检索结果-内蒙古大学图书馆

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

A Semisupervised Approach to Predicting a Twitch Streamer’s Growth based on the Game Streamed

A Semisupervised Approach to Predicting a Twitch Streamer’s...

引用

IEEE International Conference on Big Data

作者： Andrew Dybka Dominic Kocjan Samuel A. Ajila Dept. of Systems and Computer Engineering Carleton University Ottawa Canada

ISBN: (纸本)9781665480468

Games live streaming is growing rapidly as a form of entertainment. A game streamer will like to know what game to stream in order to attract huge number of viewers and followers which in turn will generate sizable income for the streamer. Using streamer’s metrics, the main goal of this research work is to design and develop a set of resources that a streamer can use to maximize the number of viewers and followers for a particular game and when to play the game. This research develops two models using machine learning techniques that can be used by game streamers to maximum the returns on investment. When both model predictions are presented as percentage, Model 1 using regression algorithms provides a MAE of 5.48 meaning the prediction has an error within 5.48% of the streamer’s total follower count. Also, Model 1 has 85.46% of its predictions’ absolute error less than or equal to 5. Similarly Model 2 with 2.53 MAE and 87.68% of its predictions’ absolute error less than or equal to 5.

关键词： Measurement Machine learning algorithms Entertainment industry Games Machine learning Forestry Predictive models

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Deep Learning Model for Detecting Breast Cancer

TechRxiv

引用

TechRxiv 2023年

作者： Banerjee, Avishek Chakraborty, Debasis Bhattacharyya, Basanti Nath, Ira Dey, Debashis Garg, Deepak Dept. of Computer Science and Business Systems Asansol Engineering College West Bengal 713305 India Dept. of Computer Science and Engineering Asansol Engineering College Asansol713305 India Dept. of Computer Science and Engineering Pailan College of Management and Technology West Bengal 700139 India Dept. of Computer Science and Engineering JIS College of Engineering West Bengal 741235 India Dept. of Computer Science and Engineering Maulana Abul Kalam Azad University of Technology West Bengal 700064 India School of Computer Science and Artificial Intelligence SR University Telangana Warangal506371 India

Cancer is a deformity of the body cells that grow out of control and spread to other parts of body. According to the American Cancer Society, early identification of cancer resulted in a 99% chance of survival in the localized stage. In this article, a benchmark cancer dataset is considered for the purpose of investigation. After data preprocessing, we attempt to predict cancer type using our proposed deep learning model named as CNN-Soft-T that combines the feature selection (FS) and classification. FS is introduced using histogram technique for anomaly detection and dimension reduction. We have compared the performance of this model to other cutting-edge machine learning approaches including Logistic Regression (LR), Naive Bayes (NB), Support Vector Machine (SVM), Random Forest (RF), Neural Network (NN) and Decision Tree (DT) in order to demonstrate its utility. We have experimentally exhibited the exceptional empirical effectiveness and biological applicability of our suggested hybrid model for cancer diagnostics and medication development. © 2023, CC BY.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Improving the Efficiency of a Multistage Evaporator Station for Sugar Production Using Neural Networks 4

Improving the Efficiency of a Multistage Evaporator Station ...

引用

4th IEEE International Conference on Modern Electrical and Energy System, MEES 2022

作者： Zaiets, Nataliia Lutska, Nataliia Vlasenko, Lidiia National University of Life and Environmental Sciences of Ukraine Det. of Automation and Robotic Systems Kyiv Ukraine National University of Food Technologies Dept. of Automation and Computer Technologies of Control Systems Kyiv Ukraine State University of Trade and Economics Dept. of Software Engineering and Cyber Security Kyiv Ukraine

ISBN: (纸本)9798350346831

The paper shows the process of developing a model of multistage evaporator station of a sugar factory based on a neural network. The neural network predicts the main performance indicators of the multistage evaporator station, such as the concentration of syrup at the output of the evaporator and the amount of evaporated water at the station. Unlike existing solutions, forecasting is performed in real time based on a set of indicators of the automation system (temperatures, flow rates, levels, pressure, density in the apparatus) and industrial laboratory (concentration of solids at the inlet to the evaporation station). The proposed neural network model has an MLP structure with 27 inputs, 2 outputs and one hidden layer with 20 neurons and predicts these indicators with an error of less than 5%. This allows to increase the informative support of the operator-technologist on the quality indicators of the enterprise without additional load on the industrial laboratory and without additional cost automatic quality devices, as well as to perform timely adjustment of the technological mode of the department. © 2022 IEEE.

关键词： Evaporation

来源：评论

学校读者我要写书评

暂无评论

Attenuation Resilient Underwater Ranging Using Petal-Like Structured Light with Tailorable Longitudinal Intensity

Attenuation Resilient Underwater Ranging Using Petal-Like St...

