检索结果-内蒙古大学图书馆

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Thangaraj, Rajasekaran Vadivel, Balasubramaniam Aravind, T. Chandhru, L. Harish, K. Eswaran, Sivaraman Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Curtin University Malaysia Department of Electrical and Computer Engineering Miri Malaysia

ISBN: (纸本)9798350310689

Plant diseases are a significant concern for the agricultural industry, as they can reduce crop yields and cause economic losses. Tea is a popular and widely consumed beverage in India, and the tea crop can be affected by different leaf diseases. Early detection of the diseases is essential to prevent the spread of other crops and minimize production losses. Traditional methods of detecting leaf diseases involve manually interpreting the images, which can be time-consuming and laborious. To address this, artificial intelligence techniques, specifically deep learning models are used for more accurate and efficient detection of tea leaf disease. This study compares the performance of several deep learning models including ResNet50, Resnet50-RS, ResNetlOl-V2, and Modified-ResNet50-V2 (M-RN50V2) and finds that the M-RN50V2 model has the highest accuracy at 90.S4%. Overall, this work aims to promote sustainable agriculture by leveraging cutting-edge technology for disease classification. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Illuminating the Interconnected Complexity of Cyberbullying Intentions within the Holistic Social Media Ecosystem 15

Illuminating the Interconnected Complexity of Cyberbullying ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Shraya, Bejgum Dopathi, Hari Charan Reddy Pattanaik, Balachandra Anitha, G. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Tamil Nadu Chennai India Wallaga University Department of Electrical and Computer Engineering Africa Nekemte Ethiopia

ISBN: (纸本)9798350370249

The research being presented here looks into the problems related to cyberbullying using data from Twitter and Wikipedia. To try and understand why people behave in this way online, the research included several challenging techniques, including a Support Vector Machine, Random Forest, Gaussian Naive Bayes, and a Voting Classifier that combines Logistic Regression, Random Forest, and Gaussian Naive Bayes. The accuracy of the Voting Classifier was 92.86% after Twitter data analysis. This demonstrates how well it detects and comprehends abusive tendencies. Not to mention, the Wikipedia dataset showed strong performance from the Voting Classifier, which had a success rate of 97.12%. Compared to other methods of research, it performed better. The research shows how machine learning algorithms can recognize and determine the identity of individuals attempting to cause harm to others via the internet. © 2024 IEEE.

关键词： Cyber Harassment Gaussian Naive Bayes Machine Learning Random Forest Support Vector Machine Voting Classifier

来源：评论

学校读者我要写书评

暂无评论

Forecasting Directional Movement of Stock Prices using Deep Learning

引用

Annals of Data science 2023年第5期10卷 1361-1378页

作者： Chandola, Deeksha Mehta, Akshit Singh, Shikha Tikkiwal, Vinay Anand Agrawal, Himanshu Department of Electrical Engineering and Computer Science York University Toronto Canada Hebert Werthim College of Engineering University of Florida Gainesville Gainesville United States Department of Electronics and Communication Engineering Jaypee Institute of Information Technology Noida India Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India

Stock market’s volatile and complex nature makes it difficult to predict the market situation. Deep Learning is capable of simulating and analyzing complex patterns in unstructured data. Deep learning models have applications in image recognition, speech recognition, natural language processing (NLP), and many more. Its application in stock market prediction is gaining attention because of its capacity to handle large datasets and data mapping with accurate prediction. However, most methods ignore the impact of mass media on the company’s stock and investors’ behaviours. This work proposes a hybrid deep learning model combining Word2Vec and long short-term memory (LSTM) algorithms. The main objective is to design an intelligent tool to forecast the directional movement of stock market prices based on financial time series and news headlines as inputs. The binary predicted output obtained using the proposed model would aid investors in making better decisions. The effectiveness of the proposed model is assessed in terms of accuracy of the prediction of directional movement of stock prices of five companies from different sectors of operation. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Development of Intelligent Remote Sensing Payloads for CubeSat Applications

Development of Intelligent Remote Sensing Payloads for CubeS...

引用

2024 Small Satellites Systems and Services Symposium, 4S 2024

作者： Juang, Jyh-Ching Lee, Pei-Jun Department of Electrical Engineering National Cheng Kung University Taiwan Department of Electronic and Computer Engineering National Taiwan University of Science and Technology Taiwan

ISBN: (纸本)9781510688940

The paper describes the development of a remote sensing payload for CubeSat applications. The inclusion of artificial intelligence into remote sensing payload has been pursued in the IRIS (Intelligent Remote sensing and Internet Satellite) and Lilium CubeSat programs. The paper discusses the development of a series of intelligent remote sensing payloads for CubeSats to address the limitations on computational resources, power, and communication bandwidth. From 2018 to 2021, under the IRIS program, an optical remote sensing payload that contains a high focal-length telescope, a CMOS detector, and the data operation board was developed. An edge intelligence for landslide detection and cloud segmentation is investigated by using MobileNet V2 network. The design has been implemented and tested by using an airborne platform. The design is further refined in the Lilium program with enhanced resolution and frame rate. Functions including auto-focus, automatic white balance, and gain control are also realized in the payload. To account for low-illumination scenario, a zero DCE (zero reference deep curve estimation) is utilized. Further, a light-weight U-net is implemented in the FPGA to achieve cloud detection and segmentation and a YOLO-SPD is implemented for object detection. This self-developed payload has been prototyped and is under tests. The payload will be integrated into the 6U Lilium-2 CubeSat and is planned to be launched in 2025. © 2025 The Authors.

