检索结果-内蒙古大学图书馆

Advances in Data engineering and Intelligent Computing Systems (ADICS), International Conference on

作者： R. Mohandas D.S.John Deva Prasanna Baiju B V S. Nathiya T. Dhiliphan Rajkumar C. Sivashankar Department of Computational Intelligence SRM Institiute of Science and Technology Chennai India Department of Datascience and Business systems SRM Institiute of Science and Technology Chennai India School of Computer Science and Engineering(SCOPE) VIT University Vellore TamilNadu India Department of Electronics and Communication Engineering Prince shri Venkateshwara Padmavathi Engineering College Chennai Dept. Of Computer Science and Engineering Kalasalingam Academy Of Research And Education Tamilnadu Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennnai India

ISBN: (数字)9798350364828

ISBN: (纸本)9798350364835

The increasing growth of Internet of Things (IoT) devices has created a wide attack surface for cyber criminals to carry out more destructive cyber attacks; therefore, the number of cyber attacks in the information security industry is increasing rapidly. As attackers use new and innovative methods to launch cyber-oriented attacks, many of these strikes have succeeded in their malicious goals. Anomaly-based intrusion detection systems (IDS) use machine learning techniques to detect and classify attacks on IoT networks. Faced with unpredictable network technologies and various infiltration methods, traditional machine learning technologies are powerless. In abounding areas of research, kernel learning methods prove that they accurately determine pathological abilities.

关键词： Learning systems Industries Pathology Machine learning algorithms Intrusion detection Machine learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An Effective Hand Gesture Recognition using Convolutional Neural Network with Long Short-Term Memory

An Effective Hand Gesture Recognition using Convolutional Ne...

引用

Evolutionary Algorithms and Soft Computing Techniques (EASCT), International Conference on

作者： G Sunil A. Saranya N. Duraimurugan R. Dineshkumar Ramachandra A C School of Computer Science & Artificial Intelligence SR University Warangal India Department of Computational Intelligence SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of ECE Saveetha School of Engineering Thandalam India Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India

A Hand Gesture (HG) constitutes a mode of nonverbal communication or non-vocal interaction, where discernible bodily movements convey specific messages, either independently or in combination with spoken language. Gesture recognition techniques are employed to create systems capable of transmitting information among individuals with disabilities for operating devices. In this paper, we propose the use of Electromyography (EMG) signals for classifying hand gestures through Employing both a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) in combination is being used. The main problem lies in the noise signals produced by the EMG sensor. In this work, we employ a Low Pass Filter for preprocessing the signal images, followed by feature extraction using the CNN model. To reduce the high-dimensional signal and normalize the features for the classification process, we utilize LSTM. This experiment was conducted using the Ninapro DB1 dataset. This model successfully addresses the previous issues and attains an overall accuracy of 95.56%, Precision 91.90%, Recall 89.50%, and F1 score 85.50% 91.90%, then the accurate classification compares to other existing models like Bidirectional Convolutional Gated Recurrent Unit, and Deformable convolutional network models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Pruning for Large-Scale Seq2Seq Speech Models without Back-Propagation

Efficient Pruning for Large-Scale Seq2Seq Speech Models with...

引用

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

作者： Tianteng Gu Bei Liu Yanmin Qian AI Institute Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University Shanghai China SJTU Paris Elite Institute of Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Large-scale Seq2Seq speech models like Whisper excel in speech recognition but are limited by their high computational demands, making them difficult to be deployed on resource-constrained devices. This paper introduces a novel and efficient pruning method for compressing these models without retraining and back-propagation, focusing on models with encoder-decoder architectures. We adapt layer-wise pruning to large speech models and introduce a mixed sparsity allocation strategy that uses only forward propagation. This approach effectively reduces model size while maintaining high performance. Evaluated on the Whisper-large-v3 across various datasets, our method can almost maintain Whisper’s performance and robustness with about 60% reduction in parameters. It could also be combined with other model compression methods such as distillation to further reducing model size.

关键词： Performance evaluation Adaptation models computational modeling Focusing Speech recognition computer architecture Speech enhancement Signal processing Robustness Resource management

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Applications for Wind Energy Forecasting in Smart Grids 10

Deep Learning Applications for Wind Energy Forecasting in Sm...

