检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei Taiwan The Department of Computer Science National Chengchi University Taipei Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan The Institute of Information Science Academia Sinica Taiwan

Multimodal deepfakes involving audiovisual manipulations are a growing threat because they are difficult to detect with the naked eye or using unimodal deep learning-based forgery detection methods. Audiovisual forensic models, while more capable than unimodal models, require large training datasets and are computationally expensive for training and inference. Furthermore, these models lack interpretability and often do not generalize well to unseen manipulations. In this study, we examine the detection capabilities of a large language model (LLM) (i.e., ChatGPT) to identify and account for any possible visual and auditory artifacts and manipulations in audiovisual deepfake content. Extensive experiments are conducted on videos from a benchmark multimodal deepfake dataset to evaluate the detection performance of ChatGPT and compare it with the detection capabilities of state-of-the-art multimodal forensic models and humans. Experimental results demonstrate the importance of domain knowledge and prompt engineering for video forgery detection tasks using LLMs. Unlike approaches based on end-to-end learning, ChatGPT can account for spatial and spatiotemporal artifacts and inconsistencies that may exist within or across modalities. Additionally, we discuss the limitations of ChatGPT for multimedia forensic tasks. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

ETHICS-2023 Session D1 - Open Forum: Building a Technology Ethics Community

ETHICS-2023 Session D1 - Open Forum: Building a Technology E...

引用

IEEE International Symposium on Ethics in Science, Technology and Engineering

作者： Thomas Creely Marc Cheong Heather Love Ketra Schmitt Ethics and Emerging Military Technology Graduate Program U.S. Naval War College School of Computing and Information Systems & Centre for AI and Digital Ethics (CAIDE) University of Melbourne English Language and Literature University of Waterloo Concordia University

This session was an open forum where audience members were invited to participate in discussions of a number of themes with relevance to ethics and technology and to future conferences in the IEEE ETHICS series. The discussions took place in small groups, with groups reporting back to the full cohort for collaborative brainstorming.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Abundance of Fish Species Populations in Manila Bay, Philippines Based on Ensemble Learning Approach

Predicting Abundance of Fish Species Populations in Manila B...

引用

International Joint Conference on Computer Science and Software Engineering (JCSSE)

作者： Sherrlyn M. Rasdas Arnel C. Fajardo Jomel S. Limbago Graduate Program Technological Institute of the Philippines Manila Philippines College of Computing Science Information and Communication Technology -CCSICT Isabela State University-Cauayan Philippines Fisheries and Aquatic Sciences Department (FASD) Cavite State University Naic Cavite Philippines

Manila Bay is a significant contributor to the Philippines' fish production, but its resources have been depleted due to overfishing, pollution, and damage, leading to a decline in fish catch and a shift towards less valuable species. Conventional approaches to fisheries stock assessment impose constraints on our comprehension of fish population dynamics. These limitations can be overcome through the utilization of machine learning techniques, which enable the forecasting and modeling of fisheries populations with improved accuracy and understanding. In this study, the commercial fisheries populations data collected from 2018 to 2021 in Manila Bay were used to predict the abundance of species fisheries production data using the K-NN - MLP - Logistic Regression (KNMLPR) model based on the majority voting ensemble approach. Analysis revealed that it is possible to combine the strengths of multiple models and improve overall predictive performance. The results also suggest that the k-nearest neighbors and logistic regression models have the best performance in predicting fish species population dynamics, while the neural network model shows slightly lower accuracy. This study provides valuable insights for fishery management and policymaking to support sustainable fishing practices in the region. Further research could focus on exploring additional machine learning algorithms and incorporating environmental factors to improve the prediction accuracy of the model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supervised Score-Based Modeling by Gradient Boosting

arXiv

引用

arXiv 2024年

作者： Zhao, Changyuan Du, Hongyang Liu, Guangyuan Niyato, Dusit College of Computing and Data Science Nanyang Technological University Singapore CNRS@CREATE 1 Create Way # 08-01 Create Tower 138602 Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong The Energy Research Institute @ NTU Interdisciplinary Graduate Program Singapore

Score-based generative models can effectively learn the distribution of data by estimating the gradient of the distribution. Due to the multi-step denoising characteristic, researchers have recently considered combining score-based generative models with the gradient boosting algorithm, a multi-step supervised learning algorithm, to solve supervised learning tasks. However, existing generative model algorithms are often limited by the stochastic nature of the models and the long inference time, impacting prediction performances. Therefore, we propose a Supervised Score-based Model (SSM), which can be viewed as a gradient boosting algorithm combining score matching. We provide a theoretical analysis of learning and sampling for SSM to balance inference time and prediction accuracy. Via the ablation experiment in selected examples, we demonstrate the outstanding performances of the proposed techniques. Additionally, we compare our model with other probabilistic models, including Natural Gradient Boosting (NGboost), Classification and Regression Diffusion Models (CARD), Diffusion Boosted Trees (DBT), and non-probabilistic GBM models. The experimental results show that our model outperforms existing models in both accuracy and inference time. © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Aedes Aegypti Egg Classification Model Using Support Vector Machine

Aedes Aegypti Egg Classification Model Using Support Vector ...

