检索结果-内蒙古大学图书馆

1st International Conference on Optimization Techniques for Learning, ICOTL 2023

作者： Preethi, P. Vasudevan, I. Saravanan, S. Krishna Prakash, R. Devendhiran, A. Kongunadu College of Engineering and Technology Dept. of Computer Science and Engineering Trichy India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Dept. of Computer Science and Engineering Chennai India Kl University Dept. of Computer Science and Engineering Vijayawada India Sona College of Technology Dept. of Information Technology Salem India Vivekanandha College of Engineering for Women Dept. of Computer Science and Technology Namakkal India

ISBN: (纸本)9798350328042

In the current interconnected and susceptible digital environment, the demand for reliable network attack prediction systems has reached a critical level. This research paper presents a novel approach for network intrusion detection utilizing the Improved Import Vector Machine (IVM) classification algorithm combined with feature selection using Cuckoo Search based Grey Wolf Optimization (CS-GWO). The aim is to improve the accuracy and effectiveness of intrusion detection systems by selecting the most relevant features and employing a powerful classification algorithm. The proposed methodology begins with data preprocessing, ensuring the dataset is appropriately cleaned and normalized. Subsequently, the CS-GWO algorithm is applied for feature selection, leveraging the strengths of both Cuckoo Search and Grey Wolf Optimization. This hybrid approach efficiently explores the search space to identify the optimal feature subset that contributes to accurate intrusion detection. Once the feature selection process is completed, the IVM classification algorithm is employed to classify network instances into intrusion or normal categories. The IVM algorithm is chosen for its ability to handle high-dimensional data and its robustness in dealing with imbalanced datasets commonly encountered in network intrusion detection. To evaluate the performance of the proposed approach, extensive experiments are conducted using benchmark datasets. Various evaluation metrics such as accuracy, precision, recall, and F1 score are utilized to assess the effectiveness of the system in detecting network intrusions. The results demonstrate that the combination of IVM classification and CS-GWO feature selection significantly improves the accuracy and efficiency of network intrusion detection. The selected features obtained through CS-GWO contribute to enhanced classification performance, enabling the system to accurately identify and respond to potential intrusions in real-time scenarios. © 2023 IE

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Optimizing mmWave UAV Networks: Mobility-Aware Deployment and Resource Allocation 100

Optimizing mmWave UAV Networks: Mobility-Aware Deployment an...

引用

100th IEEE Vehicular technology Conference, VTC 2024-Fall

作者： Li, Sicong Yoshii, Kazutoshi Shimamoto, Shigeru Ho, Tu Dac Waseda University Dept. of Communications and Computer Engineering Tokyo Japan Norwegian University of Science and Technology Dept. of Information Security and Communication Technology Trondheim Norway

ISBN: (纸本)9798331517786

Application of Unmanned Aerial Vehicles (UAVs) as small airborne base stations is gradually becoming a research hotspot in the field of wireless communications. With the flexible deployment, wide coverage and low cost, UAV communications show great potential in the fields of emergency rescue, environmental monitoring and military operations. In particular, the easier availability of line-of-sight (LOS) links for UAVs makes its combination with millimetre wave (mmWave) technology significantly enhance the communication bandwidth and data transfer rate. However, the very limited coverage of mmWave communications greatly affects the actual data rates provided by small aerial base stations of mmWave UAVs, especially considering user movement on the ground. In this paper, we study the joint optimisation problem of UAV deployment, user association, spectrum resource allocation in millimetre-wave heterogeneous networks, and explore the impact of different user movement models on system performance. Given that this problem is NP-hard, our paper proposes an MCR-SAC method to maximize the network's total throughput. Simulation results demonstrate an average 18% improvement in total transmission rate compared to the conventional. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

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

Adversarial Machine Learning Attack on Machine Learning-based Controller for Solar Inverters

Adversarial Machine Learning Attack on Machine Learning-base...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Massa, Joaquin Kim, Kyoung-Tak Kim, Taesic Ahn, BoHyun Venayagamoorthy, Kumar Zeng, Jianwu Texas A&m University-Kingsville Dept. of Electrical Engineering and Computer Science Kingsville United States Soongsil University Dept. of Electrical Engineering Seoul Korea Republic of University of Missour-Columbia Dept. of Electrical Engineering and Computer Science Columbia United States Clemson University Dept. of Electrical and Computer Engineering Clemson United States Minnesota State University Mankato Dept. of Electrical and Computer Engineering and Technology Mankato United States

