检索结果-内蒙古大学图书馆

2nd International Conference on Digital Futures and Transformative Technologies, ICoDT2 2022

作者： Hina, Iram Shaukat, Arslan Akram, Muhammad Usman National University of Sciences and Technology College of EME Dept of Computer and Software Engineering Islamabad Pakistan

ISBN: (纸本)9781665498197

Emotions are an essential part of immaculate communication. The purpose of this research work is to classify six basic emotions of humans namely anger, disgust, fear, happiness, sadness and surprise. In proposed method a sequential deep convolutional neural network is proposed for audio and visual modality. Audio classification is performed via fine-tuning of a pre-trained AlexNet model whereas, visual classification is performed with a hybrid deep network containing CNN and LSTM. Decision level and score level fusion have been implemented for multimodalities. SVM, random forest, K-NN, and logistic regression classifiers were being used for classifying emotion for fused audio-visual data. Experiments have been performed on RML and BAUM-1s dataset with LOSO and LOSGO cross validation techniques respectively. Recognition rates were extremely positive which shows the validity of the proposed methodology. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Faceswap Deepfakes Detection using Novel Multi-directional Hexadecimal Feature Descriptor 19

Faceswap Deepfakes Detection using Novel Multi-directional H...

引用

19th International Bhurban Conference on Applied Sciences and Technology, IBCAST 2022

作者： Qurat-Ul-Ain Javed, Ali Mahmood Malik, Khalid University of Engineering and Technology Dept. of Computer Science Taxila Pakistan University of Engineering and Technology Dept. of Software Engineering Taxila Pakistan Oakland University Dept. of Computer Science and Engineering United States

ISBN: (数字)9781665460514

ISBN: (纸本)9781665460514

With the growing number of sophisticated deep learning algorithms and fake video generation applications, it is now possible to create highly realistic deepfake videos. Faceswap is the most commonly employed deepfakes approach, which is challenging to detect due to variations in the facial skin tone, illumination conditions, presence of accessories like glasses on the face, compression artifacts, etc. Existing local texture descriptors have achieved better performance on face recognition applications;however, they compute only the limited directional information while ignoring the magnitude details. This motivated us to develop a robust local texture descriptor to extract more directional and magnitude details from the adjacent pixels to effectively represent the video frames. For this purpose, we proposed a robust multi-directional hexadecimal feature descriptor (MDHFD) by combining the local hexadecimal pattern (LHeXDP) and Local Adjacent Neighborhood Magnitude Pattern (LANMP). LHeXDP calculates the orientation-based pattern by computing 1st- and 2nd-order derivatives at 0°, 45°, 90°, and 135° angles from each center pixel. LANMP computes the magnitude information from each central pixel to its adjacent pixels in horizontal, vertical, diagonal, and diagonal-back directions. Histograms of both the LHeXDP and LANMP are fused to compute a multi-directional feature vector, which is used to train a support vector machine to classify between the original or faceswap deepfakes video. We measured the performance of our system on the challenging faceswap subset of a diverse and large-scale Face Forensic++ and World Leaders datasets. Experimental results illustrate that the proposed method outperforms state-of-art methods for the detection of faceswap deepfakes. © 2022 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

CapsiScan: Autonomous Robotic System for Monitoring and Managing Greenhouse-Based Capsicum Farms 5

CapsiScan: Autonomous Robotic System for Monitoring and Mana...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Jayakody, E.R.T. Rabel, W.T.T. Estrop, R.D.V. Herath, K.G.L.P. Harshanath, S.M.B. Abeygunawardhana, Pradeep K. W. Sri Lanka Institute Information Technology Dept. of Computer Systems Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. of Software Engineering Colombo Sri Lanka