引用

International Conference on Computer Research and Development (ICCRD)

作者： Cherry R. Gumiran Arnel C. Fajardo Ruji P. Medina Minh S. Dao Joel M. Gumiran Graduate Program Technological Institue of the Philippines Quezon City Philippines Philippines Isabela State University Cauayan College of Computing Studies Information and Communications Technology Philippines Graduate Prgram Technological Institue of the Philippines Quezon City Philipines Philippines Big Data Integration Research Center National Institute of Information and Communications Technology Tokyo Japan

Aedes aegypti is the dengue fever vector, affecting 3.9 billion people worldwide. Found primarily in subtropical areas such as the Philippines. Numerous approaches and procedures had used to identify this disease carrier throughout its life cycle. However, recognizing it early, primarily during the egg stage, helps monitor the disease carrier's existence. On the other hand, classifying the egg remains an issue due to its resemblance to another mosquito species. As a result, extracted traits of the Aedes egg had added to the classification model. Furthermore, the Support Vector Machine algorithm's effectiveness as a classifier improves classification accuracy, mainly when the feature extracted has been added. Thus, this paper used the Support Vector Machine in designing a model to classify Aedes aegypti eggs. This model differentiates it from non-Aedes with a classification accuracy of 98.23%, which is greater than the classification accuracy compared to previous studies using the pixel and region-based method. In addition, the newly developed model had increased accuracy compared to the model in which the features had omitted from the classification process by 3.26 percent. In addition, the model was validated on a non-Aedes dataset in which it exhibited similar characteristics. As a result, the model reveals improved categorization and is determined to be non-Aedes. Thus, this model demonstrates a considerable boost in classification accuracy.

关键词： Shape Computational modeling Support vector machine classification Color Feature extraction Classification algorithms Viruses (medical)

来源：评论

学校读者我要写书评

暂无评论

A Power-Efficient FFT Hardware Architecture Exploiting Approximate Adders

A Power-Efficient FFT Hardware Architecture Exploiting Appro...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Guilherme Ferreira Pedro T. L. Pereira Guilherme Paim Eduardo Costa Sergio Bampi Graduate Program in Microelectronics (PGMICRO) Federal University of Rio Grande do Sul (UFRGS) Brazil Graduate Program in Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Brazil

ISBN: (数字)9781728176703

ISBN: (纸本)9781728176710

This work presents an energy-efficient Fast Fourier Transform (FFT) hardware architecture exploiting approximate adder circuits. The FFT hardware architecture consists of a fixed-point fully sequential architecture with a radix-2 butterfly with decimation in time (DIT). In this paper, we explore a set of approximate adders (LOA, ETA-I, Copy-A, Copy-B, Trunc0, Trunc1) in the butterfly by varying the approximation level (K term). The Root-Mean-Square Error (RMSE) metric shows which approximate level term allows the FFT processing without widely signal losses. The results show that our best-proposed FFT employing Trunc0 approximate adder with K =10 saves up to 35% of power dissipation compared to the FFT with the original radix-2 butterfly using the synthesis tool operators.

关键词： Measurement Fast Fourier transforms Circuits and systems Hardware Energy efficiency Topology Power dissipation

来源：评论

学校读者我要写书评

暂无评论

Saasport model: Exploring protocol portability, resource elasticity and microservice architecture in the efficient execution of iot applications 20

Saasport model: Exploring protocol portability, resource ela...

引用

20th International Conferences on WWW/Internet 2021 and Applied computing 2021

作者： da Silveira, Maria Gisele Flores da Silva Silveira, Wagner da Rosa Righi, Rodrigo da Costa, Cristiano André Griebler, Dalvan Três de Maio - RS Brazil Applied Computing Graduate Program Unisinos University Av. Unisinos 950 RS São Leopoldo Brazil Av. Ipiranga 6681 RS Porto Alegre Brazil

ISBN: (纸本)9789898704344

Despite the high growth of the Internet of Things and the multitude of applications that use the information generated, it is estimated that 90 % of these data are not yet fully used. This is because IoT systems are based on heterogeneous networks and devices with resource restrictions, which cannot execute significant processing. So one of the alternatives that have been addressed is the use of cloud applications, where the data can be appropriately processed, stored, and analyzed. In the cloud, applications can then employ resource elasticity and be developed in microservice architectures. In state-of-the-art, the main efforts to provide portability and efficient treatment of IoT applications are described. However, a platform that provides protocol portability, resource elasticity using microservices architecture for the efficient execution of IoT applications has not yet been implemented. In this context, this work presents SaaSport, which among its contributions, will allow the efficient treatment of data generated by IoT devices that use the MQTT and CoAP protocols. The final result of this work demonstrates that the model provides an efficient treatment of the data generated in IoT environments. © 20th International Conferences on WWW/Internet 2021 and Applied computing 2021.

