检索结果-内蒙古大学图书馆

Enhancing Skin Cancer Detection with Multimodal Data Integration: A Combined Approach Using Images and Clinical Notes

引用

SN computer science 2025年第1期6卷 1-14页

作者： Chakkarapani, V. Poornapushpakala, S. Suresh, S. School of Electrical and Electronics Sathyabama Institute of Science and Technology (Deemed to be University) Jeppiaar Nagar Rajiv Gandhi Salai Tamilnadu Chennai 600119 India Department of Computer Applications National Institute of Technology Haryana Kurukshetra 136119 India

Skin cancer is one of the most common cancers worldwide where early detection is crucial for effectively diagnosing and treatment. Traditional diagnostic methods largely depend on dermoscopic or skin lesion image analysis. However, they are limited by the clinician’s expertise and primarily rely on image data. While most of the studies focus on improving the diagnostic accuracy using the skin lesion images, this study addresses the limitations of using just the image data and proposes a novel approach that enhances skin cancer detection by combining skin lesion images with patients’ clinical notes. The methodology proposes a multi-modal approach that combines the images data with doctor’s clinical notes to enhance early diagnosis and accurate detection of skin cancer. Clinical notes are synthetically generated using two distinct multimodal large language models (LLMs), corresponding to each patient’s skin cancer images, encapsulating both visual and textual data representative of real-world scenarios. The generated clinical notes are validated through a dual-method approach involving cross-evaluation and consensus scoring, utilizing metrics such as the BLEU score, ROUGE score, Overlap Coefficient, and Jaccard index. Furthermore, this paper compares the performance of a model built using skin lesion images with four other models built using skin lesion images and synthetically generated clinical notes. The experimental results demonstrates a significant improvement in all classification metrics compared to single-modality models, achieving an accuracy of 99.51%, precision of 96.19%, recall of 97.95%and f1-score of 97.03% with the multimodal ALBEF model that uses GPT-4-turbo for clinical notes generation. The results show a significant improvement in performance with the multi modal approach for medical diagnosis. Also, this research sets a foundational framework that can be leveraged for many potential healthcare diagnoses applications. © The Author(s), under exclusi

关键词： Dermatology Generative AI Large language models Multi-modal AI Skin cancer detection Synthetic data generation

来源：评论

学校读者我要写书评

暂无评论

Federated learning-based hybrid convolutional recurrent neural network for multi-class intrusion detection in IoT networks

引用

Discover Internet of Things 2025年第1期5卷 1-22页

作者： Selvam, Prabu Karthikeyan, P. Manochitra, S. Sujith, A.V.L.N. Ganesan, T. Ayyasamy, Rajaram Shuaib, Mohammed Alam, Shadab Rajendran, A. School of Computing SRM Institute of Science and Technology Tiruchirappalli621105 India Department of Electronics and Communication Engineering Velammal College of Engineering and Technology Tamil Nadu Madurai625009 India Department of Computer Science Engineering St Joseph’s College of Engineering Tamil Nadu Chennai600119 India School of Engineering Malla Reddy University Telangana Hyderabad500043 India Department of Computer Science Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Department of Electronics and Communication Engineering E.G.S Pillay Engineering College Tamil Nadu Nagapattinam611002 India Department of Computer Science College of Engineering and Computer Science Jazan University Jazan Saudi Arabia Department of ECE Karpagam College of Engineering Tamil Nadu Othakkal Mandapam India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

As Internet of Things (IoT) devices leads an significant challenges in securing the systems from cyber-attacks in large-scale IoT networks. Traditional methods faces struggle to precisely detecting the complex intrusion patterns due to the heterogeneity and distributed IoT devices. There is a pressing need for scalable, real-time, and privacy-preserving solutions to secure IoT and IIoT systems. For multi-class intrusion detection in IoT networks, this study proposed an novel hybrid convolutional recurrent neural network (CRNN) model based on federated learning. By integrating federated learning, the proposed approach ensures privacy by enabling decentralized model training among IoT devices without exchanging sensitive data. The hybrid CRNN model improves detection accuracy for a variety of attack types in IoT networks by combining Recurrent Neural Networks for sequential pattern recognition and Convolutional Neural Networks for feature extraction from raw data. The proposed model classifies incoming network traffic into different attack classes. The experimental results conducted on the Edge-IIoT dataset reveal that the proposed model has attained the detection accuracy of 98.93% with balanced precision and recall for all the attack types and low-support classes such as SQL Injection and Man-in-the-Middle. This balance improves model’s ability to reduce both false negatives and false positives compared with conventional approaches. Together with real-time detection, our approach excels in a privacy-preserving manner, providing a practical, scalable solution for securing complex IoT networks, and addressing critical gaps in current IDS frameworks. © The Author(s) 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Tug-of-War between Static and Dynamic Memory in Intel SGX 38