ISBN: (纸本)9798350376067

Adversarial machine learning (ML) attacks are stealthy attacks designed to mislead the ML model results. This paper explores adversarial ML attacks that generate adversarial noisy input data in an ML-based controller in a solar inverter. Three types of ML models, long short-term memory (LSTM), gated recurrent unit (GRU)), and bidirectional-LSTM (Bi-LSTM), are designed to replace proportional-integral (PI) controller-based vector control for a solar inverter and two white-box adversarial ML attacks (Basic Iterative Method (BIM) attack and Fast Sign-Gradient Method (FGSM)) are applied to the ML controllers. It is observed that the adversary ML attacks designed in stealthy way do not affect the PI controller, while significantly degrading performance of the ML-based controllers. Moreover, the BIM attack is more effective than FGSM and Bi-LSTM-based controller is relatively robust to the attacks compared to peer. © 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

Analyzing Cyberbullying Word Distribution Across Social Media to Develop Lexicon Dictionary 2

Analyzing Cyberbullying Word Distribution Across Social Medi...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Sahana, V. Anil Kumar, K.M. Jss Academy of Technical Education Dept. of Information Science and Engineering Bengaluru560060 India Jss Science and Technology University Dept. of Computer Science and Engineering Mysuru570006 India

ISBN: (纸本)9798350372892

Social media platforms have become essential tools for communication, collaboration, and exchanging information, ideas, and knowledge among users worldwide. Despite their benefits, the anonymity offered by these platforms has unfortunately led to a rise in hate speech and cyberbullying, causing concern across the globe. This issue has drawn the attention of researchers and scholars now focused on devising methods for automatically detecting cyberaggression and hate speech. The goal is to mitigate these harmful behaviors and create safer online environments [1]. This study specifically aims to identify and analyze the usage of cyberbullying language within the English Tweet corpus, focusing on distinguishing between bullying and non-bullying language. This research contributes to developing more effective cyberbullying detection models by examining the frequency and patterns of cyberbullying words. These findings are vital for enhancing the efficacy of cyberbullying detection on social networks in future research efforts. The conclusions of the experiments indicate that the SVM achieved the highest average accuracy, approximately 84 %. © 2024 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Advancements in EEG-Based Emotion and Consciousness Recognition: Techniques, Challenges, and Innovations 1

Advancements in EEG-Based Emotion and Consciousness Recognit...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Jadekar, Ranjana B. Poornima, B. Gowramma, B.H. Puneeth, S.P. Visvesvaraya Technological University Bapuji Institute of Engineering and Technology Dept. of Computer Science and Engineering Karnataka Belagavi India Visvesvaraya Technological University Bapuji Institute of Engineering and Technology Dept. of Information Science and Engineering Karnataka Belagavi India

ISBN: (纸本)9798350376517

This study delves into the application of Electroencephalogram (EEG)-based techniques for emotion and consciousness recognition, focusing on disorders of consciousness (DOC). By evaluating existing approaches in terms of techniques, methodologies, and accuracies, the research highlights the efficacy of both machine learning and deep learning models. The key challenges were identified such as noise removal due to artifacts and variability in patient responses. The findings underscore the potential of advanced computational methods in enhancing the reliability and precision of EEG-based diagnostic tools, paving the way for better clinical interventions and deeper understanding of human emotions. Also, the findings show that using deep learning, the current works have achieved better results for identification of emotion. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

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

Alpha-x Framework for Assessing Network Robustness in Nakagami-m Fading and Co-Channel Interference Environments 3

Alpha-x Framework for Assessing Network Robustness in Nakaga...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Upadhyay, Deepak Siwach, Karan Dhondiyal, Shiv Ashish Upadhyay, Abhay Gupta, Mridul Sharma, Kunj Bihari Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India G.L. Bajaj Institute of Technology and Management Dept. of Computer Science and Engineering Greater Noida India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Electronics and Communication Engineering Dehradun India

ISBN: (纸本)9798331518592

This article explores how the Alpha-x framework can improve network robustness under Nakagami-m fading and co-channel interference (CI), The study evaluates network performance using key metrics such as outage probability, spectral efficiency, and capacity degradation. The simulations show a 50% reduction in outage probability, a 20% boost in spectral efficiency, and a 33.3% lower capacity degradation compared to traditional models. These results demonstrate how the Alpha-x framework enhances network performance by adapting to various fading conditions and interference levels in wireless communication systems. The framework not only improves reliability and efficiency but also shows practical relevance in network planning and management. This can potentially lead to better user experiences and increased operational resilience. Future research could focus on optimizing the underlying algorithms and testing their performance on a larger scale in real-world environments. As telecommunications systems evolve, frameworks like Alpha-x could play a crucial role in ensuring reliable and efficient wireless networks. © 2024 IEEE.

关键词： Cochannel interference

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

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：