检索结果-内蒙古大学图书馆

Hybrid Deep Learning Models for Accurate Early Detection of Lung Cancer from MRI Scans 3

Hybrid Deep Learning Models for Accurate Early Detection of ...

3rd International Conference on Artificial Intelligence, Computational electronics and Communication System, AICECS 2024

作者： Shinde, Ashwini S Zope, Tejaswini K Bongulwar, Deepali Chavan, Manjusha N Chaudhari, Deepti A. Sonawane, Atharv Nutan Maharashtra Institute of Engineering and Technology Electronics & Telecommunication Pune India Nutan College of Engineering & Research Computer Science & Engineering Pune India Brainware University Barasat CSE - AI & ML Department West Bengal Kolkata 700125 India Sanjeevan Engineering and Technology Institute Computer Science Kolhapur India AISSMS-IOIT Artificial Intelligence-Data Science Pune India

ISBN: (纸本)9798350391244

Early identification of lung cancer is vital for improving patient outcomes, since it is a major contributor to cancer-related mortality, often resulting from late-stage diagnosis. This study addresses the challenge of accurately identifying early-stage lung cancer from MRI scans, where subtle tumors are often overlooked. Traditional diagnostic methods, reliant on manual interpretation and conventional machine learning models, fall short in handling the complexity of MRI data. In order to address these constraints, we suggest using a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) for spatial feature extraction with Transformer networks for contextual analysis. This innovative approach significantly enhances the accuracy of early-stage lung cancer detection. Performance evaluation on extensive MRI datasets demonstrates that the hybrid model achieves an accuracy of 95%, a sensitivity of 93%, and a specificity of 96%, outperforming traditional diagnostic methods. The results highlight the potential of this hybrid model to revolutionize early detection strategies, ultimately improving treatment outcomes and survival rates for lung cancer patients. © 2024 IEEE.

关键词： Deep learning Early detection Hybrid model Lung cancer MRI

来源：评论

学校读者我要写书评

暂无评论

Advancing ASR for Indian-Accented English: Dataset Creation and Whisper Fine-Tuning

引用

Procedia computer science 2025年 258卷 2510-2519页

作者： Jaswanth Kunisetty Pranav Ramachandrula Sruthi S Susmitha Vekkot Deepa Gupta Department of Computer Science & Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India Department of Electronics & Communication Engineering Amrita School of Engineering Bengaluru Amrita Vishwa Vidyapeetham India

Despite advancements in Automatic Speech Recognition (ASR) technology, accurately transcribing Indian-accented English, remains a significant challenge. The main challenge associated with the transcription of Indian English is the lack of curated datasets covering a wide range of regional accents in the Indian sub-continent. Addressing this issue, this paper concentrates on building and testing a diverse dataset that captures the nuances of Indian-accented English, covering various regions and dialects across India. In Phase 1, data was collected from over 200 speakers, yielding 70 hours of speech data using custom-made healthcare transcripts in Telugu, Hindi, Kannada, Marathi, Tamil, and Malayalam. Phase 2 data collection include 100 hours of data from around 400 speakers, with transcripts derived from novels, newspapers, books, and online articles across Tamil Nadu, Karnataka, Andhra Pradesh, Maharashtra, Madhya Pradesh, Delhi, Assam, Manipur, and Rajasthan. The comprehensive dataset, spanning a total of 633 speakers, with around 170 hours of data was collected in two phases to understand the variations in pronunciation, intonation, and phonetic emphasis characteristic of the Indian accent. Further, the training was conducted by fine-tuning the existing Whisper ASR model to enhance its performance for Indian-accented English. Our results show that the fine-tuned Whisper-Tiny model achieved a Word Error Rate (WER) of 18.141%, Whisper-Small achieved 17.36%, and Whisper-Medium achieved 15.08%, demonstrating a significant improvement in recognizing and transcribing Indian-accented English.

关键词： Automatic speech recognition Indian accent Whisper Word Error Rate

来源：评论

学校读者我要写书评

暂无评论

Optimization of Cognitive Radio System Using Self-Learning Salp Swarm Algorithm

引用

computers, Materials & Continua 2022年第2期70卷 3821-3835页

作者： Nitin Mittal Harbinder Singh Vikas Mittal Shubham Mahajan Amit Kant Pandit Mehedi Masud Mohammed Baz Mohamed Abouhawwash Department of Electronics&Communication Engineering Chandigarh UniversityMohali140413India School of VLSI Design and Embedded Systems National Institute of TechnologyKurukshetra136119India School of Electronics&Communication Engineering Shri Mata Vaishno Devi UniversityKatra182320India Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Computer Engineering College of Computer and Information TechnologyTaif UniversityTaif21994Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

