检索结果-内蒙古大学图书馆

A two-stage CNN model for the classification and severity analysis of retinal and choroidal diseases in OCT images

International Journal of Intelligent Networks 2024年第1期5卷 10-18页

作者： George, Neetha Shine, Linu N, Ambily Abraham, Bejoy Ramachandran, Sivakumar Department of Electronics and Communication Engineering Rajiv Gandhi Institute of Technology Kottayam Kerala India Department of Electronics and Communication Engineering College of Engineering Trivandrum Kerala India Department of Electronics and Communication Engineering Government Engineering College Idukki Kerala India Department of Computer Science and Engineering College of Engineering Muttathara Kerala Thiruvananthapuram India Department of Electronics and Communication Engineering Government Engineering College Wayanad Kerala India

The advancements in medical imaging techniques have brought exponential increase in the quantity and complexity of data which often require human expertise for interpretation and decision making. However, in real-world clinical settings, there is often a shortage of experts available for timely diagnosis and triage. An automated diagnostic technique aids clinicians in the precise diagnosis and effective management of diseases. In this article, a two-stage classification model using convolutional neural network (CNN) is proposed for the classification and severity analysis of retinal and choroidal diseases in optical coherence tomography (OCT) images. The proposed model can identify abnormal conditions such as Pachychoroid disorders, macular edema, and Drusen. The images are initially classified into four categories-healthy, Drusen, Pachychoroid and macular edema classes. The severity of Pachychoroid conditions, including central serous chorioretinopathy, polypoid choroidal vasculopathy, and choroidal neovascularization, is subsequently determined through a second-level classification. A modified version of the VGG16 architecture is used for the initial classification. A fine-tuned CNN with the same architecture is then employed to determine the severity of Pachychoroid diseases. Further, we make use of the UNet architecture for assessing the severity of macular edema. The proposed hybrid approach for classification and analysis achieved promising results, demonstrating consistency on par with human experts in diagnosing and grading ocular diseases. © 2024

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

An amalgamation of integrated features with DeepSpeech2 architecture and improved spell corrector for improving Gujarati language ASR system

引用

International Journal of Speech Technology 2024年第1期27卷 87-99页

作者： Dua, Mohit Bhagat, Bhavesh Dua, Shelza Department of Computer Engineering National Institute of Technology Kurukshetra India Department of Electronics Communication and Engineering Punjab Engineering College Chandigarh India

Automatic Speech Recognition systems that convert language into written text have greatly transformed human–machine interaction. Although these systems have achieved results, in languages building accurate and reliable ASR models for low resource languages like Gujarati comes with significant challenges. Gujarati lacks data and linguistic resources, making developing high-performance ASR systems quite difficult. In this paper, we propose an approach to enhance the effectiveness of a Gujarati ASR model despite resources. We achieve this by incorporating integrated features such as Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC) utilizing the DeepSpeech2 architecture and implementing an improved spell correction technique based on the Bidirectional Encoder Representations from Transformers (BERT) algorithm. Our approach has demonstrated superiority over previous state-of-the-art methodologies through testing and evaluation. The experimental results demonstrate that our proposed method consistently reduces the Word Error Rate (WER) by 10–12 percentage points compared to the existing work, surpassing the most significant improvement of 5.87%. Our findings demonstrate the viability of developing accurate and dependable ASR systems for languages with limited resources, such as Gujarati. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

EARTHEN LAMP-SHAPED DGS DUAL BAND MICROSTRIP PATCH ANTENNA FOR HIGH RETURN LOSS IN BIOMEDICAL APPLICATION

引用

Telecommunications and Radio engineering (English translation of Elektrosvyaz and Radiotekhnika) 2024年第6期83卷 23-37页

作者： Gour, Sonam Rathi, Amit Department of Electronics & Communication Engineering Manipal University Jaipur Jaipur India Department of Computer Engineering Poornima College of Engineering Jaipur India

This study illustrates a dual-band circular and pentagon antenna with dual-band configuration for the high return loss. When an antenna has a greater return loss, less power is reflected toward the transmitter, implying that the antenna and transmission line are better suited. Due to its accessibility, the FR4 substrate is used to replicate the design. With a bandwidth of 150 MHz and 200 MHz, respectively, the antenna’s dual-band performance is between 2.32 GHz to 2.47 GHz and 2.9 GHz to 3.1 GHz. The body phantom design in CST Studio is used to test the design’s biocompatibility. It is demonstrated by the improved antenna in the industrial, scientific, and medical (ISM) band region that it can be utilized for telemetry or medical services. © 2024 Begell House Inc.. All rights reserved.

