检索结果-内蒙古大学图书馆

IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Ammar Raneez Torin Wirasingha Computer Science and Engineering University of Westminster London UK Department of Computing Informatics Institute of Technology Colombo Sri Lanka

Time Series (TS) forecasting has stagnated owing to algorithm restrictions, therefore systems developed using these methods can only perform so well. TS remains a challenge despite recent advances in Deep Learning (DL) in Natural Language Processing (NLP) and Reinforcement Learning (RL). This paper reviews the literature on these algorithms, highlights studies using them, and shows their limits. Neural Ordinary Differential Equations (NODEs) with continuous-time and continuous-depth tackle TS forecasting issues. Liquid Time-Constant (LTC) networks, a more advanced and reliable implementation of these NODEs, provides fluidity. We propose a new design that uses the LTC's liquid adaptability and is more adaptable to manage immediate changes. These algorithms are more steady, adaptive, and versatile than DL, which may help overcome its TS forecasting shortcomings.

关键词： Deep learning Liquids Conferences Time series analysis Reinforcement learning Ordinary differential equations Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Handling Local Optima Trapped Situation by Improving the BAT Algorithm

引用

KSII Transactions on Internet and Information Systems 2025年第5期19卷 1564-1587页

作者： Younus, Waqar Abbas, Qamar Mazhar, Tehseen Iqbal, Muhammad Al-AlShaikh, Halah A. Shahzad, Tariq Saudagar, Abdul Khader Jilani Khan, Muhammad Amir Department of Computer Science International Islamic University Islamabad Pakistan Department of Computer Science & Information Technology Virtual University of Pakistan Lahore54000 Pakistan Institute of Computing and Information Technology Gomal University Dera Ismail Khan KP Pakistan Riyadh11432 Saudi Arabia Department of Computer Engineering COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan College of Computing Informatics and Mathematics Universiti Teknologi MARA Selangor Shah Alam40450 Malaysia

This research proposes a chaos-enhanced bat algorithm to address global optimization problems. The Bat Algorithm (BA) is a popular swarm intelligence algorithms known for its effectiveness in solving optimization problems in both academic and real life scenarios. However, the classical approach is often susceptible to getting trapped in local optima. The current study presents an improved version of the Bat algorithm to overcome these limitations. We have enhanced the Bat Algorithm to boost its local search capabilities mitigate the issue of premature convergence. An improved search equation, incorporating additional valuable information, is introduced to generate better solutions. Additionally, a random walk Levy Flight mechanism is integrated into the Bat Algorithm to prevent it from being trapped in local optima. The proposed Bat Algorithm is applied to 10 benchmark functions within metaheuristic algorithms. While these algorithms have not been thoroughly investigated or manipulated in the past they prove useful in exploring the search space for optimal solutions. Experimental results demonstrate that the proposed algorithm outperforms established methods, including both original and enhanced approaches. Copyright © 2025 KSII.

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

Apply Combined Model Between VGG16 and LightGBM on Weather Image Recognition

Apply Combined Model Between VGG16 and LightGBM on Weather I...

引用

IEEE International Conference on Research, Innovation and Vision for the Future

作者： Tran Quy Nam Irfan Syamsuddin Posts and Telecommunications Institute of Technology Hanoi Vietnam Department of Informatics & Computer Engineering Politeknik Negeri Ujung Pandang Indonesia

This research implements hybrid deep learning network models for weather image classification. The study proposes to apply a combined model, namely VGG16-LightGBM. In its architecture model, a pre-train convolutional neural network (CNN) name as VGG16 is employed for feature extraction of images and the LightGBM algorithm is used to make classification. The results on accuracy of proposed models were compared with four other models, namely Xception, Inception V3,Vgg19, Vgg16 which are all implemented by transfer learning mechanism on the same dataset. The experimental results proved that the VGG16-LightGBM gives the best performance with the highest accuracy of 81,28%, outperforms the transfer learning technique of other 4 pre-train models in the problem of weather image classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Eliminating Crossings in Ordered Graphs 19

