检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Singh, Prabhat Kumar Patidar, Harish Mandsaur University Department of Computer Science and Engineering Mandsaur India

ISBN: (纸本)9798350383652

Maithili is an Indo-Aryan language spoken by approximately 36 million speakers in Bihar and Nepal. Presently very less work available for the language. Morphological analyzers are the important component of NLP, which is the motivation towards development of the tool for the computational recognition of language. In this paper we work towards development of morphological analyzer of resource poor language Maithili. We have created dataset of Maithili for morphological analysis, having morpheme and parts of speech classes for the words of the language. We have compared performance parameters like precision, recall, F-measure and accuracy using nine different machine learning algorithms. By comparing all we have found that Instance based learning algorithm is most suitable for designing morphological analyzer for Maithili language. © 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

Enhanced Security for Medical Implants in Internet of Bio-Nano Things Using LSTM-Based Deep Learning Model

Enhanced Security for Medical Implants in Internet of Bio-Na...

引用

2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies, INSPECT 2024

作者： Bulasara, Phani Krishna Sahoo, Somya Ranjan Chawla, Rama School of Computer Science and Engineering VIT-AP University Andhra Pradesh India State Institute of Engineering & Technology Department of Computer Science and Engineering Kurukshetra India

ISBN: (纸本)9798350379525

Deep learning algorithms are efficient at predicting good models and a thorough understanding of similar problems to provide effective solutions more quickly. On the other hand, the Internet of Bio-Nano Things provides communication between bio-nano devices and remote healthcare centres. Usually, bio-nano devices do not implement security features due to resource constraints, violating client data governance. Such a network requires security features installed on a wearable device and reliable algorithms that can speedily assess patient data. Deep learning algorithms can improve bio-nano network security by preserving sensitive data. In this article, we discussed the resources of Implantable Medical Devices such as processor, memory and battery that are prone to Resource Depletion attacks. An implanted device's lifespan could be cut short by these attacks and data privacy will be lost. Many conventional models have provided security when the patient is not undergoing any physical activity. But, in this article, we explained how Long Short-Term Memory (LSTM) is utilized in analysing noisy data collected during various physical activities of the person. Our model predicts the fake device readers and achieved a mean accuracy of 99.8%. © 2024 IEEE.

关键词： Data privacy deep learning implantable medical devices Internet of bio-nano things Long short-term memory resource depletion

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach to Detecting Lung Nodules Using Swin Transformer 19

An Efficient Approach to Detecting Lung Nodules Using Swin T...

引用

19th Iranian Conference on Intelligent Systems, ICIS 2024

作者： Shakuri, Saeed Rezvanian, Alireza University of Science and Culture Department of Computer Engineering Tehran Iran

ISBN: (纸本)9798331507565

Lung cancer has the highest rate of cancer-caused deaths, and early-stage diagnosis could increase the survival rate. Lung nodules are one of the most common lung cancer signs, therefore, the development of lung nodule detection systems becomes significantly crucial. Different lung nodule detection models have been introduced, however, they haven't fully considered all aspects of efficiency. Hence, in this paper, we take a more efficient approach in introducing a lung nodule detection model while providing improvements in nodule detection. In this regard, we consider 2D slices of the CT scans which not only lead to lower computational load and complexity in training and inference phases but also, allow us to examine the potential of 2D models in lung nodule detection. Moreover, we utilize the tiny version of Swin Transformer to leverage the benefits of Vision Transformers (ViT) while having a much lower computational complexity. We also build a Feature Pyramid Network on top of our backbone to detect nodules of various sizes better, especially small nodules. Additionally, we consider Transfer Learning for the training procedure, resulting in significantly lower training iterations. The experimental results demonstrate the competitive performance of our model compared to the state-of-The-Art models with even higher mAP and mAR for small nodules by 1.3% and 1.6% respectively. Also, our proposed model achieved the highest mAP in all size nodules with 94.7% and mAR of 94.9%. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Study to Analyze Different Load Balancing Algorithmin in Cloud Computing 1

A Study to Analyze Different Load Balancing Algorithmin in C...