关键词： Biocompatibility

来源：评论

学校读者我要写书评

暂无评论

Joint Rain Streaks & Haze Removal Network for Object Detection

引用

computers, Materials & Continua 2024年第6期79卷 4683-4702页

作者： Ragini Thatikonda Prakash Kodali Ramalingaswamy Cheruku Eswaramoorthy K.V Department of Electronics and Communication Engineering National Institute of TechnologyWarangal506004India Department of Computer Science and Engineering National Institute of TechnologyWarangal506004India Department of Electronics and Communication Engineering Indian Institute of Information TechnologyDesign and ManufacturingKurnool518008India

In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant *** emergence of abundant computational resources has driven the dominance of deep Convolutional Neural Networks(CNNs),supplanting traditional methods reliant on prior ***,the evolution of CNN architectures has tended towards increasing complexity,utilizing intricate structures to enhance performance,often at the expense of computational *** response,we propose the Selective Kernel Dense Residual M-shaped Network(SKDRMNet),a flexible solution adept at balancing computational efficiency with network accuracy.A key innovation is the incorporation of an M-shaped hierarchical structure,derived from the U-Net framework as M-Network(M-Net),within which the Selective Kernel Dense Residual Module(SDRM)is introduced to reinforce multi-scale semantic feature *** methodology employs two sampling techniques-bilinear and pixel unshuffled and utilizes a multi-scale feature fusion approach to distil more robust spatial feature map *** the reconstruction phase,feature maps of varying resolutions are seamlessly integrated,and the extracted features are effectively merged using the Selective Kernel Fusion Module(SKFM).Empirical results demonstrate the comprehensive superiority of SKDRMNet across both synthetic and real rain and haze datasets.

关键词： Image deraining Selective Dense Residual Module(SDRM) Selective Kernel Fusion Module(SKFM) Selective KernelDense Residual M-Shaped Network(SKDRMNet)

来源：评论

学校读者我要写书评

暂无评论

Intelligent integrated sensing and communication:a survey

引用

Science China(Information Sciences) 2025年第3期68卷 5-46页

作者： Jifa ZHANG Weidang LU Chengwen XING Nan ZHAO Naofal AL-DHAHIR George K.KARAGIANNIDIS Xiaoniu YANG School of Information and Communication Engineering Dalian University of Technology College of Information Engineering Zhejiang University of Technology School of Information and Electronics Beijing Institute of Technology Department of Electrical and Computer Engineering The University of Texas at Dallas Department of Electrical and Computer Engineering Aristotle University of Thessaloniki

Integrated sensing and communication (ISAC) is a promising technique to increase spectral efficiency and support various emerging applications by sharing the spectrum and hardware between these functionalities. However, the traditional ISAC schemes are highly dependent on the accurate mathematical model and suffer from the challenges of high complexity and poor performance in practical scenarios. Recently, artificial intelligence (AI) has emerged as a viable technique to address these issues due to its powerful learning capabilities, satisfactory generalization capability, fast inference speed, and high adaptability for dynamic environments, facilitating a system design shift from model-driven to data-driven. Intelligent ISAC, which integrates AI into ISAC, has been a hot topic that has attracted many researchers to investigate. In this paper, we provide a comprehensive overview of intelligent ISAC, including its motivation, typical applications, recent trends, and challenges. In particular, we first introduce the basic principle of ISAC, followed by its key techniques. Then, an overview of AI and a comparison between model-based and AI-based methods for ISAC are provided. Furthermore, the typical applications of AI in ISAC and the recent trends for AI-enabled ISAC are reviewed. Finally, the future research issues and challenges of intelligent ISAC are discussed.

