Setsuo Tsuruta

A Multi-world Intelligent Genetic Algorithm to Interactively Optimize Large-scale TSP

To optimize large-scale distribution networks, solving about 1000 middle scale (around 40 cities) TSPs (traveling salesman problems) within an interactive length of time (max. 30 seconds) is required. Yet, expert-level (less than 3% of errors) accuracy is necessary. To realize the above requirements, a multi-world intelligent GA method was developed. This method combines a high-speed GA with an intelligent GA holding problem-oriented knowledge that is effective for some special location patterns. If conventional methods were applied, solutions for more than 20 out of 20,000 cases were below expert-level accuracy. However, the developed method could solve all of 20,000 cases at expert-level

Toward Sensor-Based Context Aware Systems

This paper proposes a methodology for sensor data interpretation that can combine sensor outputs with contexts represented as sets of annotated business rules. Sensor readings are interpreted to generate events labeled with the appropriate type and level of uncertainty. Then, the appropriate context is selected. Reconciliation of different uncertainty types is achieved by a simple technique that moves uncertainty from events to business rules by generating combs of standard Boolean predicates. Finally, context rules are evaluated together with the events to take a decision. The feasibility of our idea is demonstrated via a case study where a context-reasoning engine has been connected to simulated heartbeat sensors using prerecorded experimental data. We use sensor outputs to identify the proper context of operation of a system and trigger decision-making based on context information.

A multi-inner-world Genetic Algorithm to optimize delivery problem with interactive-time

Building a delivery route optimization system that improves the delivery efficiency in real time requires to solve several tens to hundreds cities Traveling Salesman Problems (TSP) within interactive response time, with expert-level accuracy (less than 3% of errors). To meet these requirements, a multi-inner-world Genetic Algorithm (Miw-GA) method was developed. This method combines two types of GApsilas inner worlds such as a 2-opt type mutation world and an NI type mutation world, randomly selecting either one of these mutation methods (inner worlds) each generation in a GA world consisting of the whole generations. This method is compared with other related works based on experimental results.

A simple optimization method based on Backtrack and GA for delivery schedule

A delivery route optimization system greatly improves the real time delivery efficiency. To realize such an optimization, its distribution network requires solving several tens to hundreds (max. 1500–2000) cities Traveling Salesman Problems (TSP) within interactive response time (around 3 seconds) with expert-level accuracy (below 3% level of error rate). Moreover, as for the algorithms, understandability and flexibility are necessary because field experts and field engineers can understand and adjust it to satisfy the field conditions. To meet these requirements, a Backtrack and Restart Genetic Algorithm (Br-GA) is proposed. This method combines Backtracking and GA having simple heuristics such as 2-opt and NI (Nearest Insertion) so that, in case of stagflation, GA can restarts with the state of populations going back to the state in the generation before stagflation. Including these heuristics, field experts and field engineers can easily understand the way and use it. Using the tool applying their method, they can easily create/modify the solutions or conditions interactively depending on their field needs. Experimental results proved that the method meets the above-mentioned delivery scheduling requirements more than other methods from the viewpoint of optimality as well as simplicity.

Topic and Opinion Classification Based Information Credibility Analysis on Twitter

At the Great Eastern Japan Earthquake in 2011, a huge amount of information about the disaster were exchanged on Twitter. On the other hand, various false information and rumor were also spread on Twitter. Therefore, it is required that people easily check information credibility. In this paper, we propose a method for automatically assessing the credibility of information based on the topic and opinion classifications. We assess the credibility of information by calculating the ratio of same opinions to all opinions about a topic. For identifying which topic is mentioned in a tweet, our method uses topic models generated by Latent Dirichlet Allocation. For identifying whether an opinion of a tweet is positive or negative, our method performs sentiment analysis using a semantic orientation dictionary. We performed our experiments on 2960 tweets and show more than 0.6 in kappa statistics between our method and human scorers.

