检索结果-内蒙古大学图书馆

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Patrícia Da Costa Morgana Da Rosa Rafael Soares Eduardo Da Costa Sergio Bampi Graduate Program on Microelectronics Federal University of Rio Grande do Sul Porto Alegre Brazil Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil Graduate Program on Microelectronics (PGMICRO) Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

This work presents an optimized exponential function VLSI hardware design by Taylor series expansion. The proposed architecture implements the exponential by approximating the logic design of a 4 th -order Taylor series and explores efficient CMOS arithmetic operation strategies. It implements a shift-based divider and explores an efficient 4-2 adder compressor in the adder tree. The proposal with a −7 to 11 input values range shows an output error of around 2% of MRED with a reduced energy consumption of 3.63 pJ/operation for 32-bit output. For a 64-bit output, the energy per operation of the VLSI exponential unit is 14.97pJ/op, being able to process a more comprehensive input range (i.e., −14 to 22) for a negligible mean output error of around 1.7% of MRED.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to Generate Equitable Text in Dialogue from Biased Training Data

arXiv

引用

arXiv 2023年

作者： Sicilia, Anthony Alikhani, Malihe Intelligent Systems Program University of Pittsburgh United States School of Computing and Information University of Pittsburgh United States

The ingrained principles of fairness in a dialogue system’s decision-making process and generated responses are crucial for user engagement, satisfaction, and task achievement. Absence of equitable and inclusive principles can hinder the formation of common ground, which in turn negatively impacts the overall performance of the system. For example, misusing pronouns in a user interaction may cause ambiguity about the intended subject. Yet, there is no comprehensive study of equitable text generation in dialogue. Aptly, in this work, we use theories of computational learning to study this problem. We provide formal definitions of equity in text generation, and further, prove formal connections between learning human-likeness and learning equity: algorithms for improving equity ultimately reduce to algorithms for improving human-likeness (on augmented data). With this insight, we also formulate reasonable conditions under which text generation algorithms can learn to generate equitable text without any modifications to the biased training data on which they learn. To exemplify our theory in practice, we look at a group of algorithms for the GuessWhat?! visual dialogue game and, using this example, test our theory empirically. Our theory accurately predicts relative-performance of multiple algorithms in generating equitable text as measured by both human and automated evaluation. © 2023, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Thai Question-Answering System Using Pattem-Matching Approach 1

Thai Question-Answering System Using Pattem-Matching Approac...

引用

1st International Conference on Technology Innovation and Its Applications, ICTIIA 2022

作者： Wongpraomas, Pongsathorn Soomlek, Chitsutha Sirisangtragul, Wanna Seresangtakul, Pusadee College Of Computing Khon Kaen University Department Of Computer Science Khon Kaen Thailand Khon Kaen University Forensic Science Program Faculty Of Science Khon Kaen Thailand

ISBN: (数字)9781665488266

ISBN: (纸本)9781665488266

Teaching concepts in Thailand's universities have abruptly changed, due to the advancement of the COVID-19 pandemic, including changes in classroom to online formats, as well as administrative difficulties. The research herein, therefore, addresses these concerns, presenting a Thai question-answering system using the pattern-matching approach. Our case study covers course information, teaching timetable, teacher schedule, and course supplements. We classified the questions into six categories according to type and acknowledged typical expressions which matched to question patterns. We use RegEx® to match a defined pattern. When a response did not match, we used word embedding to transform the question into a vector and then calculated the cosine similarity to identify the most similar pattern. The system can then generate a corresponding SQL command to query the answer from the database. We evaluated the accuracy of the proposed system with the collected data resulted in an accuracy rate of 82%. © 2022 IEEE.