引用

2024 Laser Science, LS 2024

作者： Wang, Yingning Duan, Yuxiang Zeng, Ruoyu Zhou, Huibin Jiang, Zile Zuo, Yue Ramakrishnan, Muralekrishnan Bock, Robert Mojahedi, Mo Tur, Moshe Willner, Alan E. Dept. of Electrical Engineering University of Southern California Los AngelesCA90089 United States R-DEX Systems Inc. WoodstockGA30188 United States Department of Electrical and Computer Engineering University of Toronto TorontoONM5S 3G4 Canada School of Electrical Engineering Tel Aviv University Ramat Aviv 69978 Israel

We experimentally demonstrate a petal-like attenuation-resilient ranging beam with a ~9.5-dB central power enhancement at a 0.4-meter ranging distance, achieving 5 mm average ranging errors over 0-0.4 m in scattering ...

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Goldilocks Framework: Towards Selecting the Optimal Approach to Conducting AI Projects 22

The Goldilocks Framework: Towards Selecting the Optimal Appr...

引用

1st International Conference on AI engineering - Software engineering for AI, CAIN 2022

作者： Dzhusupova, Rimman Bosch, Jan Olsson, Helena Holmstrom Control & Safety Systems McDermott Dept. of Electrical & Instrumentation The Hague Netherlands Chalmers University of Technology Department of Computer Science and Engineering Gothenburg Sweden Malmö University Department of Computer Science and Media Technology Malmö Sweden

ISBN: (纸本)9781450392754

Artificial intelligence is increasingly becoming important to businesses since many companies have realized the benefits of applying Machine Learning (ML) and Deep Learning (DL) into their operations. Nevertheless, ML/DL technologies' industrial development and deployment examples are still rare and generally confined within a small cluster of large international companies who are struggling to apply ML more broadly and deploy their use cases at a large scale. Meanwhile, current AI market has started offering various solutions and services. Thus, organizations must understand how to acquire AI technology based on their business strategy and available resources. This paper discusses the industrial experience of developing and deploying ML/DL use cases to support organizations in their transformation towards AI. We identify how various factors, like cost, schedule, and intellectual property, can be affected by the choice of approach towards ML/DL project development and deployment within large international engineering corporations. As a research result, we present a framework that covers the trade-offs between those various factors and can support engineering companies to choose the best approach based on their long-term business strategies and, therefore, would help to accomplish their ML/DL project deployment successfully. © 2022 ACM.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Analysis of Energy Potential of Micro Wind Turbines at Three Locations in the Central-Eastern Part of the Bulgarian Danube River Region

Analysis of Energy Potential of Micro Wind Turbines at Three...

引用

Communications, Information, Electronic and Energy systems (CIEES), International Conference on

作者： Nikolay Valov Katerina Gabrovska-Evstatieva Ivaylo Stoyanov Tsvetelina Kaneva Seher Kadirova Boris Evstatiev Nicolay Mihailov Dept. of Automation and Electronics University of Ruse "Angel Kanchev" Ruse Bulgaria Dept. of Computer Science University of Ruse "Angel Kanchev" Ruse Bulgaria Dept. of Electrical Power Engineering University of Ruse "Angel Kanchev" Ruse Bulgaria Dept. of Computer Systems and Technologies University of Ruse "Angel Kanchev" Ruse Bulgaria

ISBN: (数字)9798350352863

ISBN: (纸本)9798350352870

The share of renewable energy sources in the energy mix worldwide is gradually increasing. And even though they all have a highly variable nature, they can be forecasted statistically. The wind energy potential was investigated in this article in the Bulgarian Danube region, located between Ruse and Silistra. Two years of meteorological data, including the wind speed at 10 m height and the ambient temperature was used to estimate the average wind energy for each month of the year at three geographic locations – Ruse, Staro Selo (near Tutrakan), and Calarasi, Romania (near Silistra). The results showed that Staro Selo has the highest energy potential, reaching up to 0.75 kWh/day/m 2 in February, followed by Calarasi with 0.38 kWh/day/m 2 . The city of Ruse showed the lowest wind potential with the highest average monthly value reaching only 0.0027 kWh/day/m 2 . The obtained results showed that the regions around Tutrakan and Silistra are appropriate for the application of micro wind turbines.

关键词： Hands Temperature distribution Renewable energy sources Wind energy Wind speed Urban areas Wind turbines Rivers Wind forecasting Investment

来源：评论

学校读者我要写书评

暂无评论

UI/UX Design for Online Learning Approach by Predictive Student Experience 7

UI/UX Design for Online Learning Approach by Predictive Stud...

