检索结果-内蒙古大学图书馆

Imaging atomic-scale chemistry from fused multi-modal electron microscopy

npj Computational Materials 2022年第1期8卷 164-171页

作者： Jonathan Schwartz Zichao Wendy Di Yi Jiang Alyssa J.Fielitz Don-Hyung Ha Sanjaya D.Perera Ismail El Baggari Richard D.Robinson Jeffrey A.Fessler Colin Ophus Steve Rozeveld Robert Hovden Department of Materials Science and Engineering University of MichiganAnn ArborMIUSA Mathematics and Computer Science Division Argonne National LaboratoryLemontILUSA Advanced Photon Source Facility Argonne National LaboratoryLemontILUSA Dow Chemical Co. MidlandMIUSA Department of Material Science and Engineering Cornell UniversityIthacaNew YorkUSA School of Integrative Engineering Chung-Ang UniversitySeoulRepublic of Korea Department of Physics Cornell UniversityIthacaNYUSA The Rowland Institute at Harvard CambridgeMAUSA Department of Electrical Engineering and Computer Science University of MichiganAnn ArborMIUSA National Center for Electron Microscopy Lawrence Berkeley National LaboratoryMolecular FoundryBerkeleyCAUSA Applied Physics Program University of MIchiganAnn ArborMIUnited States

Efforts to map atomic-scale chemistry at low doses with minimal noise using electron microscopes are fundamentally limited by inelastic ***,fused multi-modal electron microscopy offers high signal-to-noise ratio(SNR)recovery of material chemistry at nano-and atomic-resolution by coupling correlated information encoded within both elastic scattering(high-angle annular dark-field(HAADF))and inelastic spectroscopic signals(electron energy loss(EELS)or energy-dispersive x-ray(EDX)).By linking these simultaneously acquired signals,or modalities,the chemical distribution within nanomaterials can be imaged at significantly lower doses with existing detector *** many cases,the dose requirements can be reduced by over one order of *** high SNR recovery of chemistry is tested against simulated and experimental atomic resolution data of heterogeneous nanomaterials.

关键词： materials chemistry fused

来源：评论

学校读者我要写书评

暂无评论

Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 1745-1757页

作者： Hong, Qian-Bei Wu, Chung-Hsien Wang, Hsin-Min National Cheng Kung University and Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701 Taiwan Academia Sinica Taipei115 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Academia Sinica Institute of Information Science Taipei115 Taiwan

Speech content is closely related to the stability of speaker embeddings in speaker verification tasks. In this paper, we propose a novel architecture based on self-constraint learning (SCL) and reconstruction task (RT) to remove the influence of phonetic information on speaker embedding generation. First, SCL is used to reduce the divergence of frame-level features, which can avoid ambiguity between the resulting embeddings of the two utterances being compared. Second, RT is used to further remove phonetic information in frame-level layers, focusing on speaker-discriminative feature transformation. In our experiments, the speaker embedding models were trained on the VoxCeleb2 dataset and evaluated on the VoxCeleb1, Librispeech, SITW and VoxMovies datasets. Experimental results on VoxCeleb1 show that the proposed DROP-TDNN system reduced the EER by 7.5%, compared to the state-of-the-art ECAPA-TDNN system. Furthermore, the proposed DROP-TDNN system also outperformed the ECAPA-TDNN system in the experiments on SITW, Librispeech and VoxMovies under cross-dataset conditions. In the experiments on SITW, the proposed system reduced the EER by 3.4% compared to the ECAPA-TDNN system. In the experiments on Librispeech, the proposed system demonstrated the advantage of removing phonetic information under the clean speech condition, with a significant reduction of 25.5% in EER compared to the ECAPA-TDNN system. In the experiments on VoxMovies, the proposed system reduced the EER by up to 7.9% compared to the ECAPA-TDNN system under different pronunciation and background conditions. © 2014 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling

