Kiyoshi Tanaka

Shinshu University | Shindai · Department of Electrical and Electronic Engineering

Achieving a high-resolution approximation and hitting the Pareto optimal set with some if not all members of the population is the goal for multi- and many-objective optimization problems, and more so in real-world applications where there is also the desire to extract knowledge about the problem from this set. The task requires not only to reach t...

Traditionally, encryption is applied to mask the semantic of a content, while data insertion adds data to a content for management purpose. In this work, a joint encryption and data insertion method is proposed. The input image is divided into 2 parts, where the first part is manipulated to mask the perceptual semantics, while the second part is pr...

Landscape analysis is of fundamental interest for improving our understanding on the behavior of evolutionary search, and for developing general-purpose automated solvers based on techniques from statistics and machine learning. In this paper, we push a step towards the development of a landscape-aware approach by proposing a set of landscape featu...

Sphere detection in point clouds is an important task in 3D computer vision with various applications such as reverse engineering, medical imaging, Terrestrial Laser Scans (TLS) alignment, and so on. So far, several approaches have been proposed to detect spheres in point clouds. However, conventional methods are inefficient and inaccurate because...

We investigate the properties of large-scale multi-objective quadratic assignment problems (mQAP) and how they impact the performance of multi-objective evolutionary algorithms. The landscape of a diversified dataset of bi-, multi-, and many-objective mQAP instances is characterized by means of previously-identified features. These features measure...

Dynamic Compartmental Models are linear models inspired by epidemiology models to study Multi- and Many-Objective Evolutionary Algorithms dynamics. So far they have been tested on small MNK-Landscapes problems with 20 variables and used as a tool for algorithm analysis, algorithm comparison, and algorithm configuration assuming that the Pareto opti...

Planes detection in unorganized point clouds is a fundamental and essential task in 3D computer vision. It is a prerequisite in a wide variety of tasks such as object recognition, registration,and reconstruction. Conventional plane detection methods are remarkably slow because they require the computation of point-wise normal vectors and are non-de...

Finding optimal traffic light timings at road intersections is a mandatory step for urban planners wishing to achieve a sustainable mobility in modern cities. Increasing congestion situations constantly require urbanists to enhance traffic fluidity, while limiting pollutant emissions and vehicle consumption to improve inhabitants’ welfare. Various...

We expose and contrast the impact of landscape characteristics on the performance of search heuristics for black-box multi-objective combinatorial optimization problems. A sound and concise summary of features characterizing the structure of an arbitrary problem instance is identified and related to the expected performance of global and local domi...

Extracting a priori knowledge informing about the landscape underlying an unknown optimization problem has been proved extremely useful for different purposes, such as designing finely-tuned algorithms and automated solving techniques. Focusing on continuous domains, substantial progress has been achieved with the development of the so-called explo...

A number of surrogate-assisted evolutionary algorithms are being developed for tackling expensive multiobjective optimization problems. On the one hand, a relatively broad range of techniques from both machine learning and multiobjective optimization can be combined for this purpose. Different taxonomies exist in order to better delimit the design...

Dynamic Compartmental Models (DCM) can be used to study the population dynamics of Multi- and Many-objective Optimization Evolutionary Algorithms (MOEAs). These models track the composition of the instantaneous population by grouping them in compartments and capture their behavior in a set of values, creating a compact representation for analysis a...

The stable conformation of a chemical structure can be searched by optimizing the spatial coordinates of the given arrangement of functional groups that determine the structure. Typically, the process seeks to optimize the geometry of a known particular arrangement. In our work, we combine a genetic algorithm with Open Babel's optimization algorith...

Dynamical compartmental models capture the population dynamics of Multi-objective Optimization Evolutionary Algorithms. In these models, solutions at each generation are classified in compartments according to Pareto dominance. The size of each model compartment is affected by the other components and changes throughout the generations. Once the dy...

The aim of this study is to examine the usefulness of a university branch office in a country to which the university sends its students as part of overseas internship programs to work in that country′s local companies. Eleven Japanese students who took part in internship programs in Malaysia were interviewed about their internship programs to obta...

Dominance, extensions of dominance, decomposition, and indicator functions are well-known approaches used to design MOEAs. Algorithms based on these approaches have mostly sought to enhance parent selection and survival selection. In addition, several variation operators have been developed for MOEAs. We focus on the classification and selection of...

