检索结果-内蒙古大学图书馆

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

SpikingSoft: A Spiking Neuron Controller for Bio-inspired Locomotion with Soft Snake Robots

arXiv

引用

arXiv 2025年

作者： Zhang, Chuhan Wang, Cong Pan, Wei Della Santina, Cosimo The Department of Cognitive Robotics Faculty of Mechanical Engineering Delft University of Technology Delft Netherlands The Department of Computer Science The University of Manchester Manchester United Kingdom

Inspired by the dynamic coupling of moto-neurons and physical elasticity in animals, this work explores the possibility of generating locomotion gaits by utilizing physical oscillations in a soft snake by means of a low-level spiking neural mechanism. To achieve this goal, we introduce the Double Threshold Spiking neuron model with adjustable thresholds to generate varied output patterns. This neuron model can excite the natural dynamics of soft robotic snakes, and it enables distinct movements, such as turning or moving forward, by simply altering the neural thresholds. Finally, we demonstrate that our approach, termed SpikingSoft, naturally pairs and integrates with reinforcement learning. The high-level agent only needs to adjust the two thresholds to generate complex movement patterns, thus strongly simplifying the learning of reactive locomotion. Simulation results demonstrate that the proposed architecture significantly enhances the performance of the soft snake robot, enabling it to achieve target objectives with a 21.6% increase in success rate, a 29% reduction in time to reach the target, and smoother movements compared to the vanilla reinforcement learning controllers or Central Pattern Generator controller acting in torque space. Copyright © 2025, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Hybrid Model Approaches Toward Movie Recommendation Systems and Their Comparisons

Hybrid Model Approaches Toward Movie Recommendation Systems ...

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Parikh, Jolly Antony, Saji M. Jain, Rachna Chawla, Naman Mishra, Ashish de Albuquerque, Victor Hugo C. Neto, Aloísio Vieira Lira Department of Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Electronics and Communication Engineering Bharati Vidyapeeth’s College of Engineering New Delhi India Department of Information Technology Bhagwan Parshuram Institute of Technology New Delhi India Department of Computer Science and Engineering Bhagwan Parshuram Institute of Technology New Delhi India Department of CSE Gyan Ganga Institute of Technology and Sciences Madhya Pradesh Jabalpur India Federal Institute of Education Science and Technology of Ceara Fortaleza Brazil Federal University of Ceará Fortaleza Ceará Fortaleza Brazil Graduation Program in Telecommunication Engineering Federal University of Ceará Fortaleza Ceará Fortaleza Brazil

ISBN: (纸本)9789819965465

In the contemporary digital era, individuals face an overwhelming challenge of searching for personalized content from a seemingly infinite pool of available options such as books, videos, articles, and movies. Simultaneously, digital content providers strive to attract and retain as many users on their platforms as possible for extended periods. This has led to the evolution of recommender systems, which aim to enhance user engagement and satisfaction by recommending content based on their preferences and interests. These systems employ sophisticated algorithms and data mining techniques to analyze user behavior and feedback, enabling them to make personalized recommendations to users, thereby improving their overall experience. In this paper, an investigation is conducted in which different models in machine learning with their combinations are evaluated to evaluate which model could give the best accuracy with actual ratings given by users. The models used are Lasso regression, XGBoost, K-nearest neighbor, surprise baseline only, SVD, SVDpp, and their combinations. The proposed ensembled model of XGBoost + surprise baseline + surprise KNN baseline + SVD + SVDpp, with the minimum value of RMSE as 1.111410 and MAPE value as 39.261054, is our best model and can serve as a reference for any future recommender system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

SPOC: A Scale for Potential Operation Consequences of UI Interactions

SPOC: A Scale for Potential Operation Consequences of UI Int...