引用

10th International Conference on engineering and Emerging Technologies, ICEET 2024

作者： Wadood, Hamid Haris, Muhammad Hassan, Aqib Malik, Muhammad Osama Yousaf, Hamza Ullah, Kaleem University of Alabama at Birmingham Department of Computer Science Alabama United States Institute for Insight - J Mack Robinson College of Business Georgia State University AtlantaGA United States School of Computing and Mathematical Sciences University of Greenwich London United Kingdom University of Tulsa Department of Business Analytics Oklahoma United States Stetson-Hatcher School of Business Mercer University GA30341 United States University of Engineering and Technology Department of Energy System Engineering Peshawar Pakistan

ISBN: (纸本)9798331532895

Driven by the pressing need for sustainable and reliable energy sources, this paper critically evaluates deep learning's role in advancing wind energy forecasting, highlighting its potential to address current energy demands through improved prediction accuracy. Due to the inherent unpredictability of wind, conventional forecasting models often fall short;however, deep learning models offer enhanced reliability by effectively identifying complex, embedded patterns within wind data. The paper examines techniques such as time-series recurrent neural networks, restricted Boltzmann machines, convolutional neural networks, and autoencoders, each targeting distinct challenges in wind forecasting to strengthen grid integration and ensure energy reliability. Future directions-including hybrid model approaches and model interpretability-are discussed, underscoring deep learning's promise as a powerful tool for optimizing wind energy utilization and supporting a more sustainable, low-carbon energy infrastructure. © 2024 IEEE.

关键词： Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Hybrid Method of Assessing the Development of Alzheimer’s Syndrome through CNN/LSTM and PSO

Hybrid Method of Assessing the Development of Alzheimer’s S...

引用

Smart Technologies, Communication and Robotics (STCR)

作者： B Vidhya Shriya Vidhya Muthukumar C Ganesh Babu Department of Computational Intelligence SRMIST KTR Campus Chennai India Department of Computer Science and Business Systems SRMIST KTR Campus Chennai India Department of Electronics and Instrumentation Engineering Bannari Amman Institute of Technology Sathyamangalam India

ISBN: (数字)9798350357530

ISBN: (纸本)9798350357547

Alzheimer’s Disease (AD) is a prevalent neurodegenerative disease that has a substantial influence on society. Precise estimation of Alzheimer’s disease development is essential for prompt diagnosis and customized treatment. This paper proposes a hybrid model that combines Particle Swarm Optimization (PSO), Long Short-Term Memory networks (LSTM), and Convolutional Neural Networks (CNN) to improve prediction performance. The model examines the evolution of AD using a data-focused method, making use of an extensive MRI dataset with important neuroimaging variables. AD causes mental impairment and loss of memory, which complicates medical care provided to them. Data already in the public domain are used to predict future events or outcomes for forecasting that is essential for treating the disease. Conventional approaches, like CNN and LSTM, are useful for predicting the course of an illness because they can handle temporal patterns and spatial interdependence in datasets, respectively. Using the advantages of both methodologies, a new hybrid approach is proposed in this article. In order to optimize the hybrid model variables, this work employs Particle Swarm Optimization (PSO), a highly efficient optimization approach to increase the accuracy of model forecasts. The hybrid CNN-LSTM model, with and without PSO, demonstrated accurate predictions of AD progression. Performance metrics such as F1-score, precision, accuracy, recall and ROC AUC were used to evaluate model efficacy. This research contributes to predictive analytics in healthcare, offering innovative solutions for enhancing patient outcomes in AD management.

关键词： Neuroimaging Accuracy Magnetic resonance imaging Medical services Predictive models Convolutional neural networks Alzheimer's disease Particle swarm optimization Long short term memory Optimization

来源：评论

学校读者我要写书评

暂无评论

Deep potentials for materials science

引用

Materials Futures 2022年第2期1卷 89-115页

作者： Tongqi Wen Linfeng Zhang Han Wang Weinan E David J Srolovitz Department of Mechanical Engineering The University of Hong KongHong KongHong Kong Special Administrative Region of China DP Technology BeijingPeople’s Republic of China AI for Science Institute BeijingPeople’s Republic of China Laboratory of Computational Physics Institute of Applied Physics and Computational MathematicsBeijingPeople’s Republic of China HEDPS CAPTCollege of EngineeringPeking UniversityBeijingPeople’s Republic of China School of Mathematical Sciences Peking UniversityBeijingPeople’s Republic of China Department of Mathematics and Program in Applied and Computational Mathematics Princeton UniversityPrincetonNJUnited States of America International Digital Economy Academy(IDEA) ShenzhenPeople’s Republic of China