Eliminating Crossings in Ordered Graphs

引用

19th Scandinavian Symposium on Algorithm Theory, SWAT 2024

作者： Agrawal, Akanksha Cabello, Sergio Kaufmann, Michael Saurabh, Saket Sharma, Roohani Uno, Yushi Wolff, Alexander Indian Institute of Technology Madras Chennai India Faculty of Mathematics and Physics University of Ljubljana Slovenia Institute of Mathematics Physics and Mechanics Ljubljana Slovenia Department of Computer Science Tübingen University Germany Institute of Mathematical Sciences Chennai India University of Bergen Norway Graduate School of Informatics Osaka Metropolitan University Sakai Japan Universität Würzburg Germany

ISBN: (纸本)9783959773188

Drawing a graph in the plane with as few crossings as possible is one of the central problems in graph drawing and computational geometry. Another option is to remove the smallest number of vertices or edges such that the remaining graph can be drawn without crossings. We study both problems in a book-embedding setting for ordered graphs, that is, graphs with a fixed vertex order. In this setting, the vertices lie on a straight line, called the spine, in the given order, and each edge must be drawn on one of several pages of a book such that every edge has at most a fixed number of crossings. In book embeddings, there is another way to reduce or avoid crossings;namely by using more pages. The minimum number of pages needed to draw an ordered graph without any crossings is its (fixed-vertex-order) page number. We show that the page number of an ordered graph with n vertices and m edges can be computed in 2m · nO(1) time. An O(log n)-approximation of this number can be computed efficiently. We can decide in 2O(d√k log(d+k)) · nO(1) time whether it suffices to delete k edges of an ordered graph to obtain a d-planar layout (where every edge crosses at most d other edges) on one page. As an additional parameter, we consider the size h of a hitting set, that is, a set of points on the spine such that every edge, seen as an open interval, contains at least one of the points. For h = 1, we can efficiently compute the minimum number of edges whose deletion yields fixed-vertex-order page number p. For h > 1, we give an XP algorithm with respect to h + p. Finally, we consider spine+t-track drawings, where some but not all vertices lie on the spine. The vertex order on the spine is given;we must map every vertex that does not lie on the spine to one of t tracks, each of which is a straight line on a separate page, parallel to the spine. In this setting, we can minimize in 2n · nO(1) time either the number of crossings or, if we disallow crossings, the number of tracks. © Akanks

关键词： Computational geometry

来源：评论

学校读者我要写书评

暂无评论

Improving Prediction Quality of Face Image Preference Using Combinatorial Fusion Algorithm 16th

Improving Prediction Quality of Face Image Preference Using...

引用

16th International Conference on Brain informatics, BI 2023

作者： Zhang, Zihan Schweikert, Christina Shimojo, Shinsuke Hsu, D. Frank Laboratory of Informatics and Data Mining Department of Computer and Information Science Fordham University YorkNY10023 United States Division of Computer Science Mathematics and Science St. John’s University QueensNY11439 United States Division of Biology and Biological Engineering/Computation and Neural Systems California Institute of Technology PasadenaCA91125 United States

ISBN: (纸本)9783031430749

When two face images are shown to a subject, the subject’s preference choice is influenced by many factors. Although it is a challenging task, one way to detect a subject’s preference is to analyze the eye movement gaze cascade in the recorded video sequence together with a set of extracted attributes (features). Combinatorial fusion algorithm (CFA) is a new information fusion and machine learning paradigm for combining multiple scoring systems using rank-score characteristic (RSC) function and cognitive diversity (CD). In this paper, we apply CFA in the analysis of the eye movement gaze cascade sequence. In particular, we characterize each of the attributes and measure the diversity between two attributes using RSC function and CD respectively. The novelty of the combinatorial fusion approach is the new paradigm of incorporating both score function and rank function as well as using both score combination and rank combination. In addition, our results demonstrate that weighted rank combination has some advantage over weighted score combination when the weight is measured using diversity strength. Since diversity strength depends only on cognitive diversity between two attributes but not on any specific sequence in the eye movement gaze cascade, our result facilitates learning and modeling in an unsupervised manner. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Information fusion

来源：评论

学校读者我要写书评

暂无评论

Measurement of Synthetic-Dimension Band Structures in Silicon Coupled Ring Resonators 16

Measurement of Synthetic-Dimension Band Structures in Silico...