关键词： Proximity sensors

来源：评论

学校读者我要写书评

暂无评论

Sizing electrolyzer capacity in conjunction with an off-grid photovoltaic system for the highest hydrogen production

引用

Energy Harvesting and Systems 2023年第2期10卷 331-348页

作者： Hassan, Qusay Abbas, Majid K Tabar, Vahid Sohrabi Tohidi, Sajjad Abdulrahman, Imad Saeed Salman, Hayder M. Department of Mechanical Engineering University of Diyala Baqubah Iraq Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran College of Technical Engineering Al-Farahidi University Baghdad Iraq Department of Computer Science Al-Turath University College Baghdad Iraq

The electrolysis of renewable energy to produce hydrogen has become a strategy for supporting a decarbonized economy. However, it is typically not cost-effective compared to conventional carbon-emitting methods. Due to the predicted intermediate of low-and zero-marginal-cost renewable energy sources, the ability of electrolysis to connect with electricity pricing offers a novel way to cost reduction. Moreover, renewables, particularly photovoltaics, have a deflationary effect on the value of the grid when they are deployed. This study investigates solar electrolysis configurations employing photovoltaic cells to feed a proton exchange membrane water electrolyzer for hydrogen production. Using experimental meteorological data at 1-min precision, the system has been evaluated in Baghdad, the capital of Iraq. Positioned at the yearly optimum tilt angle for the selected site, the solar array is rated at 12 kWp. Temperature effects on solar module energy loss are taken into account. Several electrolyzers with capacities ranging from 2 to 14 kW in terms of hydrogen production were examined to determine the efficacy and efficiency of renewable sources. MATLAB was utilized for the simulation procedure, with a 2021-2035 project lifespan in mind. The results suggest that a variety of potentially cost-competitive options exist for systems with market configurations that closely approximate wholesale renewable hydrogen. At 4313 h of operation per year, the planned photovoltaic array generated 18,892 kWh of energy. The achieved hydrogen production cost ranges between & amp;dollar;5.39/kg and & amp;dollar;3.23/kg, with an ideal electrolyzer capacity of 8 kW matching a 12 kWp photovoltaic array capable of producing 450 kg/year of hydrogen at a cost of & amp;dollar;3.23/kg. & amp;copy;2022 Walter de Gruyter GmbH, Berlin/Boston. © 2023 Walter de Gruyter GmbH. All rights reserved.

关键词： Electrolysis

来源：评论

学校读者我要写书评

暂无评论

Alkali niobium borogermanosilicate optical fiber derived via the molten core method [Invited]

引用

Optical Materials Express 2025年第6期15卷 1307-1317页

作者： Topper, Brian Baldus, Brandi Chapman, Kristin Walton, Matthew Dong, Liang Hawkins, Thomas W. Ballato, John Center for Optical Materials Science and Engineering Technologies Clemson University ClemsonSC29634 United States Department of Materials Science and Engineering Clemson University ClemsonSC29634 United States Department of Electrical and Computer Engineering Clemson University ClemsonSC29634 United States

Herein, multicomponent glass optical fibers are produced using the molten core fiber fabrication method. A pre-melted glass of 30 K2O-20 Nb2O5-50 GeO2 is used as a starting core material along with a low-alkali borosilicate (Duran) glass cladding. Some of the cladding dissolves into the core during the draw, and the final composition of the fiber core is a complex alkali borogermanosilicate with a little over 10 mol% Nb2O5. Although the germanium and niobium stay well confined within the core, potassium ions are observed to diffuse 10-15 µm beyond the core into the borosilicate cladding. The fibers have a large numerical aperture greater than 0.6. Yb-doped versions were fabricated to gauge feasibility of this platform for fiber gain media. Forward amplified spontaneous emission was observed with no signal;then, a 0.49 dB/cm signal amplification at 1026 nm was achieved. A parasitic background absorption coefficient value of 0.7 dB/cm at 1080 nm was measured. The phonon energy of the base niobium germanate and a simulated fiber core glass was measured using Eu3+ doped bulk glasses. The silicon and boron intrusion into the core does create high energy phonons around the rare-earth ions, but the niobium and/or germanium do appear to maintain strong influence over the excitation and the emission spectra in the Duran-diluted core glass composition. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Atomic emission spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Long-term solar radiation forecasting in India using EMD, EEMD, and advanced machine learning algorithms