CognitiveRadio(CR)has been developed as an enabling technology that allows the unused or underused spectrum to be used dynamically to increase spectral *** improve the overall performance of the CR systemit is extremely important to adapt or reconfigure the *** Decision Engine is a major module in the CR-based system that not only includes radio monitoring and cognition functions but also responsible for parameter *** meta-heuristic algorithms offer numerous advantages compared to traditional mathematical approaches,the performance of these algorithms is investigated in order to design an efficient CR system that is able to adapt the transmitting parameters to effectively reduce power consumption,bit error rate and adjacent interference of the channel,while maximized secondary user ***-Learning Salp Swarm Algorithm(SLSSA)is a recent meta-heuristic algorithm that is the enhanced version of SSA inspired by the swarming behavior of *** this work,the parametric adaption of CR system is performed by SLSSA and the simulation results show that SLSSA has high accuracy,stability and outperforms other competitive algorithms formaximizing the throughput of secondary *** results obtained with SLSSA are also shown to be extremely satisfactory and need fewer iterations to converge compared to the competitive methods.

关键词： Cognitive radio meta-heuristic algorithm cognitive decision engine salp swarm algorithm

来源：评论

学校读者我要写书评

暂无评论

Optical image encryption algorithm based on a new four-dimensional memristive hyperchaotic system and compressed sensing

引用

Chinese Physics B 2023年第11期32卷 426-445页

作者：都洋隆国强蒋东华柴秀丽韩俊鹤 Center for Physics of Low-Dimensional Materials Henan Joint International Research Laboratory of New Energy Materials and DevicesSchool of Physics and ElectronicsHenan UniversityKaifeng 475004China School of Artificial Intelligence Henan Engineering Research Center for Industrial Internet of ThingsHenan UniversityZhengzhou 450046China School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China

Some existing image encryption schemes use simple low-dimensional chaotic systems, which makes the algorithms insecure and vulnerable to brute force attacks and cracking. Some algorithms have issues such as weak correlation with plaintext images, poor image reconstruction quality, and low efficiency in transmission and storage. To solve these issues,this paper proposes an optical image encryption algorithm based on a new four-dimensional memristive hyperchaotic system(4D MHS) and compressed sensing(CS). Firstly, this paper proposes a new 4D MHS, which has larger key space, richer dynamic behavior, and more complex hyperchaotic characteristics. The introduction of CS can reduce the image size and the transmission burden of hardware devices. The introduction of double random phase encoding(DRPE) enables this algorithm has the ability of parallel data processing and multi-dimensional coding space, and the hyperchaotic characteristics of 4D MHS make up for the nonlinear deficiency of DRPE. Secondly, a construction method of the deterministic chaotic measurement matrix(DCMM) is proposed. Using DCMM can not only save a lot of transmission bandwidth and storage space, but also ensure good quality of reconstructed images. Thirdly, the confusion method and diffusion method proposed are related to plaintext images, which require both four hyperchaotic sequences of 4D MHS and row and column keys based on plaintext images. The generation process of hyperchaotic sequences is closely related to the hash value of plaintext images. Therefore, this algorithm has high sensitivity to plaintext images. The experimental testing and comparative analysis results show that proposed algorithm has good security and effectiveness.

关键词： memristor hyperchaotic system compressed sensing fractional Fourier transform optical image encryption

来源：评论

学校读者我要写书评

暂无评论

Shorting pin and SRR loaded multi-band Antenna for 4G/5G/Wi-Fi/WiMAX and IOT Applications

Shorting pin and SRR loaded multi-band Antenna for 4G/5G/Wi-...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Kumar, Anubhav Saxena, Divya Sharma, Navneet Gankotiya, Anil Raj Kumar Goel Institute of Technology and Management Department of Electronics and Communication Uttar Pradesh Ghaziabad India Abes Engineering College Applied Science & Humanities Uttar Pradesh Ghaziabad India Abes Engineering College Department of Electronics and Communication Uttar Pradesh Ghaziabad India Poornima University Department of Computer Science & Engineering Rajasthan Jaipur India

ISBN: (纸本)9798350322309

In this paper, shorting pin and SRR-loaded multi-band antenna is presented for wireless communication application. The multiple radiation strips are used with the partial ground to design a multiband operating frequency antenna. The hook and L-shaped radiating strips are used to design a two-band antenna where SRR is loaded on the antenna to implement a triple band antenna which shifted the bandwidth of the antenna. The shorting-pin is used to ground the lower arm of the antenna and enhances the impedance bandwidth with four operating bands. The obtained antenna bandwidth is 2.2-2.4/3.1-3.6/4.9-5.05/5.35-5.6 GHz and covers multiple applications in the wireless communications. © 2023 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Epidemic Diseases based on Vector-Borne Diseases using Support Vector Machine with Extreme Gradient Boost 1

Predictive Modeling of Epidemic Diseases based on Vector-Bor...

