检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Jeon, Eun Som Choi, Hongjun Buman, Matthew P. Turaga, Pavan Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of Lawrence Livermore National Laboratory LivermoreCA94550 United States College of Health Solutions Arizona State University PhoenixAZ85004 United States Geometric Media Lab School of Arts Media and Engineering School of Electrical Computer and Energy Engineering Arizona State University TempeAZ85281 United States

The analysis of wearable sensor data has enabled many successes in several applications. To represent the high-sampling rate time-series with sufficient detail, the use of topological data analysis (TDA) has been considered, and it is found that TDA can complement other time-series features. Nonetheless, due to the large time consumption and high computational resource requirements of extracting topological features through TDA, it is difficult to deploy topological knowledge in machine learning and various applications. In order to tackle this problem, knowledge distillation (KD) can be adopted, which is a technique facilitating model compression and transfer learning to generate a smaller model by transferring knowledge from a larger network. By leveraging multiple teachers in KD, both time-series and topological features can be transferred, and finally, a superior student using only time-series data is distilled. On the other hand, mixup has been popularly used as a robust data augmentation technique to enhance model performance during training. Mixup and KD employ similar learning strategies. In KD, the student model learns from the smoothed distribution generated by the teacher model, while mixup creates smoothed labels by blending two labels. Hence, this common smoothness serves as the connecting link that establishes a connection between these two methods. Even though it has been widely studied to understand the interplay between mixup and KD, most of them are focused on image based analysis only, and it still remains to be understood how mixup behaves in the context of KD for incorporating multimodal data, such as both time-series and topological knowledge using wearable sensor data. In this paper, we analyze the role of mixup in KD with time-series as well as topological persistence, employing multiple teachers. We present a comprehensive analysis of various methods in KD and mixup, supported by empirical results on wearable sensor data. We observe that app

关键词：

来源：评论

学校读者我要写书评

暂无评论

Designing an Intelligent Data Transmission Strategy Between Entities Using Wireless Communication Methodology

Designing an Intelligent Data Transmission Strategy Between ...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Geetha, R. Jayakumar, D. Devi, S. Rukmani Senthurya, S. Akula, Akhila Karthiga, R. Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Electrical and Electronics Engineering Saveetha School of Engineering Tamil Nadu Chennai India R.M.D. Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha College of Liberal Arts and Sciences Simats Deemed to Be University Chennai Department of Computer Science Tamil Nadu India Mlr Institute of Technology Department of Ece Hyderabad India R.M.K Engineering College Department of It Tamil Nadu Chennai India

ISBN: (纸本)9798350375237

Data security is of the utmost importance in wireless sensor networks due to the massive amounts of data collected and sent between nodes. An improved security method for wireless sensor networks is presented in this paper. This mechanism takes into account the application, the security level, and the bit error rate simultaneously. In order to provide the user with the ability to select between unsecure and secure modes, we made use of reserved bits of the frame control field that are contained within the communication header. The Secured and Intelligent Data Transmission Protocol (SIDTP) is the name of the unified perceptual information transmission model that is established in this research. Its purpose is to compensate for the unequal distribution of cognitive radio users across different wireless LANs. For the purpose of determining whether or not the suggested scheme is effective, the proposed model will be cross-validated with the traditional data transmission model known as Wireless Data Transmission Protocol (WDTP). The approach has the potential to optimize the utilization of spectrum resources in an efficient manner. In addition, to help lessen the risks connected with wireless networks, this study lays out a technique for transmitting data using cyclic delay full diversity sensing information coding. In order to evaluate the performance of the system against a variety of correlation coefficients, we developed a system simulation model. The result of the study showed that cyclic delay diversity systems had overall interference intensity similar to frequency division duplex as well as time division duplex. As an added bonus, this enhances its anti-jamming attack capabilities. The proposed system has been planned and implemented, and significant trials have been carried out in an industrial setting. Additionally, a prototype of the system has been designed. Compared to conventional communication interfaces that are only equipped with a single wireless interf

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches 25

SketchFlex: Facilitating Spatial-Semantic Coherence in Text-...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Lin, Haichuan Ye, Yilin Xia, Jiazhi Zeng, Wei Thrust of Computational Media and Arts The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Academy of Interdisciplinary Studies The Hong Kong University of Science and Technology Guangdong China School of Computer Science and Engineering Central South University Changsha China The Hong Kong University of Science and Technology (Guangzhou) Guangdong Guangzhou China The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798400713941

