检索结果-内蒙古大学图书馆

11th Electrical Power, Electronics, Communications, Control, and informatics Seminar, EECCIS 2022

作者： Perdana, Rizal Setya Adikara, Putra Pandu Indriati Kurnianingtyas, Diva Brawijaya University Faculty of Computer Science Department of Informatics Engineering Malang Indonesia

ISBN: (数字)9781665406482

ISBN: (纸本)9781665406482

This study presents architecture in learning human-machine conversation using a human language known as chatbots. Given an utterance, a chatbot attempt to reply using human language by mimicking human intelligence in communication. Previous works in this domain were mostly implemented in English, thus it remains a problem when bringing to a low-resource language, e.g., Indonesian. The limited availability of human-to-human dialog history led to difficulty in the learning process of machine learning algorithms. Therefore, this study proposed a Knowledgeable Chatbot (KC), an enhanced pipeline that enables to receiving of transferred knowledge from another task. A data augmentation pipeline is proposed to handle the limited number of available. To deal with the low-resource language, this study proposed to incorporate a pre-trained language model to gain contextualized language understanding. As this research can be categorized as preliminary, extensive experiments are required to prove the effectiveness of each part. Standard automatic metrics for information retrieval and classification prove that KC excels in the ablation study. © 2022 IEEE.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Enhancing Smart Mobility Through Machine Learning and Neural Networks 7

Enhancing Smart Mobility Through Machine Learning and Neural...

引用

7th Edition Global Conference on Wireless and Optical Technologies, GCWOT 2024

作者： Nadeem, Muhammad Haider, Waleej Ahmed, Haris Khan, Sallar Sir Syed University of Engineering & Technology Department of Computer Science & Information Technology Karachi Pakistan School of Informatics & Cybersecurity Technological University Dublin Dublin Ireland

ISBN: (纸本)9798331534271

This study investigates the prediction of taxi trip durations in New York City using machine learning (ML) models and neural networks (NN). Three models Linear Regression, Random Forest Regressor, and a Neural Network were developed and evaluated on a dataset containing various trip details. The analysis highlighted the importance of geographic and temporal features in predicting trip durations. The Neural Network model outperformed others, achieving a mean squared error (MSE) of 12,577,211 and a root mean squared error (RMSE) of 3,546, significantly better than the comparative models. These results underscore its capacity to capture complex urban mobility patterns effectively. The superior performance of the Neural Network supports its potential to optimize traffic flow and reduce congestion in dense urban environments, offering substantial improvements to urban transportation systems. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Compact Yet Highly Accurate Printed Classifiers Using Sequential Support Vector Machine Circuits

arXiv

引用

arXiv 2025年

作者： Sertaridis, Ilias Besias, Spyridon Afentaki, Florentia Balaskas, Konstantinos Zervakis, Georgios Department of Computer Engineering & Informatics University of Patras Patras Greece

Printed Electronics (PE) technology has emerged as a promising alternative to silicon-based computing. It offers attractive properties such as on-demand ultra-low-cost fabrication, mechanical flexibility, and conformality. However, PE are governed by large feature sizes, prohibiting the realization of complex printed Machine Learning (ML) classifiers. Leveraging PE’s ultra-low non-recurring engineering and fabrication costs, designers can fully customize hardware to a specific ML model and dataset, significantly reducing circuit complexity. Despite significant advancements, state-of-the-art solutions achieve area efficiency at the expense of considerable accuracy loss. Our work mitigates this by designing area- and power-efficient printed ML classifiers with little to no accuracy degradation. Specifically, we introduce the first sequential Support Vector Machine (SVM) classifiers, exploiting the hardware efficiency of bespoke control and storage units and a single Multiply-Accumulate compute engine. Our SVMs yield on average 6x lower area and 4.6% higher accuracy compared to the printed state of the art. © 2025, CC BY.

关键词： Cost engineering

来源：评论

学校读者我要写书评

暂无评论

Gigahertz Optical Digital-to-Analog Multiplier

Gigahertz Optical Digital-to-Analog Multiplier

引用

2023 International Russian Automation Conference, RusAutoCon 2023

作者： Kamenskiy, Vladislav Sokolov, Sergey Kurinenko, Marianna Rostov State Transport University «automation and Remote Control in Railway Transport» Department Rostov-on-Don Russia Moscow Technical University of Communications and Informatics Department of Informatics and Computer Engineering Rostov-on-Don Russia

ISBN: (纸本)9798350345551

The article analyzes modern computing devices that perform multiplication operations. The main classes of multipliers built on the basis of both electronic and optical elements are considered. The main disadvantage of these devices, which negatively affects their performance, is the inability to carry out parallel calculations with them. In turn, this disadvantage is due to the fact that multiplication of the multi-bit binary number in general is carried out by calculating the partial products of the bits of the multipliers and their addition with the inevitable implementation of a corresponding, usually very large, number of transfers. The presence of a large number of transfers fundamentally does not allow solving the problem of increasing the speed of calculations. The developed optical binary digital-to-analog multiplier is devoid of this drawback. This optical digital-to-analog multiplier is implemented on the basis of optical splitters, optical couplers and optical banners with a well-developed technology for their manufacture today, which provides a minimum delay time of the optical signal (in the picosecond range). The functional diagram of the proposed optical digital-to-analog multiplier is shown and the principle of its operation is described. The possibility of increasing the speed of this optical digital-to-analog multiplier to the potential for optical information processing circuits is shown. © 2023 IEEE.