Back to the Future: Bidirectional Information Decoupling Net...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Li, Yiyang Zhao, Hai Zhang, Zhuosheng Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Multi-turn dialogue modeling as a challenging branch of natural language understanding (NLU), aims to build representations for machines to understand human dialogues, which provides a solid foundation for multiple downstream tasks. Recent studies of dialogue modeling commonly employ pre-trained language models (PrLMs) to encode the dialogue history as successive tokens, which is insufficient in capturing the temporal characteristics of dialogues. Therefore, we propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder, which explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks. Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN. The official implementation of BiDeN is available at https://***/EricLee8/BiDeN. © 2022 Association for Computational Linguistics.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Gender-Based Bimodal Analysis of Speech and Text in Non-Contextual Emotion Recognition

Gender-Based Bimodal Analysis of Speech and Text in Non-Cont...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Abby Rasya Angkasa Amalia Zahra Wai-Keung Fung Computer Science Department BINUS Graduate Program - Master of Computer Science Jakarta Indonesia Engineering Department Cardiff Metropolitan University - Cardiff School of Technologies Cardiff United Kingdom

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

Emotion recognition can help human-computer interactions by enabling systems to respond empathetically and adapt to users' emotional conditions. This capability improves user experience, supporting the development of a more intuitive and emotionally responsive communication system. This study analyzes a bimodal approach based on gender (male and female) to recognize emotions without contextual information in dialogue analysis. Utilizing the Multimodal EmoryNLP dataset extracted from the TV series Friends with acted speech, we focused on four primary emotions: Angry, Neutral, Joy, and Scared. The model used in this study for text classification is RoBERTa, and wav2vec 2.0 is used for audio feature extraction with the Bi-LSTM model for classification. The experiment results using weighted F1-score reveal that data augmentation enhanced the performance of analyzing the original dataset from 0.46% to 0.52% and the male dataset from 0.43% to 0.51 %. In comparison, the female dataset remained consistent at 0.46%. The weighted F1-score and Unweighted Averaged Recall (UAR) from the male dataset are higher, 51 % and 48%, respectively, than those from the female dataset, 46% and 47%, respectively. Gender-based analysis indicated that male and female datasets exhibited distinct performance patterns, highlighting variations in emotional expression and recognition between genders. These findings underscore the effectiveness of multimodal strategies in emotion recognition and suggest that gender-specific factors play a significant role in enhancing classification performance. While these results highlight performance trends, further validation through repeated trials and statistical analyses could provide stronger generalizations and insights into gender-based differences.

关键词： Emotion recognition TV Statistical analysis Text categorization Speech recognition Linguistics Feature extraction Data augmentation Market research User experience

来源：评论

学校读者我要写书评

暂无评论

Sentence Representation Learning with Generative Objective rather than Contrastive Objective

Sentence Representation Learning with Generative Objective r...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Wu, Bohong Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However, contrastive objectives which dominate the current sentence representation learning bring little linguistic interpretability and no performance guarantee on downstream semantic tasks. We instead propose a novel generative self-supervised learning objective based on phrase reconstruction. To overcome the drawbacks of previous generative methods, we carefully model intra-sentence structure by breaking down one sentence into pieces of important phrases. Empirical studies show that our generative learning achieves powerful enough performance improvement and outperforms the current state-of-the-art contrastive methods not only on the STS benchmarks, but also on downstream semantic retrieval and reranking tasks. Our code is available at https://***/chengzhipanpan/PaSeR. © 2022 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deep Learning with Backtracking Search Optimization Based Skin Lesion Diagnosis Model

引用

computers, Materials & Continua 2022年第1期70卷 1297-1313页

作者： C.S.S.Anupama L.Natrayan E.Laxmi Lydia Abdul Rahaman Wahab Sait Jose Escorcia-Gutierrez Margarita Gamarra Romany F.Mansour Department of Electronics&Instrumentation Engineering V.R.Siddhartha Engineering CollegeVijayawada520007India Department of Mechanical Engineering Saveetha School of EngineeringSIMATSChennai602105India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Archives and Communication King Faisal University31982Kingdom of Saudi Arabia Electronic and Telecommunicacions Program Universidad Autonoma del CaribeBarranquilla08001Colombia Department of Computational Science and Electronic Universidad de la CostaCUCBarranquilla08001Colombia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

