检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1362-1372页

作者： Ralekar, Chetan Choudhary, Shubham Gandhi, Tapan Kumar Chaudhury, Santanu Department of Brain and Cognitive Sciences Massachusetts Institute of Technology CambridgeMA02139 United States Harvard John A. Paulson School of Engineering and Applied Sciences CambridgeMA02138 United States Department of Electrical Engineering Indian Institute of Technology New Delhi110016 India Department of Computer Science and Engineering Indian Institute of Technology Jodhpur342030 India

Deep neural networks (DNNs) currently constitute the best-performing artificial vision systems. However, humans are still better at recognizing many characters, especially distorted, ornamental, or calligraphic characters compared with the highly sophisticated recognitionmodels. Understanding themechanism of character recognition by humans may give some cues for building better recognition models. However, the appropriate methodological approach to using these cues has not been much explored for developing character recognition models. Therefore, this paper tries to understand the process of character recognition by humans and DNNs by generating visual explanations for their respective decisions. We have used eye tracking to assay the spatial distribution of information hotspots for humans via fixation maps. We have proposed a gradient-based method for visualizing the reasoning behind the model's decision through visualization maps and have proved that our method is better than the other class activation mapping methods. Qualitative comparison between visualization maps and fixation maps reveals that both model and humans focus on similar regions in character in the case of correctly classified characters. However, when the focused regions are different for humans and model, the characters are typically misclassified by the latter. Hence, we propose to use the fixation maps as a supervisory input to train the model that ultimately results in improved recognition performance and better generalization. As the proposedmodel gives some insights about the reasoning behind its decision, it can find applications in fields, such as surveillance and medical applications, where explainability helps to determine system fidelity. Impact Statement-Humans and DNNs rely on selective information uptake while classifying a character. This information selection strategy can be understood by visualizing the important, informative character regions that ultimately govern the decision o

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Hardware Accelerator of Morphological Image Processor 3

Reconfigurable Hardware Accelerator of Morphological Image P...

引用

3rd IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2023

作者： Lin, Ming-Yi Hsieh, Sheng-Hsien Chen, Ching-Han Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan Bachelor's Program in Artificial Intelligence and Mechatronics National Pingtung University of Science and Technology Pingtung Taiwan

ISBN: (纸本)9798350333862

Researchers emphasize the importance of hardware accelerators for mathematical morphology. If there are any issues, the hardware architecture may need to be redesigned. Thus, we propose a novel, reconfigurable hardware architecture with pipeline techniques for acceleration. With the order control register, there is no need to modify the architecture even if different results are expected. Furthermore, the hardware architecture caters to specific purposes instead of requiring a purpose-built hardware design. © 2023 IEEE.

关键词： Reconfigurable hardware

来源：评论

学校读者我要写书评

暂无评论

Indoor Positioning System Classification with Wi-Fi Signal Data: A Machine Learning Approach

Indoor Positioning System Classification with Wi-Fi Signal D...

引用

International Conference on Knowledge and Smart Technology (KST)

作者： Ivan Alexander Gede Putra Kusuma Yaya Heryadi Widodo Budiharto Computer Science Departement Binus Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Departement School of Computer Science - Computer Science Department Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331520403

ISBN: (纸本)9798331520410

Indoor positioning systems (IPS) are critical for enabling accurate navigation, asset tracking, and emergency response in indoor environments where GPS fails. This study evaluates five machine learning algorithms-K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Decision Tree, and Random Forest-using two benchmark datasets, UJIIndoorLoc and UTSIndoorLoc. The results reveal that SVM achieves the highest accuracy, with 81.3 % on UJIIndoorLoc and 92 % on UTSIndoorLoc, followed by MLP with $\mathbf{7 8. 8 \%}$ and 90.9 %, respectively. Random Forest provides stable performance, with 77.6 % and 86.08 %, while KNN reaches 75 % and 89.7 %, performing well in structured environments. Decision Tree shows the lowest accuracy, 71.2 % and 76.54 %, highlighting its limitations with complex data. The UTSIndoorLoc dataset consistently yields higher accuracies, demonstrating its structured signal distribution. These findings underscore SVM and MLP as optimal algorithms for Wi-Fi fingerprinting IPS, offering robust and scalable solutions for indoor localization.

关键词： Support vector machines Accuracy Machine learning algorithms Nearest neighbor methods Fingerprint recognition Decision trees IP networks Random forests Wireless fidelity Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

CREAI 2023 - Preface to the Second Workshop on Artificial Intelligence and Creativity 2

CREAI 2023 - Preface to the Second Workshop on Artificial In...