关键词： Optical data processing

来源：评论

学校读者我要写书评

暂无评论

Depth and Pitch Control of Autonomous Underwater Glider Using Model Predictive Control with ARX Model

Depth and Pitch Control of Autonomous Underwater Glider Usin...

引用

2023 International Conference on Electrical engineering and informatics, ICEEI 2023

作者： Jeremy, Jason Hidayat, Egi Muhammad Idris Siregar, Simon Trilaksono, Bambang Riyanto Habibullah, Natsir School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Telkom University Faculty of Applied Science Department Computer Engineering Bandung Indonesia

ISBN: (纸本)9798350381290

Autonomous Underwater Gliders (AUGs) are extensively developed vehicles capable of prolonged exploration and observation in complex marine environments. Control of the AUG is challenging due to its slow response system and its constraints. In this research, a linear model representation of AutoRegressive eXogenous input (ARX) will be constructed using input and output data from the AUG system, built Model Predictive Control (MPC), analyzed the performance, comparing with traditional Proportional-Integral-Derivative (PID). The objective is to enhance setpoint tracking accuracy and minimize energy to extend exploration time while faced with constraints. Simulation results reveal MPC exhibits potential setpoint tracking, low overshoot as low as 0.6% up to 0.3m/s maximum depth rate, has relatively low input changes indicating good efficiency compared to PID. MPC approach effectively addresses slow response systems, managing momentum, and handling actuator constraints commonly encountered in AUG. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Intelligent Intrusion Detection System to Secure E-Commerce Communication Systems

引用

computer Systems Science & engineering 2023年第11期47卷 2513-2528页

作者： Adil Hussain Kashif Naseer Qureshi Khalid Javeed Musaed Alhussein Department of Transportation Engineering Chang’an UniversityXi’anChina Department of Electronic&Computer Engineering University of LimerickLimerickV94 T9PXIreland Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjahUnited Arab Emirates Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Kingdom of Saudi Arabia

Information and communication technologies are spreading rapidly due to their fast proliferation in many *** number of Internet users has led to a spike in cyber-attack incidents.E-commerce applications,such as online banking,marketing,trading,and other online businesses,play an integral role in our *** Intrusion Detection System(NIDS)is essential to protect the network from unauthorized access and against other *** existing NIDS systems are based on the Backward Oracle Matching(BOM)algorithm,which minimizes the false alarm rate and causes of high packet drop *** paper discussed the existing NIDS systems and different used pattern-matching techniques regarding their weaknesses and *** address the existing system issues,this paper proposes an enhanced version of the BOM algorithm by using multiple pattern-matching methods for the NIDS system to improve the network *** proposed solution is tested in simulation with existing solutions using the Snort and NSL-KDD *** experimental results indicated that the proposed solution performed better than the existing solutions and achieved a 5.17%detection rate and a 0.22%lower false alarm rate than the existing solution.

关键词： E-commerce NIDS security algorithm network applications CIA detection

来源：评论

学校读者我要写书评

暂无评论

IOT Based Smart Parking System Using Ensemble Learning

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3637-3656页

作者： Walaa H.Elashmawi Ahmad Akram Mohammed Yasser Menna Hisham Manar Mohammed Noha Ihab Ahmed Ali Department of Computer Science Faculty of Computers and InformaticsSuez Canal University4.5 Km the Ring RoadIsmailiaIsmailia41522Egypt Department of Computer Engineering and Software Systems Faculty of EngineeringAin Shams UniversityAl-Abbaseya4543070Egypt Department of Computer Science Faculty of Computer ScienceMisr International University28 KM Cairo–Ismailia RoadCairo44971Egypt College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Higher Future Institute for Specialized Technological Studies Cairo3044Egypt

Parking space is usually very limited in major cities,especially Cairo,leading to traffic congestion,air pollution,and driver *** car parking systems tend to tackle parking issues in a non-digitized *** systems require the drivers to search for an empty parking space with no guaran-tee of finding any wasting time,resources,and causing unnecessary *** address these issues,this paper proposes a digitized parking system with a proof-of-concept implementation that combines multiple technological concepts into one solution with the advantages of using IoT for real-time tracking of park-ing *** authentication and automated payments are handled using a quick response(QR)code on entry and *** experiments were done on real data collected for six different locations in Cairo via a live popular times *** machine learning models were investigated in order to estimate the occu-pancy rate of certain ***,a clear analysis of the differences in per-formance is illustrated with the final model deployed being *** has achieved the most efficient results with a R^(2) score of 85.7%.