关键词： artificial intelligence deep learning deep reinforcement learning federated learning generative artificial intelligence integrated sensing and communication machine learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

A review on Gujarati language based automatic speech recognition (ASR) systems

引用

International Journal of Speech Technology 2024年第1期27卷 133-156页

作者： Dua, Mohit Bhagat, Bhavesh Dua, Shelza Chakravarty, Nidhi Department of Computer Engineering National Institute of Technology Kurukshetra India Department of Electronics Communication and Engineering Punjab Engineering College Chandigarh Chandigarh India

Automatic speech recognition (ASR) plays a crucial role in facilitating natural and efficient human–computer interaction. This paper offers a comprehensive review of ASR systems tailored specifically for the Gujarati language. Existing literature on Gujarati ASR indicates that most survey papers have focused solely on back-end classification methods. This paper aims to fill this gap by presenting a comprehensive survey that encompasses feature extraction techniques, backend models, speech datasets, and evaluation metrics. This review provides an in-depth analysis of the cutting-edge methodologies employed in the development of Gujarati ASR systems. Firstly, the paper discusses various feature extraction techniques. Secondly, it covers classification models and their impact on ASR performance. Thirdly, the study delves into available speech datasets relevant to the Gujarati language, offering valuable insights for researchers and practitioners. Finally, the paper reviews the evaluation parameters used in ASR systems. Additionally, it gives an overview of online toolkits, resources, and language models pertinent to Gujarati ASR. This review serves as a comprehensive reference for academics and professionals involved in the research and development of ASR systems for the Gujarati language. The parameters selected for comparison include front-end feature extraction methods, back-end classification techniques, speech dataset, and evaluation metrics. Furthermore, the paper discusses both the contributions and limitations encountered by current ASR systems during the review. Finally, it addresses various challenges that still persist and provides directions for future research in this critical field. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Duplicate image detection using deep learning modified SVM and k-NN classification method for multimedia application

引用

Soft Computing 2024年第13-14期28卷 7659-7670页

作者： Singh, Mahesh K. Kumar, Sanjeev Ranjan, Rajeev Nandan, Durgesh Department of Electronics and Communication Engineering Aditya Engineering College Surampalem India Department of Electronics and Communication Engineering Chandigarh University Punjab Gharuan India School of Computer Science and Artificial Intelligence SR University Telangana Warangal India

This paper discussed an efficient technique to detect near-duplicate images with higher accuracy. The proposed method improved the existing accuracy of near-duplicate image detection and classification using Haar wavelet feature extraction and classification algorithm. Due to advancements in digital image acquisition and image editing software, near-duplicate image counterfeiting has become predictable. This expanding problem needs the creation of sophisticated detection algorithms capable of effectively preventing the spread of near-duplicate image deception. Support vector machine (SVM) and K-near neighbor (KNN) classifiers are used in the classification stage of a modified deep learning model with a convolutional neural network (CNN). The classification model finds the better result on the Imperial College London dataset, with 99.12% using CNN with KNN classifier and 98.63% for CNN with SVM classifier. The classification model also gives better results on the Nanyang Technological University dataset, with 98.36% using CNN with the KNN classifier and 97.85% for CNN with the SVM classifier. The model is tested using publicly available images to find the results. According to the comparison results, this model performed significantly better result than the previous model. As a result, digital image forensics has become more critical, particularly in identifying image duplication. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A novel Cosine-Cosine chaotic map-based video encryption scheme

引用

Journal of engineering and Applied Science 2024年第1期71卷 36页

作者： Kumari, Sweta Dua, Mohit Dua, Shelza Dhingra, Deepti Department of Computer Engineering National Institute of Technology Kurukshetra India Department of Electronics and Communication Engineering National Institute of Technology Kurukshetra India

The surge in online activities has led to the increasing popularity of sharing video data across diverse applications, including online education tutorials, social networking, video calling, and OTT platforms. Encryption prevents unauthorized access to the transmitted data over unreliable channels. The well-known features of chaos theory such as random behaviour, unpredictability, and initial parameters dependency facilitate its use in cryptography. Many security issues are faced by chaos-based cryptosystems because of their less complexity. Hence, a new Cosine-Cosine chaotic map characterized by intricate chaotic behaviour is designed in the current study. Additionally, we formulate an original video encryption scheme employing this Cosine-Cosine chaotic map. The encryption process involves five steps, beginning with the segmentation of the original video into frames based on its frame rate. In the second phase, a 384 bits pseudorandom key is generated that is further divided into three subkeys of 128 bits each. The novel Cosine-Cosine chaotic map-based sequence is generated. In the fourth step, red, green, and blue components are encrypted using the pseudorandom key and the chaotic sequence. In the last step, we combine encrypted frames to get cipher video. The security analysis validates that the proposed encryption protects against eavesdropping. © The Author(s) 2024.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