ISBN: (纸本)9798350358131

The automation of processes in greenhouses provides a significant advantage to the agricultural sector. Due to the rapid growth of the population, increasing demand for food and labor shortage make the autonomous monitoring and management of agricultural work more important. Capsicum is a largely consumed vegetable in South Asia, which can be efficiently grown in greenhouses. Although there are many capsicum farms, they lack quality and efficient production to match the increasing demand. This paper proposes a robotic system for use in capsicum greenhouses that can navigate and monitor the plants to identify diseases, track the yield, and take remediation actions. The robot navigates to each plant in the greenhouse autonomously by using the SLAM approach with the use of laser range sensor data. The 4 DoF robotic arm of the robot has a camera and a sprayer attached to its end to investigate plants and spray remedies to diseased plants. The robotic arm moves around the plant to capture the images to detect deceases and count the pods to estimate the yield. The sprayer of the robot sprays remedies precisely to targeted plants to control pests and diseases. The system was successfully implemented and tested with the proposed functions. © 2023 IEEE.

关键词： Greenhouses

来源：评论

学校读者我要写书评

暂无评论

Role-Specific Physiological Responses and Quality of Experience in Collaborative Virtual Reality Tasks: A Comparative Study of Leaders and Followers

Role-Specific Physiological Responses and Quality of Experie...

引用

Virtual Reality (ICVR), IEEE International Conference on

作者： Bhagyabati Moharana Conor Keighrey Niall Murray Dept of Computer and Software Engineering Technological University of the Shannon Midlands Ireland

ISBN: (数字)9798350364231

ISBN: (纸本)9798350364248

The emergence of Collaborative Virtual Reality (CVR) technology has transformed team-based interactions across diverse fields, offering immersive and interactive environments that enhance collaborative efforts. However, a critical gap remains in understanding the Quality of Experience (QoE) from a task role-specific perspective within these environments. This study addresses this gap by evaluating the QoE differences between leaders and followers in CVR settings, using both subjective assessments and objective physiological measures. The research employs advanced biosensors, including eye-tracking and physiological responses, to examine how distinct roles influence cognitive load, emotional states, and overall user satisfaction. Participants engaged in a collaborative 'pick and place' task within a VR environment, with data collected on electrodermal activity (EDA), heart rate (HR), blood volume pulse (BVP), inter-beat interval (IBI), skin temperature, and pupil dilation (PD). The NASA Task Load Index (NASA-TLX) was also used to measure perceived workload. Findings reveal significant differences in physiological responses between leaders and followers, with leaders experiencing higher cognitive and temporal demands. The results suggest that role-specific QoE evaluations can inform the design of more equitable and effective CVR systems, enhancing user satisfaction and collaboration outcomes. This study advances the field by integrating multimodal data acquisition and providing insights into CVR environments for diverse collaborative roles.

关键词： Temperature measurement Heart rate Collaboration Virtual environments Particle measurements Physiology Skin Quality of experience Pupils Blood

来源：评论

学校读者我要写书评

暂无评论

Automated, Unsupervised, and Auto-parameterized Inference of Data Patterns and Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Qin, Qiaolin Li, Heng Merlo, Ettore Lamothe, Maxime Dept. of Computer and Software Engineering Polytechnique Montreal Montreal Canada

With the advent of data-centric and machine learning (ML) systems, data quality is playing an increasingly critical role for ensuring the overall quality of software systems. Data preparation, an essential step towards high data quality, is known to be a highly effort-intensive process. Although prior studies have dealt with one of the most impacting issues, data pattern violations, these studies usually require data-specific configurations (i.e., parameterized) or use carefully curated data as learning examples (i.e., supervised), relying on domain knowledge and deep understanding of the data, or demanding significant manual effort. In this paper, we introduce RIOLU: Regex Inferencer autO-parameterized Learning with Uncleaned data. RIOLU is fully automated, automatically parameterized, and does not need labeled samples. RIOLU can generate precise patterns from datasets in various domains, with a high F1 score of 97.2%, exceeding the state-of-the-art baseline. In addition, according to our experiment on five datasets with anomalies, RIOLU can automatically estimate a data column’s error rate, draw normal patterns, and predict anomalies from unlabeled data with higher performance (up to 800.4% improvement in terms of F1) than the state-of-the-art baseline, even outperforming ChatGPT in terms of both accuracy (12.3% higher F1) and efficiency (10% less inference time). A variant of RIOLU, with user guidance, can further boost its precision, with up to 37.4% improvement in terms of F1. Our evaluation in an industrial setting further demonstrates the practical benefits of *** Codes 68P01 © 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

