检索结果-内蒙古大学图书馆

Joint Workshop of the 9th Financial technology and Natural Language Processing, FinNLP 2025, the 6th Financial Narrative Processing, FNP 2025, and the 1st Workshop on Large Language Models for Finance and Legal, LLMFinLegal 2025, co-located with the 31st International Conference on Computational Linguistics, COLING 2025

作者： Nishida, Shunsuke Utsuro, Takehito Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan

ISBN: (纸本)9798891762091

In this paper, we study the task of generating financial news articles related to stock price fluctuations. Traditionally, reporters manually write these articles by identifying the causes behind significant stock price volatility. However, this process is time-consuming, limiting the number of articles produced. To address this, the study explores the use of generative AI to automatically generate such articles. The AI system, similar to human reporters, would analyze stock price volatility and determine the underlying factors contributing to these fluctuations. To support this approach, we introduces a Japanese dataset called JFinSR, which includes stock price fluctuation rankings from "Kabutan" and related financial information regarding factors of stock price rise / decline from "Nihon Keizai Shimbun (Nikkei)." Using this dataset, we implement the few-shot learning technique on large language models (LLMs) to enable automatic generation of high-quality articles from factors of stock price rise / decline that are available in Nikkei. In the evaluation, we compare zero-shot and few-shot learning approaches, where the few-shot learning achieved the higher F1 scores in terms of ROUGE-1/ROUGE-L metrics. © 2025 Association for Computational Linguistics.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A deep learning framework for automatic assessment of presence in virtual reality using multimodal behavioral cues

引用

Neural Computing and Applications 2025年第8期37卷 6283-6303页

作者： Pannattee, Peerawat Shimada, Shogo Yem, Vibol Nishiuchi, Nobuyuki Graduate School of Systems Design Tokyo Metropolitan University Tokyo191-0065 Japan Graduate School of Science and Technology Degree Program in Systems and Information Engineering University of Tsukuba Ibaraki3058573 Japan

Effective development of virtual reality (VR) applications is heavily reliant on the evaluation of user experience (UX). However, traditional methods such as questionnaires have inherent limitations which hinder their ability to capture nuanced behavioral responses and impede the agility of VR content creation: They are time-consuming, burdensome for users, and require significant human effort for interpretation. This study introduces an automated framework aimed at addressing the limitations of questionnaire-based evaluations to assess UX in VR. Our primary focus is to validate the concept of this framework through assessment of the sense of presence (SOP), a crucial psychological perception with significant impact on VR UX. Our proposed framework utilizes a deep neural network (DNN) to analyze patterns in multimodal behavioral cues, including facial expressions, head movements, and hand movements, to predict scores from the Igroup Presence Questionnaire (IPQ). Additionally, we introduce two statistical profiles: the Visual Entropy Profile (VEP), which offers insights into visual complexity by depicting scene entropy, and the Experiential Presence Profile (EPP), which is designed to capture users’ historical SOP levels to enable personalized baseline and sensitivity estimation. The proposed framework achieves a significant correlation between actual and predicted IPQ scores, with a Spearman’s rank correlation coefficient of 0.7303, showcasing the potential of DNNs in analyzing complex behavioral signals and automating SOP assessment. This study represents a pioneering effort in leveraging DNNs for the automatic assessment of SOP and paves the way for future advances in automatically assessing VR UX and unlocking new opportunities in the field. © The Author(s) 2025.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

A Design Study on Integrated Complex Coefficient Filters with Peripheral Circuits for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, information and systems 2025年第1期145卷 16-24页

作者： Shouno, Kazuhiro Sato, Lina Fukagawa, Kanta Tanimoto, Hiroshi Muto, Cosy Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan

This paper proposes a measurement technique for an integrated complex filter. The proposed method is based on two measurement methods with integrated circuitry for calibration. It is accomplished by applying square waves to an FUT (Filter Under Test) instead of sinusoidal waves or by superposing transfer characteristics obtained by applying a single sinusoidal wave to an FUT. In both of the above methods, the output signal connected to the external measurement equipment via a 50 Ω coaxial cable and so on. In this case, the output signal of the FUT should be amplified by internal or external amplifiers, which degrades the response. However, it is cancelled out by the proposed calibration circuitry with some analog switches. In addition to the above, for the RC polyphase filter, the source resistance and the load capacitance degrade the measurement results and their effect is discussed. The validity of the proposal is confirmed through computer simulation for a third-order RCPF whose passband is 8–40 MHz fabricated by Phenitec 0.6 µm CMOS process. It is shown that the measurement error is −1.10 dB for the square-wave method and −1.00 dB and −0.43 degrees for the superposition method at 40 MHz. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

Assessment methodology for the resilience of energy systems in positive energy buildings

引用

e-Prime - Advances in Electrical engineering, Electronics and Energy 2025年 11卷

作者： Jimba, Chiho Akimoto, Yutaro Okajima, Keiichi University of Tsukuba Degree Programs in Systems and Information Engineering Graduate School of Science and Technology Japan