关键词： Pattern matching

来源：评论

学校读者我要写书评

暂无评论

Optimizing in-band network telemetry problem

引用

Procedia Computer Science 2024年 239卷 2074-2081页

作者： Thierno Bocar N’Diaye Marcelo Caggiani Luizelli Jules Degila Luciana Salete Buriol Institut de Mathematiques et Sciences Physiques Universite d’Abomey-Calavi (UAC) Benin Graduate Program in Electrical Engineering Universidade Federal do Pampa (UNIPAMPA) Brazil Graduate Program in Computing Universidade Federal do Rio Grande do Sul (UFRGS) Brazil

In-band network telemetry is a powerful framework for network monitoring. It allows the collection of telemetry data in real-time and provides network-wide visibility. However, depending on the routing of network flows and which telemetry data are collected, the network-wide visibility and the performance of monitoring applications may decrease. In this paper, we present the in-band network telemetry problem and extend the existing mathematical optimization models of the problem by proposing a new model that computes the routing of network flows. Results show that the new model outperforms existing models in term of network coverage and monitoring applications performance. The results of this work can be useful for network managers and enterprises to gain real-time insights into network performance.

关键词： Network monitoring Monitoring application Optimization In-band network telemetry Network flows routes

来源：评论

学校读者我要写书评

暂无评论

OSM: Leveraging model checking for observing dynamic 1 behaviors in aspect-oriented applications

arXiv

引用

arXiv 2024年

作者： AlSobeh, Anas Mohammad Ramadan Department of Information Systems Faculty of Information Technology and Computer Science Yarmouk University Irbid Jordan Program of Information Technology School of Computing College of Engineering Computing Technology and Mathematics Southern Illinois University CarbondaleIL United States

In the intricate domain of software systems verification, dynamically model checking multifaceted system characteristics remains paramount, yet challenging. This research proposes the advanced observe-based statistical model-checking (OSM) framework, devised to craft executable formal models directly from foundational system code. Leveraging model checking predicates, the framework melds seamlessly with aspect-oriented programming paradigms, yielding a potent method for the analytical verification of varied behavioral attributes. Exploiting the transformative capacity of OSM framework, primary system code undergoes a systematic metamorphosis into multifaceted analysis constructs. This not only simplifies the model verification process but also orchestrates feature interactions using an innovative observing join point abstraction mechanism. Within this framework, components encompassing parsing, formal verification, computational analytics, and rigorous validation are intrinsically interwoven. Marrying the principles of model checking with aspect-oriented (AO) modularization, OSM framework stands as a paragon, proficiently scrutinizing and affirming system specifications. This ensures the unyielding performance of electronic health record systems amidst shifting preconditions. OSM framework offers runtime verification of both object-oriented and AO deployments, positioning itself as an indispensable open-source resource, poised to automate the enhancement of system performance and scalability. Copyright © 2024, The Authors. All rights reserved.

关键词： Aspect oriented programming

来源：评论

学校读者我要写书评

暂无评论

Diffusion models applied to skin and oral cancer classification

arXiv

引用

arXiv 2025年

作者： Uliana, José J.M. Krohling, Renato A. Labcin - Nature-inspired Computing Lab Federal University of Espírito Santo Vitória Brazil Labcin - Nature-inspired Computing Lab Graduate Program in Computer Science PPGI UFES Federal University of Espírito Santo Vitória Brazil

This study investigates the application of diffusion models in medical image classification (DiffMIC), focusing on skin and oral lesions. Utilizing the datasets PAD-UFES-20 for skin cancer and P-NDB-UFES for oral cancer, the diffusion model demonstrated competitive performance compared to state-of-the-art deep learning models like Convolutional Neural Networks (CNNs) and Transformers. Specifically, for the PAD-UFES-20 dataset, the model achieved a balanced accuracy of 0.6457 for six-class classification and 0.8357 for binary classification (cancer vs. non-cancer). For the P-NDB-UFES dataset, it attained a balanced accuracy of 0.9050. These results suggest that diffusion models are viable models for classifying medical images of skin and oral lesions. In addition, we investigate the robustness of the model trained on PAD-UFES-20 for skin cancer but tested on the clinical images of the HIBA dataset. © 2025, CC BY.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Prediction of Bankruptcy among Middle 40 per Cent (M40) in Malaysia using Support Vector Machine 22

Prediction of Bankruptcy among Middle 40 per Cent (M40) in M...

