Message from the Winner

We are truly humbled and deeply honored to have been chosen as recipients of the JACIII Best Paper Awards for 2023. This recognition is not only a testament to our team’s dedication and hard work but also a reflection of the collective efforts and encouragement from the wider research community. We would like to extend our profound gratitude to the esteemed members of the JACIII Editorial Committee, the dedicated administrative staff, the meticulous reviewers, and every individual who has supported and championed this journal.
The awarded papers focus on adapting the widely-used techniques in explainable AI, Gradient-weighted Class Activation Mapping (Grad-CAM), to address regression problems. Moreover, they address significant challenges of deep learning-based gaze estimation algorithms: the black-box problem.
Through these studies, we believe we have expanded the applicability of explainable AI and contributed to the development of AI systems that humans can trust.
We anticipate that the domain of human-centered AI will continue to expand, and the fields exploring these areas will become increasingly diverse. Journals such as the JACIII, which cover a broad range of topics from foundational to applied research, will undoubtedly grow in significance for researchers like us.
We are committed to advancing research of the highest caliber and meeting the expectations of all stakeholders. We would like to express our heartfelt gratitude for these prestigious awards.

Message from the Winner

Hello fellow researchers and academics,
I would like to take this opportunity to thank the JACIII and Fuji Technology Press for publishing my paper and giving me the prestigious award of “Young Researcher Award 2023.” It is a privilege and an honor for my work to be showcased in the JACIII and to present at the associated CCS conference. Our paper, “LSTM Network Classification of Dexterous Individual Finger Movements,” was the first that was produced as part of my research into using LSTM networks to classify sEMG signals. Typically, this type of network has been applied to natural language processing or other sequential data sequences, but we have applied it to bio-signal classification. This was the first step toward achieving our goal of developing a system that can classify complex hand gestures and other grasping movements for potential application with anthropomorphic robotic hands.
Furthermore, I would like to thank the team of editors that provided me with crucial feedback throughout the submission process and helped me to refine my submission. I would also like thank everyone who read my paper and found it helpful or of some interest. Finally, I wish to thank my family for supporting me throughout this process and my supervisors for helping me write a paper worthy of such an award.

Message from the Winner

I am immensely proud to have received the JACIII Young Researcher Award 2023. I would like to express my gratitude to the JACIII editorial board, award committee members, and co-authors.
Our paper, entitled “Automatic Neonatal Alertness State Classification Based on Facial Expression Recognition,” proposes a video image analysis and machine learning classification system, based sleep-wake states, for neonates in neonatal intensive care unit.
Based on Brazelton’s alertness definitions, the proposed method uses machine learning to categorize sleep-wake states into four or six classes. Since the input data are the video images of neonates, the proposed method extracts the histogram of oriented gradients (HoG) or the gradient feature from each slice, and these are then merged in an average merge or a standard deviation merge. The experimental results show that the weighted support vector machine classifier using the HoG feature and average merging achieves the highest classification performance.
We are currently working on developing a hybrid model that combines facial expression and body motion for the alertness state classification. Lastly, I am considering continuing our collaborative research in the medical engineering field in the future.

Message from the Winner

It is our great honor to be selected for the JACIII’s Best Paper Award 2022, and we would like to express our sincere appreciation to the JACIII editorial board and office members, the reviewers, and all the supporters of this journal. Our paper, “Three-Mode Fuzzy Co-Clustering Based on Probabilistic Concept and Comparison with FCM-Type Algorithms,” was first motivated by our desire to utilize three-mode co-occurrence information in collaborative recommendations, such that personalized food recommendations can be realized by considering not only user-food preference tendencies but also intrinsic user-ingredient preferences. In the proposed method, fuzzy partitioning is achieved by introducing a probabilistic concept into a fuzzy c-means type of clustering, and the degree of partition fuzziness can be tuned through comparison with the fuzziness degree of probabilistic models. The proposed method is therefore supported by the advantages of both fuzzy set theory and probability theory, and it is expected to develop a new direction in fuzzy-probability hybridization.
Finally, we would like to once again express our sincere gratitude to all those involved in the JACIII journal, and we hope that it will continue to publish papers that pioneer new fields of computational intelligence and intelligent informatics.

Message from the Winner

Thank you to the JACIII editorial board for giving me the award. I am honored to receive it. This paper is thanks to the guidance of my teacher, Professor Hirota.
This paper, “Path Planning Based on Improved Hybrid A* Algorithm,” is a study of the Hybrid A* algorithm. In this paper, the artificial potential field (APF) concept is applied in order to optimize the paths generated by the Hybrid A* algorithm. The generated path not only satisfies the non-holonomic constraints of the vehicle but is also smooth, and it keeps a comfortable distance from the obstacle at the same time.
Once again, I would like to thank everyone who contributed to this paper and made it possible for me to receive this award. I hope the JACIII journal has more and more excellent papers in the future.

