检索结果-内蒙古大学图书馆

European Signal Processing Conference (EUSIPCO)

作者： Evangelos Georgatos Christos Mavrokefalidis Kostas Berberidis Computer Engineering and Informatics Department University of Patras Greece

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

In distributed learning, a network of agents co-operate for solving a common task, like training a particular neural network. The devices usually adopt an iterative procedure with two steps, namely, they, first, perform local optimization, using, e.g., stochastic gradient descent, and, then, they exchange information among them in order to achieve consensus on the final solution. In current literature, the proposed distributed algorithms achieve consensus using averaging rules over the received information at each agent. Here, the paper departs from this paradigm and focuses on “single agent” cooperation strategies in which each agent selects a particular neighbor at each iteration and uses only that information during the local optimization step. Three selection rules are designed and it is shown that they inherit the convergence properties of commonly used averaging rules. Moreover, their effectiveness is demonstrated experimentally in classification tasks over other algorithms using well-known datasets for a wide range of scenarios, capturing factors like non-IID datasets, network size, and AI model size.

关键词： Training Performance evaluation computer aided instruction Distance learning Signal processing algorithms Stochastic processes Signal processing Classification algorithms Partitioning algorithms Optimization

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

Eye State Classification Using Ensemble Machine Learning Models and SMOTE on EEG Data 9

Eye State Classification Using Ensemble Machine Learning Mod...

引用

9th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2024

作者： Trigka, Maria Dritsas, Elias Mylonas, Phivos Athena Research and Innovation Center Industrial Systems Institute Patras26504 Greece University of West Attica Department of Informatics and Computer Engineering Egaleo12243 Greece

ISBN: (纸本)9798350342482

Electroencephalography (EEG) data presents complex and high-dimensional signals, offering great potential for applications in various fields such as neurofeedback, clinical diagnostics, cognitive neuroscience, human-computer interaction (HCI), and beyond. Analyzing EEG signals requires expertise not only from neuroscience, but also from signal processing, machine learning (ML), and statistics to extract meaningful information from brain activity recordings. Specifically, the combination of EEG and ML can provide an advantage in addressing challenging classification tasks in these fields. The present study focuses on the classification of eye state (open or closed) using Ensemble ML models such as Random Forest (RF), Gradient Boosting (GB), AdaBoost, XGBoost, and LightGBM on EEG data. We apply the Synthetic Minority Over-sampling Technique (SMOTE) to address the class imbalance and conduct a comparative analysis of the models' performance with and without SMOTE using 10-fold cross-validation across several metrics namely, Accuracy, Precision, Recall, F1-score, and the Area Under the Curve (AUC). The experimental results highlight the importance of addressing the class imbalance in EEG data to improve model performance. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Estimation of Ball Position Using Depth Camera for Middle Size Goalkeeper Robot 24

Estimation of Ball Position Using Depth Camera for Middle Si...

引用

24th International Electronics Symposium, IES 2022

作者： Suwandi, Dekasari Putri Wibowo, Iwan Kurnianto Bachtiar, Mochamad Mobed Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

EEPIS Robot Soccer On Wheeled (ERSOW) has a goalkeeper robot used as a defense to prevent the opposing team from scoring goals. The ability to detect the ball is one of the main abilities that a goalkeeper robot must-have. The goalkeeper robot needs the ability to able to detect the ball when it bounces in the air. In this research, a ball detection system will be designed for the goalkeeper robot using a Depth Camera which is placed above the robot's head and facing perpendicular to the front from the robot's point of view. The depth camera was chosen because it has a 3D-based object recognition feature so that it can be used to calculate the distance between the robot's position and the ball even though the ball is soaring in the air. Data from the depth camera will be presented in Red, Green, Blue, and Depth (RGB-D) formats. The image from the camera reading with the Depth format will be processed for estimation of the ball's position. The results of the position estimation test get an average position error on the X, Y, and Z axes of 69.53 mm, 46.11 mm, and 65.77 mm. © 2022 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

CNN-based Segmentation and Classification of Sound Streams under realistic conditions 26

CNN-based Segmentation and Classification of Sound Streams u...

引用

26th Pan-Hellenic Conference on informatics, PCI 2022

作者： Tsalera, Eleni Papadakis, Andreas Samarakou, Maria Voyiatzis, Ioannis Department of Informatics and Computer Engineering University of West Attica Greece Athens Greece

ISBN: (纸本)9781450398541

Audio datasets support the training and validation of Machine Learning algorithms in audio classification problems. Such datasets include different, arbitrarily chosen audio classes. We initially investigate a unifying approach, based on the mapping of audio classes according to the Audioset ontology. Using the ESC-10 audio dataset, a tree-like representation of its classes is created. In addition, we employ an audio similarity calculation tool based on the values of extracted features (spectrum centroid, the spectrum flux and the spectral roll-off). This way the audio classes are connected both semantically and in feature-based manner. Employing the same dataset, ESC-10, we perform sound classification using CNN-based algorithms, after transforming the sound excerpts into images (based on their Mel spectrograms). The YAMNet and VGGish networks are used for audio classification and the accuracy reaches 90%. We extend the classification algorithm with segmentation logic, so that it can be applied into more complex sound excerpts, where multiple sound types are included in a sequential and/or overlapping manner. Quantitative metrics are defined on the behavior of the combined segmentation and segmentation functionality, including two key parameters for the merging operation, the minimum duration of the identified sounds and the intervals. The qualitative metrics are related to the number of sound identification events for a concatenated sound excerpt of the dataset and per each sound class. This way the segmentation logic can operate in a fine- and coarse-grained manner while the dataset and the individual sound classes are characterized in terms of clearness and distinguishability. © 2022 ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Hybridization Model of Frame Semantics and deep learning for text semantic similarity calculation 6

Hybridization Model of Frame Semantics and deep learning for...