Text-to-image models can generate visually appealing images from text descriptions. Efforts have been devoted to improving model controls with prompt tuning and spatial conditioning. However, our formative study highlights the challenges for non-expert users in crafting appropriate prompts and specifying fine-grained spatial conditions (e.g., depth or canny references) to generate semantically cohesive images, especially when multiple objects are involved. In response, we introduce SketchFlex, an interactive system designed to improve the flexibility of spatially conditioned image generation using rough region sketches. The system automatically infers user prompts with rational descriptions within a semantic space enriched by crowd-sourced object attributes and relationships. Additionally, SketchFlex refines users' rough sketches into canny-based shape anchors, ensuring the generation quality and alignment of user intentions. Experimental results demonstrate that SketchFlex achieves more cohesive image generations than end-to-end models, meanwhile significantly reducing cognitive load and better matching user intentions compared to region-based generation baseline. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Diffusion model Generative artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Using log analytics and process mining to enable self-healing in the Internet of Things

引用

Environment Systems and Decisions 2022年第2期42卷 234-250页

作者： Singh, Prasannjeet Saman Azari, Mehdi Vitale, Francesco Flammini, Francesco Mazzocca, Nicola Caporuscio, Mauro Thornadtsson, Johan Department of Computer Science and Media Technology Linnaeus University Växjö Sweden Department of Electrical Engineering and Information Technologies University of Naples Federico II Naples Italy School of Innovation Design and Engineering Mälardalen University Västerås Sweden Information Sigma Technology Gothenburg Sweden

The Internet of Things (IoT) is rapidly developing in diverse and critical applications such as environmental sensing and industrial control systems. IoT devices can be very heterogeneous in terms of hardware and software architectures, communication protocols, and/or manufacturers. Therefore, when those devices are connected together to build a complex system, detecting and fixing any anomalies can be very challenging. In this paper, we explore a relatively novel technique known as Process Mining, which—in combination with log-file analytics and machine learning—can support early diagnosis, prognosis, and subsequent automated repair to improve the resilience of IoT devices within possibly complex cyber-physical systems. Issues addressed in this paper include generation of consistent Event Logs and definition of a roadmap toward effective Process Discovery and Conformance Checking to support Self-Healing in IoT. © 2022, The Author(s).

关键词： Anomaly detection Cyber-physical systems Data driven Resilience Self-diagnostics Self-repair

来源：评论

学校读者我要写书评

暂无评论

A predictive model for regional zenith tropospheric delay correction

引用

Astronomical Techniques and Instruments 2024年第1期1卷 76-83页

作者： Yu Lei Danning Zhao School of Computer Science&Technology Xi’an University of Posts&TelecommunicationsXi’an 710121China School of Electrical&Electronic Engineering Baoji University of Arts and SciencesBaoji 721016China

The conventional zenith tropospheric delay(ZTD)model(known as the Saastamoinen model)does not consider seasonal variations affecting the delay,giving it low accuracy and *** may be improved with adjustments to account for annual and semi-annual *** method uses ZTD data provided by the Global Geodetic Observing System to analyze seasonal variations in the bias of the Saastamoinen model in Asia,and then constructs a model with seasonal variation corrections,denoted as *** overcome the dependence of the model on in-situ meteorological parameters,the SSA+GPT3 model is formed by combining the SSA and GPT3(global pressure-temperature)*** results show that the introduction of annual and semi-annual variations can substantially improve the Saastamoinen model,yielding small and time-stable variations in bias and root mean square(RMS).In summer and autumn,the bias and RMS are noticeably smaller than those from the Saastamoinen *** addition,the SSA model performs better in low-latitude and low-altitude areas,and bias and RMS decease with the increase of latitude or *** prediction accuracy of the SSA model is also evaluated for external *** results show that the accuracy of the SSA model(bias:-0.38 cm,RMS:4.43 cm)is better than that of the Saastamoinen model(bias:1.45 cm,RMS:5.16 cm).The proposed method has strong applicability and can therefore be used for predictive ZTD correction across Asia.

关键词： Zenith tropospheric delay Saastamoinen model Seasonal variations Asian area Accuracy analysis

来源：评论

学校读者我要写书评

暂无评论

All patched up: Effective integration of real and synthetic features into a single image for object detection

All patched up: Effective integration of real and synthetic ...