Nowadays,quality improvement and increased accessibility to patient data,at a reasonable cost,are highly challenging tasks in healthcare *** of Things(IoT)and Cloud Computing(CC)architectures are utilized in the development of smart healthcare *** entities can support real-time applications by exploiting massive volumes of data,produced by wearable sensor *** advent of evolutionary computation algorithms andDeep Learning(DL)models has gained significant attention in healthcare diagnosis,especially in decision making *** cancer is the deadliest disease which affects people across the *** skin lesion classification model has a highly important application due to its fine-grained variability in the presence of skin *** current research article presents a new skin lesion diagnosis model i.e.,Deep Learning with Evolutionary Algorithm based Image Segmentation(DL-EAIS)for IoT and cloud-based smart healthcare ***,the dermoscopic images are captured using IoT devices,which are then transmitted to cloud servers for further ***,Backtracking Search optimization Algorithm(BSA)with Entropy-Based Thresholding(EBT)i.e.,BSA-EBT technique is applied in image *** by,Shallow Convolutional Neural Network(SCNN)model is utilized as a feature *** addition,Deep-Kernel Extreme LearningMachine(D-KELM)model is employed as a classification model to determine the class labels of dermoscopic *** extensive set of simulations was conducted to validate the performance of the presented method using benchmark *** experimental outcome infers that the proposed model demonstrated optimal performance over the compared techniques under diverse measures.

关键词： Intelligent models skin lesion dermoscopic images smart healthcare internet of things

来源：评论

学校读者我要写书评

暂无评论

AI Recommendations: Friend or Foe? Unraveling the Impact on Consumer Benefits and Privacy 11

AI Recommendations: Friend or Foe? Unraveling the Impact on ...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Dewanthi, Desyra Sukma Kristopo, Hari Qomariyah, Nunung Nurul Axel, Muhammad Business Management & Marketing Program Binus Business School International Undergraduate Program Bina Nusantara University Management Department Jakarta11480 Indonesia Bina Nusantara University Faculty of Engineering Food Technology Department Jakarta11480 Indonesia School of Computing and Creative Arts Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350389654

Artificial Intelligence (AI) and marketing have transformed consumer behavior and shopping experiences, especially through Recommender Systems (RSs) in e-commerce. RSs use algorithms to provide personalized recommendations, enhancing shopping convenience. However, this raises data privacy and ethical concerns, as RSs rely on user data. This research explores the quality determinants of RSs and their impact on consumer behavior, focusing on privacy awareness and its effect on repurchase intentions. Using a qualitative approach with semi-structured interviews, the study targets Indonesian respondents aged 18-40 with e-commerce experience. Findings reveal that recommendation quality, especially self-reference and vividness, significantly influences purchasing decisions. Respondents prefer recommendations that match their preferences and are visually appealing. Positive shopping experiences are linked to efficient and accurate RSs, but there's a need for improvements in transparency, novelty, diversity, and advanced technologies like AR. Respondents are aware of digital data storage but have limited understanding of privacy concerns. They trust e-commerce platforms with basic personal details but are hesitant to share sensitive information. Despite privacy issues, e-commerce remains vital, with respondents emphasizing the need for transparency, robust security, and clear explanations for data use to maintain trust. Addressing these issues not only enhances customer experience but also demonstrates that consumer trust directly impacts the sustainability and success of the business. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Development of Detection Lung Disease Stand Alone System Based on Convolutional Neural Network (CNN)

Development of Detection Lung Disease Stand Alone System Bas...

