检索结果-内蒙古大学图书馆

TaxDiff: taxonomic-guided diffusion model for protein sequence generation

science China(Information sciences) 2025年第4期68卷 385-386页

作者： Zongying LIN Hao LI Liuzhenghao LV Yu WANG Bin LIN Junwu ZHANG Zijun CHEN Calvin Yu-Chian CHEN Li YUAN Yonghong TIAN School of Electronic and Computer Engineering Peking University AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Peng Cheng Laboratory School of Chemical Biology and Biotechnology Peking University

Protein design aims to generate protein variants with targeted biological functions, which is significant in multiple biological areas, including enzyme reaction catalysis, vaccine design, and fluorescence intensity. Protein design contains two paradigms: sequence generation and structure generation. Recently, EvoDiff [1] proposed a universal designing paradigm, combining structure and sequence generation using the diffusion framework, which improves the protein design efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using CNN and Transformer Model for Unimodal Speech Emotion Recognition on MELD and IEMOCAP

Using CNN and Transformer Model for Unimodal Speech Emotion ...

引用

2025 International Conference on Advancement in Data science, E-learning and Information System, ICADEIS 2025

作者： Aurelio, Clarence Chowanda, Andry Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331513320

Emotion Recognition is one field that is taking the world by storm in this current age. Multimodal emotion recognition has shown promising results however, previous studies shows that recognition using speech is a field has not performed that greatly. Previous research used popular methods such as CNN, RNN, and other machine learning methods has been used to achieved good results with the help of other modality, where if speech were to be used alone the results won't be as good. A factor that contributes to the result of the speech modality not performing as well is the fact of the dataset and the way it was processed. Therefore, this research looks into what makes speech one of the lowest performing modalities by preprocessing the dataset using a different method than previous researches as well as using a CNN model paired with a Transformer model. Results achieved from this research showed an improvement when using IEMOCAP by 8.09% and MELD by 1.06%. A comparison results of using the pre-processed data with previous studies model was also done to compare the results. In conclusion, this research has explored a different preprocessing method and deep learning model that has achieved results better than previous works with the same dataset. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Neural Computing-Based Access Control Protocol for AI-Driven Intelligent Flying Vehicles in Industry 5.0-Assisted Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 3573-3581页

作者： Mahmood, Khalid Tariq, Tayyaba Sangaiah, Arun Kumar Ghaffar, Zahid Saleem, Muhammad Asad Shamshad, Salman National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan National Yunlin University of Science and Technology International Graduate School of AI Douliu64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102 2801 Lebanon University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China The University of Lahore Department of Software Engineering Lahore54590 Pakistan

The continuous revolution in Artificial Intelligence (AI) has played a significant role in the development of key consumer applications, including Industry 5.0, autonomous decision-making, fault diagnosis, etc. In practice, autonomous and intelligent robots and flying vehicles (i.e., drones) are also becoming the integral part of Industry 5.0. These vehicles are attaining significant importance nowadays because of their applications in consumer electronics. However, there may be numerous privacy issues in such an infrastructure. Nevertheless, neural computing-driven security solutions have played a significant role in overcoming the security and privacy issues of AI-driven intelligent flying vehicles. Motivated by these facts, this article presents a neural computing-based access control protocol for AI-driven flying vehicles to prevent all possible security threats. A detailed security evaluation of the devised protocol is done formally using the extensively recognized Real-Or-Random (ROR) oracle model. Similarly, the informal security analysis ensures the resistance of our scheme against various potential attacks under the assumptions of CK and DY adversarial models. Moreover, detailed performance scrutiny of the devised protocol with various existing schemes shows the robustness and supremacy of our scheme in terms of computation, communication overhead, and security attributes. © 1975-2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation

引用

Research 2024年第2期6卷 29-40页

作者： Jiawen Deng Zhuang Chen Hao Sun Zhexin Zhang Jincenzi Wu Satoshi Nakagawa Fuji Ren Minlie Huang The CoAl group DCSTInstitute for Artificial InteligenceState Key Lab of Intelligent Technology and SystemsBeijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Graduate School of Information Science&Technology The University of Tokyo.Tokyo 1138654Japan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengduSichuan611731China

Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language *** data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English *** significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain *** alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language Dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model ***,we employ a multiteacher distillation framework to enhance detection performance with unsupervised *** is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to *** soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive *** conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.