引用

2nd Workshop on Artificial Intelligence and Creativity, CREAI 2023

作者： De Filippo, Allegra Milano, Michela Presutti, Valentina Saffiotti, Alessandro Department of Computer Science and Engineering University of Bologna Italy Department of Modern Languages Literature and Cultures University of Bologna Italy AASS Cognitive Robotic Systems Laboratory Örebro University Sweden

In recent years, Artificial Intelligence (AI) has gained increasing popularity in the area of art creation, by demonstrating its great potential. Research in this topic has developed AI systems able to generate creative outputs in fields such as music, painting, games, design and scientific discovery, either autonomously or in collaboration with humans. Therefore, AI also helped to analyze and study the mechanisms of creativity from a broader perspective: from the socio-anthropological to psychological, as well as cognitive impact of the autonomous creative processes of artificial intelligence. These advances are leading to new opportunities research perspectives, while also posing challenging questions related to authorship, integrity, bias and evaluation of AI artistic outputs. CREAI, the workshop on AI and creativity, tries to address these research lines and aims to provide a forum for the AI community to discuss problems, challenges and innovative approaches in the various sub-fields of AI and creativity. © 2023 CEUR-WS. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Chain of Custody for Digital Evidence with Hyperledger Fabric 39

Blockchain-Based Chain of Custody for Digital Evidence with ...

引用

39th International Conference on Information Networking, ICOIN 2025

作者： Loffi, Leandro Camillo, Gerson Luiz Westphall, Carla Merkle Westphall, Carlos Becker Department of Post-Graduate Program in Computer Science SC PO Box 476 Florianópolis88040-970 Brazil

ISBN: (纸本)9798331506940

The increasing presence of digital evidence in legal, criminal, and civil cases requires adaptations to traditional chain-of-custody processes to ensure the integrity of this evidence. This work proposes the use of blockchain technology, specifically through Hyperledger Fabric, to strengthen the chain of custody for digital evidence. The developed solution employs smart contracts to immutably record each stage of evidence handling, from collection to transfer of custody, ensuring data authenticity, integrity, and traceability. Our implementation demonstrates that blockchain technology can significantly reduce the risk of evidence tampering, improve process efficiency, and facilitate audits, thereby contributing to greater reliability in the presentation of evidence during judicial proceedings. © 2025 IEEE.

关键词： Blockchain Chain of Custody Digital Evidence Hyperledger Fabric

来源：评论

学校读者我要写书评

暂无评论

Boost DC-DC Converter with Non-dissipative Snubber

引用

IEEJ Transactions on Electrical and Electronic Engineering 2024年第11期19卷 1858-1878页

作者： Yau, Yeu-Torng Department of Ph.D. Program Prospective Technology of Electrical Engineering and Computer Science National Chin-Yi University of Technology Taichung No.57 Sec. 2 Zhongshan Rd. Taiping Dist Taichung41170 Taiwan

To provide a hold-up time function in DC-DC supplies for cell site stations or data centers, using a boost converter with a bulk output capacitor as a front-end converter stage is a simple and highly cost-effective solution. However, conventional boost converters with a hard-switching operation result in low conversion efficiency and increased electromagnetic interference emissions. In this paper, a boost converter with a new non-dissipative snubber is proposed that only requires two additional diodes, an inductor, and a multilayer ceramic capacitor. The main feature of the proposed snubber is that the components are not located on the main power processing path. This means they only require low ratings, improving cost-effectiveness. A prototype converter is analyzed, realized, and applied to a 300 W redundant DC-DC power supply module for a 5G cell base station. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. © 2024 The Author(s). IEEJ Transactions on Electrical and Electronic Engineering published by Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

关键词： Boost converter

来源：评论

学校读者我要写书评

暂无评论

A Predictive Model for Student Academic Performance in Online Learning System 1

A Predictive Model for Student Academic Performance in Onlin...

引用

1st International Conference on Digital Government Technology and Innovation, DGTi-Con 2022

作者： Prasertisirikul, Pariyanuch Laohakiat, Sirisup Trakunphutthirak, Ruangsak Sukaphat, Sasivimon Program Bangkok Thailand Srinakharinwirot University Department of Computer Science Bangkok Thailand

ISBN: (数字)9781665495554

ISBN: (纸本)9786168001226

As COVID-19 has brought a major disruption in educational system, online learning has replaced the traditional classroom learning during the pandemic in many parts of the world. One of the inferior point of online learning is that it has less interaction between the instructors and the learners. Therefore, closed and active monitoring of the student's academic activities is especially required in this mode of learning. The predictive model becomes one of the main tool for active monitoring that allows the instructors to forecast the final performance of the students to determine appropriate guidance or attention for each student. In this study, predictive models based on machine learning models for student performance are proposed using the log files that record student activities in online learning system. Different sets of features are used to determine the most suitable machine learning model. Several preprocessing methods are employed to improve the performance prediction including handling imbalanced data with Synthetic Minority Over-sampling Technique (SMOTE) and choosing relevant features by XGBoost model. The model with the highest performance yields the prediction accuracy as high as 83.95%. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

FinGAT: Financial Graph Attention Networks for Recommending Top-K Profitable Stocks