引用

1st International Conference on Software, Systems and Information Technology, SSITCON 2024

作者： Satish, E.G. Haq, Quazi Mohd. Imranul Mahaboob John, Y.M. Hassan, Muntather Muhsin Jothi, E. Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bengaluru India University of Nizwa College of Arts and Sciences Department of Biological Sciences and Chemistry Nizwa Oman Mahendra College of Engineering Department of Electronics and Communication Engineering Salem India The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq New Prince Shri Bhavani College of Engineering and Technology Department of Information Technology Chennai India

ISBN: (纸本)9798350352931

In recent years, the globalization and progressive climatic changes lead to increase in the occurrence of Vector Borne Diseases (VBD) from endemic regions to non-endemic regions. The common forms of VBD includes malaria, chikungunya, dengue fever, yellow fever and plague. The existing methods for predicting epidemic diseases did not handle non-linear relationships and complex interactions. Therefore, this paper proposes Support Vector Machine with Extreme Gradient Boost (SVM-XGBOOST) for predicting epidemic diseases based on vector borne diseases. Initially, vector borne diseases dataset is taken which contains epidemiological data and information related to climate. Then, this data is preprocessed by using cross validation to generalize the model well and it evaluates the quality of data. After that, Least Absolute Shrinkage and Selection Operator (LASSO) or (L1Regularization) is used for selecting features which selects the relevant features automatically and handles noisy data. finally, classification is done by using SVM-XGBOOST which handles non-linear relationships and handles complex interactions. The proposed SVM-XGBOOST achieved better results in terms of accuracy (98.45%), Precision (95.50%), Recall (97.98%), and F1 score (9 7. 2 5 %). © 2024 IEEE.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

A Review on Vulnerabilities to Modern Processors and its Mitigation for Various Variants 4th

A Review on Vulnerabilities to Modern Processors and its Mit...

引用

4th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2022

作者： Praveen Kumar, E. Priyanka, S. Sudhakar, T. School of Electronics Engineering VIT-AP University Amaravathi India School of Computer Science and Engineering VIT-AP University Amaravathi India

Recently, security researchers have found two hardware security vulnerabilities namely Spectre and Meltdown, related to computer memory. They are not singular, many variants of these two vulnerabilities are being a head ache for secure hardware designers. These attacks affect the modern CPUs which use speculative and out-of-order execution for optimization. This attack may affect the computing device which using the processor like Intel, AMD, ARM, and other processors like ARM processors that may use by mobile devices. By exploiting these attack that may allow the adversary to gain the control of a device to capture all the secrete data available on the system or a memory. These vulnerabilities need the better solution at the hardware level, but the problem is hardware updates is not possible at the real-time. In the face, the software-based solution is not addressed by the long run to avoid this attack, this solution is only for time constrain. This paper presents the solution for different variants of Spectre and Meltdown vulnerabilities and how they are dangerous to the modern processors like Intel, AMD, and so on to avoid the damage of the hardware using Hardware Performance Counters (HPCs). Finally, some of the mitigation techniques against these vulnerabilities are suggested based on the running application of a device. © 2023 The Authors. Published by Elsevier B.V.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

Hash Table Assisted Efficient File Level De-Duplication Scheme in SD-IoV Assisted Sensing Devices

引用

Intelligent Automation & Soft Computing 2023年第10期38卷 83-99页

作者： Ghawar Said Ata Ullah Anwar Ghani Muhammad Azeem Khalid Yahya Muhammad Bilal Sayed Chhattan Shah Department of Computer Science International Islamic UniversityIslamabad44000Pakistan Department of Computer Science National University of Modern LanguagesIslamabad44000Pakistan Department of Electrical and Electronics Engineering Nisantasi UniversityIstanbul34467Turkey Department of Computer Engineering Hankuk University of Foreign StudiesYongin-siGyeonggi-do17035Korea Department of Information and Communication Engineering Hankuk University of Foreign StudiesYongin-siGyeonggi-do17035Korea

The Internet of Things(IoT)and cloud technologies have encouraged massive data storage at central ***-defined networks(SDN)support the processing of data and restrict the transmission of duplicate *** is necessary to use a data de-duplication mechanism to reduce communication costs and storage *** State of the art schemes suffer from computational overhead due to deterministic or random tree-based tags generation which further increases as the file size *** paper presents an efficient file-level de-duplication scheme(EFDS)where the cost of creating tags is reduced by employing a hash table with key-value pair for each block of the ***,an algorithm for hash table-based duplicate block identification and storage(HDBIS)is presented based on fingerprints that maintain a linked list of similar duplicate blocks on the same *** tables normally have a consistent time complexity for lookup,generating,and deleting stored data regardless of the input *** experiential results show that the proposed EFDS scheme performs better compared to its counterparts.