To fill the gap between accurate(and expensive)ab initio calculations and efficient atomistic simulations based on empirical interatomic potentials,a new class of descriptions of atomic interactions has emerged and been widely applied;*** learning potentials(MLPs).One recently developed type of MLP is the deep potential(DP)*** this review,we provide an introduction to DP methods in computational materials *** theory underlying the DP method is presented along with a step-by-step introduction to their development and *** also review materials applications of DPs in a wide range of materials *** DP Library provides a platform for the development of DPs and a database of extant *** discuss the accuracy and efficiency of DPs compared with ab initio methods and empirical potentials.

关键词： deep potential atomistic simulation machine learning potential neural network

来源：评论

学校读者我要写书评

暂无评论

Proactive Network Optimization Using Deep Learning in Predicting IoT Traffic Dynamics

Proactive Network Optimization Using Deep Learning in Predic...

引用

Innovative Practices in Technology and Management (ICIPTM), International Conference on

作者： S. Anu Priya Niyati Bhat B. Rajesh Kanna S. Rajalakshmi R. Beaulah Jeyavathana Srimathi S Department of Computer Applications Vels Institute of Science Technology & Advanced Studies ((VISTAS) Chennai B.E Computer Engineering University of Mumbai Mumbai Department of Electronics and Communication Engineering Alagappa Chettiyar College of Engineering and Technology Karaikudi Department of Electronics and Communication Engineering RMK College of Engineering and Technology Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

ISBN: (数字)9798350307757

ISBN: (纸本)9798350307764

Problems have arisen in allocating and managing network resources effectively because of the proliferation of IoT gadgets. This study aims to provide a deep learning-based strategy for forecasting and analyzing IoT traffic patterns to solve this problem. The model uses recurrent neural networks (RNNs) with Long Short-Term Memory (LSTM) cells to capture the complex temporal dependencies in IoT data streams. Following careful data gathering from various IoT sources, a thorough preprocessing phase is performed to account for missing values and outliers. Effective modeling is enabled by applying feature engineering approaches to distill meaningful information and by temporally aggregating the dataset. The heart of the study is the creation of a sequence-to-sequence architecture that allows for reliable forecasting of future IoT traffic trends. Mean Squared Error (MSE) and other performance metrics measure the quality of the proposed model's predictions. In addition to its predictive abilities, the model's analytical section reveals interesting facts about the fundamental habits underpinning IoT traffic. This dual purpose helps network managers better comprehend the ever-changing IoT ecosystem and allocate scarce resources. The results of this study have important implications for network optimization, providing a preventative strategy for dealing with the difficulties posed by the exponential growth of IoT data traffic. Regarding accuracy and interpretability, the suggested deep learning model significantly contributes to the development of intelligent network resource management in the IoT era.

关键词： Deep learning Analytical models Recurrent neural networks Ecosystems Predictive models Traffic control Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Investigating dispersive optical solitons with the generalized stochastic perturbed Schrödinger–Hirota equation incorporating power-law nonlinearity and multiplicative white noise

引用

Optik 2024年 310卷

作者： Arnous, Ahmed H. Hashemi, Mir Sajjad Elsherbeny, Ahmed M. Secer, Aydin Ozisik, Muslum Bayram, Mustafa Department of Physics and Engineering Mathematics Higher Institute of Engineering El–Shorouk Academy Cairo Egypt Department of Mathematics Basic Science Faculty University of Bonab Bonab Iran Department of Physics and Mathematics Engineering Faculty of Engineering Ain Shams University Cairo11517 Egypt Department of Computer Engineering Biruni University Turkey Department of Mathematical Engineering Yildiz Technical University Turkey