Distributed renewable energy systems are emerging in communities and buildings in response to global warming. Concurrently, the frequency of large-scale power outages, which are often triggered by natural disasters and heavy rainfall, has increased. This trend highlights the necessity to develop robust energy systems that integrate distributed renewable energy with other sources. Economic and resilience assessments of photovoltaic (PV) and battery systems within infrastructure contexts have been extensively studied. However, resilience evaluation at the building level is necessary. Given that energy resilience encompasses various assessment aspects, the importance of employing multiple indicators for a comprehensive quantitative evaluation of resilience in PV and battery installations is increasing. This study introduced a methodology to quantitatively assess the resilience of energy systems. It employs multiple resilience indicators and simulates a power outage scenario in a positive energy building (PEB) equipped with PV and batteries. Additionally, this study analyzed the impact of different weather conditions on resilience. An assessment using multiple resilience indicators reveals that energy systems are more resilient on favorable weather days and that resilience is maximized when supply interruptions coincide with daylight hours. Furthermore, while no single indicator can measure resilience, this study shows that the use of multiple indicators enables the clarification and comparison of electricity supply and demand conditions during a disaster. © 2025 The Author(s)

关键词： Battery Energy evaluation Power outage PV Renewable energy

来源：评论

学校读者我要写书评

暂无评论

Implementation and Evaluation of 0.6 µm CMOS Complex RCPF for Accurate Frequency Response Measurement

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, information and systems 2025年第1期145卷 25-37页

作者： Sato, Lina Fukagawa, Kanta Shouno, Kazuhiro Tanimoto, Hiroshi Muto, Cosy Moriyama, Seijiro Takahashi, Chikau Yoshino, Michitaka Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan Anagix Corporation 3-22-27 Numama Kanagawa Zushi249-0004 Japan Takamori Corporation Japan Research Center for Micro-Nano Technology Hosei University 3-11-15 Midori-cho Koganei Tokyo184-0003 Japan

This paper describes the implementation and evaluation of an RC polyphase filter (RCPF) and circuitry for measuring its frequency characteristics. The integrated circuit is fabricated on a 0.6 µm CMOS process and its supply voltage is 5 V. The integrated circuit includes a filter under test (FUT), a four-phase square wave generator, several analog switches and differential amplifiers to amplify the high-impedance signals of the RCPF. This FUT is a third-order complex RCPF whose passband is 8 − 40 MHz. This paper describes the design of these circuits in detail. This integrated circuit can select two measurement methods by means of external control signals. The first method uses a four-phase square wave. The frequency characteristics are measured by using an on-chip four-phase square wave generator driven by an external clock generator and by a spectrum analyzer tuned to the fundamental frequency. The second method uses an external network analyzer. Furthermore, this integrated circuit is equipped with a calibration circuit to measure the frequency characteristics of the circuitry except FUT by passing through the input / output signals of the FUT. As a result, the frequency characteristics of the FUT itself can be accurately measured. The effectiveness is confirmed through evaluation of the fabricated integrated circuit. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Differential amplifiers

来源：评论

学校读者我要写书评

暂无评论

A Method of Detecting Port Bay Numbers and Optimizing Effects Under Various Weather Scenarios

A Method of Detecting Port Bay Numbers and Optimizing Effect...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Jiazheng Li Lei Ao Kai Sheng Yoshiki Yamaguchi Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan Key Laboratory of Collaborative Intelligence Systems Ministry of Education School of Electronic Engineering Xidian University Xi'an Shaanxi China Academy of Advanced Interdisciplinary Research Xidian University Xi'an Shaanxi China Institute of Systems and Information Engineering University of Tsukuba Japan

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Ports are transportation hubs located along coasts, rivers, lakes, and reservoirs, with water and land transport facilities that allow ships to enter, exit, and berth safely. The port bay numbers are located on the land side of the port and are rectangular frames of specific sizes designated by port management, containing unique codes. These codes identify where containers are stacked under various weather conditions. Therefore, the ability to quickly and accurately recognize bay numbers in all weather conditions has become a significant issue affecting work efficiency, especially in rainy ports. However, collecting images of bay numbers during rainy days is not permitted due to safety restrictions. In this article, we first generate images of rainy scenes based on images collected in sunny weather. We then compare two detection algorithms and select the one with a smaller decrease in detection metrics but fewer model parameters. Finally, we incorporate an attention mechanism into the chosen algorithm to optimize and enhance target detection performance across various weather scenarios.