Application to Enhance the Programming Knowledge of Children 6

Application to Enhance the Programming Knowledge of Children

引用

6th International Conference on Advancements in Computing, ICAC 2024

作者： Dissanayake, Anuga Lakpriya, Vishwa Sanjeevan, Mahendran Fahmi, Ahamed Siriwardana, Samanthi E.R. Samaraweera, Mihiri Sri Lanka Institute of Information Technology Dept. of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept. of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798331517878

This proposal outlines the development of a comprehensive educational platform aimed at bridging the Information Technology knowledge gap among Tamil-speaking students in Sri Lanka. The platform is designed to enhance programming skills through personalized quizzes, hands-on projects, and adaptive learning models. The application focuses on two primary components: the first component emphasizes project-based learning and assessments, leveraging advanced Artificial Intelligence models for generating educational content. This model is combined with Retrieval-Augmented Generation, which retrieves relevant external information to refine and tailor the educational content to each student's needs. This component keeps students engaged and challenged at appropriate levels, promoting deeper understanding and practical Information Technology skills. The second component involves a Level-based IT Fundamental Knowledge Evaluation system, which incorporates machine learning algorithms to predict student performance, recommend customized learning paths, and assess overall technical knowledge. The platform also integrates the OpenAI Application Programming Interface, which provides real-time Tamil translation, making the content more accessible to the target demographic. The platform empowers educators to better address individual student needs with real-time feedback and tailored experiences. Its innovative approach enhances Information Technology education, equipping Sri Lankan students with essential programming skills to succeed globally. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design of a Smart and Green Industry 4.0 Architecture 24

Design of a Smart and Green Industry 4.0 Architecture

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Hamdan, Khaled Kazar, Okba College of It Uaeu Dept. of Computer Science and Software Engineering United Arab Emirates College of It Uaeu Dept. of Information Systems & Security United Arab Emirates

ISBN: (纸本)9798350384307

The industrial sector has entered a phase of profound change which sees digital technologies being integrated into the heart of industrial processes. This fourth industrial era gives birth to a new generation of factory called 'Digital Factory', 'Industry 4.0'. This industrial change is the result of the integration of new digital technologies into manufacturing processes and the optimization of energy consumption. The commitment to the environment is also a key and success factor of Industry 4.0 and green in particular the reduction of carbon emissions and pollution. This is how smart green industry try to take in charge the problem of energy consumption and to reduce the Co2 pollution. The goal of this paper is to present the new model of smart green industry using distributed artificial intelligence based on multi-agent system (MAS). The motivation to use the intelligent approach based on MAS is based on the similarity between the fundamental concepts of the cyber-physical system and those contained in the architecture and operation of MAS such as communication, coordination, decision and cooperation. © 2023 IEEE.

关键词： environmental impact Industry 4.0 smart and green Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Heuristic approaches for hiding sensitive frequent itemsets in uncertain databases 5

Heuristic approaches for hiding sensitive frequent itemsets ...

引用

5th International Conference on Pattern Analysis and Intelligent Systems, PAIS 2023

作者： Lefkir, Mira Nouioua, Farid Fournier-Viger, Phillipe University Mohamed El Bachir El Ibrahimi of Bordj Bou Arreridj BBA Dept. of Computer Science Algeria Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350381450

Pattern mining is a core objective within data mining, involving the detection of frequent itemsets (collections of values) within databases. This process serves to extract valuable insights from the data, facilitating informed decision-making. In recent times, a range of algorithms has emerged to adapt this task to the realm of uncertain *** has a wide range of applications, such as analyzing medical data to identify correlated symptoms based on their existential probabilities. However, pattern mining algorithms also pose the risk of revealing sensitive information. As far as we know, there is no existing solution that addresses the inadvertent disclosure of sensitive itemsets when pattern mining algorithms are employed on uncertain databases. This paper addresses this problem by proposing three heuristic approaches, which ensure that sensitive expected frequent itemsets are not discovered while minimizing undesirable side effects for other itemsets. The first heuristic approach (called aggregate) deletes some transactions from an uncertain database. The second approach (named disaggregate) removes some selected items from each transaction. And the third approach (called the hybrid approach) combines the two previous approaches, and deletes some selected items from some selected transactions. An experimental evaluation is presented to assess and compare the effectiveness of the three approaches. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Sankalpa - Interactive Digital Learning Platform to Enrich Students with Special Needs 5

Sankalpa - Interactive Digital Learning Platform to Enrich S...