A Tug-of-War between Static and Dynamic Memory in Intel SGX

引用

38th International Conference on VLSI Design, VLSID 2025

作者： Kumar, Sandeep Panda, Abhisek Nerlikar, Advait Sarangi, Smruti R. School of Information Technology IIT Delhi Delhi India Computer Science and Engineering IIT Delhi Delhi India Electrical and Electronics Engineering BITS Pilani Goa India

ISBN: (纸本)9798331522445

Security of applications and data in a cloud setting has become a first-class design criterion. Hardware vendors have proposed trusted execution environments or TEEs where the hardware guarantees an application's data and code security both at rest and in-use, even from privileged entities such as operating systems and hypervisors. Software Guard eXtension, or SGX, is a popular, trusted execution environment or TEE solution from Intel. To ensure security guarantees, SGX provides secure sand-box environments called enclaves, which have encrypted physical memory. In the latest version of SGX, we start an enclave with a the specified amount of 'static' memory specified by a developer. Subsequently, we add additional memory pages 'dynamically' to an enclave depending on an application's memory usage. In this paper, we analyze the impact of the allocation and freeing of static and dynamic pages on an application's performance. We observe that inappropriately setting the static memory size may lead to a performance slowdown of up to 20x. We present Harmony - a profile-guided optimizer that measures the impact of dynamic memory management on an application's performance, and suggests a near-optimal distribution for static and dynamic memory pages. We show that Harmony improves the execution latency of an application by up to 68% and 29% when compared with the purely dynamic and purely static allocation schemes, respectively. © 2025 IEEE.

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

Transforming High-Frequency Trading Predictions with CNN-LSTM Networks 5

Transforming High-Frequency Trading Predictions with CNN-LST...

引用

5th IEEE International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Priya, S. Baghavathi Priyanga, S. Kamisetty, Sri Surya Shobith Neelapala, Venkata Sai Vinay Nithila, G. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science & Engineering Chennai India Vellore Institute of Technology Department of Electronics & Communication Engineering Vellore India Vellore Institute of technology Department of Computer Science & Engineering Vellore India

ISBN: (纸本)9798350356236

High-Frequency Trading (HFT) has transformed financial markets by enabling rapid and automated trading. However, the prediction of critical market metrics, such as trading volumes, remains a challenge due to the noisy and complex nature of financial data. This paper presents a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) model designed specifically for predicting trading volumes in the NIFTY50 index using high-resolution, minutelevel Yahoo Finance data. By combining CNN's spatial feature extraction capabilities with LSTM's temporal modeling strengths, the proposed approach effectively captures the intricate patterns and sequential dependencies inherent in high-frequency trading datasets. Comprehensive data preprocessing, including noise reduction and temporal segmentation, coupled with advanced cross-validation techniques, ensures robust performance across market conditions. Comprehensive evaluations using metrics such as Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R2) demonstrate the model's efficacy in capturing intricate financial dynamics. This work underscores the potential of hybrid deep learning models in enhancing predictive analytics for high-frequency trading applications in emerging markets. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-Dialect End-to-End ASR Model Jointly with Beam Search Threshold Pruning and LLM

引用

SN computer science 2025年第4期6卷 1-12页

作者： Shunmuga Priya, M.C. Karthika Renuka, D. Ashok Kumar, L. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Department of Information Technology PSG College of Technology Coimbatore India Department of Electrical and Electronics Engineering Thiagarajar College of Engineering Madurai India