Difficult Pareto set topology refers to multi-objective problems with geometries of the Pareto set such that neighboring optimal solutions in objective space differ in several or all variables in decision space. These problems can present a tough challenge for evolutionary multi-objective algorithms to find a good approximation of the optimal Paret...

This paper proposes a series of new approaches to improve Generative Adversarial Network (GAN) for conditional image synthesis and we name the proposed model as “ArtGAN”. One of the key innovation of ArtGAN is that, the gradient of the loss function w.r.t. the label (randomly assigned to each generated image) is back-propagated from the categorical...

Extensive efforts so far have been devoted to the design of effective surrogate models aiming at reducing the computational cost for solving expensive black-box continuous optimization problems. There are, however, relatively few investigations on the development of methodologies for combinatorial domains. In this work, we rely on the mathematical...

Pareto local optimal solutions (PLOS) are believed to highly influence the dynamics and the performance of multi-objective optimization algorithms, especially those based on local search and Pareto dominance. A number of studies so far have investigated their impact on the difficulty of searching the landscape underlying a problem instance. However...

The road to a better design of multi- and many-objective evolutionary algorithms requires a deeper understanding of their behavior. A step on this road has recently been taken with the proposal of compartmental models to study population dynamics. In this work, we push this step further by introducing a new set of features that we link with algorit...

Despite the extensive application of multi-objective evolutionary algorithms (MOEAs) to solve multi-objective optimization problems (MOPs), understanding their working principles is still open to research. One of the most popular and successful MOEA approaches is based on Pareto dominance and its relaxed version, Pareto ϵ-dominance. However, such a...

The working principles of the well-established multi-objective evolutionary algorithm Moea/d relies on the iterative and cooperative improvement of a number of single-objective sub-problems obtained by decomposition. Besides the definition of sub-problems, selection and replacement are, like in any evolutionary algorithm, the two core elements of M...

In multi-objective optimization, a scalable test problem is one that can be formulated for an arbitrary number of objectives. Scalable test problems evaluate the conceptual foundations of the so-called many-objective evolutionary algorithms. As an important class of problems, scalable test problems should contemplate a wide variety of features allo...

This work investigates levels of service in urban transportation coupling a multi-objective evolutionary algorithm with the multi-agent traffic simulator MATSim. The evolutionary algorithm searches combinations of the number of private/public transportation users, capacity of buses, and time interval between bus departures minimizing traffic densit...

Power generation from solar energy is one of many alternative ways to solve the current energy crisis and environmental problems affecting our world. In this study, a system that utilizes low-temperature heat (under 100 °C) from solar energy to generate electricity by a small-scale Organic Rankine Cycle system is proposed. The system is analyzed us...

3D planes detection is an important task that has numerous applications in urban environments. However, current methods do not deal appropriately with the noise and quantization artifacts of low-cost sensors. In this paper, we present the Scaled Difference of Normals, a points filter that addresses these issues and is implemented on top of the Fast...

This work applies evolutionary computation and machine learning methods to study the transportation system of Quito from a design optimization perspective. It couples an evolutionary algorithm with a microscopic transport simulator and uses the outcome of the optimization process to deepen our understanding of the problem and gain knowledge about t...

DMQ scenario data sets. (GZ)

In many practical situations the decision-maker has to pay special attention to decision space to determine the constructability of a potential solution, in addition to its optimality in objective space. Practically desirable solutions are those around preferred values in decision space and within a distance from optimality. This work investigates...

Artwork is a mode of creative expression and this paper is particularly interested in investigating if machine can learn and synthetically create artwork that are usually non- figurative and structured abstract. To this end, we propose an extension to the Generative Adversarial Network (GAN), namely as the ArtGAN to synthetically generate high qual...

Gait recognition has been considered as an unique and useful biometric for person identification at distance. However, variations in covariate factors such as view angles, clothing, and carrying condition can alter an individual’s gait pattern. These variations make the task of gait analysis much more complicated. Recognizing different subjects und...

In the view of the total energy consumption by economic sectors of Thailand, it was shown that the greatest energy consumption derived from the industrial sector, where consumed both thermal energy and electrical energy for the processes. In this study, a novel concept of Organic Rankine Cycle (ORC) power generation is proposed. The power is genera...

This work investigates levels of service in urban transportation coupling a multi-objective evolutionary algorithm with the multi-agent traffic simulator MATSim. The evolutionary algorithm searches combinations of number of private/public transportation users, capacity of buses, and time interval between bus departures minimizing traffic density, t...

