检索结果-内蒙古大学图书馆

A computer program FOR SYNTHESIS OF DECOUPLED MULTIVARIABLE FEEDBACK SYSTEMS

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 1969年第6期AC14卷 652-+页

作者： GILBERT, EG PIVNICHNY, JR Computer Information and Control Engineering Program University of Michigan Ann Arbor MI USA IBM Corporation Endicott NY USA

Recently Gilbert [6] obtained general solution results on the decoupling of multivariable systems by state feedback. This paper presents a general-purpose computer program which carries out all of the calculations necessary for reducing these results to a useful synthesis procedure. The program is described in general terms and several examples of its application are given.

关键词： State feedback MIMO Automatic control Military computing Application software Sufficient conditions Distillation equipment Terminology

来源：评论

学校读者我要写书评

暂无评论

Intelligent Tutoring System: A Pedagogical Model Approach Based on Deep Reinforcement Learning

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第4期52卷 1196-1212页

作者： Alshaikh, Fatema Hewahi, Nabil Computing and Information Science program University of Bahrain Bahrain Computer science working University of Bahrain Bahrain

The primary goals of research in the fields of Artificial Intelligence (AI) and Machine Learning (ML) are to develop an autonomous agent that can perform tasks or make decisions without human intervention. Deep Reinforcement Learning (DRL) is a machine learning technique employed in Intelligent Tutoring Systems (ITS). Deep reinforcement learning is the integration of Reinforcement Learning (RL) and Deep learning (DL) techniques. In ITS, DRL provides students with individualized learning experiences based on their learning styles and preferences. This work uses a deep reinforcement learning architecture to build a pedagogical model for ITS. We present four different models. The first model is based on the Deep Q-Network (DQN) structure. The second and third models (Double DQN and Dueling DQN) are extensions of the DQN algorithm and have been further developed to address some limitations of the DQN approach. Double DQN solves the problem of overestimation of Q-values, while Dueling DQN improves the representation of the value function. The last proposed model is a hybrid model that combines the standard DQN with a learning classifier system based on Genetic Algorithms (GA). The findings of the study indicate that both Double DQN and Dueling DQN showed complete data efficiency with 100% accuracy, 1.0 F1 score, and 1.0 precision at the highest training level of 1000 episodes and 10 steps, whereas DQN performed fairly but was outperformed by advanced techniques at the same configuration level. The standard DQN achieves a precision of 0.975, an F1 score of 0.987, and an accuracy of 98%. On the other hand, the hybrid approach, which combines GA with DQN, consistently performed worse than the other three individual models in all training setups. © (2025), (International Association of Engineers). All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

THE REAL WORLD COMPUTING program - MITIS NEXT computer RESEARCH INITIATIVE

引用

SCIENCE 1992年第5082期258卷 581-582页

作者： YONEZAWA, A Professor of computer science at University of Tokyo Tokyo 113 Japan and a member of the Evaluation and Promotion Committee for the RWC Program

Describes the Real World Computing program (RWC), a new national research program funded by Japan's Ministry of International Trade and Industry (MITI) at a level of $500 million over the next 10 years. Replacing the Fifth Generation computer Project; Emphasis on technologies that match the flexibilities of human information processing capabilities; Novel functions for applications; Neural network systems; Optical computing systems.

关键词： Collaboration Information processing Funding Operating systems Industrial research Technology Subcontractors Patents

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impacts of Dynamic Game Balancing in a Survival Roguelike Chess Game

Analyzing the Impacts of Dynamic Game Balancing in a Surviva...

引用

2025 International Conference on Advancement in Data Science, E-learning and Information System, ICADEIS 2025

作者： Mario Arifin, Yulyani Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program - Doctor of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331513320

This research investigates the novel application of Dynamic Game Balancing (DGB) techniques in the context of a hybrid chess-survival roguelike game, a unique combination of genres not widely explored in previous studies. The study addresses two primary research questions: the identification of suitable DGB techniques for these genres and the enhancement of user experience through DGB. A game prototype was developed using Unity, where players control a chess knight in a turn-based system, facing increasingly challenging enemy pieces. The DGB system dynamically adjusts the game's difficulty based on player performance, utilizing various inputs such as damage received or dealt, health points, powerup usage, and decision speed. Preliminary results from 14 beta-testers show overall positive feedback, with players reporting higher engagement and enjoyment due to the seamless difficulty adjustments, as reflected by the high mean scores from surveys like the User Experience Questionnaire (UEQ). This research fills a gap in the literature by demonstrating the feasibility and benefits of integrating DGB in a chess-survival roguelike setting. These findings highlight the potential for DGB to significantly improve player experience in hybrid game genres, suggesting that its application can create more adaptive and immersive gaming environments in various other genres as well. © 2025 IEEE.

