Misato Tanaka

Automatic generation method to derive for the design variable spaces for interactive Genetic Algorithms

In the growing E-commerce market, many online shopping sites have adopted product recommendation systems to expand their business opportunities. We have focused on iGA (interactive Genetic Algorithm) as a solution to product recommendation algorithms. Although iGA is an optimization technique for users preference through the interaction between systems and users, iGA requires extraction of design variables to apply the product recommendation. Extracting design variables from existing products by hand is unrealistic because there are a wide variety of products on shopping sites that are updated rapidly. To address this problem, we have proposed an automatic generation method of a design variable space based on the collective preference data on the web. In this paper, we introduce several design variable spaces generated by books on Amazon, which maintain recommendation relations among products. The distributions of books generated by the proposed method are influenced by their authors. Then, subjective experiments confirmed that test subjects searched solutions by their unique preference.

Working Memory Training Strategies and Their Influence on Changes in Brain Activity and White Matter

In this study, we investigated whether different working memory training tasks influence brain activity and white matter changes. Thirteen participants were involved in our interventional study over a period of one month. During pre- and post-training, brain activity and structural integrity were measured using functional magnetic resonance imaging and diffusion tensor imaging. The reading span task was used to measure working memory capacity in participants performing different strategies. Participants were classified into a training group (10 participants) and a control group (4 participants). The training group was further divided into the imagery strategy group and rehearsal strategy group. Only the imagery strategy group improved working memory capacity, showing significantly increased activation in the anterior cingulate cortex and fractional anisotropy adjacent to the right temporal gyrus. Consequently, adopting the appropriate strategy is important for improving working memory capacity as different strategies affect brain activity and white matter to different degrees.

Construction of an Interactive System Aims to Extract Expert Knowledge about the Condition Cultured Corneal Endothelial Cells

We aim to construct an expert system for diagnosing the health of corneal endothelial cells. To construct the proposed system, we first constructed a system that confirms whether experts use the same criteria to diagnose the condition of cells. In the constructed system, an expert interacts with a computer that generates images of cells by simulation. These images describe cells that are in the best condition, according to expert diagnosis. By comparing the results from multiple experts, we can elucidate whether experts use the same criterion for diagnosis. The proposed system is composed of an interactive genetic algorithm (IGA) and involves the simulation of cells. We confirmed the system operated normally through operational experiments. In another experiment, conducted with no experts, we confirmed that this system could generate images demonstrating a predetermined feature value.

Functional brain network extraction using a genetic algorithm with a kick-out method

This paper proposed the method to reduce the calculating time to reveal the functional brain network associated with a task using a genetic algorithm and functional near-infrared spectroscopy (fNIRS) data. Changes in the cerebral blood flow during a task are obtained as time series data is analyzed using fNIRS, and a correlation matrix for multiple fNIRS channels is created for each subject. The subject group is divided into two groups, and a classifier of the two groups learns the correlation matrix as a feature quantity. The correlation matrix changes as the feature quantity changes with the combinations of channels, which affects classifier accuracy. If the combination of channels with the best classifier accuracy is identified, these channels can be considered important to the creation of the functional brain network for a target task. In our study, a genetic algorithm (GA) is used for channel selection. However, learning the classifier to calculate the evaluation value and optimization by the GA requires significant time. Thus, to increase search efficiency, we propose the kick-out method to skip the evaluation value calculation for poor individuals according to a previous evaluation value. We evaluated the effectiveness of the proposed method using fNIRS data recorded during a mental rotation test. Results show that important channels that express the functional brain network were selected and that processing time was reduced significantly by the proposed method.

Crossover method for interactive genetic algorithms to estimate multimodal preferences

We apply an interactive genetic algorithm (iGA) to generate product recommendations. iGAs search for a single optimum point based on a users Kansei through the interaction between the user and machine. However, especially in the domain of product recommendations, theremay be numerous optimum points. Therefore, the purpose of this study is to develop a new iGA crossover method that concurrently searches for multiple optimum points for multiple user preferences. The proposed method estimates the locations of the optimum area by a clustering method and then searches for the maximum values of the area by a probabilistic model. To confirm the effectiveness of this method, two experiments were performed. In the first experiment, a pseudouser operated an experiment system that implemented the proposed and conventional methods and the solutions obtained were evaluated using a set of pseudomultiple preferences. With this experiment, we proved that when there aremultiple preferences, the proposed method searches faster and more diversely than the conventional one. The second experiment was a subjective experiment. This experiment showed that the proposed method was able to search concurrently for more preferences when subjects had multiple preferences.