引用

1st International Conference on Innovative Sustainable Technologies for Energy, Mechatronics and Smart Systems, ISTEMS 2024

作者： Chauhan, Neeru Sharma, Aditya Chandigarh University Department of Computer Science and Engineering Mohali India

ISBN: (纸本)9798350384246

With its service flexibility and remuneration model, which allows users to pay only for what they need, cloud computing is a quickly evolving area. However, in the cloud services environment, security, load balancing, and the ability to absorb mistakes are all key concerns. The load balancing algorithm will be the topic of this document. Posting/ uploading data is one of the ways that Cloud Service Providers (CSPs) can meet consumers' QoS (Quality of Service) needs while also in-creasing profitability by optimizing their resources. Load balancing is distributing the load across different nodes that provide the best possible use of resources when the nodes are full of activity. The main goal of this study is the comparison of several load balancing strategies. This work will help readers read multiple algorithms of load balancing at once. © 2024 IEEE.

关键词： Virtualization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Framework with Wilson Loop Perceptron for Measuring the Rate of Mutation Patterns between DNA and RNA Viruses

引用

SN computer science 2025年第2期6卷 1-20页

作者： Fongngen, Weerasak Kanjamapornkul, Kabin Petharn, Surapong Department of Computer Science Faculty of Science Lampang Rajabhat University Lampang 52100 Thailand Department of Chemistry Faculty of Science Center of Excellence in Computational Chemistry (CECC) Chulalongkorn University Bangkok 10330 Thailand

The Wilson loop is indicative of the pathway encompassed within the viral replication process, which carries the coherent gauge field behavior present in the genetic coding of the virus. We enhance the capabilities of the support spinor machine by integrating supplementary attributes through the incorporation of the knot and link characteristics of the Wilson loop, as derived from biological contexts. This framework was employed to get into more deeper understanding of the mutational dynamics within viral replication, with particular emphasis on the concurrent quantum genotyping transfer along the continuous gauge field’s geodesic evolutionary trajectory. This trajectory links the genetic code existing in viral RNA and protein. Furthermore, a comparative analysis was undertaken to quantifying the mutation patterns in the replication loop of the evolutionary pathway. This was achieved by utilizing the spectrum of tensor correlation between the Marburg virus and the Monkeypox virus. The computational results for the mutation rates of the Marburg virus, 2.31×10-4 and the Monkeypox virus, 9.61×10-6, align with the biological hypothesis that RNA viruses mutate at a faster rate than DNA viruses. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Marburg virus Quantum genotyping Support vector machine Wilson loop

来源：评论

学校读者我要写书评

暂无评论

Traffic Flow Forecasting and Disseminating Model for Connected Autonomous Vehicles 3

Traffic Flow Forecasting and Disseminating Model for Connect...

引用

3rd IEEE World Conference on Applied Intelligence and Computing, AIC 2024

作者： Bansal, Nishu Bali, Rasmeet S Chandigarh University Computer Science & Engineering Department Mohali India

ISBN: (纸本)9798350384598

With the development of Connected Autonomous Vehicles (CAV), there is a need to reduce the transit/delay time of vehicles on road. If the information about road scenario and traffic status is communicated before hand, then it would be easier for CAVs to plan their route so that they can reach the destination in minimum time. To accomplish this objective, the traffic needs to be predicted on the required location and at particular time. Also the predicted information should be disseminated to the neighboring CAVs. Deep Learning techniques, Convolutional Neural Network (CNN) and Long short-term memory (LSTM) are proposed in Traffic Flow Forecasting and Disseminating (TFFD) model for forecasting the traffic information. The information dissemination is proposed through Osmotic Computing (OC). The model has been validated using simulations that exhibit its viability. © 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

Design of a Novel 1x4 Two-Dimensional Demultiplexer Based on Multicore Photonic Crystal Fiber

引用

International Journal of Electronics and Telecommunications 2023年第3期69卷 469-473页

作者： Harrat, Assia Ahlem Debbal, Mohammed Eddine Ouadah, Mohammed Chamse Department of Electronics and Telecommunications Faculty of Science and Technology University of Belhadj Bouchaib Algeria Department of Telecommunications Faculty of Electrical and Computer Engineering University of Mouloud Mammeri Algeria

This work suggests a brand-new 1*4 two-dimensional demultiplexer design based on multicore photonic crystal fiber. Numerical models show that the optical signals can be separated in a photonic crystal fiber construction using optical signals with wavelengths of 0.85, 1.1, 1.19, and 1.35 µm injected on the center core and separated into four cores. The innovative design switches different air-hole positions using pure silica layers throughout the length of the fiber to regulate the direction of light transmission between layers. Wavelength demultiplexers are essential parts of optical systemic communications. They serve as a data distributor and can use a single input to produce multiple outputs. The background material is frequently natural silica, and air holes can be found anywhere throughout the length of the fiber as the low-index components. The simulation results showed that after a 6 mm light propagation, the four-channel demux can start to demultiplex. © 2023 Polish Academy of sciences. All rights reserved.

