检索结果-内蒙古大学图书馆

52nd IEEE Photovoltaic Specialist Conference, PVSC 2024

作者： Kurokawa, Yasuyoshi Iseki, Yoshiko Gotoh, Kazuhiro Miyamoto, Satoru Ozaki, Ryo Nakamura, Kyotaro Ohshita, Yoshio Usami, Noritaka Niigata University Dept. Electrical and Information Engineering Niigata950-2181 Japan Intereisciplinaty Research Center for Carbon-Neutral Technologies Niigata University Niigata950-2181 Japan Toyota Technological Institute Dept. Advanced Science and Technology Nagoya468-8511 Japan Nagoya University Dept. Materials Process Engineering Nagoya464-8603 Japan Institute of Materials and Systems for Sustainability Nagoya University Nagoya464-8601 Japan Institutes of Innovation for Future Society Nagoya University Nagoya464-8601 Japan

ISBN: (纸本)9781665464260

Lightweight and flexible PV modules are required to apply PV to buildings and vehicles. One way to realize lightweight and flexible PV is to make the silicon substrate thinner. However, thinner substrates result in lower near-infrared light absorption. Although light trapping structure (LTS) can increase light absorption, conventional alkali-etched pyramid textures are not specialized for near-infrared light and are insufficient to improve near-infrared light absorption. Therefore, in this study, a honeycomb LTS was implemented into the rear side of Si heterojunction (SHJ) solar cells by a nanoimprinting method, which enables us to prepare submicron-sized LTS on solar cells over a large area. As a result, in the near-infrared range of more than 1000 nm, the reflectance of the sample with honeycomb LTS was reduced compared to that without the LTS. The reflectance at 1050 nm was reduced from 59.2 to 41.5%. The external quantum efficiency (EQE) in the near-infrared range of more than 1000 nm was also increased by the LTS, leading to the improvement of the short-circuit current density (Jsc) by 0.02 mA/cm2 © 2024 IEEE.

关键词： Honeycomb structures

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Bias-Variance Trade-Off Through Functional Constraints

Multi-Task Bias-Variance Trade-Off Through Functional Constr...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Juan Cerviño Juan Andrés Bazerque Miguel Calvo-Fullana Alejandro Ribeiro Dept. of Electrical and Systems Engineering University of Pennsylvania Philadelphia USA Dept. of Electrical and Computer Engineering University of Pittsburgh Pittsburgh USA Dept. of Information and Communication Technologies Universitat Pompeu Fabra Barcelona Spain

Multi-task learning aims to acquire a set of functions, either regressors or classifiers, that perform well for diverse tasks. At its core, the idea behind multi-task learning is to exploit the intrinsic similarity across data sources to aid in the learning process for each individual domain. In this paper we draw intuition from the two extreme learning scenarios – a single function for all tasks, and a task-specific function that ignores the other tasks dependencies – to propose a bias-variance trade-off. To control the relationship between the variance (given by the number of i.i.d. samples), and the bias (coming from data from other task), we introduce a constrained learning formulation that enforces domain specific solutions to be close to a central function. This problem is solved in the dual domain, for which we propose a stochastic primal-dual algorithm. Experimental results for a multi-domain classification problem with real data show that the proposed procedure outperforms both the task specific, as well as the single classifiers.

关键词： Soft sensors Signal processing algorithms Signal processing Multitasking Acoustics Classification algorithms Task analysis

来源：评论

学校读者我要写书评

暂无评论

Mobile Gateways for LoRa End-Devices: Support Connectivity on the Move

Mobile Gateways for LoRa End-Devices: Support Connectivity o...

引用

IEEE International Workshop on computer-Aided Modeling, Analysis, and Design of Communication Links and Networks, CAMAD

作者： Vasileios Moysiadis Dimitrios N. Skoutas Charalabos Skianis Thomas Lagkas Vasileios Argyriou Panagiotis Sarigiannidis Dept. of Electrical and Computer Engineering University of Western Macedonia Kozani Greece Dept. of Information and Communication Systems Engineering University of the Aegean Samos Greece Dept. of Computer Science International Hellenic University Greece Dept. of Networks and Digital Media Kingston University Kingston upon Thames United Kingdom

ISBN: (数字)9798350377644

ISBN: (纸本)9798350377651

This paper proposes a method enabling mobile LoRa gateways to support mobile end devices. The approach utilizes trilateration and similar approaches based on RSSI to estimate the position of end devices and specify the movement of the gateways to maintain contact. The evaluation of the proposed method tests various parameters such as speed and number of end devices, and it shows that it is able to retain contact even with speeds up to 12 mps. Moreover, the evaluation shows that the ADR-MIN algorithm performs better in this scenario than the default ADR.