引用

Artificial Intelligence x Multimedia (AIxMM), Conference on

作者： Florian Eggenkemper Teresa Rehers Jana Swerew Robert Mertens Centre for Cognitive Science & Institute of Psychology Technical University of Darmstadt Germany Dept. of Computer Science and Engineering HSW University of Applied Sciences Germany BHH University of Applied Sciences Hamburg Germany

ISBN: (数字)9798350390971

ISBN: (纸本)9798350390988

Many approaches rely on a semantic understanding of screen contents to perform further actions on this information. This is relevant for test automation, robotic process automation, or context based assistive tasks (digital agents). Most of these approaches just analyze basic information about user interface elements but fall short in predicting the consequences of single user interface actions. Possible consequences of UI actions include (permanent) data loss, effects on the reputation of people (e.g. posting on social media), or other irreversible consequences. This makes it necessary to identify and analyze the potential consequences of operation on user interfaces to prevent automatic systems from making possibly fatal mistakes with a high impact on the human user. This paper presents a Scale for Potential Operation Consequences (SPOC) and demonstrates an automatic rating system based on Large Language Models (LLMs), that can be performed locally or in cloud implementations. The LLM-based ratings were tested against a human control group based on a questionnaire (n=35), and proved to perform as well as their human counterparts, making SPOC a robust and automation-friendly rating system for user interface element actions.

关键词： Intelligent automation Social networking (online) Large language models Semantics User interfaces

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis and Remediation of Insecure Direct Object References (IDOR) Vulnerabilities in Android APIs

Comprehensive Analysis and Remediation of Insecure Direct Ob...

引用

Cryptography, Informatics, and Cybersecurity (ICoCICs), IEEE International Conference on

作者： Semi Yulianto Roni Reza Abdullah Benfano Soewito Computer Science Department Binus Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Faculty of Informatics Engineering National Institute of Science and Technology Jakarta Indonesia Computer Science Department Binus Graduate Program. Master of Computer Science Bina Nusantara University Jakarta Indonesia

The escalating visibility of secure direct object reference (IDOR) vulnerabilities in API security, as indicated in the compilation of OWASP Top 10 API Security Risks, highlights a noteworthy peril to sensitive data. This study explores IDOR vulnerabilities found within Android APIs, intending to clarify their inception while evaluating their implications for application security. This study combined the qualitative and quantitative approaches. Insights were obtained from an actual penetration test on an Android app into the primary reasons for IDOR vulnerabilities, underscoring insufficient input validation and weak authorization methods. We stress the frequent occurrence of IDOR vulnerabilities in the OWASP Top 10 API vulnerability list, highlighting the necessity to prioritize them in security evaluations. There are mitigation recommendations available for developers, which recognize its limitations involving a possibly small and homogeneous selection of tested Android applications, the testing environment that could cause some inaccuracies, and the impact of time constraints. Additionally, the study noted insufficient threat modeling and root cause analysis, affecting its generalizability and real-world relevance. However, comprehending and controlling IDOR dangers can enhance Android API security, protect user data, and bolster application resilience.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Architecture for Passive Rootkit Detection with Data Enrichment

Multi-agent Architecture for Passive Rootkit Detection with...

引用

International Conference on computer science, Electronics, and Industrial engineering, CSEI 2022

作者： Trinks, Maickel Gondim, João Albuquerque, Robson Professional Post-Graduate Program in Electrical Engineering - PPEE - Department of Electrical Engineering University of Brasília DF Brasília Brazil Department of Computer Science Universidade de Brasília DF Brasília Brazil

ISBN: (纸本)9783031305917

The added value of the information transmitted in a cybernetic environment has resulted in a sophisticated malicious actions scenario aimed at data exfiltration. In situations with advanced actors, like APTs, such actions use obfuscation techniques of harmful activities as persistence assurance on strategic targets. The MADEX and NERD architectures proposed flow analysis solutions to detect rootkits that hide network traffic;however, it presents some operational cost, either in traffic volume or due to lack of aggregated information. In that regard, this work changes and improves user flow analysis techniques to eliminate impacts on network traffic, with data enrichment on local and remote bases, detection of domains consulted by rootkits and aggregation of information to generate threat intelligence, while maintaining high performance. The results show the possibility of aggregating information to data flows used by rootkits in order to have effective cyber defense actions against cybernetic threats without major impacts on the existing network infrastructure. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Behavior Profiling of Role-Playing Game Players Based on Heuristic Event Log Mining 25th

Behavior Profiling of Role-Playing Game Players Based on Heu...