This paper aims to develop a novel robust multi-dialect end-to-end ASR system with beam search threshold pruning. The efficacy of our proposed model is evaluated using word error rate (WER). Our key contributions are: (1) To develop an end-to-end ASR system using attention-based neural network architecture and analyze the effectiveness of two features such as MFCC and log mel filter bank energies on multiple speech dialect corpora including American, Britain, and Indian accents;(2) To integrate beam search threshold pruning as a decoding mechanism to reduce the decoding time (3) To conduct an experimental analysis to test the model performance and compare the results against baseline system. (4) Post processing analysis are carried out using Llama2-7B based large language model(LLM) for enhancing the performance of proposed ASR system. The proposed model significantly improves performance by 1.91% and 4.29% over clean and noisy speech in librispeech corpus. Similarly, for the Indian accented speech, the model attains an average WER of about 6.6%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Automatic speech recognition Beam search Decoding LLM Log Mel filter bank energies

来源：评论

学校读者我要写书评

暂无评论

On the Stability of Random Access with Congestion Control 14th

On the Stability of Random Access with Congestion Control

引用

14th EAI International Conference on Wireless and Satellite Systems, WiSATS 2024

作者： Xu, Yu Cui, Chen Wang, Zhenyong Guo, Qing School of Electronics and Information Engineering Harbin Institute of Technology Harbin150001 China National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing100871 China Songjiang Laboratory Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9783031861956

The random access protocol is a critical technique widely used in various wireless networks. A significant challenge is analyzing the stability of the random access system when a large number of users transmit packets independently. Although the congestion control policy can enhance the stability of the system, there is currently a lack of quantitative analysis on the stability of random access with congestion control. In this paper, we analyze the random access system with congestion control and quantify its stability. Specifically, we consider a congestion control scheme to enhance the stability of the random access system and present the graphical analytical model. Based on this graphical model, we qualitatively discuss the behavioral variations of the system as it works and quantify its stability. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

Ultra Energy Efficient Reliable and Robust DLJLFET-Based-PUF for IoT Devices 3rd

Ultra Energy Efficient Reliable and Robust DLJLFET-Based-PUF...

引用

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Rajan, Chithraja Kumar, Rakesh Panchore, Meena Singh, Jawar School of Computer Science and Engineering Ramdeobaba University Maharashtra Nagpur440013 India Department of Electronics and Communication Engineering National Institute of Technology Patna Bihar800005 India Department of Electronics and Communication Engineering Indian Institute of Technology Patna Patna India

ISBN: (纸本)9789819743582

Physically Unclonable Function (PUF) emerged as a prominent hardware security solution for Internet of Things (IoTs) devices. PUFs are also used for generating secret keys for cryptography and for low-cost authentication in the high security of integrated circuits (ICs). Some natural variations occur during the manufacture of ICs. These variations are inevitable and uncertain. The PUF generates a different and unique random number by using this variation as the output key for the same input, even though this variation in the output is very small. In this article, a detailed comparative performance analysis of junctionless field effect transistor (JLFET)-based PUF and dopingless JLFET (DLJLFET)-based PUF is presented. A PUF circuit is designed using a five-stage ring oscillator (RO). It is observed that the delay in DLJLFET-based RO is 61% lower and consumes 47% less energy than JFLET-based RO at a supply voltage of 0.5 V because JLFET shows a higher leakage current due to high doping in the channel. Further, we did Monte Carlo simulation for 100 runs and observed that DLJLFET-PUF gives more unique PUF as mean HD is close to 50% and frequency of oscillation of DLJLFET is about 2 times higher than JLFET-PUF so DLJLFET-PUF will take less time during encryption and decryption for incoming and outgoing data, thus the output key generation will be faster. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Hardware security

来源：评论

学校读者我要写书评

暂无评论

Near-Field Communications: Shape and Structure Design for Uniform Planar Array

引用

IEEE Internet of Things Journal 2025年第11期12卷 15151-15165页

作者： Chen, Siyu Gu, Juping Duan, Wei Zhang, Lei Dang, Shuping Wen, Miaowen Ding, Zhiguo Ho, Pin-Han Nantong University School of Information Science and Technology Nantong226019 China Suzhou University of Science and Technology China Hubei Polytechnic University Department of Electronics and Information Engineering Huangshi435003 China University of Bristol School of Electrical Electronic and Mechanical Engineering BristolBS8 1UB United Kingdom South China University of Technology School of Electronic and Information Engineering Guangzhou510640 China Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates University of Electronic Science and Technology of China Shenzhen Institute for Advanced Study Shenzhen518000 China University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada

