /
    • pp.75-82
    • /
    • 1991
  • This research is concerned with Machine-Part Group Formation(MPGF) methodology for Flexible Manufacturing Systems(FMS). The purpose of the research is to develop a new heuristic algorithm for effectively solving MPGF problem. The new algorithm is proposed and evaluated by 100 machine-part incidence matrices generated. The performance measures are (1) grouping ability of mutually exclusive block-diagonal form. (2) number of unit group and exceptional elements, and (3) grouping time. The new heuristic algorithm has the following characteristics to effectively conduct MPGF : (a) The mathematical model is presented for rapid forming the proper number of unit groups and grouping mutually exclusive block-diagonal form, (b) The simple and effective mathematical analysis method of Rank Order Clustering(ROC) algorithm is applied to minimize intra-group journeys in each group and exceptional elements in the whole group. The results are compared with those from Expert System(ES) algorithm and ROC algorithm. The results show that the new algorithm always gives the group of mutually exclusive block-diagonal form and better results(85%) than ES algorithm and ROC algorithm.

  • PDF

Development of a Computer System for the Lot-sizing and Scheduling of the Side Frame Press Shop (상용차 Side Frame 공정의 생산계획 및 일정계획 수립 시스템 개발)

  • Hwang, Hark;Cha, Chun-Nam;Sun, Ji-Ung;Hann, Kyu-Hun;Moon, Seong-Woo;Lee, Suk;Hong, Seong-Pyo
    • IE interfaces
    • /
    • v.9 no.2
    • /
    • pp.3-17
    • /
    • 1996
  • Productivity improvement is one of the most challenging problem facing the motor industry. This paper deals with the lot sizing and production scheduling problems of the side frame press shop in a domestic truck manufacturing company. The problems can not be solved simultaneously due to the computational complexity. Thus, we present a heuristic method which solves the two problems sequentially with the objective of maximizing the press utilization while maintaining a minimum inventory level. A micro-computer-based software is developed for easy implementation of the heuristic in the shop floor level.

  • PDF

A Heuristic for Scheduling Production of Components at a Single Facility (단일설비 생산체제에서 부품의 일정계획에 관한 발견적 기법)

  • Gim, Bong-Jin
    • Journal of Korean Institute of Industrial Engineers
    • /
    • v.20 no.2
    • /
    • pp.31-38
    • /
    • 1994
  • We consider a single-machine scheduling problem dealing with the manufacture of components for subsequent assembly into end products. Each product requires both unique components and common components, and each production requires a setup. By making some assumptions on the data and the availability of the components for assembly, Baker provides on efficient dynamic programming algorithm for obtaining the optimal schedule. In this paper we do not impose any requirement on the data, and we solve the more complicated batching and sequencing problem. We suggest a simple heuristic method that is efficient and finds solutions that are optimal or close to the optimal solution.

  • PDF