引用

22nd IEEE Student Conference on Research and Development, SCOReD 2024

作者： Sabri, Nurbaity Sahiq, Aqilah Nadiah Md Hamzah, Hazwa Hanim Mohamed Sain, Hartayuni Mangshor, Nur Nabilah Abu Shari, Anis Amilah Universiti Teknologi MARA Cawangan Melaka College of Computing Informatics and Mathematics Kampus Jasin Melaka Malaysia Universiti Teknologi MARA Cawangan Melaka Faculty of Business and Management Kampus Bandaraya Melaka Malaysia Tadulako University Statistics Study Program Mathematics and Natural Science Faculty Palu94118 Indonesia

ISBN: (纸本)9798331510077

The Middle 40 Per Cent (M40) demographic comprises a substantial proportion of Malaysia's consumer base, comprising the median 40% of income earners. This group is a big part of the country's customer base. The rising cost of living, flat wage growth, and rising family debt make this group especially vulnerable to financial instability. Given these economic pressures, predicting the possibility of bankruptcy in this population is becoming increasingly crucial to allow for early intervention and preventive actions. Support Vector Machines (SVM) are recognized for their efficacy in classification tasks, particularly with small or imbalanced datasets. SVM prediction will be utilized using 14694 samples of the Debt Management program (DMP) dataset from 2016 to 2020. Twenty-three (23) features will be implemented on the dataset and Synthetic Minority Oversampling Technique (SMOTE) to improve the imbalanced datasets. The experiment demonstrates that the SVM classifier obtained 91.1% accuracy when implementing PUK kernels. It suggests that SVM is a plausible alternative model for predicting personal bankruptcy in the M40 group. To anticipate personal bankruptcy for M40, additional prediction models will be evaluated in the future. © 2024 IEEE.

关键词： Prediction models

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

Blockchain-Empowered Cyber-Secure Federated Learning for Trustworthy Edge computing

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Moore, Ervin Imteaj, Ahmed Hossain, Md Zarif Rezapour, Shabnam Amini, M. Hadi MiamiFL33199 United States Center FIU United States School of Computing Southern Illinois University Carbondale United States Enterprise and Logistics Engineering program at FIU United States

Federated Learning (FL) is a privacy-preserving distributed machine learning scheme, where each participant's data remains on the participant's devices and only the local model generated utilizing the local computational power is transmitted throughout the database. However, the distributed computational nature of FL creates the necessity to develop a mechanism that can remotely trigger any network agents, track their activities, and prevent threats to the overall process posed by malicious participants. Particularly, the FL paradigm may become vulnerable due to an active attack from the network participants, called a poisonous attack. In such an attack, the malicious participant acts as a benign agent capable of affecting the global model quality by uploading an obfuscated poisoned local model update to the server. This paper presents a cross-device FL model that ensures trustworthiness, fairness, and authenticity in the underlying FL training process. We leverage trustworthiness by constructing a reputation-based trust model based on agents' contributions toward model convergence. We ensure fairness by identifying and removing malicious agents from the training process through an outlier detection technique. Additionally, we establish authenticity by generating a token for each participating device through a distributed sensing mechanism and storing that unique token in a blockchain smart contract. Further, we insert the trust scores of all agents into a blockchain and validate their reputations using various consensus mechanisms that consider the computational task. © 2020 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compressors Topologies

New Energy-Efficient 3-2 and 4-2 Approximate Adder Compresso...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Rodrigo Lopes Leonardo Antonietti Morgana M. A. Rosa Eduardo Costa Rafael Soares Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil PPGC & PGMICRO - Informatics Institute Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

Addition units are present across many computational kernels inherent in various error-tolerant applications, including machine learning, signal, image, and video processing. Notably, adder compressors are the target when high speed and low power are the main design concerns. This work introduces energy-efficient structures of 3-2 approximate adder compressors (Ax3-2) and three distinct versions of 4-2 approximate adder compressors (Ax4-2). We compared our proposed Ax3-2 and Ax4-2 compressors with state-of-the-art energy-efficient approximate adder compressors (AxACs). Both Ax3-2 and Ax4-2 models passed through rigorous tests as standalone units. Furthermore, we integrated the Ax4-2 models into an essential application kernel appearing in video coding, i.e., the Sum Squared Differences (SSD) video accelerator. We introduce Ax3-2 and Ax4-2 that yield a new Pareto front concerning both energy-quality and area-quality trade-offs, thereby demonstrating a marked improvement over the prevailing state-of-the-art energy-efficient AxACs.

关键词：

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：