引用

16th Pacific Rim Conference on Lasers and Electro-Optics, CLEO-PR 2024

作者： Zhang, Ruming Li, Liucun Kamata, Mikiya Baba, Toshihiko Ozawa, Tomoki Ota, Yasutomo Iwamoto, Satoshi Research Center for Advanced Science and Technology The University of Tokyo Tokyo153-8904 Japan Yokohama National University Department of Electrical and Computer Engineering Yokohama240-8501 Japan Advanced Institute for Materials Research Tohoku University Sendai980-8577 Japan Keio University Department of Applied Physics and Physico-Informatics Yokohama223-8533 Japan

We fabricated integrated silicon coupled-ring resonators and measured photonic band structures for synthetic frequency lattices with different configurations. A phase difference between two modulation signals introduc... 详细信息

ISBN: (纸本)9798350372076

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Leveraging Resource-Aware Deep Collaborative Learning Towards Secure B5G-Driven IoT-Fog-Based Consumer Electronic Systems

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Tripathy, Subhranshu Sekhar Bebortta, Sujit Chakraborty, Chinmay Senapati, Dilip Pani, Subhendu Kumar Guduri, Manisha School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Department of Computer Science Ravenshaw University Cuttack Odisha India Department of Electronics and Communication Engineering Birla Institute of Technology Jharkhand India Department of Computer Science University of Delhi Delhi India Kausalya Ganga Bhubaneswar Odisha India School of Computing and Informatics University of Louisiana at Lafayette LA USA

The integration of Fog computing and 5G communication may enhance Cyber Physical Systems (CPSs) for effective time identification of cyber attacks among consumer electronics. An unsupervised Intrusion Detection System (IDS) based on Generative Adversarial Networks (GANs) and Recurrent Neural Networks (RNNs) is presented in this study. This system is tailored to the resource limitations of consumer electronics within CPSs. By leveraging the processing power of fog nodes and the low-latency capabilities of 5G networks, cyber attacks can be swiftly identified. The use of a trained Long Short-Term Memory (LSTM) network encoder improves detection rates by enhancing reconstruction loss computation. Experimental results demonstrate that this approach, implemented through distributed fog computing infrastructure, offers better detection rates with a 15.2% reduction in detection latency and a 24.2% decrease in overall energy consumption compared to baseline methods. This innovative system could serve as an effective alternative for securing consumer electronic devices integrated into CPSs. IEEE

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Start from Zero: Triple Set Prediction for Automatic Knowledge Graph Completion

arXiv

引用

arXiv 2024年

作者： Zhang, Wen Xu, Yajing Ye, Peng Huang, Zhiwei Xu, Zezhong Chen, Jiaoyan Pan, Jeff Z. Chen, Huajun School of Software Technology Zhejiang University China College of Computer Science of Technology Zhejiang University China Innovation Research Institute Co. Ltd. China Department of Computer Science The University of Manchester Department of Computer Science University of Oxford United Kingdom School of Informatics The University of Edinburgh United Kingdom

Knowledge graph (KG) completion aims to find out missing triples in a KG. Some tasks, such as link prediction and instance completion, have been proposed for KG completion. They are triple-level tasks with some elements in a missing triple given to predict the missing element of the triple. However, knowing some elements of the missing triple in advance is not always a realistic setting. In this paper, we propose a novel graph-level automatic KG completion task called Triple Set Prediction (TSP) which assumes none of the elements in the missing triples is given. TSP is to predict a set of missing triples given a set of known triples. To properly and accurately evaluate this new task, we propose 4 evaluation metrics including 3 classification metrics and 1 ranking metric, considering both the partial-open-world and the closed-world assumptions. Furthermore, to tackle the huge candidate triples for prediction, we propose a novel and efficient subgraph-based method GPHT that can predict the triple set fast. To fairly compare the TSP results, we also propose two types of methods RuleTensor-TSP and KGE-TSP applying the existing rule- and embedding-based methods for TSP as baselines. During experiments, we evaluate the proposed methods on two datasets extracted from Wikidata following the relation-similarity partial-open-world assumption proposed by us, and also create a complete family data set to evaluate TSP results following the closed-world assumption. Results prove that the methods can successfully generate a set of missing triples and achieve reasonable scores on the new task, and GPHT performs better than the baselines with significantly shorter prediction time. The datasets and code for experiments are available at https://***/zjukg/GPHT-for-TSP. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Mqtt Routing Optimizing Based Intrusion Detection for Internet of Things Using Hybrid Machine Learning

Mqtt Routing Optimizing Based Intrusion Detection for Intern...