Message from the Winner

I am truly honored to have been selected for the prestigious JACIII Young Researcher Award 2022. I sincerely appreciate the co-authors, the editorial office of JACIII, the reviewers, and the laboratory members.
It has been almost three years since 2019 when we worked on this paper related to recommendation algorithms. Companies such as YouTube, Amazon, and Netflix, which are also the background of our research, have increased in scale since that time, and content on the Internet continues to grow at a phenomenal pace.
In this context, the influence of recommendation algorithms is significant, and expectations for their performance improvement seem to be escalating day by day.
This research is to create recommendation data using a generative system that is based on graph convolution. Generative systems have already achieved remarkable success in pictures and photographs, and I believe their application fields will further expand.
We can also expect further developments in the field of recommendation systems. I am confident that our paper in the JACIII will contribute to the future development of this field.
Once again, it is a great pleasure for me to receive this prestigious award for our research, and I would like to express my deepest gratitude.
I believe this award and commendation will be a great encouragement to all students and researchers who are working on the recommendation algorithm.
I also wish for the development of the JACIII and the field of computational intelligence and intelligent informatics.

Message from the Winner

I am very honored to receive the JACIII Best Paper Award 2021. I would like to express my sincere gratitude to the editorial board, reviewers, and everyone else who supported this study.
This paper, “Self-Structured Cortical Learning Algorithm by Dynamically Adjusting Columns and Cells,” is a study of the cortical learning algorithm (CLA). CLA is a time-series data prediction algorithm based on the human neocortex, the most important part of human intelligence. In this paper, we propose a method of dynamically increasing or decreasing self-structures, which are called columns and cells and which correspond to human neurons, to adjust them depending on the input data. The proposed method eliminates the need for column and cell parameters, which were previously determined statically. Furthermore, the experimental results on a multistep prediction of real-world power consumption show that the proposed self-structured CLA achieves high prediction accuracy.
Once again, I would like to express my gratitude to everyone involved in publishing this paper and making it possible for me to receive this award. I wish for the future development of scientific research in the field of computational intelligence and intelligent informatics.

Message from the Winner

It is a great honor for me to receive the JACIII Young Researcher Award 2021. This award is the best form of praise for our work and will provide strong stimulation for our passion for research. We are deeply grateful to the JACIII editorial board/office, which made our paper easy to understand and gave it a beautiful layout. We are also grateful to the reviewers, who provided insightful comments that gave our paper more meaning and research value. Next, I wish to give my deepest thanks to my co-authors for their considerable contributions to emotion recognition based on multi-composition deep forest and transferred convolutional neural network. Our many discussions resulted in numerous rewrites, not to mention memories I will cherish forever.
We propose a novel emotion-recognition framework that uses a knowledge-transfer approach to capturing features, employing an improved, deep-forest model to determine the final emotions. The structure of a very deep, convolutional network is learned from ImageNet and is utilized to extract face and emotion features from other data sets, thereby solving the problem of insufficiently labeled samples. These features are then input into a classifier, “multi-composition deep forest,” which consists of 16 forests for facial emotion recognition, to enhance the diversity of the framework. The proposed method does not require that a network be trained with a complex structure, and the decision-tree-based classifier can achieve accurate results with very few parameters, making it easier to implement, train, and apply. Moreover, the classifier can adaptively decide the complexity of its model without iteratively updating parameters.
This truly interesting work is an indication of a new direction in facial emotion recognition. I hope that this paper promotes the development of both transfer learning and deep forest as well as related research, so that facial emotion recognition may find additional applications. The JACIII, the most popular journal of computational intelligence and intelligent informatics, is a powerful platform for sharing ideas and work, and I look forward to its continued improvement and success going forward.

Message from the Winner

I am very honored to receive the JACIII Young Researcher Award 2021. I am deeply grateful to the JACIII editorial office, reviewers, co-authors, and all supporters of this paper, “Object-Oriented 3D Semantic Mapping Based on Instance Segmentation.” This award is highly encouraging to my further study. My research interests include Visual SLAM and Robot Semantic Understanding. This paper proposes an object-oriented, 3D semantic mapping method that combines state-of-the-art, deep-learning-based Instance Segmentation and a Visual SLAM algorithm. The method helps robots not only gain navigation-oriented geometric information about the surrounding environment but also obtain individually-oriented attribute and location information about the objects. An object recognition and target association algorithm applied to continuous image frames is also proposed. The algorithm combines visual SLAM, which uses visual consistency between image frames to promote the results of object matching and recognition over continuous image frames, to improve the accuracy of object recognition. I hope that this study will contribute to the development of both Semantic Robot and Visual SLAM, and that Semantic Visual SLAM will be promoted and widely used in the future. I also wish for the development of the JACIII and the field of computational intelligence and intelligent informatics. Thank you.