引用

25th International computer Symposium on New Trends in computer Technologies and Applications, ICS 2022

作者： Lin, Jason Tsai, Chia-Wei Yang, Chun-Wei Lafortune, Elie Department of Computer Science and Engineering National Chung Hsing University Taichung40227 Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung404 Taiwan Master Program for Digital Health Innovation College of Humanities and Sciences China Medical University Taichung406040 Taiwan

ISBN: (纸本)9789811995811

In this paper, we propose a novel player behavior model called the action priority model (APM) for representing player action behaviors. A play log is stored based on the game grammar under analysis, and heuristic filtering rules are applied to eliminate uninteresting events. The proposed model uses sequences and tendencies of event types as the main mining criteria to extract significant player action behaviors. Action sequences reflect the interdependencies of different actions and how a player may use their insights about the game rules to form a (hidden) action priority list (APL) with respect to action types. By mining for significant events from play logs, we aim to produce the APM and APL for different players. In experiments, the fuzzy miner tool was used to analyze a few event logs for the World of Warcraft game to obtain some noticeable discoveries about the structural and timing patterns of effective players. Experimental results show that two players in the same class with similar contributions to encounters will have a similar mined APM and may not have a minimal delay in the timing of actions. Players with a high contribution to an encounter will have an APM like a simulated optimal player along with large thickness edges in the APM to indicate a significant routine of actions. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Causal net Fuzzy miner Player behavior

来源：评论

学校读者我要写书评

暂无评论

SpikingSoft: A Spiking Neuron Controller for Bio-inspired Locomotion with Soft Snake Robots

SpikingSoft: A Spiking Neuron Controller for Bio-inspired Lo...

引用

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Chuhan Zhang Cong Wang Wei Pan Cosimo Della Santina Department of Cognitive Robotics Faculty of Mechanical Engineering Delft University of Technology Delft Netherlands Department of Computer Science The University of Manchester Manchester United Kingdom

ISBN: (数字)9798331520205

ISBN: (纸本)9798331520212

关键词： Torque Deformation Simulation Neurons Snake robots Reinforcement learning Soft robotics Turning Generators Oscillators

来源：评论

学校读者我要写书评

暂无评论

Instance Regularization for Discriminative Language Model Pre-training

Instance Regularization for Discriminative Language Model Pr...

引用

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

作者： Zhang, Zhuosheng Zhao, Hai Zhou, Ming 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 Langboat Technology

Discriminative pre-trained language models (PrLMs) can be generalized as denoising auto-encoders that work with two procedures, ennoising and denoising. First, an ennoising process corrupts texts with arbitrary noising functions to construct training instances. Then, a denoising language model is trained to restore the corrupted tokens. Existing studies have made progress by optimizing independent strategies of either ennoising or denosing. They treat training instances equally throughout the training process, with little attention on the individual contribution of those instances. To model explicit signals of instance contribution, this work proposes to estimate the complexity of restoring the original sentences from corrupted ones in language model pretraining. The estimations involve the corruption degree in the ennoising data construction process and the prediction confidence in the denoising counterpart. Experimental results on natural language understanding and reading comprehension benchmarks show that our approach improves pre-training efficiency, effectiveness, and robustness. Code is publicly available at https://***/cooelf/InstanceReg. © 2022 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Hybrid Classical-Quantum Optimization for Ensemble Learning 9

Hybrid Classical-Quantum Optimization for Ensemble Learning

引用

9th International Conference on Advanced Informatics: Concepts, Theory and Applications, ICAICTA 2022

作者： Yulianti, Lenny Putri Santoso, Judhi Trisetyarso, Agung Surendro, Kridanto Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia Bina Nusantara University Program - Computer Science Bandung Indonesia

ISBN: (数字)9781665456685

ISBN: (纸本)9781665456685

Ensemble learning has gained attention due to its ability to improve predictive performance in classification and regression problems. However, there are several issues related to optimizing accuracy, diversity, and efficiency simultaneously in the ensemble learning process. Existing studies mostly focus on one or two of them, or focus on all three but only on the specific process of ensemble learning. Besides, the quantum approach has been expected to accelerate the optimization process while maintaining accuracy. The contribution of this study is to design a hybrid classical-quantum methodology for optimizing ensemble learning in a holistic way. This methodology combines classical (i.e. clustering, improved evaluation measures, and generalized weighted ensemble with internally tuned hyperparameters) and quantum (i.e. quantum annealing) approaches, and this methodology is analyzed to provide more optimal results. © 2022 IEEE.

关键词： Learning systems

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：