检索结果-内蒙古大学图书馆

13th International Conference on Information technology in Asia, CITA 2023

作者： Makoui, Farshid Haidary Gulliver, T. Aaron Dakhilalian, Mohammad University of Victoria Dept. of Electrical & Computer Engineering VictoriaBC Canada Isfahan University of Technology Dept. of Electrical & Computer Engineering Isfahan Iran

ISBN: (纸本)9798350326208

The Shor algorithm demonstrates the significant risk that quantum attacks pose to the security of widely used cryptographic primitives. However, code-based cryptography has been shown to be resistant to these attacks. To date, no polynomial-time attack exists that can break code-based cryptosystems such as the McEliece cryptosystem. Despite this, these cryptosystems are not employed in practical applications in domains such as online banking, blockchains, and e-commerce platforms. The primary reason is the large sizes of the public and private keys associated with code-based cryptosystems. In this paper, a new code-based cryptosystem is introduced which employs a dual matrix based on the transpose and inverse of the parity check matrix to reduce the key size compared to the McEliece cryptosystem. © 2023 IEEE.

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

Stage Wise Classification and prediction of Alzheimer disease using Hybrid Appraoch 4

Stage Wise Classification and prediction of Alzheimer diseas...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Prabagaran, A. Dwivedi, Vinay Neelam Rani, Jyoti Angelin Blessy, J. Padmanabhan, P. Gupshup Technology India Pvt Ltd Bengaluru India Galgotias University School of Computer Science and Engineering Uttar Pradesh Greater Noida India Noida Institute of Engineering & Technology Department of Computer Science and Engineering Uttar Pradesh Greater Noida India Galgotias Univeristy School of Computing Science and Engineering Dept of Computer Application India Greater Noida Institute of Technology Department of Computer Science and Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350349900

Alzheimer's, the most prevalent cause of dementia, leads to a continuous decline in cognitive functions, social skills, and behavior, affecting individuals' independent functioning. As per survey 2010 in India around 3.7 million affected by dementia, and this data is expected to twofold by 2030. The associated cost of care is projected to triple, necessitating ongoing support. This issue is a significant societal concern that warrants careful consideration. Prediction and classification of Alzheimer's disease (AD) are crucial for identifying and addressing it at earlier stages. The disease is typically classified into three stages: early-stage dementia, middle-stage, and late-stage. However, several challenges exist, including limited awareness, diagnostic difficulties, insufficient technologies and treatments, unpredictable progression across stages, and a lack of comprehensive stage-by-stage predictions. This work proposes a hybrid model for predicting, classifying, and stage-wise classifying Alzheimer's disease. The hybrid model aims to address the challenges associated with the disease, utilizing different features for prediction and classification. The hybrid model used a Random forest, convolutional neural network (CNN), kernel density algorithm (KDA) with hyperparameter tuning for accurate prediction and classification. The proposed hybrid method used Random forest used for basic classification, CNN and kernel density for stage wise classification. The proposed hybrid method achieved an impressive 95.6% accuracy in stage wise classification and prediction of AD. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Text Phishing Detection System using Random Forest Algorithm 3

Text Phishing Detection System using Random Forest Algorithm

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Rajoju, Radhika Sathvika, Vangala Smaran, Guthikonda Narayana Sai Tejashwini, Chettipelli Reddy, Gangasani Aditya Kakatiya Institute of Technology & Science Dept of Cse Warangal India Computer Science and Engineering Kakatiya Institute of Technology & Science Warangal India

ISBN: (纸本)9798350375190

This research paper presents a comprehensive exploration of advanced text classification methodologies, specifically tailored for the intricate task of distinguishing phishing emails from legitimate ones. Employing cutting-edge natural language processing techniques, our study meticulously pre-processes the dataset, ensuring optimal refinement through meticulous steps such as null value elimination, text normalization, punctuation removal, and stop-word elimination. By harnessing sophisticated feature engineering techniques like CountVectorizer and TF-IDF Transformer, we seamlessly convert textual data into numerical representations, enabling our machine learning algorithms to operate with precision and efficiency. The experimentation phase rigorously evaluates a diverse range of classifiers, including Naive Bayes, Decision Trees, Logistic Regression, Random Forest, AdaBoost and KNN. Remarkably, our findings highlight Random Forest as the standout performer, boasting an impressive accuracy rate of 96%. This exceptional performance underscores the algorithm's efficacy in accurately discerning between phishing attempts and genuine communications. As such, we advocate for the widespread adoption of Random Forest as the preferred model for email classification tasks, offering unparalleled accuracy and robustness essential for real-world deployment in cybersecurity contexts. © 2024 IEEE.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

IRS Controlling Method With Machine Learning Based on Position Information 13

IRS Controlling Method With Machine Learning Based on Positi...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Tsuchiya, Yoshihiko Suga, Norisato Uruma, Kazunori Fujisawa, Masaya Tokyo University of Science Dept. of Information and Computer Technology Tokyo Japan Shibaura Institute of Technology Dept. of Information and Communication Engineering Tokyo Japan Kogakuin University Dept. of Computer Science Tokyo Japan