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

Risk prediction method of multi-source network information cross-space fusion based on reinforcement learning 2

Risk prediction method of multi-source network information c...

引用

2nd IEEE International Conference on Sensors, Electronics and computer engineering, ICSECE 2024

作者： Chen, Yiping Zheng, Yingzi Guangzhou Institute of Science and Technology Department of Computer Science and Engineering Guangzhou510540 China

ISBN: (纸本)9798350373646

In order to improve the level of cross-space transmission and sharing of multi-source network information, it is necessary to effectively predict the process risk of fusion, and a risk prediction method of cross-space fusion of multi-source network information based on reinforcement learning is proposed. A cross-spatial dimension construction and transformation model of multi-source network information is constructed, and a feature-tag correlation selection model is established. Combined with the maximum feature-tag correlation identification method, the cross-spatial transformation and reinforcement tracking learning of multi-source network information are realized, and the redundancy test in the process of information cross-spatial fusion is realized by reinforcement learning. The frame structure model of network topology transmission is established according to the self-organized decentralized distributed networking mode of multi-source network space, and the reinforcement learning of information fusion risk prediction is realized by using the replacement parameter configuration and protocol configuration of channel resources, according to the reinforcement learning results. The simulation results show that the proposed method has a high degree of fitness for risk prediction of cross-space fusion of multi-source network information, improves the utilization rate of networking channels, and has good reliability in the process of channel access and resource allocation, effectively reducing the fusion risk, thus improving the transmission channel balance of multi-source networks. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data science Analysis Using Deep Learning Techniques in Mining Biological Data

Data science Analysis Using Deep Learning Techniques in Mini...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Murala, Praveena Sivaraman, K. Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350359688

The complexity and size of biological datasets have led to an exponential increase in the demand for advanced data analysis tools in biological research. Traditional statistical methods and machine learning algorithms usually fail to capture complicated patterns in these datasets. The paper fills that gap by proposing a novel deep learning-based method for mining biological data. The suggested method overcomes the constraints of existing systems by utilizing Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) to extract hierarchical features and temporal correlations, respectively. Preprocessing techniques, supervised learning, transfer learning, and ensemble procedures are utilized to boost the system's accuracy (0.95), precision (0.94), recall (0.96), and F1score (0.95) when compared to other systems. The results indicate significant gains in accuracy across a variety of datasets, with the proposed system displaying computational efficiency, training in 8 hours and inference in 1 second, versus 15 hours and 5 seconds for conventional systems. The study underlines the critical need for new approaches in the field, as well as the transformational potential of the suggested system to accelerate medical, genetic, and biotechnology discoveries. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

A Study on Recognizing Handwritten Mathematical Expressions 1

A Study on Recognizing Handwritten Mathematical Expressions

引用

1st IEEE International Conference on Communications and computer science, InCCCS 2024

作者： Ragupathy, Ashwin Gangwani, Gariman Shrinivedhaa, R. Uma, D. Department of Computer Science and Engineering PES University Bengaluru India

ISBN: (纸本)9798350358858

Handwritten mathematical expressions play a critical role in numerous domains, encompassing education, engineering, and science. The advent of deep neural networks, specifically those employing attention mechanisms and encoder-decoder architectures, has led to the widespread utilization of online recognition for handwritten mathematical *** this research, Convolutional Neural Networks (CNNs) are extensively studied for their efficacy in transforming hand-drawn mathematical expressions into the corresponding LATEX representations. To further improve handwritten expression recognition, we investigate deep neural network models, such as VGG-16 and analyse its performance . We also studied the integration of transformer-based decoders in the recognition process, which offers concise model architectures and enhanced attention to image features like, Attention Aggregation based Bi-directional Mutual Learning Network (ABM) to leverage complementary information from both left-to-right (L2R) and right-to-left (R2L) directions. Moreover, we also studied and implemented handwritten expression recognition, incorporating syntax information into an encoder-decoder network. The proposed method utilizes grammar rules for converting LATEX markup sequences into parsing trees, significantly improving recognition accuracy. The approach outperforms previous methods on benchmark data sets . We studied the behaviour of Syntax Aware network for multiple different classes of mathematical expression © 2024 IEEE.

关键词： Deep neural 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：