引用

2023 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2023

作者： Dale, Ashley S. Christopher, Lauren Reindl, William Sanchez, Edwin Brunes, Sam Bickel, Will Martin, Jasmine William, Albert Indiana University Purdue University Indianapolis Dept. of Electrical and Computer Engineering IndianapolisIN46202 United States Indiana University Purdue University Indianapolis Dept. of Computer and Information Science IndianapolisIN46202 United States Indiana University Purdue University Indianapolis Dept. of Human-Centered Computing Media Arts and Sciences Indiana IndianapolisIN46202 United States

ISBN: (纸本)9798350359527

Synthetic data and data augmentation are commonly used to supplement a small set of real images and create a dataset with diverse features, improving the robustness of a computer vision model. However, there is no consensus on how to best leverage synthetic data for object detection tasks in a real environment. Our work answers the following questions: First, is it more important for synthetic data to have realistic backgrounds or realistic instances? Second, is pixel saliency a valid metric for explaining the relative importance of real and synthetic instances? We explore these questions by placing synthetic object instances in real environments and vice versa to create synthetically blended data, rather than a dataset with distinct real and synthetic images. Our results show that when there is good overlap between the feature domains of the real and synthetic images, there is no benefit to augmenting the training data with patches. However, given a domain gap between real and synthetic data for a given class, model performance improved ≈ 60%, with greater gains observed when increasing the number of images with real backgrounds. These results show that the relationship of synthetic to real features should be considered when constructing a dataset for domain transfer tasks. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards the Improvement of the Cognitive Process of the Synthesized Speech of Mathematical Expression in MathML: An Eye-Tracking 2

Towards the Improvement of the Cognitive Process of the Synt...

引用

2nd International Conference on Interactive media, Smart Systems and Emerging Technologies, IMET 2022

作者： Souza, Adriana Freitas, Diamantino Bahia Federal Institute of Education Science and Technology Bahia Brazil Doctoral Program in Digital Media Faculty of Engineering of the University of Porto Porto Portugal Faculty of Engineering of the University of Porto Speech Processing Laboratory Electrical and Computer Engineering Department Porto Portugal

ISBN: (数字)9781665470162

ISBN: (纸本)9781665470162

Being one essential part of the solutions we are developing to provide accessibility for blind persons, synthesized speech of mathematical content, although having evolved in naturalness in recent years, still keeps a characteristic of generating very long outputs, which makes it difficult for a person who uses a screen reader to memorize. Eye-gaze tracking has been useful for studying cognitive processes and student's effort in performing tasks therefore it seems attractive as a means to understand how people analyze, process, and break down extensive math expressions into smaller ones. This understanding can help to build a similar model of auditory rendering of MathML capable of avoiding cognitive overload. Therefore, we carried out an experiment to do a gaze-based analysis of reading and memorizing mathematical expressions. Our sample consisted of fourteen participants, and seven mathematical expressions were used in the experiment. The results showed that the computed complexity of the expressions and the average duration of eye-gaze fixations have a strong and significant relationship. Therefore, we conclude that the complexity variable must always be considered in the speech synthesis process of mathematical expressions. However, when considering why participants requested the repetition of an expression with not larger complexity during the memorization process, a tentative interpretation based on the number of MathML tree nodes and the computed complexity of the expressions was not enough to explain it, indicating that other factors need to be investigated. Although some answers to the research questions were not yet conclusive, we consider this research relevant because it points to directions for the work in order to minimize the cognitive processing and mental load of the synthesized speech rendering of mathematical expressions. © 2022 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Controller for Autonomous Following of a Target Platform for Drones 2

A Lightweight Controller for Autonomous Following of a Targe...

引用

2nd International Conference on Cybernetics and Innovations, ICCI 2023

作者： Farooq, Aadil Shafi, Sadman Ullah, Zahid Quresh, Moomal Chumuang, Narumol Ucy Dept. of Electrical and Computer Engineering Cyprus Penn State University Dept. of Electrical Engineering United States Politecnico di Milano Dept. of Electronics Information and Bioengineering Italy University of Lyon CNRS INSA-Lyon Universite Claude Bernard Lyon 1 France Muban Chombueng Rajabhat University Dept. of Digital Media Technology Thailand

ISBN: (纸本)9798350336573

Drones or Unmanned Aerial Vehicles (UAVs) are providing interminable opportunities to capture high-quality video feeds that were previously impossible and have transformed the digital era. Many applications today require computer vision (CV) and machine learning (ML) techniques to extract the useful information captured from the onboard camera, and send it to an embedded controller that can make independent decisions. For instance, maneuvering the drone to follow a target platform by using only the onboard camera feed is critical in target tracking. Therefore, in this paper, we exploit the applicability of a low-computational embedded tracking controller to follow a target platform e.g. a car or pedestrian, and thus, react in real-time, adjusting the drone steering angles and velocity. We developed a system that enables drones to follow a target platform autonomously without requiring continuous human intervention on an embedded state-of-the-art STM32 Nucleo board. The system includes a lightweight controller that controls the drone's movement and enables it to track and follow a target platform accurately. To validate the performance of our embedded controller, we performed a number of experiments in an open-source AirSim simulator. The tracking controller footprint and memory consumption was less than 3%, and was able to reliably track and trail the target platform in different environmental conditions. © 2023 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Optimization of Multi-Channel Quartz Crystal Microbalance for Gas Sensing Application 8

Optimization of Multi-Channel Quartz Crystal Microbalance fo...