引用

6th International Conference on computer Information Science and Application Technology, CISAT 2023

作者： Haijing, Liu Department of Computer Engineering Taiyuan Institute of Technology Taiyuan China College of computing informatics and media University Technology Mara Malaysia

ISBN: (纸本)9781510668546

Text semantic similarity computation is a fundamental problem in the field of natural language processing. In recent years, text semantic similarity algorithms based on deep learning have become the mainstream research paradigm, but they suffer from the problem of insufficient understanding of text semantics and thus unclear interpretation of computational results. In this paper, we propose a text semantic encoding model combining Frame semantic theory and deep learning, which enriches the semantic representation within sentences by making full use of the Frame, Frame Elements, lexical units, and inter-Frame relations in the Frame semantic knowledge base and combining them with the Bert model, and interacts with the semantics between sentences through Siamese Transformer encoders. The experiments are validated on MSRParaphraseCorpus and quora-question-pairs, and the results show that the model proposed in this paper outperforms similar models in terms of F1 values. © 2023 SPIE.

关键词： Semantics

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

Late Breaking Results: Energy-Efficient Printed Machine Lear...

引用

Design, Automation and Test in Europe Conference and Exhibition

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

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

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.

关键词： Support vector machines Energy consumption Accuracy Machine learning algorithms Limiting Circuits Europe Energy efficiency Hardware Batteries

来源：评论

学校读者我要写书评

暂无评论

Screen Reading Regions in Social Media Comments: An Eye-Tracking Analysis of Visual Attention on Smartphones 23

Screen Reading Regions in Social Media Comments: An Eye-Trac...

引用

Proceedings of the 27th Pan-Hellenic Conference on Progress in Computing and informatics

作者： Stavroula Dritsa Andreas Mallas Michalis Xenos Department of Computer Engineering & Informatics University of Patras Greece

ISBN: (纸本)9798400716263

Our study examines how formatted text influences reading behavior concerning the smartphone screen regions users utilize on social media comments. Aiming to research visual attention in scrollable content, we investigate the differences in the distribution of visual attention in screen regions between social media comment sections and the users’ preferred reading regions across all cases examined. An experiment was conducted with participants (n = 47) engaging in reading activities on the comment section of four social media -Twitter, YouTube (in two versions), Facebook, and Instagram- chosen due to their popularity and the users’ familiarity with them. Results showed that users’ visual attention is distributed differently between social media. Different reading styles were observed, with users not utilizing the entirety of the screen but instead focusing on specific screen regions that varied between users.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Design Patterns on Unity Components to Increase Reusability and Game Speed Development 25

Implementation of Design Patterns on Unity Components to Inc...

引用

25th International Electronics Symposium, IES 2023

作者： Yunanto, Andhik Ampuh Jamal, Sabila Sa'Adah, Umi Aziz, Adam Shidqul Permatasari, Desy Intan Nailussa'Ada Hardiansyah, Fadilah Fahrul Politeknik Elektronika Negeri Surabaya Keputih Sukolilo Department of Informatics and Computer Engineering East Java Surabaya City60111 Indonesia

ISBN: (纸本)9798350314731

In the past few years, a few game studios have already developed mid-core games. In this kind of game, U is one of the most crucial and complex parts. Game companies have to develop their products quickly and effectively so they can compete in the industry. Developing games quickly with a good architecture is not easy, especially the products that are developed are products with high complexity. Plus, currently, there is still no special framework or library that helps the development of mid-core games. This research implements design patterns to develop Unity Engine framework to develop game UI components. Validation results showed an increase in the development time by 28% to 91% and in the interaction cost by 10% to 66%. Moreover, the survey result also shows a customer satisfaction rate of 78% using CSAT formula. It is considered an excellent response by CSAT standard, so it could be concluded that according to customer, this framework already has an excellent performance. © 2023 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Support Vector Machine: Melanoma Skin Cancer Diagnosis based on Dermoscopy Image 24

Support Vector Machine: Melanoma Skin Cancer Diagnosis based...

引用

24th International Electronics Symposium, IES 2022

作者： Ibrahim, Tirta Farisaldi Setiawardhana Sigit, Riyanto Politeknik Elektronika Negeri Surabaya Informatics and Computer Engineering Department Surabaya Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

Melanoma is one of the most deadly types of skin cancer. Until now, the diagnosis of melanoma skin cancer is still using the biopsy method, which is the procedure of taking a small portion of tissue from the patient's body to be examined using a microscope. This method is considered less effective because finding the type of melanoma skin cancer requires a long preparation and a slightly longer wound healing time. Suppose this melanoma can be diagnosed from the start for patients suffering from malignant melanoma tumors. In that case, it can be treated immediately so that the percentage of patient recovery will be higher. Therefore, in this study, a rapid dermoscopy image computerized analysis system was designed so that it can be used to classify the type of melanoma image or not (nevus) with Gray Level Co-occurrence Matric (GLCM). For the classification method used, the support vector machine (SVM) is one of the supervised learning that is usually used for classifications such as (Support Vector Classification) and regression (Support Vector Regression). This method is believed to be quite good and accurate in performing dermoscopy image recognition which is used as input and for image processing. The system for diagnosing melanoma will be implemented in a graphic user interface that will facilitate the user interface experience. The results of this study are information about skin cancer from the image, whether it is melanoma or not (nevus) which can help dermatologists diagnose melanoma quickly. In this study, 2589 data training was conducted, and testing was carried out on 192 testing data. The test results obtained an accuracy rate of 83% and an error percentage of 17%. © 2022 IEEE.

关键词： Support vector machines

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：