Analysis of Brain Areas Activated while Using Strategies to Improve the Working Memory Capacity

Improvement of the working memory capacity is expected to enhance the reasoning task and reading comprehension abilities. The aim of this study was to investigate effective methods for improving the working memory capacity. We used the reading span test (RST) as a task and examined the types of strategies that can be used to process tasks as well as strategies that may improve working memory capacity. In this experiment, we used functional magnetic resonance imaging to observe the brain areas activated in subjects during RST. We examined the high-span subjects (HSS) in the preliminary RST and found that the HSS used a scene imagery strategy when performing RST. The low-span subjects (LSS) were trained to learn the same strategy that was used by HSS. We observed that the similar brain areas as those in HSS were activated in LSS and their RST scores were improved.

The effects of button arrangement on evaluations in interactive Genetic Algorithms

We discussed the effects of button arrangement on evaluations in interactive Genetic Algorithms (iGAs). It was reported that the visual interface effects humans subjective. The visual interface systems of iGAs may affect the solutions as humans evaluate the candidate solutions, evaluation of these candidates may be affected by the interface. In this paper, we conduct the two experiments. One of them is the experiment to verify the association between gazing and evaluation. The experiment showed that visual interface systems effects to the evaluation of human subjective. This means that evaluation value is changed according to visual interface or locations of systems. The other is the experiment to discuss the effect to iGA search. Since visual interface affects evaluation values, derived solution by iGA is different with along to the different visual interface. From these results, visual interface of iGA should be designed carefully to use the positive or negative effect of interface design and location.

120 Offspring Generation Method for interactive Genetic Algorithms considering Multimodal Preferences and Dependencies

近年,嗜好情報に基づいてユーザに対する挙動を変化さ せるシステムが増加している.ショッピングサイトにおけ る商品推薦はその 1つである.これらのシステムを実現 する推薦手法としては協調フィルタリング (collaborative filtering) 2) とコンテンツに基づいたフィルタリング (contents-based filtering)の2つに大別できる .コンテンツ に基づいたフィルタリングでは,ユーザの行動履歴から獲 得した嗜好情報をモデル化するフェーズが必要となる.嗜 好をモデル化するアプローチには,ユーザの行動履歴や対 象となる情報の特徴量をベクトルで表現するベクトル空間 モデルや,嗜好を適合度関数でモデル化するアプローチが 存在する.後者の嗜好の適合度関数は,入力を対象となる 情報,出力を嗜好への適合度とする関数であり,適合度の最 大化を行うことでユーザに提示する情報を最適化すること が可能である.しかし,ユーザの嗜好を表現する適合度関 数を予め把握することは難しい.そのため,ユーザとのイ ンタラクションによって適合度関数を推定し,対象の最適 化を行う手法として対話型遺伝的アルゴリズム(interactive Genetic Algorithms: iGAs) が提案されている. iGAは,ユーザの主観的評価に基づいて感性情報の獲得 とその解析を行う手法として知られており,数値化が難し い補聴器のパラメータ調整など,嗜好が単峰性である問題 に多く適用されている.本研究ではこれに対して嗜好が多 峰性であり,その適合度値の優劣が顕著でない問題にも対 応した iGAの実現を目指す.このような多峰性の問題とし ては,ショッピングサイトにおける商品提示に iGAを利用 する場合などが考えられる.例えば,商品を選択する場合 には複数の好みが同時に存在する可能性があり,そのよう な状況ではすべての好みを反映した提示を行うことが売上 の向上やユーザの満足に繋がる.また,それぞれの好みに おいて設計変数間に依存関係が存在する場合は,それらの 依存関係を考慮した探索を行う必要がある. iGAでは人間が評価を行うため,探索世代数が通常の遺 伝的アルゴリズム(Genetic Algorithms: GAs) と比較して 少なく,個体生成を行う交叉のフェーズが探索に大きな影 響を与える.そこで本研究では,商品推薦のように嗜好が 多峰性でかつ,それぞれの峰のピーク値の差が有意に認め られない場合や,設計変数間に依存関係がある場合でも, iGAの探索が有効に働くような個体生成方法について検討 する.提案手法では,ユーザが評価した個体に対してクラ スタリングを適用し,各クラスタ内で構築した確率モデル に基づいて個体生成を行う.提案手法の有効性は,Tシャ ツを対象商品とする擬似的な商品選択システムを構築し, 被験者実験を行い検証する.