关键词： IoT XGBoost linear regression random forest ensemble learning isolation forest

来源：评论

学校读者我要写书评

暂无评论

Late Breaking Results: Energy-Efficient Printed Machine Learning Classifiers with Sequential SVMs

arXiv

引用

arXiv 2025年

作者： Besias, Spyridon Sertaridis, Ilias Afentaki, Florentia Balaskas, Konstantinos Zervakis, Georgios Department of Computer Engineering & Informatics University of Patras Patras Greece

Printed Electronics (PE) provide a mechanically flexible and cost-effective solution for machine learning (ML) circuits, compared to silicon-based technologies. However, due to large feature sizes, printed classifiers are limited by high power, area, and energy overheads, which restricts the realization of battery-powered systems. In this work, we design sequential printed bespoke Support Vector Machine (SVM) circuits that adhere to the power constraints of existing printed batteries while minimizing energy consumption, thereby boosting battery life. Our results show 6.5x energy savings while maintaining higher accuracy compared to the state of the art. © 2025, CC BY.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Optimization of Chasing and Catching Skills on Robot Soccer ERSOW 24

Optimization of Chasing and Catching Skills on Robot Soccer ...

引用

24th International Electronics Symposium, IES 2022

作者： Ihsan, Fadl Lul Hakim Dewantara, Bima Sena Bayu Wibowo, Iwan Kurnianto Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

The wheeled soccer robot competition is held annually in Indonesia and internationally through the Indonesian Robot Contest and Robocup Middle Size League (MSL) competitions. The rate of occurrence of the ball moving freely on the field during the match is quite high. At this time the movement of the ERSOW robot to catch the ball is by chasing and following the path of the ball on the field without taking into account the speed of the ball. The movement of the ERSOW Robot with this method is very vulnerable and can still be optimized. The ball is very susceptible to failure to be caught due to being controlled by the opponent or the ball being out. In addition, chasing the ball requires a longer time due to the path of the robot that continues to change following the current position of the ball movement. So the development of robot skills in chasing and blocking the ball is needed to increase the chance of controlling the ball. Based on the results of the literature study, was found a ball blocking ability on the soccer ball intercept robot. This research is focused on how the robot can chase and catch the ball with the ability to intercept. The robot's ability to know the direction of the ball's movement and cut the ball's movement or intercept is needed. By utilizing data processing from vision to obtain ball speed data and speed algorithm calculations, a more optimal method of chasing and catching the ball is obtained. Based on the results of the 180-degree angle experiment, the success of ERSOW in catching the ball using this method was 94.7%. © 2022 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Classification of Adversarial Attacks Using Ensemble Clustering Approach

引用

computers, Materials & Continua 2023年第2期74卷 2479-2498页

作者： Pongsakorn Tatongjai Tossapon Boongoen Natthakan Iam-On Nitin Naik Longzhi Yang Center of Excellence in AI&Emerging Technologies School of ITMae Fah Luang UniversityChiang RaiThailand Department of Computer Science Aberystwyth UniversityAberystwythUnited Kingdom School of Informatics and Digital Engineering Aston UniversityBirminghamUnited Kingdom Department of Computer and Information Sciences Northumbria UniversityNewcastleUnited Kingdom

As more business transactions and information services have been implemented via communication networks,both personal and organization assets encounter a higher risk of *** safeguard these,a perimeter defence likeNIDS(network-based intrusion detection system)can be effective for known *** has been a great deal of attention within the joint community of security and data science to improve machine-learning based NIDS such that it becomes more accurate for adversarial attacks,where obfuscation techniques are applied to disguise patterns of intrusive *** current research focuses on non-payload connections at the TCP(transmission control protocol)stack level that is applicable to different network *** contrary to the wrapper method introduced with the benchmark dataset,three new filter models are proposed to transform the feature space without knowledge of class *** ECT(ensemble clustering based transformation)techniques,i.e.,ECT-Subspace,ECT-Noise and ECT-Combined,are developed using the concept of ensemble clustering and three different ensemble generation strategies,i.e.,random feature subspace,feature noise injection and their *** on the empirical study with published dataset and four classification algorithms,new models usually outperform that original wrapper and other filter alternatives found in the *** is similarly summarized from the first experiment with basic classification of legitimate and direct attacks,and the second that focuses on recognizing obfuscated *** addition,analysis of algorithmic parameters,i.e.,ensemble size and level of noise,is provided as a guideline for a practical use.

关键词： Intrusion detection adversarial attack machine learning feature transformation ensemble clustering

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：