检索结果-内蒙古大学图书馆

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Yuya Masuda Shunta Shimizu Hiroshi Ishikawa Department of Computer Science and Communications Engineering Waseda University Tokyo Japan

ISBN: (数字)9798331507022

ISBN: (纸本)9798331507039

Video super-resolution (VSR) has gained significant attention due to its potential to enhance video quality. However, existing VSR models are often computationally heavy, limiting their practical application. To address this, we propose a two-step approach: applying 2D super-resolution (SR) followed by image-to-image conditional generation. Initial experiments using Mean Squared Error (MSE) show significant improvements. Replacing MSE with Mean Absolute Error (MAE) and blending it with Structural Similarity Index Measure (SSIM) further enhances performance. Our method achieves superior results with reduced computational complexity, offering a practical solution for real-world VSR applications. Our code is available at https://***/msdsm/efficient-video-sr-2steps.

关键词： Visualization Limiting Computational modeling Superresolution Measurement uncertainty Loss measurement Quality assessment Indexes Computational complexity Video recording

来源：评论

学校读者我要写书评

暂无评论

Motion Saliency Based Human Action Recognition in RGBD Videos

Motion Saliency Based Human Action Recognition in RGBD Video...

引用

IEEE International Conference on Intelligent computer Communication and Processing (ICCP)

作者： Alexander Gutev Carl James Debono Department of Communications and Computer Engineering University of Malta Msida Malta

ISBN: (数字)9798331539979

ISBN: (纸本)9798331539986

Human action recognition (HAR) systems need to process large volumes of data posing several challenges including, but not limited to, accurately identifying the actions and classifying them in near real time. Most of the state of the art solutions rely on machine learning techniques where a substantial amount of time is required both for the training and the inference phases. Existing solutions try to reduce the size of the data that is processed by the HAR classifier by constructing a spatio-temporal region of interest (ST-ROI) based on skeleton data, such as the model-based multimodal network (MMNet). However, the performance of these solutions depends on the accuracy of the skeleton data. This paper presents a novel solution to reduce the size of the data that is processed during classification by constructing an ST-ROI using regions identified as motion salient. The results show that the classification accuracy of the proposed solution is comparable to existing solutions such as MMNet but with a training time that is drastically lower.

关键词： Training Energy consumption Accuracy Estimation Machine learning Skeleton Real-time systems Human activity recognition Saliency detection Videos

来源：评论

学校读者我要写书评

暂无评论

Estimating Answer Strategies using Online Handwritten Data: A Study using Geometry Problems 23

Estimating Answer Strategies using Online Handwritten Data: ...

引用

Proceedings of the 15th International Conference on Education Technology and computers

作者： Kazuaki Okada Masashi Kudo Hayato Yamana Department of Computer Science and Communications Engineering Waseda University Japan

ISBN: (纸本)9798400709111

Emphasis has been placed on logical reasoning skills as a necessary ability and quality for the next generation. Developing logical reasoning skills is one of the objectives of the geometry curriculum in secondary education. Understanding an individual's strategy for finding a solution is necessary to assess his/her logical reasoning abilities. This study is the first to estimate answer strategies using online handwritten data automatically. Using geometry problems as our subject, we: 1) detect symbols written in a diagram; and 2) classify the answer strategies using XGBoost with the features combining uni-grams, bi-grams, and 1-skip-grams of symbols in their written order. Our experimental evaluation with 38 university students for a single geometry problem confirmed that answer strategies were successfully classified into three categories with an accuracy of 0.71, which shows the feasibility of the automatic detection of answer strategies.

关键词： Educational Data Mining Learning Analytics Online Handwritten Data Pen-based Computing

来源：评论

学校读者我要写书评

暂无评论

QoS aware Joint Radar Communication Optimization via Backtrack based Training Network

QoS aware Joint Radar Communication Optimization via Backtra...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Junlong Wang Zhenni Pan Shigeru Shimamoto Department of Communications and Computer Engineering Waseda University Tokyo Japan

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Joint Radar Communication (JRC) system achieves radar detection and communication transmission using a shared hardware platform, making it more suitable for integration, miniaturization, and efficient spectrum utilization compared to traditional standalone radar or communication devices. Due to the mutual interference between the two subsystems, there is growing interest in reducing negative impacts and optimizing the overall performance of JRC systems. Among various approaches, optimizing resource scheduling strategies within JRC systems to balance the performance of each subsystem in different environments and enhance system Quality of Services (QoS) values has become a significant research direction. In this paper, we propose a deep learning-based optimization framework tailored for JRC systems. By analyzing the current application environment of JRC systems, the proposed method dynamically adjusts the energy resource allocation strategy within the JRC system. This approach aims to balance the subsystems’ performance concerning the current system environment and demands, achieving self-optimization to adapt to the current application scenarios. Simulation results indicates that our proposal could improved the JRC average performance under different application scenarios.