引用

2024 International Conference on Decision Aid Sciences and Applications, DASA 2024

作者： Hoomod, Haider K. Al-Hamami, Mohammad Alaa Kadhim, Aqeel Kamil Mohammed, Qutaiba Humadi Niaf, Jolan Rokan College of Education Mustansiriyah University Baghdad Iraq Applied Science University Manama Department of Management Information Systems Manam Bahrain Imam Al-Kadhim College Computer Techniques Engineering Department Baghdad Iraq College of Nursing University of Baghdad Baghdad Iraq Informatics Institute for Postgraduate Studies University of Information Technology and Communications Baghdad Iraq

ISBN: (纸本)9798350369106

With the advent of the Internet of Things, a world was born in which everything could be uniquely identified and monitored, tracked, and managed by computer programs. Items can self-configure using a predefined communication protocol. Other software programs can be linked to operate together using Message Queue Telemetry Transport Protocol (MQTT) or MQSeries components. Business integration software and middleware are common terms for this category of applications. With its suggested lightweight, easy-to-implement, and lowbandwidth system for billions of smart items, the MQTT protocol offers a wide range of potential applications, including home automation. In order to enhance the power savings in MQservice routing, we presented an intelligent assistant for optimizing routing model. For Internet of Things (IoT) purposes, it introduces an optimal routing model based on optimized hybrid machine learning-based anomaly detection (OHMLA). In order to extend the reach of a network, the offered approach allows Internet of Things devices to make efficient use of energy. To further enhance Intrusion Detection identification and get optimum network selection routes, the moth Salp Swarm technique (SSA) technique is used for the optimized hyperparameters. The model is capable of accurately detecting attacks that result in network congestion, causing delays in connection response and data transfer in IoT network. © 2024 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Discrepancy and Thematic Bibliometric Analyses of the Remaining Limitations in Artificial Intelligence

Discrepancy and Thematic Bibliometric Analyses of the Remain...

引用

2024 IEEE International Conference on Computing, ICOCO 2024

作者： Mansor, Mahayaudin M. Ibrahim, Nurain Radi, Noor Fadhilah Ahmad Rahim, Nadirah Abdul Yahaya, Syarul Heiry Bakar, Mohd Aftar Abu Zakaria, Roslinazairimah School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Malaysia Institute of Big Data Analytics and Artificial Intelligence Universiti Teknologi MARA Malaysia Department of Electrical and Computer Engineering Kuliyyah of Engineering International Islamic University Malaysia Department of Science Computer and Mathematics Universiti Teknologi MARA Penang Campus Malaysia Department of Mathematical Sciences Faculty of Science & Technology Universiti Kebangsaan Malaysia Centre for Mathematical Sciences Universiti Malaysia Pahang Al-Sultan Abdullah Malaysia

ISBN: (纸本)9798331530303

As artificial intelligence (AI) advances, it is essential to continuously comprehend its limitations to optimise the integration of AI into autonomous systems that empower humans. The first objective of this study is to highlight the key capabilities of both humans and AI, focusing on the differences and identifying limitations of AI from the literature. Through discrepancy analysis, this study uses a Venn diagram to visualise the remaining limitations of AI into five key domains: (i) emotional intelligence, (ii) consciousness and awareness, (iii) creative imagination, (iv) communication, and (v) ethical decision-making. Furthermore, this study employs thematic bibliometric analysis to provide a more detailed examination of each AI limitation as the second objective. This study has identified underdeveloped and emerging research themes with potential for future development, such as emotion recognition, human-computer interaction, digital health, and situational awareness, which may require further research. Additionally, this study commends the ongoing efforts to harness AI’s computational power and algorithmic innovations to enhance AI’s overall performance and applicability. ©2024 IEEE.

关键词： Emotion Recognition

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：