关键词： Performance evaluation Network servers Conferences Computational modeling LoRa Logic gates Low-power wide area networks

来源：评论

学校读者我要写书评

暂无评论

Hash Tag-Based Sentiment Analysis Using A Deep Learning Approach

Hash Tag-Based Sentiment Analysis Using A Deep Learning Appr...

引用

International Conference on Advanced Computing and Communication systems.(ICACCS)

作者： R. Venkatesan M. Sangeetha S. Nivedha M. Selvakumar K.S. Chandru P. Parthasarathi Department of Information Technology Bannari Amman Institute of Technology Erode India Department of Information Technology K S Rangasamy College of Technology Namakkal India Dept. of Computer Science & Engineering Hindusthan College of Engg and Technology Coimbatore India Dept. Computer Science & Business Systems Bannari Amman Institute of Technology Erode India Dept. Computer Science and Engineering Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

Social commerce uses a variety of social networking sites like Facebook, Instagram, Twitter, Pinterest, and business Whatsapp as a platform to promote products and services. Since advertising, a product, or service in s-comm will reach as high as a possible number of users on networking sites. Ads will spread virally by sharing among friends and friends of friends. So that wider reachability is possible and shortly will get the customer for our business. The success of an s-comm campaign is measured by the degree to which consumers interact with the sellers through review comments, likes, and shares between friends. Customer behavior analysis is needed for s-comm marketing because social commerce can significantly boost economic growth. The sentiment analysis of customer recommendations was investigated using a dataset of women's s-comm apparel hashtags and reviews. So for such reviews are experimented with different machine learning algorithms (Decision tree, SVM, Random Forest, KNN, Naïve Bayes and LSTM). These models handled the common English reviews and compared the metrics (Accuracy, Sensitivity and Specificity) with one another. Instead of working with individual model, this paper introduces a novel hybrid approach that integrates CNN and Ada Boost LSTM algorithms to provide better results in sentiment analysis when compared to other machine learning algorithms mentioned above. While considering the hash tag with common review comments the hybrid system is out performed. The comparison analysis is done for performance matrices namely accuracy of 98%, specificity of 98.1%, and sensitivity of 98.1%. In the s-commerce transaction industry, this hybrid approach will help to create a deeper understanding of consumer sentiment analysis and psychologically attract clients.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Sensitivity Machine learning algorithms Reviews Social networking (online) Biological system modeling Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Distributed Ensemble of Diverse Deep Learning Models for Predicting COVID-19 Cases 20

A Distributed Ensemble of Diverse Deep Learning Models for P...

引用

20th International Conference on Smart technologies, EUROCON 2023

作者： Hassan, Mohammad Mehedi Alrakhami, Mabrook S. Elhendi, Ahmed Zohier Alqahtani, Salman A. King Saud University Information Systems Department Ccis Riadh 11543 Saudi Arabia King Saud University Science Technology and Innovation Dept. Riadh 11543 Saudi Arabia King Saud University Computer Engineering Department Ccis Riadh 11543 Saudi Arabia

ISBN: (纸本)9781665463973

The outbreak of the COVID-19 pandemic has resulted in a significant impact on global health and economy. Forecasting the spread of COVID-19 cases is essential for policymakers to make informed decisions and allocate resources accordingly. Deep learning has shown promising results in predicting the spread of infectious diseases, including COVID-19. However, selecting the most appropriate model for a given forecasting task can be challenging, as no single model is guaranteed to perform well for all scenarios. In this paper, we propose a distributed ensemble approach that combines the predictions of different deep learning models, including Autoregressive Integrated Moving Average (Auto-ARIMA), Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), to improve the accuracy of COVID-19 case forecasts. Specifically, we train each deep learning model on a subset of the data and aggregate their predictions to obtain an ensemble forecast. To achieve a distributed ensemble, we use an edge computing framework to train the deep learning models on multiple nodes in a parallel and distributed manner. We evaluate our approach on publicly available COVID-19 datasets, and our results show that the proposed ensemble model outperforms the individual models in terms of forecasting accuracy. Furthermore, our distributed ensemble approach significantly reduces the training and prediction time compared to training each model separately. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Deciphering Deceit: Multimodal Classification of Optimal Algorithms for Fake Website Detection

Deciphering Deceit: Multimodal Classification of Optimal Alg...