Message from the Winner

It is our honor to receive the JACIII’s Best Paper Award 2020, and we would sincerely like to thank the JACIII editorial office, reviewers, and all who supported this study. The work that received this honor was the “Crystalizing Effect of Simulated Annealing on Boltzmann Machine.” In this work, a method of obtaining an accurate estimate of the posterior distribution of a stacked Boltzmann machine (deep Boltzmann machine) is studied. It applies to simulated annealing the same analogy of the oating zone method that was employed to generate silicon crystals in material science and engineering. Additionally, we investigated the reason behind its capacity for high accuracy, concluding that it comes from the restricting effect of information flow of simulated annealing with non-uniform temperature distribution. Again, we would like to express our appreciation to the JACIII for giving us a chance to publish this work. We hope the results contained in the paper will encourage future scientic work. We will continue to carry out investigations based on these results, further contributing to humanity.

Message from the Winner

I am honored to receive the JACIII Young Researcher Award 2020 and grateful to the JACIII editorial board/office, reviewers, and co-authors of our paper. In this paper, I present a method of classifying swimming styles that is based on Random Forest and Out-of-Bag features selection and uses a single inertial sensor attached to a swimmer. I also develop a support system for swimmers. I hope that our system helps many swimmers to improve their performance. If the paper interests you, please read it. Beside this, I am interested in using adaptive data analysis methods, including machine learning and artificial intelligence, on various kinds of data, such as signals, images, and natural languages.
I have been an Assistant Professor in the Department of Industrial Engineering and Management, College of Industrial Technology, Nihon University, Japan since April 2019. Because there are many students interested in soft computing at this institute, I teach them various soft computing methods. I hope that my activities and research help to make for a better society. I also hope for the continued development of soft computing.

Message from the Winner

We are very honored to receive the JACIII’s Best Paper Award 2019. We would like to thank the award committee for this great honor. We have proposed a user modeling method based on personal values. The method is called Rating Matching Rate (RMRate), which was reported in our previous publication on the JACIII. Using RMRate, personal values are modeled as the effect of an item’s attributes on a user’s rating. Assuming that the personal values strongly affect our evaluation of unpopular items, this paper examines its effectiveness for long tail item recommendation. The proposed long tail item recommendation consists of RMRate, user-based collaborative filtering, and a strategy for selecting long tail items. The experimental results show incorporating personal values enables the recommendation of long tail items while maintaining recommendation accuracy. As introducing personal values into recommender systems is a relatively new idea, we decided to submit our papers related to RMRate to the JACIII, which encourages the submission of reports on pioneering studies. We would like to submit our papers to the JACIII to report on subsequent studies in the future.

Message from the Winner

I am very honored to receive this prestigious award, the “JACIII Young Researcher Award 2019.” I am deeply grateful to the JACIII editorial board/office, reviewers, co-authors, and all supporters of this paper, “Characteristics of Rough Set C-Means Clustering.” This award is highly encouraging to my further study. My research interests include cluster analysis (clustering) and soft computing, especially rough set theory. This paper introduces the perspective of rough set theory to hard C-means (HCM; k-means) clustering to deal with uncertainty. The proposed method, rough set C-means (RSCM), is a clustering model based on the object space granulated by a binary relation. RSCM uses the rough set to approximate each temporal cluster and considers whether it is positive, possible, or uncertain that an object belongs to each cluster. While fuzzy clustering has been well studied and widely used, rough set-based clustering has not been well studied, leaving room for further investigation. Since cluster structures in the real-world dataset are not always clear, the handling of uncertainty based on rough sets is a very important and interesting subject. I hope that this study will contribute to the development of both clustering and rough set theory, and that rough set-based clustering will be promoted and widely used in the future. I also wish for the development of JACIII and the field of computational intelligence and intelligent informatics. Thank you.

Message from the Winner

I would like to thank the award committee of the JACIII of Fuji Technology Press for granting me this award. It is a great honor and an affirmation of my current academic level.

I am now a Ph.D. candidate at the Beijing Institute of Technology, China. When my supervisor, Professor Yaping Dai, notified me by email that my paper had been selected to win the JACIII Best Review Paper Award, I was amazed and excited. As this is my first time to win a best paper award issued by a famous international journal, I would also like to share my happiness with my labmates, friends, and family members.

This paper was written with the help of Professors Yaping Dai and Kaoru Hirota. I would like to thank them for enhancing the quality of the paper, modifying the English in it, and providing meaningful academic advice in general. The main purpose of this paper was to survey recent prominent works on crowd counting and anomaly detection based on the analysis of pedestrians. These two tasks are significant research areas that have been gathering attention in the fields of intelligent surveillance systems and public security. In fact, by the end of 2019, top computer vision conferences such as CVPR and ICCV will have published more than 20 papers on crowd counting alone. I hope that this paper can provide some meaningful basic knowledge to those who are interested and would like to learn more about crowd counting and anomaly detection.

I continue to do research on the task of crowd counting and have already finished some additional works. I would very much appreciate the opportunity to discuss related issues with experts in this field and to collaborate, if possible.