ISBN: (纸本)9798350355079

Intelligent Reflecting Surfaces (IRS) is attracting attention for wireless communications at high-frequency band. IRS can control radio propagation by reflecting radio waves and shifting their phase. As one of the methods to control IRS, location-based methods have been proposed. However, to achieve highly accurate IRS control by the methods, the assumed propagation model must match the actual propagation environment. This study proposes a method to control the IRS from location information adapted to the propagation environment by using machine learning. Numerical experiments confirm that the proposed method can appropriately control IRS regardless of the propagation environment. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

SMOTE and Hyperparameter Optimization: A Dual Machine Learning Strategy for Enhancing Coupon Recommendation in Vehicular Contexts 3

SMOTE and Hyperparameter Optimization: A Dual Machine Learni...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Ravikumar, R.N. Jain, Sanjay Sarkar, Manash Amity University Rajasthan Dept. of Computer Science and Engineering Jaipur India Atria Institute of Technology Dept. of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350319125

This study centers on enhancing the accurateness of coupon recommendation algorithms within the framework of in-vehicle settings. The In-Vehicle Coupon Recommendation dataset from the UCI Repository was utilized in this study. A range of machine learning algorithms, such as Random Forest, Gradient Boosting, Extra Trees, LightGBM, XGBoost, AdaBoost, Stochastic Gradient Descent (SGD), and CatBoost, were employed for analysis. Among the several algorithms considered, CatBoost exhibited notable performance, with a baseline accuracy of 74%. In order to improve the efficacy of the model, we utilized the 'Synthetic Minority Over-sampling Technique' (SMOTE) to mitigate the issue of class imbalance. This was subsequently followed by a thorough hyperparameter adjustment of the CatBoost algorithm. The improved model demonstrated a significant upgrade, with an accuracy rate of 77%. Additionally, there were noteworthy improvements in precision, recall, and F1 score. The AUC, which represents the Area Under the Receiver Operating Characteristic Curve, saw a notable improvement to 0.82. This signifies a noteworthy enhancement in the capacity to differentiate between positive and negative cases. The results emphasize the efficacy of CatBoost in the context of recommending coupons within vehicles, while also drawing attention to the influence of preprocessing methods and hyperparameter adjustment in enhancing the model's overall performance. This study is a valuable contribution to the domain of personalized advertising in the context of vehicles, providing valuable insights for the advancement of coupon recommendation systems that are more precise and dependable. © 2023 IEEE.

关键词： Coupon Recommendation Hyperparameter Tuning Machine Learning Recommender System SMOTE

来源：评论

学校读者我要写书评

暂无评论

Short-term Wind Power Ramp Forecasting Using Sequential Approach

Short-term Wind Power Ramp Forecasting Using Sequential Appr...

引用

2024 IEEE International Conference on Modeling, Simulation and Intelligent Computing, MoSICom 2024

作者： Gopalakrishnan, Leechita Barrera, Julian L Cardenas Fatima, N. Sabiyath B.S. Abdur Rahman Crescent Institute of Science and Technology Dept. of Computer Science and Engineering Chennai India University of New Brunswick Dept. of Electrical and Computer Engineering Fredericton Canada

ISBN: (纸本)9798331533311

As wind energy becomes a key player in the global transition to renewable energy, its variability presents significant challenges. Accurate wind ramp forecasting is crucial for managing such rapid fluctuations in wind power output, ensuring grid stability, and enhancing the reliability of renewable energy integration. This paper presents a short-term wind ramp forecasting model using a sequential approach: initially forecasting wind power through the integration of Variational Mode Decomposition (VMD) and the XGBoost algorithm, and subsequently detecting wind ramps using the Definition Based Sign Indicator (DSI) method. The historical wind speed and power data for Turkey was obtained from Kaggle. The dataset comprises readings from a wind turbine's SCADA system in Turkey, with measurements recorded at 10minute intervals. Variational Mode Decomposition (VMD) was applied to deconstruct and restore the historical wind power of the wind field, resulting in the formation of three training datasets. Wind power projections for the subsequent 8 hours, at 10 -minute intervals, are generated using historical wind power, wind speed, and wind direction as inputs. The DSI algorithm is employed to identify ramps. To assess the predictive capability of the proposed model, two algorithms, SVR and XGBoost, were employed for forecasting and the resulting error is minimal. The proposed model, VMD + XGBOOST is also compared without VMD to evaluate the performance. Taking mean square error (MSE), root mean square error (RMSE) mean absolute error (MAE), and symmetric mean absolute percentage error (sMAPE) as evaluation indicators, the results show that the forecasted accuracy of wind power is significantly improved after VMD processing. The performance of XGBOOST is better than SVR in the two evaluation indicators. Precision, Recall, and F1-score are calculated to evaluate the accuracy of the predicted wind ramps. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Minimization of data centers in survivable dynamic SDM-EONs 14