This work proposes the use of simple closed state models to capture, analyze and compare the dynamics of multi- and many-objective evolutionary algorithms. Two- and three-state models representing the composition of the instantaneous population are described and learned for representatives of the major approaches to multi-objective optimization, i....

Gait classification is the problem of recognising individuals by the way in which they walk. The presence of covariate factors such as different clothing types, carrying conditions, walking surfaces, etc., can seriously complicate the task. Clothing, for instance, can occlude a significant amount of gait features and make human recognition difficul...

Recently, Convolutional Neural Networks (CNNs) have become a popular choice to tackle image classification tasks. Despite that, it is almost infeasible to embed the CNNs into resource limited hardware (e.g. mobile devices) due to its extremely high memory requirement. To address this problem, several methods were proposed to reduce the CNN memory r...

In this paper, we attempt to understand and to contrast the impact of performance of randomized search heuristics for black-box multiobjective combinatorial optimization problems. At first, we measure the performance of two conventional dominance-based approaches with unbounded archive on a benchmark of enumerable binary optimization problems with...

The proper setting of algorithm parameters is a well-known issue that gave rise to recent research investigations from the (offline) automatic algorithm configuration perspective. Besides, the characteristics of the target optimization problem is also a key aspect to elicit the behavior of a dedicated algorithm, and as often considered from a lands...

In this work, we propose a scrambling framework for block transform compressed image. First, three attacks are proposed to sketch the outline of the original image directly from its scrambled counterpart by exploiting information deduced from the transformed components. Based on the proposed sketch attacks, a scrambling framework aiming to minimize...

In evolutionary multi-objective optimization, variation operators are crucially important to produce improving solutions, hence leading the search towards the most promising regions of the solution space. In this paper, we propose to use a machine learning modeling technique, namely random forest, in order to estimate, at each iteration in the cour...

In this work, we study the effects of mutation operators combined with a varying mutation schedule applied to traffic signal optimization. An evolutionary algorithm with specialized mutation operators coupled with a microscopic traffic simulator tackles the optimization of traffic signal settings in different mobility scenarios. Experimental result...

Gait recognition is recognizing human through the style in which they walk. However, the recognition task can become complicated due to the existence of covariate factors (e.g. clothing, camera viewpoint, carrying condition, elapsed time, walking surface, etc). Amongst all the covariate factors, clothing is the most challenging one. This is because...

In this paper, we attempt to understand and to contrast the impact of problem features on the performance of randomized search heuristics for black-box multi-objective combinatorial optimization problems. At first, we measure the performance of two conventional dominance-based approaches with unbounded archive on a benchmark of enumerable binary op...

“Ceci n’est pas une pipe” French for “This is not a pipe”. This is the description painted on the first painting shows in the figure above. But to most of us, how could this painting is not a pipe, at least not to the great Belgian surrealist artist Ren ́e Magritte. He said that the painting is not a pipe, but rather an image of a pipe. In this pap...

It is generally believed that Local search (Ls) should be used as a basic tool in multi-objective evolutionary computation for combinatorial optimization. However, not much effort has been made to investigate how to efficiently use Ls in multi-objective evolutionary computation algorithms. In this paper, we study some issues in the use of cooperati...

In this study, a novel concept of Organic Rankine Cycle (ORC) power generation from industrial waste heat recovery (IWHR) combined with solar hot water system (SHWS) by using vapor compression heat pump (VCHP) as heating booster was proposed. The system is mathematically modeled and simulated to evaluate the economics and the environmental impact o...

Due to its simplicity and effectiveness in solving many optimization problems, Particle Swarm Optimization (PSO) has attracted the attention of many researchers in the last few years. Nonetheless, in more complicated problems (involving multi-modality, non-separable, etc.), the use of PSO becomes limited and sometimes impractical. In this paper, we...

Multi-objective evolutionary algorithms (MOEAs) based on decomposition are aggregation-based algorithms which transform a multi-objective optimization problem (MOP) into several single-objective subproblems. Being effective, efficient, and easy to implement, Particle Swarm Optimization (PSO) has become one of the most popular single-objective optim...

There is a significant body of research on neutrality and its effects in single-objective optimization. Particularly, the neutrality concept has been precisely defined and the neutrality between neighboring solutions efficiently exploited in local search algorithms. The extension of neutrality to multi-objective optimization is not straightforward...

In this article we work towards the desired future smart city in which IT and knowledge will hopefully provide a highly livable environment for citizens. To this end, we test a new concept based on intelligent LED panels (the Yellow Swarm) to guide drivers when moving through urban streets so as to finally get rid of traffic jams and protect the en...