Personalizing Learning Processes by Data Mining

A modeling approach for learning processes is utilized to process, evaluate and refine them. A formerly-developed concept called storyboarding has been applied at Tokyo Denki University (TDU) to model the various curricula for students to progress in their studies. Along with this particular storyboard, we developed a data mining technology to estimate chances for success for the students following each curricular path. Here, we introduce a concept of learner profiling. The profile represents the students’ individual properties, talents and preferences constructed through mining personal meta data about learning preferences.

Inner Random Restart Genetic Algorithm to optimize delivery schedule

A delivery route optimization system greatly improves the real time delivery efficiency. To realize such an optimization, its distribution network requires solving several tens to hundreds (maximum 2 thousands or so) cities Traveling Salesman Problems (TSP) within interactive response time (around 3 seconds) with expert-level accuracy (below 3% level of error rate). To meet these requirements, an Inner Random Restart Genetic Algorithm (Irr-GA) method is proposed. This method combines random restart and GA that has different types of simple heuristics such as 2-opt and NI (Nearest Insertion). Including these heuristics, field experts and field engineers can easily understand the way and use it. Using the tool applying their method, they can easily create/modify the solutions or conditions interactively depending on their field needs. Experimental results proved that the method meets the above-mentioned delivery scheduling requirements more than other methods from the viewpoint of optimality as well as simplicity.

Toward Making Didactics a Subject of Knowledge Engineering

Learning systems suffer from a lack of an explicit and adaptable didactic design. A way to overcome such deficiencies is (semi-) formally representing the didactic design. A modeling approach, storyboarding, is outlined here. Storyboarding is setting the stage to apply knowledge engineering technologies to verify, validate the didactics behind a learning process. As a vision, didactics can be refined according to revealed weaknesses and proven excellence. Furthermore, successful didactic patterns can be inductively inferred by analyzing the particular knowledge processing and its alleged contribution to learning success.

A method for solving nested combinatorial optimization problems - a case of optimizing a large-scale distribution network

The optimization of a large-scale distribution network is considered to be a nested combinatorial problem consisting of the following steps: (1) the decision about part delivery volume per part manufacturer; (2) the decision about depots and trucks for the transportation of parts; and (3) the generation of delivery routes for each truck. In such a nested combinatorial problem, a high-level and mathematically strict optimization is desirable as the first step. In addition, at each step, human multi-sided inspection is desired, which requires interactive simulation. Thus, for the first step, a method using linear programming (LP) is proposed. For the second and third steps, a method using a genetic algorithm (GA) is proposed. The latter guarantees interactive responsiveness and realizes expert-level accuracy, through enabling the solution of 1000 mid-scale traveling salesman problems (TSPs) for a distribution network within 30 seconds and within a 3% error. Experimental results proved that the proposed method enables the optimization of a nationwide large-scale distribution network.

A Case Based Approach for an Intelligent Route Optimization Technology

This paper introduces a Case Based Approximation method to solve large scale Traveling Salesman Problems in a short time (around 3 seconds) with an error rate below 3%. This method is based on the insight, that a majority of real world problems are very often similar to previous ones at least for route scheduling. Thus, a solution can be derived from former solutions as follows: (1) selecting a most similar TSP from a library (CB: Case Base) of former TSP solutions, (2) removing the locations that are not including in the newly given problem or TSP and (3) adding the new locations by Nearest Insertion (NI) and possibly adjusting by NI incorporated GA. This way of creating solutions by Case Based Reasoning (CBR) avoids the computational costs to create new solutions from scratch. The evaluation of this method revealed remarkable results. Though even the world fastest most optimal approximate TSP solving method LKH needed more than 3 seconds or the worst error rate exceeded 3 seconds, the worst error rate of the proposed method is less than 1 % within 3 seconds. This is about 10-100 times better than that of our former approach BR-GA (Backtrack and Restart type GA).