关键词： Performance evaluation Analytical models Vehicular and wireless technologies Radar detection Radar Quality of service Interference Data models Proposals Optimization

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter Aided Depth-based Motion Saliency Detection in Human Activity Recognition Applications

Kalman Filter Aided Depth-based Motion Saliency Detection in...

引用

Mediterranean Electrotechnical Conference (MELECON)

作者： Alexander Gutev Carl Debono Department of Communications and Computer Engineering University of Malta Msida Malta

ISBN: (数字)9798350387025

ISBN: (纸本)9798350387032

The computational resources required by video processing tasks in human activity recognition (HAR) applications can be reduced if the input data is limited to only those regions which contain motion. This demands accurate identification of these regions to maximize the computational savings while maintaining similar performances of the video processing tasks. This work explores the use of Kalman filtering in combination with depth-based motion saliency to find the regions of human activity within video content. The Kalman filter tracks salient regions throughout the RGBD (Red, Green, Blue plus Depth) video and facilitates merging of regions pertaining to the same object. Experimental results show that a superior performance is achieved when compared to the state of the art BSUV-Net 2.0 algorithm.

关键词： Accuracy Tracking Filtering Pipelines Merging Kalman filters Human activity recognition

来源：评论

学校读者我要写书评

暂无评论

Leveraging Data from Vast Unexplored Seas: Positive Unlabeled Learning for Refining Prediction Area in Good Fishing Ground Prediction 27th

Leveraging Data from Vast Unexplored Seas: Positive Unlabel...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Konii, Haruki Nakano, Teppei Miyazawa, Yasumasa Ogawa, Tetsuji Department of Communications and Computer Engineering Waseda University Tokyo Japan Intelligent Framework Laboratory Tokyo Japan Application Laboratory Japan Agency for Marine-Earth Science and Technology Yokohama Japan

ISBN: (纸本)9783031781919

This paper proposes a Positive Unlabeled (PU) learning approach to narrow down the prediction area in the context of good fishing ground prediction. PU learning, a type of semi-supervised learning, is particularly suitable for scenarios characterized by limited positive examples and abundant unlabeled data, as often encountered in fishing ground prediction tasks, where the explored sea areas identified as productive fishing spots are treated as positive instances and the vast unexplored sea areas as unlabeled data. Conventional methods often struggle to accurately model the characteristics of good fishing grounds, resulting in overly broad prediction areas or overly restrictive constraints. To tackle this challenge, we present a PU learning-based method designed to identify negative examples from the unlabeled data and consequently refine the area predicted as positive. Specifically, we train a prediction model for fishing duration, which can be considered a surrogate indicator of good fishing grounds. Subsequently, we apply this model to predict the fishing duration for unexplored areas;those areas exhibiting short fishing durations are deemed reliable negative examples. By incorporating both past positive examples and selected negative examples into a binary classification framework for predicting good fishing grounds, we aim to fine-tune the prediction area. To the best of our knowledge, this study represents the first application of PU learning in the domain of good fishing ground prediction. Experimental comparisons conducted using data from bullet tuna trolling validate the efficacy of the proposed methodology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Optimized Learning Model for Brain-computer Interface Using Electroencephalogram (EEG) for Neuroprosthetics Robotic Arm Design for Society 5.0

Optimized Learning Model for Brain-Computer Interface Using ...

引用

2024 IEEE International Conference on Computing, Semiconductor, Mechatronics, Intelligent Systems and communications, COSMIC 2024

作者： Arun Kumar, S. Anand, L. Kannur, Anil School of Computing SRM Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India School of Computing SRM Institute of Science and Technology Department of Networking and Communications Tamil Nadu Potheri SRM Nagar Kattankulathur India Dr. P.G. Halakatti College of Engineering and Technology Department of Computer Science and Engineering Karnataka Vijayapura India

ISBN: (纸本)9798331517892

The brain activity can be represented by EEG, which does it by measuring voltage fluctuations in the brain. in this paper, the work intends to develop a Brain-computer Interface-based system that can identify and forecast the class of motor action corresponding to the left or right direction. There are two datasets used in this study, relating to motor movements - left/right-hand movement and eye open/close. The collected data is pre-processed by applying a Convolution Neuron Network to obtain a frequency domain matrix. The result computed by applying CNN provides a condensed representation of the data. The second dataset captured brain impulses corresponding to two states of the eyes opened and eyes closed, over a period of two minutes. This system is designed to effectively separate and utilize signals, with the adoption of AI techniques in these devices emerging as the most viable option for Society. The overall efficiency of this system ranges from 80% to 87%. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Shoe-Based PDR System for Two-Dimensional Tracking