Local search (LS) is at the cornerstone of many advanced heuristics for single-objective combinatorial optimization. In particular, the move strategy, allowing to iteratively explore neighboring solutions, is a key ingredient in the design of an efficient local search. Although LS has been the subject of some interesting investigations dedicated to...

In this work, we propose a novel sketch attack for H.264/AVC format-compliant encrypted video. We briefly describe the notion of sketch attack, review the conventional sketch attacks designed for DCT based compressed image, and identify their shortcomings when applied to attack compressed video. Specifically, the conventional DCT based sketch attac...

This work integrates a multi-objective evolutionary algorithm with the multi-agent transport simulator MATSim and the comprehensive modal emission model simulator CMEM to analyze the evolutionary optimization of traffic signals minimizing travel time and fuel consumption on a real-world large scenario. We simulate the movement of 20.000 vehicles on...

This work analyses the behavior and compares the performance of MOEA/D, IBEA using the binary additive \(\varepsilon \) and the hypervolume difference indicators, and A\(\varepsilon \)S\(\varepsilon \)H as representative algorithms of decomposition, indicators, and \(\varepsilon \)-dominance based approaches for many-objective optimization. We use...

This work analyses the behavior and compares the performance of MOEA/D, IBEA using the binary additive ε and the hyper-volume difference indicators, and AεSεH as representative algorithms of decomposition, indicators, and ε-dominance based approaches for many-objective optimization. We use small MNK-landscapes to trace the dynamics of the algorithm...

The multi-objective evolutionary algorithm based on decomposition (MOEA/D) is an aggregation-based algorithm which has became successful for solving multi-objective optimization problems (MOPs). So far, for the continuous domain, the most successful variants of MOEA/D are based on differential evolution (DE) operators. However, no investigations on...

Gait recognition is used to identify individuals by the way they walk. Recent research in automated human gait recognition has mainly focused on developing robust features representations and matching algorithms. To our best knowledge, feature selection is rarely addressed in gait classification problems. In this paper, we evaluate the performance...

MOEA/D is an aggregation-based evolutionary algorithm which has been proved extremely efficient and effective for solving multi-objective optimization problems. It is based on the idea of decomposing the original multi-objective problem into several single-objective subproblems by means of well-defined scalarizing functions. Those single-objective...

Computationally hard multi-objective combinatorial optimization problems are common in practice, and numerous evolutionary multi-objective optimization (EMO) algorithms have been proposed to tackle them. Our aim is to understand which (and how) problem features impact the search performance of such approaches. In this paper, we consider two prototy...

This paper proposes a novel reversible unified information hiding method for the JPEG compressed image, aiming to achieve scrambling and external data insertion simultaneously. The properties of DC coefficients, energy of AC coefficient block, and run of zero AC coefficients are exploited. Two techniques are proposed to degrade the perceptual quali...

This paper fundamentally investigates the performance of evolutionary multiobjective optimization (EMO) algorithms for computationally hard 0–1 combinatorial optimization, where a strict theoretical analysis is generally out of reach due to the high complexity of the underlying problem. Based on the examination of problem features from a multiobjec...

This work extends the concept of neutrality used in single-objective optimization to the multi-objective context and investigates its effects on the performance of multi-objective dominance-based local search methods. We discuss neutrality in single-objective optimization and fitness assignment in multi-objective algorithms to provide a general def...

In this work, a format-compliant encryption method with the data embedding feature for JPEG compressed image is proposed. First, DC coefficients are encoded based on the regions induced by the textural information carried by AC coefficients. Second, AC coefficients are scanned in eight different orders and the order that results in the smallest bit...

Feature selection is considered an important step for gait pattern recognition. The task of a gait classifier could be simplified by eliminating redundant and irrelevant attributes for classification. With that, the size of the feature set could be reduced and subsequently a more comprehensible analysis of the extracted patterns could be carried ou...

Differential evolution (DE) is a powerful and simple algorithm for single-and multi-objective optimization. However, its performance is highly dependent on the right choice of parameters. To mitigate this problem, mechanisms have been developed to automatically control the parameters during the algorithm run. These mechanisms are usually a part of...

Differential evolution (DE) is a very powerful and simple algorithm for single-and multi-objective continuous optimization prob-lems. However, its success is highly affected by the right choice of pa-rameters. Authors of successful multi-objective DE algorithms usually use parameters which do not render the algorithm invariant with re-spect to rota...