引用

International Conference of computer and Informatics engineering (IC2IE)

作者： Edgar Caesar Liewarnata Yosica Mariana Sofyan Tan Suryadiputra Liawatimena Winda Astuti Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Product Design Program Industrial Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta Indonesia Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331505530

ISBN: (纸本)9798331505547

Lung disease, especially Tuberculosis (TBC), placed the highest death rate in Indonesia. Tuberculosis (TB) in Indonesia is ranked second after India. Therefore, it is important to reduce or early detection of the lung disease, to prevent this disease and speed up handling. The system can recognize the disease lung identification, and the system applied as standalone system. In this work, the Convolutional Neural Network (CNN) approach for identifying diseases lung identification is proposed. The Mel Frequency Cepstral Coefficient (MFCC) applied to process the stethoscope sounds which will used as input to the CNN. The performance of the proposed system has been investigated and resulted. The accuracy of 99% and 98%, for training and testing accuracy respectively. Furthermore, the system accurately detects lung diseases identification.

关键词： Training Accuracy Tuberculosis Pulmonary diseases Lungs Stethoscope Recording Convolutional neural networks Mel frequency cepstral coefficient Testing

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Models Are Not Pragmatically Competent in Referring Expression Generation

arXiv

引用

arXiv 2025年

作者： Ma, Ziqiao Ding, Jing Zhang, Xuejun Luo, Dezhi Ding, Jiahe Xu, Sihan Huang, Yuchen Peng, Run Chai, Joyce Computer Science and Engineering Division University of Michigan United States Weinberg Institute for Cognitive Science University of Michigan United States Department of Statistics University of Michigan United States GrowAI

Referring Expression Generation (REG) is a core task for evaluating the pragmatic competence of vision-language systems, requiring not only accurate semantic grounding but also adherence to principles of cooperative communication (Grice, 1975). However, current evaluations of vision-language models (VLMs) often overlook the pragmatic dimension, reducing REG to a region-based captioning task and neglecting Gricean maxims. In this work, we revisit REG from a pragmatic perspective, introducing a new dataset (RefOI) of 1.5k images annotated with both written and spoken referring expressions. Through a systematic evaluation of state-of-the-art VLMs, we identify three key failures of pragmatic competence: (1) failure to uniquely identify the referent, (2) inclusion of excessive or irrelevant information, and (3) misalignment with human pragmatic preference, such as the underuse of minimal spatial cues. We also show that standard automatic evaluations fail to capture these pragmatic violations, reinforcing superficial cues rather than genuine referential success. Our findings call for a renewed focus on pragmatically informed models and evaluation frameworks that align with real human communication. © 2025, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Blockchain and API Development to Improve Relational Database Integrity and System Interoperability

引用

Procedia computer science 2023年 216卷 151-160页

作者： Andhika Naafi Ramadhan Kharisma Naufal Pane Kun Rifki Wardhana Suharjito Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Industrial Engineering Department BINUS Graduate Program – Master of Industrial Engineering Bina Nusantara University Jakarta 11480 Indonesia

Technological developments have resulted in a trend of cryptocurrencies that use a technology called blockchain to create and record all transactions made into a digital ledger. Along with the emergence of the trend of cryptocurrencies, this development has also resulted in crimes that hit the digital world, such as data leakage and cyber espionage. This threat can be prevented by applying blockchain technology to the database that has been used. Therefore, we need a system that can facilitate the use of blockchain technology and can process data from an existing relational database into a blockchain-based database. The system developed in this study was built with the FastAPI framework that uses the Python programming language and the React framework that uses the Javascript programming language. This system was tested using Katalon and Wireshark software to perform throughput testing and man-in-the-middle attacks. Evaluation of this system is assessed based on the average throughput time and also the results of Wireshark packet capture. The system designed in this research is expected to help overcome interoperability problems when using blockchain and improve relational database integrity. The results of the test show that the system is safe from man-in-the-middle attacks while sending data through API and has a faster throughput time than BigchainDB system by 4.151 seconds.

关键词： Blockchai Cybercrim Database Interoperability

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：