引用

Blockchain and Distributed systems.Security (ICBDS), IEEE International Conference on

作者： Supriya Thombre Vaibhaw Doifode Sakshi Kokardekar Udit Hasija Sampada Wazalwar Dept. of Computer Technology Yeshwantrao Chavan College of Engineering Nagpur India Dept. of Electrical Engineering Yeshwantrao Chavan College of Engineering Nagpur India KPIT Technologies Limited Pune India Dept. of Computer Science and Engineering Bhartiya Vidyapeeth College of Engineering New Delhi India Dept. of Information Technology G.H. Raisoni College of Engineering Nagpur India

ISBN: (数字)9798350354348

ISBN: (纸本)9798350354355

Detecting fake website URLs is crucial in today's digital era, where online scams and malicious/ fraudulent activities abound. Such websites pose a myriad of problems in the digital landscape, ranging from financial loss and identity theft to the dissemination of misinformation and the erosion of trust in online platforms. Individuals who fall victim to fraudulent websites may suffer financial repercussions, as they may unknowingly disclose confidential information such as details of credit card or login credentials. Moreover, fake websites can deceive users by spreading false information or promoting illegitimate products and services, which can undermine public trust in online sources and exacerbate societal issues such as misinformation and cybercrime. Therefore, there is a pressing need to detect fake websites promptly to mitigate these risks and protect users' privacy, financial security, and trust in the online environment. This study by the authors evaluates the predictive performance of five machine learning (ML) models— Random Forest (RF) Classifier, Decision Tree (DT)) Classifier, K-Neighbors (KN) Classifier, SGD Classifier and Gaussian NB (GNB)—in the reference of malicious and fake website URL detection. Leveraging a diverse dataset encompassing both benign and malicious URLs, our analysis encompasses rigorous evaluation metrics. The results highlight distinct strengths and weaknesses among the models, offering valuable insights for practitioners seeking to optimize predictive capabilities in the realm of cybersecurity. These findings contribute to the ongoing refinement of machine learning strategies for effective malicious URL detection and mitigation.

关键词： Uniform resource locators Privacy Machine learning algorithms Prevention and mitigation Identity theft Pressing Predictive models Prediction algorithms Fake news Random forests

来源：评论

学校读者我要写书评

暂无评论

A Model for Intelligible Interaction Between Agents That Predict and Explain

arXiv

引用

arXiv 2023年

作者： Baskar, A. Srinivasan, Ashwin Bain, Michael Coiera, Enrico Dept. of Computer Science Information Systems BITS Pilani Goa Campus India Dept. of Computer Science Information Systems and APPCAIR BITS Pilani Goa Campus India School of Computer Science Engineering University of New South Wales Australia Centre for Health Informatics Macquarie University Sydney Australia

Machine Learning (ML) has emerged as a powerful form of data modelling with widespread applicability beyond its roots in the design of autonomous agents. However, relatively little attention has been paid to the interaction between people and ML systems. In this paper we view interaction between humans and ML systems.within the broader context of communication between agents capable of prediction and explanation. We formalise the interaction model by taking agents to be automata with some special characteristics and define a protocol for communication between such agents. We define One- and Two-Way Intelligibility as properties that emerge at run-time by execution of the protocol. The formalisation allows us to identify conditions under which run-time sequences are bounded, and identify conditions under which the protocol can correctly implement an axiomatic specification of intelligible interaction between a human and an ML system. We also demonstrate using the formal model to: (a) identify instances of One- and Two-Way Intelligibility in literature reports on humans interacting with ML systems.providing logic-based explanations, as is done in Inductive Logic Programming (ILP);and (b) map interactions between humans and machines in an elaborate natural-language based dialogue-model to One- or Two-Way Intelligible interactions in the formal model. © 2023, CC BY.

关键词： Inductive logic programming (ILP)

来源：评论

学校读者我要写书评

暂无评论

Accelerating Real-Time Imaging for Radiotherapy: Leveraging Multi-GPU Training with PyTorch 22

Accelerating Real-Time Imaging for Radiotherapy: Leveraging ...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Obe, Ruth Kaufmann, Brandt Baird, Kaelen Kadel, Sam Soltani, Yasmin Cham, Mostafa Gobbert, Matthias K. Barajas, Carlos A. Jiang, Zhuoran Sharma, Vijay R. Ren, Lei Peterson, Stephen W. Poif, Jerimy C. U. of Houston-Clear Lake Dept. of Computer Science and of Software Engineering United States U. of San Francisco Dept. of Mathematics and Statistics United States Skidmore College Dept. of Computer Science and of Mathematics United States Mount Holyoke College Dept. of Computer Science and of Psychology United States U. of Houston Dept. of Biomedical Engineering United States U. of Maryland Dept. of Information Systems Baltimore County United States U. of Maryland Dept. of Mathematics and Statistics Baltimore County United States Medical Physics Graduate Program Duke University United States U. of Maryland School of Medicine Dept. of Radiation Oncology United States U. of Maryland School of Medicine Department of Radiation Oncology United States U. of Cape Town Dept. of Physics South Africa H3D Inc. United States