With the flourishing development of 6G wireless networks, the demand of spectrum efficiency rapidly increases, in order to support the demands of high quality data transmission and connections of massive users. Among various promising technologies, the technology of near-field communications provides a great potential to address such an issue due to the unique spherical-wave channels for electromagnetic (EM) propagation. In this paper, multiple-input single-output (MISO) near-field communications is comprehensively studied to clarify the influences of the shape and structure of uniform planar array (UPA) on the system performance, considering three cases with uniform linear array (ULA), rectangular UPA, and circular UPA. In particular, we reveal the properties of rapid deterioration for signal-to-noise ratio (SNR) from the reduced projection aperture in near-field communications and investigate the single spherical crown antenna design and spherical crown antenna array design in order to address this issue. Moreover, we also characterize the role of antenna projection aperture in details, and theoretically analyze the shape of UPA, yielding the corresponding exact closed-form expressions for SNR and outage probability (OP). Based on these above analytical results, we find out that adjusting the spacing between adjacent antennas to control the relative angle between user and selected antennas is an efficient way to improve the projection aperture of antenna and SNR. Simulation results are shown to well match analytical results, which validate the correctness of our analysis, clarifying that our proposed designs outperform the conventional works and illustrating a better stability for angle variations. © 2025 IEEE.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Extremum Encoding for Joint Baseband Signal Compression and Time-Delay Estimation for Distributed Systems

Extremum Encoding for Joint Baseband Signal Compression and ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Weiss, Amir Kochman, Yuval Wornell, Gregory W. Faculty of Engineering Bar-Ilan University Israel School of Computer Science and Engineering The Hebrew University of Jerusalem Israel Research Laboratory of Electronics Massachusetts Institute of Technology United States

ISBN: (纸本)9798350368741

The ubiquitous time-delay estimation (TDE) problem becomes nontrivial when sensors are non-co-located and communication between them is limited. Building on the recently proposed "extremum encoding" compression-estimation scheme, we address the critical extension to complex-valued signals, suitable for radio-frequency (RF) baseband processing. This extension introduces new challenges, e.g., due to unknown phase of the signal of interest and random phase of the noise, rendering a naïve application of the original scheme inapplicable and irrelevant. In the face of these challenges, we propose a judiciously adapted, though natural, extension of the scheme, paving its way to RF applications. While our extension leads to a different statistical analysis, including extremes of non-Gaussian distributions, we show that, ultimately, its asymptotic behavior is akin to the original scheme. We derive an exponentially tight upper bound on its error probability, corroborate our results via simulation experiments, and demonstrate the superior performance compared to two benchmark approaches. © 2025 IEEE.

关键词： compression for estimation data compression distributed estimation max-index estimator Time-delay estimation

来源：评论

学校读者我要写书评

暂无评论

Innovative Approach for Early Heart Disease Prediction: Gaussian Mixture Model and K-Nearest Neighbour 3

Innovative Approach for Early Heart Disease Prediction: Gaus...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Surendran, R. Anandaraj, B. Deepa, P. Mageshwari, M. Balamurugan, K.S. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering Madnapalle Institute of Technology & Science Andhra Pradesh Madanapalle India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer science and engineering Karpaga Vinayaga College of Engineering and Technology Tamil Nadu Chengalpattu India Department of Electronics and communication engineering Karpaga Vinayaga College of Engineering and Technology Tamil Nadu Chengalpattu India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

An Electrocardiogram (ECG) contributes significantly to early diagnosis and classification of heart diseases, arrhythmia which means irregular heart rate. Regrettably, the process became difficult due to asymmetric and minimal amplitude from recordings of ECG and cannot do the extraction from multiple signals. By using machine learning technology, it can classify and extract multiple samples, but cannot extract the data features from complex data structures. To overcome the limitations, previously introduced metaheuristic optimization (MHO) to improve the classification and extraction. Proposed a method which supports and K-Nearest Neighbour (KNN) Gaussian Mixture Model (GMM) algorithms for determine the abnormalities, predicting cardiac events, and improve diagnostic accuracy. As a result, this can help us to get results more quickly and accurately with sensitivity 99.7% and accuracy 99.2%, for helping healthcare professionals in diagnosing arrythmias, myocardial infarction and any other heart conditions. © 2025 IEEE.

关键词： Adversarial machine learning

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：