引用

IEEE Transactions on Knowledge and Data Engineering 2023年第1期35卷 469-481页

作者： Hsu, Yi-Ling Tsai, Yu-Che Li, Cheng-Te National Taiwan University Master Program in Statistics Taipei10617 Taiwan National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan National Cheng Kung University Institute of Data Science Tainan701 Taiwan

Financial technology (FinTech) has drawn much attention among investors and companies. While conventional stock analysis in FinTech targets at predicting stock prices, less effort is made for profitable stock recommendation. Besides, in existing approaches on modeling time series of stock prices, the relationships among stocks and sectors (i.e., categories of stocks) are either neglected or pre-defined. Ignoring stock relationships will miss the information shared between stocks while using pre-defined relationships cannot depict the latent interactions or influence of stock prices between stocks. In this work, we aim at recommending the top-K profitable stocks in terms of return ratio using time series of stock prices and sector information. We propose a novel deep learning-based model, Financial Graph Attention Networks (FinGAT), to tackle the task under the setting that no pre-defined relationships between stocks are given. The idea of FinGAT is three-fold. First, we devise a hierarchical learning component to learn short-term and long-term sequential patterns from stock time series. Second, a fully-connected graph between stocks and a fully-connected graph between sectors are constructed, along with graph attention networks, to learn the latent interactions among stocks and sectors. Third, a multi-task objective is devised to jointly recommend the profitable stocks and predict the stock movement. Experiments conducted on Taiwan Stock, S&P 500, and NASDAQ datasets exhibit remarkable recommendation performance of our FinGAT, comparing to state-of-the-art methods. © 1989-2012 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot Planning for Filming Groups of Moving Actors Leveraging Submodularity and Pixel Density 63

Multi-Robot Planning for Filming Groups of Moving Actors Lev...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Hughes, Skyler Martin, Rebecca Corah, Micah Scherer, Sebastian Program Carnegie Mellon University Nsf Reu Program United States Robotics Institute Carnegie Mellon University Airlab United States Colorado School of Mines Department of Computer Science United States

ISBN: (纸本)9798350316339

Observing and filming a group of moving actors with a team of aerial robots is a challenging problem that combines elements of multi-robot coordination, coverage, and view planning. A single camera may observe multiple actors at once, and a robot team may observe individual actors from multiple views. As actors move about, groups may split, merge, and reform, and robots filming these actors should be able to adapt smoothly to such changes in actor formations. Rather than adopt an approach based on explicit formations or assignments, we propose an approach based on optimizing views directly. We model actors as moving polyhedra and compute approximate pixel densities for each face and camera view. Then, we propose an objective that exhibits diminishing returns as pixel densities increase from repeated observation. This gives rise to a multi-robot perception planning problem that we solve via a combination of value iteration and greedy submodular maximization. We evaluate our approach on challenging scenarios modeled after various social behaviors and featuring different numbers of robots and actors and observe that robot assignments and formations arise implicitly given the movements of groups of actors. Simulation results demonstrate that our approach consistently outperforms baselines, and in addition to performing well with the planner's approximation of pixel densities our approach also performs comparably for evaluation based on rendered views. Overall, the multi-round variant of the sequential planner we propose meets (within 1%) or exceeds formation and assignment baselines in all scenarios. © 2024 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Mammogram Breast Cancer Classification Based on Deep-Convolutional Neural Network

Mammogram Breast Cancer Classification Based on Deep-Convolu...

引用

2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023

作者： Amadea, Avissa Aurellia Sari, Christy Atika Rachmawanto, Eko Hari Sari, Wellia Shinta Noori, Mohammed S. Alkhafaji, Mohamed Ayad University of Dian Nuswantoro Study Program in Informatics Engineering Semarang Indonesia University of Dian Nuswantoro Study Program in Information Systems Semarang Indonesia Northern Technical University Department of Computer Engineering Technology Mosul Iraq National University of Science and Technology Department of Computer Science DhiQar Iraq

ISBN: (纸本)9798350339215

Based on WHO's data, breast cancer is one of the most deadly diseases that has claimed many victims, especially women. This disease begins with the presence of an undetected and eventually turns into malignant (cancer). This happens due to ignorance of the importance of having a medical check-up even though in good health. Doctors and researchers can prevent the development of tumor cells through treatment that begins with radiological examinations to identify the possibility of a person being affected by this disease. One of the most frequently used techniques is Mammography. This technique can detect the presence of tumor cells using advanced technology and several methods in displaying the patient's diagnostic results on low-dose X-rays in the form of mammogram images. The technology is inseparable from the methods used to identify the presence of tumor cells. In this study, we have proposed the CNN method based on the deep-CNN model to identify mammogram images in the detection of breast cancer cells with average evaluation results in terms of accuracy, precision, recall, specificity, and f-measure on mammogram image datasets of 99.52%, 99.72%, 99.31%, 99.72%, and 99.5%. These results showed that this method has a good performance in breast cancer detection. © 2023 IEEE.

关键词： Diseases

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：