关键词： COLD dealing limitations

来源：评论

学校读者我要写书评

暂无评论

MEASURING THE ELASTIC-PLASTIC SURFACE DISPLACEMENT OF PARTIALLY COMPRESSED WOOD AND EVALUATION OF PARTIAL COMPRESSIVE LOAD PERPENDICULAR TO THE GRAIN

Journal of Structural and Construction Engineering

引用

Journal of Structural and Construction Engineering 2023年第805期88卷 467-478页

作者： Inoue, Sakiko Muramoto, Makoto Graduate School of Science and Technology Doctoral Program of Architecture Kyoto Institute of Technology Japan Faculty of Design and Architecture Kyoto Institute of Technology Japan

In this paper, the elastic-plastic displacement shape of the specimen surface during the experiment of compression perpendicular to the grain of the wood was measured using digital image correlation. And, it becomes possible to predict the transition of partial compressive load perpendicular to the grain, by using the stress-strain relation of allover compression perpendicular to the grain. This result is useful in making predictions for the partial compression perpendicular to the grain and the yield strength of wood joints. © 2023 Architectural Institute of Japan. All rights reserved.

关键词： Image correlation

来源：评论

学校读者我要写书评

暂无评论

Applying Burn-in Strategy to Deep Reinforcement Learning with Spiking Neural Networks 13

Applying Burn-in Strategy to Deep Reinforcement Learning wit...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Iwata, Takahiro Yoshioka, Seankein Miki, Daisuke Graduate School of Computer Science Chiba Institute of Technology Chiba Japan Chiba Institute of Technology Department of Computer Science Chiba Japan

ISBN: (纸本)9798350373332

In recent years, neural networks in deep reinforce-ment learning (D RL) have achieved success in various tasks, owing to their high expressiveness and flexibility. Neural networks are expected to be increasingly used for robot control. However, large neural networks consume a significant amount of power during training and operation. Given that the power supply that can be installed in robots is limited, challenges remain in the practical application of robot control using DRL, which includes large-scale neural networks. Conversely, spiking neural networks (SNNs) have high power efficiency, which is achieved through dedicated computational elements. Previous studies reported that SNNs can be applied to DRL to learn a robot's walking motion in a virtual environment and reduce energy consumption. Although previous studies have applied SNNs to DRL, they have the drawback of recursive computation, causing output delays. In this study, we propose a method that combines SNNs with a structure that addresses the issues of previous studies using a twin-delayed deep deterministic policy gradient (TD3). In addition, a burn-in strategy was introduced to estimate the action values using the internal states of the SNNs. Experiments in a virtual environment showed that the proposed method achieved higher rewards than the previous methods. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analysing Relaxation Effects Through Natural Experiences Using Natural Sounds and VR Devices 14

Analysing Relaxation Effects Through Natural Experiences Usi...

引用

14th International Conference on Information technology in Medicine and Education, ITME 2024

作者： Suzuki, Yukizi Sekine, Yusuke Tago, Kiichi Chiba Institute of Technology Graduate School of Information and Computer Science Narashino Japan

ISBN: (纸本)9798350356670

In recent years, studies have been conducted on virtual reality (VR) relaxation using VR devices to reduce stress. Our previous study suggested that VR relaxation using a virtual world, a 360-degree image, and a 360-degree video could produce comparable relaxation effects. However, in our study, the 360-degree image had no sound. The addition of natural sounds to the image may potentially enhance the relaxation effect. Therefore, this study aims to investigate the impact of incorporating natural sounds into the 360-degree image for relaxation. We employ five evaluation metrics to measure the relaxation effect: electroencephalography (EEG), heart rate, salivary amylase, State-Trait Anxiety Inventory (STAI), and a subjective stress questionnaire. These metrics are used to calculate the relaxation scores. The experimental results revealed a significant difference in relaxation scores derived from the EEG data. It suggests that adding natural sounds to 360-degree images can enhance the relaxation effect of VR relaxation. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Invisible Cloak to AI Recognition from All Horizontal Directions by Adversarial Patch 18

Invisible Cloak to AI Recognition from All Horizontal Direct...