Minimization of data centers in survivable dynamic SDM-EONs

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Chandra, Sourabh Mondal, Khokan Calcutta Institute of Technology Dept. of Computer Science & Engineering Howrah India Techno India University Dept. of Computer Science & Engineering Kolkata India

ISBN: (纸本)9798350335095

Energy consumption due to massive use of data center (DC) is increasing rapidly. The need to improve the energy efficiency of such DC aims to develop an effective DC-placement algorithm. Again, a sudden disaster in the network can affect both fiber path as well as the DC nodes resulting in fiber cuts and huge data loss. Space division multiplexing-based elastic optical network (SDM-EON), being more efficient than the traditional elastic optical network (EON) due to the inclusion of multiple cores in a single fiber link, tries to maximize the utilization of resources by reducing blocking probability. This paper presents a novel DC-placement algorithm in dynamic DC-based SDM-EONs which focuses on enhancing energy efficiency in the network, thereby ensuring the survivability of the network against any sudden disaster. Rigorous simulation analysis proves the efficacy of the proposed algorithm over other existing algorithms. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Based on Transfer Learning a Performance Analysis and Comparative Study of CNN for Accurate Plant Disease Detection

Based on Transfer Learning a Performance Analysis and Compar...

引用

2023 IEEE International Conference on Network, Multimedia and Information technology, NMITCON 2023

作者： Nithin, S. Nishanth, M.S. Kodipalli, Ashwini Rao, Trupthi Kumaraswamy, S. Global Academy of Technology Dept of Computer Science and Engineering Banglore India Global Academy of Technology Dept of Artificial Intelligence and Data Science Banglore India Global Academy of Technology Department of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350300826

This paper investigates the use of Convolutional Neural Networks (CNNs) for plant disease diagnosis, utilizing the notion of transfer learning to develop a deep CNN network at a low cost. The dataset utilized includes 30,000 pictures from 18 distinct categories. Several architectural models, including ResNet50, ResNet50V2, VGG16, VGG19, EfficientNetB0, MobileNet, MobileNetV2, NASNetMobile, and DenseNet, were created using transfer learning methodologies. The models are trained on the target plant disease dataset while keeping the features learnt from large-scale image datasets like ImageNet. Performance criteria such as accuracy, precision, and recall are used to assess the models' accuracy in detecting various plant diseasesx. Furthermore, the research investigates the effect of dropout on accuracy and other model parameters in the context of transfer learning. Finally, the outcomes of a tailored model with and without batch normalization are compared. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Crop And Fertilizer Recommendation to Improve Crop Yield using Deep Learning 2

Crop And Fertilizer Recommendation to Improve Crop Yield usi...

引用

2nd International Conference on Electronics and Renewable Systems, ICEARS 2023

作者： Thendral, R. Vinothini, M. Ifet College of Engineering Dept of Information Technology Villupuram India Ifet College of Engineering Dept of Computer Science Engineering Villupuram India

ISBN: (纸本)9798350346640

To fulfill the rising global food demand, agricultural production must be improved. Using fertilizers as efficiently as possible based on the needs of the various crops is one approach to this. To assist farmers to increase agricultural yields, deep learning algorithms may be used to produce suggestions for crops and fertilizers. A deep learning model is created using methods like CNNs, RNNs, or LSTM networks, and suggestions for crops and fertilizers are then made depending on the input data. The procedure entails gathering data on crop yields, soil properties, and fertilizer consumption. The model's accuracy may then be tested to get better outcomes over time. The development of crop and fertilizer recommendations using deep learning can assist farmers in increasing crop yields, enhancing agricultural sustainability, and meeting the global demand for food. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Systematic Common Information Model (CIM) Profile Management for Advanced Distribution Management System

引用

Transactions of the Korean Institute of Electrical Engineers 2024年第1期73卷 1-9页

作者： Kim, Hyun Joong Oh, Jae Young Yoon, Yong Tae Jung, Wonwook Shim, Jaeseong Shon, Jin-Man Dept. of Electrical Engineering Hoseo University Korea Republic of Dept. of Energy Engineering Korea Institute of Energy Technology Korea Republic of Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Korea Electric Power Corporation Research Institute Rep. of Korea Korea Republic of

Common Information Model (CIM) is an essential technique for ensuring interoperability in Energy Management Systems (EMS) by defining data profiles for information exchange. Given the changing system environment, CIM undergoes periodic revisions, necessitating updates to the profiles used in EMS. However, comparing and interpreting CIM as defined in the Unified Modeling Language (UML) can be time-consuming and may lead to human errors. In this context, this study proposes systematic approaches for managing data profiles using an automatic tracking function for CIM and a structured process for profile management. The effectiveness of this approach is demonstrated by applying it to profiles defining the key functions of Korea's advanced distribution management system (ADMS), such as operational limits, renewable energy sources, and power transformers. This research can serve as a guideline for addressing practical issues in securing interoperability in ADMS. © 2024 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Interoperability

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：