关键词： Game design

来源：评论

学校读者我要写书评

暂无评论

Edge-IoTDistilBERT: Fine-Tuning DistilBERT for Multi-Class Classification of Network Packet Attacks

Edge-IoTDistilBERT: Fine-Tuning DistilBERT for Multi-Class C...

引用

2025 International Conference on Advancement in Data Science, E-learning and Information System, ICADEIS 2025

作者： Setiawan, Valentino Soewito, Benfano Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331513320

This exponential proliferation of IoT devices is creating an ever-growing demand for efficient cybersecurity solutions in resource-constrained environments. In this study, we propose Edge-IoTDistilBERT, a fine-tuned DistilBERT model, intended for the multi-class classification of network packet attacks within IoT ecosystems. Our proposed model was trained on the Edge-IIoT dataset, representative of all traffic classes and attack variants with high accuracy of up to 99.99%, outperforming state-of-the-art solutions. The new preprocessing pipeline of PCAP to text would transform the network traffic to a textual form allowing the model to learn the pattern in the dataset and making it able to generalize its content. Our fine-tuned model show a robust result on imbalanced dataset with two diffrent splits namely 80-20 and 70-30. The result shown by Edge-IoTDistilBERT place this model as a feasible effective cybersecurity solution for IoT networks, offering a good trade-off between high performance and resource constraints linked to edge devices. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabel 12-Lead EKG Anomaly Detection 59

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabe...

引用

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Detore, Ian Samsundar, John Davis, Cleon Johns Hopkins University Electrical and Computer Engineering Program BaltimoreMD United States Johns Hopkins University Electrical and Computer Engineering Program LaurelMD United States

ISBN: (纸本)9798331513269

This study introduces two novel hybrid machine-learning architectures for multilabel anomaly detection in electrocardiograms (EKGs): a 1D modified ResNet combined with a transformer encoder and an equivalent 2D ResNet-Transformer hybrid. This work is among the first to utilize two separate CNN-transformer architectures tailored specifically for temporal and spatial features in multilabel EKG data. Our models address the challenges of imbalanced data and multilabel classification by leveraging the PTB-XL dataset, containing over 21,000 annotated samples across five diagnostic superclasses, namely myocardial infarction, conduction disturbances, hypertrophy, ST-T wave changes, and normal EKGs. We applied advanced data augmentation techniques to mitigate class imbalance, including the Multilabel Synthetic Minority Over-Sampling Technique (ML-SMOTE). Additionally, we employed digital signal processing to denoise the EKG signals and convert time-series data into time-frequency representations for 2D modeling. Experimental results demonstrate the effectiveness of our approach, with the 1D model achieving an area under the curve (AUC) of 91.5% and the 2D model achieving an AUC of 87.2%. These findings demonstrate the potential of specialized architectures for comprehensive multilabel EKG anomaly detection. © 2025 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Cognitive Assessment of Students Using Testing Instruments on computer Networks Courses in Informatics and computer Engineering Education Study program at UNJ 8

Cognitive Assessment of Students Using Testing Instruments o...

引用

8th International Conference on Education and Technology, ICET 2022

作者： Duskarnaen, Muhammad Ficky Sastrawijaya, Yuliatri Ajie, Hamidillah Arrazi, Muhammad Fakhruddin State University of Jakarta Informatics and Computer Engineering Education Study Program Jakarta Indonesia

ISBN: (数字)9781665492140

ISBN: (纸本)9781665492140

This study aims to design an assessment instrument to assess students' cognition in computer networking lessons. The design and design of the test instrument followed the ADDIE model, from the analysis stage to determine student targets and characteristics, then the design stage, determining learning objectives, learning material design, and question grids, at this stage the number of Subject Matter Experts (SME) was also determined as many as 6 people, for 6 Subject Matter Experts (SME), the minimum acceptable Content Validation Ratio (CVR) is 0.99, while the Content Validation Index (CVI) is 0.83. At the development stage, 81 items were designed as a draft assessment instrument. At the implementation stage, the Subject Matter Experts (SME) assessed each item on the draft assessment instrument. This study uses a quantitative content validity approach from the Lawshe model with a 3-point scale as follows: essential, useful but not necessary, and non-essential. Each Subject Matter Expert (SME) was given an instrument to assess each item in the test instrument. The Subject Matter Expert (SME) will determine whether an important question is given, normal or normal, or whether the question is not important given to students. At the evaluation stage, the Subject Matter Expert (SME) assessment of the draft test instrument will be compiled and the Content Validation Ratio (CVR) value and the Content Validation Index (CVI) value calculated to determine content validity. © 2022 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

From light sensing to adaptive learning:hafnium diselenide reconfigurable memcapacitive devices in neuromorphic computing