引用

8th IEEE International Conference on Recent Advances and Innovations in engineering, ICRAIE 2023

作者： Zainuddin, Ahmad Anwar Bhattacharjee, Soumik Md Ralib, Aliza Aini Mohd Sukri, Nurain Sufi Sabreena Binti Kamarudin, Saidatul Izyanie Subramaniam, Krishnan Handayani, Dini Reyasudin Basir Khan, M. Muhammad Saifudin, Nik Nor International Islamic University Malaysia Computer Science Kuliyyah of Information Communication Technology Kuala Lumpur Malaysia Universitat Bremen Digital Media Masters Germany International Islamic University Malaysia Department of Electrical and Computer Engineering Kuala Lumpur Malaysia Selangor Shah Alam Malaysia Mila University Department of Mechanical Engineering Nilai Negeri Sembilan Malaysia Kuala Lumpur Malaysia

ISBN: (纸本)9798350315516

Mass detection sensor Quartz Crystal Microbalance (QCM) measures mass sensitivity by piezoelectric, high frequency shaving on nanograms these sensors detect with high precise geometry, low cost and ease of production. Conventional QCM sensors are limited to one electrode structure that minimizes the range of sensing. On a single quartz crystal substrate, three new QCM Multi-Channel sensors are developed and optimized that include 2-channel, 3-channel and 4-channel QCM sensors the COMSOL Multiphysics software is used to design and simulate the multi-channel sensors to enhance the device structure for applications with less interference frequency. From the results, it shows that the least interferences exhibit frequency values of 9.58MHz as both QCMs for the 5mm centre-to-centre (c2c). However, due to small c2c distances that decrease accuracy and operating disadvantages, this design was not selected. For 3 channel sensors, however, three resonant peaks show a similar value of 9.58MHz when c2c is maintained at 7mm. With the highest c2c distance this design shows less interference. Finally, for 4-channel sensors, a distance of 6 mm c2c also has a minimum interference with a 9.58 MHz resonance frequency. This shows that 4 channel sensors with the highest c2c can provide greater operational convenience and less interference at frequencies and thus maximize measurement accuracy. Multi-sensor arrays are advantageous when detecting a large number of analytes at the same time or when only selective coatings (coatings that respond to more than one analyte at the same time) are available these sensor arrays, which use only one sensor and combine it with enhanced signal evaluation methods or prior sample separation to achieve the results of multi-sensor arrays, are becoming increasingly popular. © 2023 IEEE.

关键词： Quartz crystal microbalances

来源：评论

学校读者我要写书评

暂无评论

Towards Seamless Connectivity: Implementing 6G Communication Technologies in Next-Generation Networks 3

Towards Seamless Connectivity: Implementing 6G Communication...

引用

3rd International Conference for Advancement in technology, ICONAT 2024

作者： Kalaiselvi, K. Sankar, R. Supriya, S. Kaushik, G. Swamy, Hemanth Devika, M. Saveetha College of Liberal Arts and Sciences SIMATS Department of Data Analytics Tamilnadu Chennai India Chennai Institute of Technology Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India MLR Institute of Technology Department of Electronics and Communication Engineering Hyderabad India Motorola Solutions United States Dhanalakshmi College of Engineering Department of AI& DS Tamil Nadu Chennai India

ISBN: (纸本)9798350354171

Advanced wireless networks are essential given the increase in demand for smart services enabled by the Internet of Everything (IoE). Despite the fact that 5G networks could enable Internet of Everything (IoE)-based services, they can't meet all of the requirements needed to create intelligent applications. In order to overcome the shortcomings of the current infrastructure, there is an increasing demand to investigate the potential of 6G wireless communication technologies. Complex network optimization problems can be resolved by integrating artificial intelligence into sixth generation networks. An increasing user base and support for large-scale data-driven applications are essential given the fast evolving 6G landscape. In addition to highlighting network needs, critical supporting technologies, and a comparison of 5G and 6G networks, this study looks at recent advancements and trends in 6G technology. The report also explores new approaches to 6G connectivity, such as edge computing, backscatter communications, AI-driven IoT networks, and holographic beamforming, all of which are meant to support intelligent communities. In order to achieve the goal of 6Gbased IoT networks, it concludes by outlining potential research avenues. © 2024 IEEE.

关键词： Internet of Everything

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：