引用

7th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2023

作者： Chaganti, Koushik Reddy Ramula, Uttham Sai Sathyanarayana, Cheruku Changala, Ravindra Kirankumar, N. Gupta, K. Gurnadha University of the Cumberlands Dept. of Computer and Information Systems KY United States Nalla Malla Reddy Engineering College Dept of CSE India Guru Nanak Institutions Technical Campus Dept of IT Hyderabad India JNTUA Dept of CSE Anantapuram India K L Deemed to Be University Dept of CSE AP Vaddeswaram India

ISBN: (纸本)9798350340600

This study examines how an User Interface (UI) and User Experience (UX) design for online learning/educational platforms can be designed in a way that can be fully effective for achieving educational outcomes. In order to find out the importance of UI/UX design, a quick survey was conducted using Google Form about user experience in terms of UI of tools and websites, audio, video clarity, screen sharing, messaging chat, number of maximum participants, network adaptability, course, name, age, cost and demographic location. In this survey, 560 students participated from across the discipline. Out of 560 participants only 530 respondents, out of 530, 359(67.9%) were male and 171(32.1%) respondents are female. 470 (88.7%) respondents feel that UI design is vital for a tool or website while 401 (75.6%) respondents had bad experience of UI, 106 (26.4%) students continue with website even it has bad UX and 295 (73.6%) students leave the website. 350 (66.6%) respondents prefer to ease of use, 53 (10%) respondents prefer mobile accessibility, 111 (21%) students prefer technical support and 148 (28%) respondents prefer cost more than UI design of e-learning platforms. The survey shows that most of the respondents are male and mean (SD) age 21 years. Zoom app and Udemy are their most preferred tool and online learning platform respectively. In this study, a number of user studies are given that may be used to evaluate UI and UX and examine usability as well as utility. Additionally, applying ML techniques on curated datasets to find best UI design of tool and website for online platform. © 2023 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning based Routing in an Air-to-Air Ad-hoc Network 41

Deep Reinforcement Learning based Routing in an Air-to-Air A...

引用

41st IEEE/AIAA Digital Avionics systems Conference, DASC 2022

作者： Wang, Zhe Han, Ruixuan Li, Hongxiang Knoblock, Eric J. Apaza, Rafael D. Gasper, Michael R. University of Louisville Dept. of Electrical and Computer Engineering LouisvilleKY United States Nasa Glenn Research Center Communications and Intelligent Systems Division ClevelandOH United States

ISBN: (数字)9781665486071

ISBN: (纸本)9781665486071

This paper studies the Multiple Sources and Multiple Destinations (MSMD) routing problem in a dynamic Air-to-Air Ad-hoc Network (AAAN). We consider a spectrum-limited scenario where multiple links have to share the same frequency channel so that co-channel interference becomes inevitable. As a result, routing decisions and spectrum access are coupled and must be jointly considered. This paper proposes a deep Q-learning-based algorithm to find an optimal routing and channel selection strategy that minimizes the end-to-end communication delay. Specifically, under the assumption that only local information is available to every node, the Deep Q-Network (DQN) is trained offline to learn the optimal routing and channel selection strategy. After the trained DQN is implemented in every node, multiple relay nodes can simultaneously determine their next-hop relay and channel selections in real-time. Simulation results demonstrate the efficacy of our proposed algorithm. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Digital AirComp-Assisted Federated Edge Learning with Adaptive Quantization

Digital AirComp-Assisted Federated Edge Learning with Adapti...

引用

IEEE International Conference on Human-Machine systems

作者： Ghazaleh Kianfar S. Jamal Seye Dmohammadi Jamshid Abouei Arash Mohammadi Konstantinos N. Plataniotis Concordia Institute of Information Systems Engineering (CIISE) Concordia University Montreal Canada Dept. of Electrical Engineering Yazd University Yazd Iran The Edward S. Rogers Sr. Dept. of Electrical & Computer Engineering University of Toronto Canada

ISBN: (数字)9798350315790

ISBN: (纸本)9798350315806

Federated edge learning (FEEL) has been introduced for training machine learning models on distributed datasets for applications such as human monitoring. However, some challenges exist concerning the number of communication rounds and communication energy consumption involved in transmiting gradients during the training process. Moreover, over-the-air computation (AirComp) technology has gained attention recently, benefiting from superposition characteristic of wireless channels to compute functions over the air. While primarily designed for analog systems, there is potential for applying this technology in digital systems with embedded modulation schemes. This paper addresses these challenges by proposing a digital AirComp system for federated learning aggregation. The system employs a multi-bit quantization scheme to modulate gradients, adhering to a maximum transmission power constraint. An adaptive quantization scheme is also introduced, which considers the impact of quantization error and the error induced by additive white Gaussian noise. We derive closed-form expressions for pre-processing coefficients at devices and post-processing scaler at the access point (AP) to minimize the mean-squared error between high-precision and quantized qradients under the maximum transmission power constraint. Finally, the performance of the proposed scheme is evaluated in terms of achieved test accuracy, mean-squared error (MSE), and energy consumption, demonstrating its potential effectiveness compared to the benchmark schemes.

关键词： Training Performance evaluation Energy consumption Quantization (signal) Accuracy Federated learning Wireless networks

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：