ISBN: (纸本)9798350345346

Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mit-igate unnecessary radiation exposure in healthy tissues. Real-time imaging of prompt gamma rays with Compton cameras has been suggested to improve therapy efficacy. However, the camera's non-zero time resolution leads to incorrect interaction classifications and noisy images that are insufficient for accurately assessing proton delivery in patients. To address the challenges posed by the Compton camera's image quality, machine learning techniques are employed to classify and refine the generated data. These machine-learning techniques include recurrent and feedforward neural networks. A PyTorch model was designed to improve the data captured by the Compton camera. This decision was driven by PyTorch's flexibility, powerful capabilities in handling sequential data, and enhanced G PU usage. This accelerates the model's computations on large-scale radiotherapy data. Through hyperparameter tuning, the validation accuracy of our PyTorch model has been improved from an initial 7 % to over 60 %. Moreover, the PyTorch Distributed Data Parallelism strategy was used to train the RNN models on multiple G PU s, which significantly reduced the training time with a minor impact on model accuracy. © 2023 IEEE.

关键词： Clas-sification Compton camera Distributed Data Parallelism Proton beam therapy PyTorch Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Machine Learning-Based Controller Area Network Intrusion Detection systems

Comparative Evaluation of Machine Learning-Based Controller ...

引用

International Conference on information and Communication systems.(ICICS)

作者： Omar Y. Al-Jarrah Omar A. Ramadan Baha Alsaify Suboh Alkhushayni Dept. Network Engineering and Security Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan Dept. Mechanical Engineering Faculty of Engineering Jordan University of Science and Technology Irbid Jordan Dept. Information Systems Yarmouk University Irbid Jordan

The controller area network (CAN) protocol is widely used in vehicle networks. However, it lacks essential security features like confidentiality and authentication. To enhance vehicle security, researchers have proposed and developed various methods, including intrusion detection systems.(IDSs). These IDSs play a key role in early detection of potential cyberattacks, safeguarding vehicles, passengers, and road users. Machine learning (ML) algorithms are increasingly employed in CAN IDSs but they face challenges due to diverse experimental settings, datasets, and metrics used for evaluation, impeding progress and comparison of different approaches in this field. This study aims to benchmark well-recognized ML algorithms, including gaussianNB, k-nearest neighbors (KNN), decision trees (DT), random forest (RF), long short-term memory (LSTM), and convolutional neural networks (CNN), for intrusion detection in CAN. We evaluate the performance of these algorithms using seven evaluation metrics on the real ORNL automotive dynamometer (ROAD) dataset, a state-of-the-art benchmark in this field. Experimental results demonstrate that KNN, DT, RF, LSTM, and CNN can detect various types of attacks (e.g., Fuzzing, targeted ID, and masquerade attacks) with high accuracy. However, the computational and time efficiency of tree-based classifiers, namely DT and RF, makes them a potentially appealing choice for real-time intrusion detection tasks in CAN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced Visual Interfaces and Interactions in Cultural Heritage (AVICH 2024) 24

Advanced Visual Interfaces and Interactions in Cultural Heri...

引用

Proceedings of the 2024 International Conference on Advanced Visual Interfaces

作者： Tsvi Kuflik Berardina Nadja De Carolis Cristina Gena Antonio Origlia Julia Sheidin Information Systems The University of Haifa Israel Department of Computer Science dipartimento di informatica universita' di bari Italy Computer Science Department of Computer Science University of Torino Italy Dept. of Electrical Engineering and Information Technology URBAN/ECO Research Center ?Federico II? University Naples Italy Italy Information Systems Braude College Israel

ISBN: (纸本)9798400717642

Cultural Heritage (CH) is a challenging domain of application for novel information and Communication technologies (ICT), where visualization plays a major role in enhancing the visitors’ experience, whether onsite or online. Technology-supported natural human-computer interaction is a key factor in enabling access, both on-site and online, to CH assets. Recent advances in ICT enhance visitors’ access to online collections as well as their CH experience onsite, bringing even wider audiences than those who visit the physical museums. The range of visualization devices – from tiny smartwatch screens, through large situated public displays, to the latest generation of immersive Head-Mounted Displays – together with the increasing availability of real-time 3D rendering technologies for online and mobile devices and, recently, Internet of Things (IoT) approaches, Social Robotics, requires exploring how they can be applied successfully in CH. Following the successful workshops at AVI 2016, AVI 2018, AVI 2020, AVI 2022 and AVI 2024 and a large number of recent events and projects focusing on CH, the goal of the workshop is to bring together researchers and practitioners interested in presenting and discussing the potential of state of the art advanced visual interfaces in enhancing our daily cultural heritage experience. This year the workshop theme will be: AVI for accessibility in CH.

关键词：

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：