引用

5th International Conference on Advancements in Computing, ICAC 2023

作者： Basnayaka, A.I. Epitakaduwa, E.K.G.D. Jayawardena, C.P.U. Zoysa, Ashan Dharmakeerthi, Uditha Jayawardena, Sanath Sri Lanka Institute of Information Technology Dept of Computer Science and Software Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept of Computer Science and Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Dept of Computer Science and Network Engineering Malabe Sri Lanka

ISBN: (纸本)9798350358131

The term special needs mean the special educational needs that the students who suffer from learning disabilities must have due to several reasons. Learning impairment is a condition of the neurological system that impairs one's capacity to efficiently acquire and process knowledge. Failures in diagnosing the people with learning disabilities have been repeatedly highlighted and remain unpopular among people in the developing countries like Sir Lanka. Dyscalculia (difficulties in math), dysgraphia (difficulties in writing) and dyslexia (difficulties in reading) can be considered as some of the major learning disability issues. The 'mobile application based' solution 'Sankalpa Math Master' has been created to offer a game based all-in-one solution including screening, and intervention to identify one of the above-mentioned learning disabilities called 'Dyscalculia'. Dyscalculia is generally distinguished by challenges in learning math, including organizing problems, multi-step calculations, transposing numbers, distinguishing directions, and understanding mathematical signs, leading to confusion with basic operations and facts. The provided solution has been accurate with the use of machine learning and deep learning techniques. In the process of screening with the use of Support Vector Machine (SVM) machine learning algorithm 99.77% of accuracy level has been obtained. The skill level prediction process has acquired an accuracy level of 97% with the use of Random Forest machine learning algorithm. Sri Lankan traditional education system will be vastly benefited by the high level of accuracy in screening, skill predicting, and other game and voice chat-based activities. The students with special needs will gain more effective and personalized learning experience which will improve their learning abilities and help to close the technology gap in education. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Harnessing LLMs for VQA: A Prompted Benchmark with Animate/Inanimate Keywords 15

Harnessing LLMs for VQA: A Prompted Benchmark with Animate/I...

引用

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Lee, Chanwoo Lee, Hyunjeong Kim, Minsang Kim, Hyun Jang, Haneol Park, Cheoneum Seoul Woman's University Dept. of Software Convergence Seoul Korea Republic of Hanbat National University Dept. of Computer Engineering Daejeon Korea Republic of Korea University Dept. of Computer Science and Engineering Seoul Korea Republic of Electronics and Telecommunications Research Institute Superintelligence Creative Research Lab. Daejeon Korea Republic of

ISBN: (纸本)9798350364637

In the field of NLP, Large Language Models (LLMs) have recently achieved significant advancements, leading to the development of various benchmarks for their evaluation. Along-side NLP, Vision Language Models (VLMs) have also VLM have also significantly progressed, similar to LLMs. However, benchmarks for VLMs are still relatively underdeveloped compared to those for NLP, and their construction is often costly. In this work, we propose an automatically generated benchmark for evaluating VLMs based on LLMs and conduct a visual question answering task to assess this benchmark. The benchmark includes multiple-choice questions that not only distinguish between animate and inanimate objects but also generate these distinctions automatically, along with entity and object information within images. We evaluate the performance of open VLM using the generated multiple-choice questions, demonstrating the model's capabilities and the significance of the automatically generated benchmark. Finally, we discuss the necessity and future directions for benchmark research in this area. © 2024 IEEE.

关键词： Visual languages

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：