关键词： Hash table de-duplication linked list IoT sensing devices

来源：评论

学校读者我要写书评

暂无评论

Detection of pneumonia progression in lungs of individuals affected with covid 19 severely using deep learning techniques 3

Detection of pneumonia progression in lungs of individuals a...

引用

3rd International Conference for Emerging Technology, INCET 2022

作者： Gadipudi, Praneeth Teja, Palachuri Sai Yelamancheli, Chandana Sowmya. Thaniserikaran, Adith Mohiuddin, Rayyan Joy, Ajin Srm University Department of Computer Science and Engineering Andhra Pradesh Amaravati India Srm Department of Computer Science and Engineering Institute of Science and Technology Tamil Nadu Kattankulathur India Icfai University Department of Computer Science and Engineering Hyderabad India National Institute of Technology Department of Computer Science and Engineering Telangana Warangal India National Institute of Technology Department of Electrical Engineering Telangana Warangal India JSPMs' Rajarshi Shahu College of Engineering Department of Electronics and Telecommunication Engineering Maharashtra Pune India

ISBN: (纸本)9781665494991

The coronavirus sickness (COVID-19) is a worldwide pandemic that was detected in December 2019 by a Chinese physician in Wuhan, Hubei Province, mainland China. There is presently no licensed human vaccine to combat it. When individuals are close together, COVID-19 spreads more fast. As a consequence, travel constraints are in place to minimize the disease from spreading, and regular Washing the hands is encouraged so that the infections that occur due to the virus. Other indications and symptoms include chest discomfort, sputum production, and a sore throat. COVID19 could lead to a very dangerous disease which is pneumonia which occurs due to the virus. When employing CT scans or Xrays to identify the symptoms that are occuring due to the cause of covid-19 in the last region of the lungs then the accuracy is better than when utilizing RT-PCR. But as there are very less radiologists as compared to the new residents or the people that have come and aslo there has been seen many re examinations occurring of these patients. To solve this kind of the issues or problems that is limiting the CT scans and the x-rays the speed of this procedure must be boosted. This may be done by adding artificial intelligence (AI) approaches into contemporary diagnostic systems. The main motive of the paper is to provide the best accuracy to detect the disease using CNN along with a comparison with the transfer learning approach. © 2022 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

MeHyper: Accelerating Hypergraph Neural Networks by Exploring Implicit Dataflows 31

MeHyper: Accelerating Hypergraph Neural Networks by Explorin...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhao, Wenju Yao, Pengcheng Chen, Dan Zheng, Long Liao, Xiaofei Wang, Qinggang Ma, Shaobo Li, Yu Liu, Haifeng Xiao, Wenjing Sun, Yufei Zhu, Bing Jin, Hai Xue, Jingling Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore Guangxi University School of Computer Electronics and Information NanNing530004 China University of New South Wales School of Computer Science and Engineering SydneyNSW2052 Australia

ISBN: (纸本)9798331506476

Hypergraph Neural Networks (HGNNs) are increasingly utilized to analyze complex inter-entity relationships. Traditional HGNN systems, based on a hyperedge-centric dataflow model, independently process aggregation tasks for hyperedges and vertices, leading to significant computational redundancy. This redundancy arises from recalculating shared information across different tasks. For the first time, we identify and harness implicit dataflows (i.e., dependencies) within HGNNs, introducing the microedge concept to effectively capture and reuse intricate shared information among aggregation tasks, thereby minimizing redundant computations. We have developed a new microedge-centric dataflow model that processes shared information as fine-grained microedge aggregation tasks. This dataflow model is supported by the Read-Process-Activate-Generate execution model, which aims to optimize parallelism among these tasks. Furthermore, our newly developed MeHyper, a microedge-centric HGNN accelerator, incorporates a decoupled pipeline for improved computational parallelism and a hierarchical feature management strategy to reduce off-chip memory accesses for large volumes of intermediate feature vectors generated. Our evaluation demonstrates that MeHyper substantially outperforms the leading CPUbased system PyG-CPU and the GPU-based system HyperGef, delivering performance improvements of 1,032.23 × and 10.51 ×, and energy efficiencies of 1,169.03 × and 9.96 ×, respectively. © 2025 IEEE.

关键词： Redundancy

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：