Shoe-Based PDR System for Two-Dimensional Tracking

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Dai Kajimoto Yusuke Tanaka Siya Bao Nozomu Togawa Department of Computer Science and Communications Engineering Waseda University Ashirase Corporation

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The most famous absolute self-positioning is GPS (Global Positioning System). However, GPS cannot be used in indoor and underground environments. Thus, relative positioning methods such as sensor-based pedestrian dead reckoning (PDR) are required. The visually impaired has difficulty using navigation devices using visual information, such as smartphones, and it is necessary to develop navigation devices using non-visual information. In this paper, we propose a highly accurate two-dimensional PDR using Ashirase device, a shoe-based wearable sensor. This sensor provides non-visual navigation aids through the underfoot vibrations and has an accurate position estimation as the sensor is strongly attached to the shoe. The proposed method obtained a low estimation error <0.2% walking in straight lines and <1.2% walking in circles.

关键词： Legged locomotion Vibrations Visualization Accuracy Pedestrians Dead reckoning Wearable devices Wearable sensors Smart phones Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Intrusion Detection System using Machine Learning and Deep Learning Algorithms

A Comprehensive Analysis of Intrusion Detection System using...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Varaprasad, R. Prabhu Chakkaravarthy, A. Veeresha, M. Srm Institute of Science and Technology Department of Networking and Communications Kattankulathur India Dr. K.V. Subba Reddy Institute of Technology Department of Computer Science and Engineering Kurnool India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360660

The Internet of Things (IoT) plays an essential character in both domestic and corporate sectors by facilitating connectivity and automation through a network of devices and sensors. IoT wearable gadgets, sensors, and embedded devices are widely utilized for data collection and transmission. However, privacy and security are challenging tasks to be achieved while the standard implementation of monitoring and security operations is not possible because of large number of IoT devices, their heterogeneity and technical specification limitations. In order to solve this issue, Intrusion Detection System (IDS) is introduced to secure the network against various vulnerabilities and threats. To identify intrusion attacks accurately, Machine learning (ML) and Deep Learning (DL) algorithms namely, Random Forest (RF), Logistic Regression (LR), Decision Tree (DL), AdaBoost, XGboost, Convolutional Neural Network (CNN), Deep Convolutional Neural Network (DCNN), and Long Short-Term Memory (LSTM), Deep Neural Network (DNN) are used. This research aims to identify the strengths, relationship, and challenges of the ML and DL-based prediction approaches. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Meta-heuristics for Feature Selection and Classification in Diagnostic Breast Cancer

引用

computers, Materials & Continua 2022年第10期73卷 749-765页

作者： Doaa Sami Khafaga Amel Ali Alhussan El-Sayed M.El-kenawy Ali E.Takieldeen Tarek M.Hassan Ehab A.Hegazy Elsayed Abdel Fattah Eid Abdelhameed Ibrahim Abdelaziz A.Abdelhamid Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Communications and Computers Engineering Department Faculty of EngineeringDelta University for Science and TechnologyInternational Coastal RoadGamasa CityDakhliyaEgypt Faculty of Applied Health Science Technology Delta University for Science and TechnologyMansoura35712Egypt Faculty of Medicine Head of Internal Medicine DepartmentDelta University for Science and TechnologyMansouraEgypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura University35516MansouraEgypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams University11566CairoEgypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia

One of the most common kinds of cancer is breast *** early detection of it may help lower its overall rates of *** this paper,we robustly propose a novel approach for detecting and classifying breast cancer regions in thermal *** proposed approach starts with data preprocessing the input images and segmenting the significant regions of *** addition,to properly train the machine learning models,data augmentation is applied to increase the number of segmented regions using various scaling *** the other hand,to extract the relevant features from the breast cancer cases,a set of deep neural networks(VGGNet,ResNet-50,AlexNet,and GoogLeNet)are *** resulting set of features is processed using the binary dipper throated algorithm to select the most effective features that can realize high classification *** selected features are used to train a neural network to finally classify the thermal images of breast *** achieve accurate classification,the parameters of the employed neural network are optimized using the continuous dipper throated optimization *** results show the effectiveness of the proposed approach in classifying the breast cancer cases when compared to other recent approaches in the ***,several experiments were conducted to compare the performance of the proposed approach with the other *** results of these experiments emphasized the superiority of the proposed approach.

关键词： Breast cancer image segmentation dipper throated optimization feature selection meta-heuristics

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：