引用

Environmental Monitoring and Assessment 2025年第3期197卷 1-36页

作者： RajasundrapandiyanLeebanon, T. Murugan, N. S. Sakthivel Kumaresan, K. Jeyabose, Andrew Department of Electrical and Electronics Engineering TamilNadu College of Engineering Tamil Nadu Coimbatore India Department of Mechanical Engineering Park College of Engineering & Technology TamilNadu Coimbatore India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Solar radiation plays a critical role in the carbon sequestration processes of terrestrial ecosystems, making it a key factor in environmental sustainability among various renewable energy sources. This study integrates two advanced signal processing techniques—empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD)—with machine learning (ML) algorithms, including multilayer perceptron (MLP), random forest regression (RFR), support vector regression (SVR), and ridge regression, to forecast long-term solar radiation. Meteorological data spanning 13 years (2000–2012) from seven locations across India (Bhubaneswar, Chennai, Delhi, Hyderabad, Nagpur, Patna, and Trivandrum) were used for training and testing. The optimal model was identified based on performance metrics, including the highest linear correlation coefficient (R), and the lowest mean absolute error (MAE) and root mean square error (RMSE). The results indicate that EEMD integrated with ML algorithms consistently outperformed EMD-based approaches. Among the ML models evaluated, EEMD integrated with MLP achieved the best performance across all locations, with RMSE = 0.332, MAE = 0.26, and R2 = 0.99. Furthermore, a comparative analysis with previous studies demonstrated that the proposed approach provides superior accuracy, underscoring its efficacy in solar radiation forecasting. © The Author(s) 2025.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Exploratory Data Analysis of Walmart Outlets Sales using Data Analytics Techniques

Exploratory Data Analysis of Walmart Outlets Sales using Dat...

引用

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Ramasami, Meaga Varsha Thangaraj, Rajasekaran Manoj Kumar, S. Eswaran, Sivaraman Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Curtin University Malaysia Department of Electrical and Computer Engineering Miri Malaysia

ISBN: (纸本)9798350310689

Sales fluctuation is the biggest problem faced by every retailer. The key to solving this issue is finding the invisible pattern of the components that have an effect on sales prediction. Nowadays retailers require a 360-degree vision of their customers to compete in the market. To achieve sales and marketing objectives, retailers must build strong promotions and offers. Retail companies employ the data from the previous year to analyse and predict sales for the upcoming year using data analysis applications. Additionally, it provides retailers with analytical insights, particularly in identifying the products liked by the customers in a particular store. In this paper, Walmart store the world's largest retailer dataset is used to figure out the business drivers and forecast which departments will be impacted by multiple parameters like average temperature, fuel price, and unemployment rate along with holidays reference and their effect on sales at stores of various locations. By visualising the analysed data, the Scala and Python API of the Spark framework is utilised to understand Walmart's marketing initiatives and data-driven plans and to acquire fresh insights into consumer behaviour. © 2023 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Movie Sense—Hybrid Movie Recommendation System with Sentimental Analysis 3rd

Movie Sense—Hybrid Movie Recommendation System with Sentime...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Sudhane, G. Sai Rao, G. Venkateswara Vani, V. Karthik, N. Department of Electrical and Electronics Engineering Puducherry India Department of Computer Science and Engineering National Institute of Technology Puducherry Puducherry Karaikal609609 India

ISBN: (纸本)9789819783540

Post-pandemic, with the advent of many OTT platforms, there are a number of different movies and web series available which makes it difficult for the users to find a suitable movie to watch. So the movie recommendation system helps the users by recommending some movies based on their past search history, their interests and also considering the movie genre, actors, director and movie ratings. Our system uses a hybrid filtering technique which makes the system suitable for new users as well by considering the interests of various other users using SVD. Sentimental Analysis is done using a Sentiment Intensity Analyzer (SIA). Since it uses the most accurate methods, it makes the system a robust one. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Correntropy-Based Data Selective Adaptive Filtering

引用

IEEE Transactions on Circuits and Systems I: Regular Papers 2024年第2期71卷 754-766页

作者： Chien, Ying-Ren Wu, Sheng-Teng Tsao, Hen-Wai Diniz, Paulo S.R. Adaptive and Autonomous Communication Laboratory Department of Electrical Engineering National Ilan University Yilan City260007 Taiwan College of Electrical Engineering and Computer Science Graduate Institute of Communication Engineering National Taiwan University Taipei10617 Taiwan Program of Electrical Engineering Department of Electronics and Computer Engineering COPPE/Poli Universidade Federal do Rio de Janeiro Rio de Janeiro68504 Brazil

Data selection can be used in conjunction with adaptive filtering algorithms to avoid unnecessary weight updating and thereby reduce computational overhead. This paper presents a novel correntropy-based data selection method as an alternative to conventional data selection mechanisms based on squared error values. We developed a variable correntropy sensing algorithm to maximize the instantaneous correntropy function for the Gaussian kernel function to mitigate the impact of impulse noise and other forms of noise that can be disregarded in data selection. The proposed data selection mechanism can be implemented with any adaptive filtering algorithm. In simulations, the proposed method (implemented with the least mean squared algorithm) outperformed comparable error-based data selection schemes in terms of hit rate and miss rate, and the resulting weight updating ratio was close to the expected weight updating ratio. © 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

关键词： Adaptive filters

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：