引用

Light(Science & Applications) 2025年第1期14卷 215-226页

作者： Bashayr Alqahtani Hanrui Li Abdul Momin Syed Nazek El-Atab Electrical and Computer Engineering Program Computer Electrical Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)ThuwalSaudi Arabia Electrical Engineering Department College of EngineeringPrincess Nourah Bint Abdulrahman University(PNU)RiyadhSaudi Arabia

Advancements in neuromorphic computing have given an impetus to the development of systems with adaptive behavior,dynamic responses,and energy efficiency *** charge-based or emerging memory technologies such as memristors have been developed to emulate synaptic plasticity,replicating the key functionality of neurons—integrating diverse presynaptic inputs to fire electrical impulses—has remained *** this study,we developed reconfigurable metal-oxide-semiconductor capacitors(MOSCaps)based on hafnium diselenide(HfSe2).The proposed devices exhibit(1)optoelectronic synaptic features and perform separate stimulus-associated learning,indicating considerable adaptive neuron emulation,(2)dual light-enabled charge-trapping and memcapacitive behavior within the same MOSCap device,whose threshold voltage and capacitance vary based on the light intensity across the visible spectrum,(3)memcapacitor volatility tuning based on the biasing conditions,enabling the transition from volatile light sensing to non-volatile optical data *** reconfigurability and multifunctionality of MOSCap were used to integrate the device into a leaky integrate-and-fire neuron model within a spiking neural network to dynamically adjust firing patterns based on light stimuli and detect exoplanets through variations in light intensity.

关键词： integrate volatile integrating

来源：评论

学校读者我要写书评

暂无评论

FPGA implementation of low cost and low power chaotic encryption scheme based on a discrete-space chaotic map

引用

Multimedia Tools and Applications 2025年 1-22页

作者： Moreira Bezerra, João Inácio Machado, Gustavo Iankowski Soares, Rafael Valduga de Almeida Camargo, Vinícius Molter, Alexandre Post Graduate Program in Computer Science Universidade Federal de Pelotas Rio Grande do Sul Pelotas96010610 Brazil Graduate Program in Computer Engineering Universidade Federal de Pelotas Rio Grande do Sul Pelotas96010610 Brazil Post Graduate Program in Mathematical Modeling Universidade Federal de Pelotas Rio Grande do Sul Capão do Leão96160000 Brazil

The exponential growth of the number of devices connected to the Internet and the use of IoT applications increases the amount of data exchange over public channels in low-cost and low-power embedded systems. Images are the most widely shared files, and standard symmetric algorithms such as the Advanced Encryption Standard (AES) are optimized for text but not image encryption. Consequently, new approaches like chaotic encryption have attracted researchers’ interest. Chaotic encryption schemes have been analyzed mostly from a software standpoint, but recent advancements in the field, through the use of discrete chaotic maps, enabled the development of simpler hardware implementations of ciphers with promising reductions in power and cost and increased performance. This work presents the Field-programmable Gate Array (FPGA) implementation of a simultaneous permutation-diffusion chaotic encryption scheme utilizing a discrete-space chaotic map. The FPGA implementation of the cipher is analyzed considering area, maximum frequency, and power consumption, and comparisons are made with the AES. The proposed algorithm has a satisfactory trade-off between area, power and performance, obtaining a peak throughput 59% higher than state-of-the-art symmetric ciphers in the literature. Thus, the proposed cipher shows that chaotic ciphers are viable for both high-performance and low-power embedded devices. Tests verified the security of the proposed cipher against statistical, differential, brute-force, and chosen plain-text attacks. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Using CNN and Transformer Model for Unimodal Speech Emotion Recognition on MELD and IEMOCAP

Using CNN and Transformer Model for Unimodal Speech Emotion ...

引用

2025 International Conference on Advancement in Data Science, E-learning and Information System, ICADEIS 2025

作者： Aurelio, Clarence Chowanda, Andry Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798331513320

Emotion Recognition is one field that is taking the world by storm in this current age. Multimodal emotion recognition has shown promising results however, previous studies shows that recognition using speech is a field has not performed that greatly. Previous research used popular methods such as CNN, RNN, and other machine learning methods has been used to achieved good results with the help of other modality, where if speech were to be used alone the results won't be as good. A factor that contributes to the result of the speech modality not performing as well is the fact of the dataset and the way it was processed. Therefore, this research looks into what makes speech one of the lowest performing modalities by preprocessing the dataset using a different method than previous researches as well as using a CNN model paired with a Transformer model. Results achieved from this research showed an improvement when using IEMOCAP by 8.09% and MELD by 1.06%. A comparison results of using the pre-processed data with previous studies model was also done to compare the results. In conclusion, this research has explored a different preprocessing method and deep learning model that has achieved results better than previous works with the same dataset. © 2025 IEEE.

关键词： Contrastive Learning

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：