This article aims to introduce the generalized stochastic perturbed Schrödinger–Hirota equation, which incorporates multiplicative white noise in the Itô sense. The study focuses on investigating the stochastic optical soliton solutions related to the governing model to understand the characteristics and properties of these soliton solutions. We can achieve this by utilizing the enhanced Kudryashov method and the enhanced direct algebraic approach. The study stands out for its innovative approach to examining the effects of multiplicative white noise on stochastic optical soliton solutions through the lens of the generalized stochastic perturbed Schrödinger–Hirota equation. Utilizing the enhanced Kudryashov method alongside the novel enhanced direct algebraic method, this research effectively identifies and delineates a range of soliton solution types, such as bright, dark, singular, and straddled solitons. This thorough investigation not only underscores the efficacy and efficiency of these methods but also sheds light on the impact of noise on the structural and dynamic properties of soliton solutions, supported by illustrative visualizations. A notable finding is that all solutions derived using the enhanced direct algebraic method feature a nonzero coefficient for the highest-order term of the auxiliary equation. The diversity of solutions obtained through these approaches includes bright, dark, singular, and straddled solitons. Additionally, the study reveals Weierstrass and Jacobi elliptic doubly periodic solutions, which can transition into various soliton types under specific parameter conditions, offering a broader understanding of soliton behavior and properties. © 2024

关键词： Solitons

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Security of Merkle-Damgård Hash Functions and Combiners in Quantum Settings 16th

Evaluating the Security of Merkle-Damgård Hash Functions an...

引用

16th International Conference on Network and System Security, NSS 2022

作者： Bao, Zhenzhen Guo, Jian Li, Shun Pham, Phuong School Of Physical And Mathematical Sciences Nanyang Technological University Singapore Singapore Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Institute for Network Sciences and Cyberspace Tsinghua University Beijing China

ISBN: (纸本)9783031230196

In this work, we evaluate the security of Merkle-Damgård (MD) hash functions and their combiners (XOR and concatenation combiners) in quantum settings. Two main quantum scenarios are considered, including the scenario where a substantial amount of cheap quantum random access memory (qRAM) is available and where qRAM is limited and expensive to access. We first convert a rich set of known tools invented for generic attacks in the classical setting to quantum versions. That includes Joux’s multi-collision, expandable message, diamond structure, and interchange structure. With these basic tools in hand, we then present generic quantum attacks on the MD hash functions and hash combiners, and carefully analyze the complexities under both quantum scenarios. The considered securities are fundamental requirements for hash functions, including the resistance against collision, (second-)preimage, and herding attacks. The results are consistent with the conclusions in the classical setting, that is, the considered resistances of the MD hash functions and their combiners are far less than ideal, despite the significant differences in the expected security bounds between the classical and quantum settings. Particularly, the generic attacks can be improved significantly using quantum computers under both scenarios. These results serve as an indication that classical hash constructions require careful security re-evaluation before being deployed to the post-quantum cryptography schemes. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Infection in Diabetic Foot Ulcer Images Using Improved-CNN-SVM Approach 7

Automatic Detection of Infection in Diabetic Foot Ulcer Imag...

引用

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

作者： Sivashankar, G. Avinash, Bhagyalakshmi Shabbir Alam, Mohammad Vyankatesh Ghamande, Manasi Gupta, Keerat Kumar Rastogi, Ravi SRM Institute of Science and Technology Department of Computational Intelligence Tamilnadu Chennai India JSS Dental College & Mysore Dept of Orthodontics & Dentofacial Orthopaedics Karnataka Mysore India College of CS &iT Department of Computer Science Jazan University Jizan Saudi Arabia Vishwakarma Institute of Information Technology E and AS Pune India Graphic Era Deemed to Be University Department of Civil Engineering Uttarakhand Dehradun India NIELIT Electronics Division Uttar Pradesh Gorakhpur India

ISBN: (纸本)9798350340600

Unregulated glucose levels in the blood lead to the chronic disease diabetes. Diabetic foot ulcers (DFUs) and other devastating outcomes may be avoided with early detection. The lower limb of a diabetic patient may need to be amputated if they experience a DFU. DFU is difficult to diagnose and usually requires a number of expensive and time-consuming clinical investigations for the treating physician. Applying deep learning, machine learning, and computer vision techniques in today's age of data deluge has resulted in a number of solutions that can help doctors make more accurate diagnoses in less time. As a result, researchers have recently focused more on developing methods for automatically identifying DFU. Preprocessing, segmentation, feature extraction, and model training are all used in the suggested method. It does noise reduction and RGB to HSI color space conversion during preprocessing. OSTU thresholding segmentation is used for the separation. It uses histogram for feature extraction and Improved CNN-SVM for model training. The new method is compared to two common approaches, including CNN and CNN-SVM, and fares better than both. © 2023 IEEE.

关键词： Diagnosis

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：