关键词： Elasticity

来源：评论

学校读者我要写书评

暂无评论

Predicting User Preferences with Neural Network Learning to Rank Method 5

Predicting User Preferences with Neural Network Learning to ...

引用

5th IEEE International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2021

作者： Qomariyah, Nunung Nurul Fajar, Ahmad Nurul Bina Nusantara University Faculty Of Computing And Media Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program-Master Of Information Systems Management Information Systems Management Department Jakarta11480 Indonesia

ISBN: (纸本)9781665401968

User preference learning has been around for many years. This is a common problem arise in e-commerce system, where the companies need to understand their customers in order to sell the correct products to their target customers. The user preference is also needed in the movie domain area, as the film companies who produce the movie also need to understand how the customers value their movie products, whether the market like it or not. This can help them to predict the best components for the future movie. In order to produce the recommendation to the customer, we can show a list of item in a correct order, sorted from the most relevant/the most liked one to the most irrelevant item. In this paper, we utilize the Learning to Rank (LTR) approach from information retrieval domain area to learn the user preference in recommender system domain. We applied LTR with pairwise approach from the two most popular algorithms in this area, i.e. RankNet and LambdaRank, on 25, 345 user ratings from 5, 000 movie dataset and evaluate both algorithms. We used a Neural Network architecture as the learning mechanism. We also measuring the speed performance of the two algorithms. © 2021 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Data Logging and Non-invasive IoMT Approach for Rats Monitoring in Laboratory Experiments 37th

Data Logging and Non-invasive IoMT Approach for Rats Monit...

引用

37th International Conference on Advanced Information Networking and Applications, AINA 2023

作者： Barbosa, Bryan C. M. Garan, Steven A. Quintela, Barbara Melo Dantas, Mario R. Universidade Federal de Juiz de Fora Juiz de Fora Brazil Center for Research and Education in Aging University of California Berkeley and Lawrence Berkeley National Laboratory BerkeleyCA United States Computational Physiology and High Performance Computing Laboratory and Computer Science Department at Universidade Federal de Juiz de Fora Juiz de Fora Brazil Computer Science Graduate Program at Universidade Federal de Juiz de Fora Juiz de Fora Brazil

ISBN: (纸本)9783031290558

It is being observed that the use of Internet of Medical Things (IoMT) in health sciences research grows as the technology and miniaturization of devices occur. Those devices often times suffer from several issues such as: being invasive, lacking the ability to collect many signals concurrently and communication. The present work proposes an approach to the use of an ultra-small IoMT device to fulfill the functions of a bio-signals data collector, a mathematical models processor, a data transmitter-receptor through the network, and a mechanical actuators controller. Our test environment was conceived to be used in animal models. This is an ongoing project from which partial results indicate that, when functioning, the device will use real-time data for monitoring bio-signals and helping with decision-making as it interacts with the organism. The data collection is going to be made through low-cost non-invasive sensors. Therefore, it can favor installation, maintenance, access, and promote a better quality of life for the user. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Bayesian artificial brain with ChatGPT

arXiv

引用

arXiv 2023年

作者： Krohling, Renato A. Ufes - Federal University of Espírito Santo Labcin - Nature-Inspired Computing Lab Ppgi - Graduate Program in Informatics Av. Fernando Ferrari 514 Prédio CT X ES VitóriaCEP 29060-270 Brazil

This paper aims to investigate the mathematical problem-solving capabilities of Chat Generative Pre-Trained Transformer (ChatGPT) in case of Bayesian reasoning. The study draws inspiration from Zhu & Gigerenzer's research in 2006, which posed the question: Can children reason the Bayesian way? In the pursuit of answering this question, a set of 10 Bayesian reasoning problems were presented. The results of their work revealed that children's ability to reason effectively using Bayesian principles is contingent upon a well-structured information representation. In this paper, we present the same set of 10 Bayesian reasoning problems to ChatGPT. Remarkably, the results demonstrate that ChatGPT provides the right solutions to all problems. © 2023, CC BY.

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：