引用

18th International Conference on Ubiquitous Information Management and Communication, IMCOM 2024

作者： Imaeda, Takumi Uda, Ryuya Graduate School of Bionics Computer and Media Science Tokyo University of Technology Graduate School Tokyo192-0982 Japan

ISBN: (纸本)9798350331011

Humans have a right not to be recognized by AI without permission while surveillance cameras and drones are coming to recognize humans automatically. The adversarial patch is one of the technologies that prevents objects from being recognized by AI. The patch was applied to a board to work in the real world. Moreover, it was improved to be a T-shirt with wrinkle resistance. Furthermore, it was also improved to have shooting angle resistance. However, all patches in the existing research do not have enough shooting resistance from all angles, especially from the side and from the back. Therefore, we proposed a cloak that had shooting resistance from all angles, but a pattern in a patch was sometimes misrecognized as a human. Hence, in this paper, we improved our cloak by changing the initial image to create adversarial patches. We also evaluated the recognition by AI. As a result, every pattern in a patch was no longer misrecognized as a human. On the contrary, the human detection rate increased to about 26 %, while in the previous cloak it was 1.2 %. We considered the reason for the increase to be the color of the initial image, and found a better color than the original image. We believe that a cyan initial image will make our cloak completely invisible to the AI recognition from all horizontal directions. © 2024 IEEE.

关键词： Security of data

来源：评论

学校读者我要写书评

暂无评论

Perfomance Improvement of mpdCNN as Ensemble Learning Model on Low Resolution Image-Face Recognition System 8

Perfomance Improvement of mpdCNN as Ensemble Learning Model ...

引用

8th International Conference on Electronics, Materials Engineering and Nano-technology, IEMENTech 2025

作者： Wangean, Daniel Anando Suhartono, Derwin Bina Nusantara University Master of Computer Science Binus Graduate Program Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331520762

Low resolution image-face recognition system is one of the challenging aspects of face recognition models' development. From machine learning, deep learning, and into ensemble learning are implemented to develop face recognition models. Including mpdCNN that published by Mishra in a journal article. This mpdCNN already achieved 88.6% accuracy score on SCFace dataset while published. Based on literature review, ensemble learning model can be improved by modifying parallel layers. The purpose of this research is to improve mpdCNN's performance by implementing some modifications include adding parallel layers, alternating the fusion layers, expanding the layers, and adding residual connections. Some modifications were successfully improved mpdCNN's accuracy score. By adding parallel layers and residual connections into mpdCNN's architecture, the modified mpdCNN that proposed in this research achieved 92.33% accuracy score, measured by Rank-k evaluation metric. © 2025 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Implementation of Dynamic Image for Facial Expression Recognition on Indonesian Facial Expression Dataset 6

Implementation of Dynamic Image for Facial Expression Recogn...

引用

6th IEEE International Conference on Artificial Intelligence in Engineering and technology, IICAIET 2024

作者： Iswanto, Irene Anindaputri Chowanda, Andry Soeparno, Haryono Budiharto, Widodo Binus Graduate Program Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350389692

In recent times, there has been considerable attention directed towards Facial Expression Recognition (FER) due to its extensive utility across diverse domains. However, the universality of facial expressions has been challenged by studies suggesting that cultural backgrounds significantly influence the perception and recognition of emotions. This paper addresses the need for culturally specific datasets in FER tasks, particularly in underrepresented regions like Indonesia. The study introduces dynamic images as an alternative input representation for facial expression recognition tasks, aiming to assess their efficacy using the Indonesian Mixed Emotions Dataset (IMED). Through experimentation using EfficientNet model, the performance of dynamic images is compared with static image and video inputs. Results indicate that dynamic images exhibit promising performance, with an accuracy of 94.28%. These results outperform static image datasets and nearly match the performance of video-based models, which achieved an accuracy of 97.93 %, despite using fewer data. Nonetheless, challenges such as data imbalance and the quality of generated dynamic images persist, suggesting avenues for further research and model refinement. This study provides valuable insights into methodological advancements in FER, particularly in limited dataset conditions, laying the groundwork for future developments in dynamic image-based facial expression recognition algorithms. © 2024 IEEE.

关键词： Dynamic Image EfficientNet Facial Expression Recognition IMED

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：