关键词： YOLO Measurement Codes Attention mechanisms Seaports Reservoirs Safety Rivers Marine vehicles Meteorology

来源：评论

学校读者我要写书评

暂无评论

Embedded Topic Models Enhanced by Wikification 1

Embedded Topic Models Enhanced by Wikification

引用

1st Workshop on Advancing Natural Language Processing for Wikipedia, WikiNLP 2024

作者： Shibuya, Takashi Utsuro, Takehito Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan

ISBN: (纸本)9798891761889

Topic modeling analyzes a collection of documents to learn meaningful patterns of words. However, previous topic models consider only the spelling of words and do not take into consideration the homography of words. In this study, we incorporate the Wikipedia knowledge into a neural topic model to make it aware of named entities. We evaluate our method on two datasets, 1) news articles of New York Times and 2) the AIDA-CoNLL dataset. Our experiments show that our method improves the performance of neural topic models in generalizability. Moreover, we analyze frequent terms in each topic and the temporal dependencies between topics to demonstrate that our entity-aware topic models can capture the time-series development of topics well. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Unified Framework to Construct Fast Row-Action-Type Iterative CT Reconstruction Methods with Total Variation Using Multi Proximal Splitting 21

Unified Framework to Construct Fast Row-Action-Type Iterativ...

引用

6th International Conference on Biomedical Signal and Image Processing, ICBIP 2021

作者： Kim, Heejeong Sadakata, Kazuya Kudo, Hiroyuki Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Japan

ISBN: (纸本)9781450390507

Recently, to realize low-dose scan in CT imaging, a number of iterative reconstruction methods with Total Variation (TV) regularization have been investigated. In particular, reconstruction methods based on proximal splitting framework have been actively researched thanks to the following two reasons. First, they allow to use the TV regularization term, which is known to be a non-differentiable function that cannot be handled with classical optimization methods. Second, using the proximal splitting leads to a new class of iterative reconstruction methods which cannot be found in the literature. The major drawback of existing research in this direction is that most of them use the proximal splitting which divides the cost function into a sum of only two terms like famous Chambolle-Pock algorithm and FISTA. In this paper, we propose a unified framework to construct a class of row-action-type iterative methods which converge very fast using frameworks of multi proximal splitting which divides the cost function into a sum of arbitrary number of sub-cost functions (more than two). The use of multi proximal splitting naturally allows us to construct row-action-type iterative methods converging to an exact minimizer of the cost function very quickly. In mathematical literature, there exist only three different frameworks of multi proximal splitting, which are the Passty splitting, Dykstra-like splitting, and modified Dykstra-like splitting. We develop three new iterative methods, i.e. the Passty iterative method, Dykstra-like iterative method, and modified Dykstra-like iterative method, by using these frameworks, for the case where the cost function is a sum of the standard least-squares data fidelity and the TV regularization term. We have compared the proposed three iterative methods with an empirical standard method using ordered-subset technique called OS-SIRT-TV method. The results demonstrate that the performances of proposed methods significantly outperform OS-SIRT

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

CNN Model Compression by Merit-Based Distillation 19

CNN Model Compression by Merit-Based Distillation

引用

19th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2023

作者： Morikawa, Takumi Kameyama, Keisuke University of Tsukuba Degree Programs in Systems and Information Engineering Graduate School of Science and Technology Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Tsukuba Japan

ISBN: (纸本)9781665476928

Deep learning has advanced dramatically in recent years, and especially large convolutional neural networks (CNNs) have shown outstanding performance in a wide variety of tasks. However, such large-scale CNNs may not be able to be utilized in practice because they require a lot of computational resources. Therefore, there is a need to realize a CNN in a small model that has high performance similar to the large CNN. One method to solve these problems is Distillation, which uses a model of large scale and high performance as the teacher and a small model as the student model, and performs model compression by transferring the knowledge of the teacher model to the student model. However, in distillation, even when the teacher model incorrectly guesses the training input, the student model learns to mimic the teacher. This can prevent the student model from learning better. In this paper, we propose Meritbased Distillation, in which the accuracy of the teacher model's output determines the degree to which the student model mimics the teacher model's output, thereby preventing the student to learn undesired mappings. In the experiment, the effect of the Merit-based Distillation is evaluated. Consequently, the proposed method outperforms the improvements in the generalization by the student models trained by other known methods. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Curriculums Generated by Classifier Ensembles 19

Machine Learning Curriculums Generated by Classifier Ensembl...

引用

19th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2023

作者： Huang, Tzu-Jui Kameyama, Keisuke University of Tsukuba Degree Programs in Systems and Information Engineering Graduate School of Science and Technology Tsukuba Japan University of Tsukuba Faculty of Engineering Information and Systems Tsukuba Japan

ISBN: (纸本)9781665476928

Image classification is a fundamental task that attempts to classify the images into the classes they belong to. CNN is commonly used for the classification due to its flexibility and stability. This paper treats Curriculum Learning as an assistant method that decides the procedure the CNN ought to be trained. Curriculum Learning is generally defined as a method that divides and orders the training datasets into several different levels of learning difficulties. This paper utilizes the idea of ensemble classification that trains according to the order based on the consensus of different machine learning models. As a result, the proposed Ensemble-Generated Curriculum Learning model achieves higher accuracy compared to that of a single-stage CNN learning with dog face recognition and CIFAR-10 datasets. © 2023 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：