From Past to Present: A Comprehensive Review of Antenna Technology in Modern Wireless communication

引用

Journal of engineering Science and Technology Review 2024年第3期17卷 179-200页

作者： Mishra, Brijesh Singh, Aditya Kumar Satheesha, T.Y. Verma, Ramesh Kumar Singh, Vivek Department of Electronics and Communication Engineering School of Engineering and Technology CMR University Karnataka Bengaluru India Department of Electronics and Communication Engineering Noida Institute of Engineering and Technology U.P. Greater Noida India School of Computer Science Engineering REVA University Karnataka Bengaluru India Department of Computer Science and Engineering IMS Engineering College Uttar Pradesh Ghaziabad India Department of Electronics and Communication Engineering Nagarjuna College of Engineering and Technology Karnataka Bengaluru India

This research looks at microwave devices, specifically, patch antenna along with electromagnetic spectrum, shape, mechanism, analytical methods, simulation tools, and feeding procedures. Patch antennas are distinguished by their rectangular form, with a patch on one side and a ground plane on the other. Patch antennas work by exciting electromagnetic waves inside the patch, which are subsequently transmitted into the surrounding environment. The report also outlines numerous ways for evaluating the performance of microstrip patch antennas. The electromagnetic characteristics of the antenna are analyzed using the transmission line model, cavity model, and multiport network model (MNM). The integral equations that regulate the behavior of the antenna are solved using the method of moments (MoM) and the finite element method (FEM). The spectral domain technique (SDT) is used to analyze the antenna’s frequency response, while the finite difference time domain (FDTD) approach is used to analyze the antenna’s time-domain behavior. Overall, these methodologies give a thorough understanding of microstrip patch antenna performance and may be utilized to optimize their design. Furthermore, several patch antenna feeding methods, such as probe feed, microstrip line feeding, aperture coupling, proximity coupling, and CPW feed, are investigated. Attaching a microstrip line to the patch, which is subsequently linked to the RF source, is what microstrip line feeding entails. Aperture coupling entails making a hole in the ground plane that allows the RF source to feed the patch directly. Proximity coupling is accomplished by placing a probe near the patch, which creates an electromagnetic field on the patch. Patch antenna simulation software includes programmers such as HFSS, CST, and FEKO. These tools simulate the patch antenna’s performance, including its radiation pattern, gain, and input impedance. These simulations may be used to optimize the patch antenna design for specific a

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

A transformer based real-time photo captioning framework for visually impaired people with visual attention

引用

Multimedia Tools and Applications 2024年第41期83卷 88859-88878页

作者： Muhammed Kunju, Abubeker Kiliyanal Baskar, S. Zafar, Sherin A R, Bushara S, Rinesh A, Shafeena Karim Kerala Kanjirapally India Faculty of Engineering Department of Electronics and Communication Engineering Karpagam Academy of Higher Education Coimbatore India Department of Computer and Electronics Engineering SEST- Jamia Hamdard New Delhi India Department of Electronics and Communication Engineering KMEA College of Engineering Kerala Cochin India Department of Computer Science and Engineering V.S.B College of Engineering Technical Campus Coimbatore India

In recent years, transformer-based photo captioning frameworks plays a crucial role in improving individuals’ overall well-being, self-reliance, and inclusivity by giving them access to visual content via written and voiced explanations. This research investigates a two-layer transformer architecture to capture extensive relationships in visual data effectively. Using a two-layer transformer design, visual attention mechanism enables the model to autonomously identify relevant regions within a picture while generating a particular word within the anticipated caption. To get the features from the images, a pre-trained Inception V3 model is used, and the feature maps are extracted from the final convolutional block. The dataset used in this research was Flick8k, Flick30k, among bespoke datasets. The model was trained on a TPU platform and implemented on a Raspberry Pi 4B graphics processing unit. To assess the efficacy of the two-layer transformer model for photo captioning, a series of experiments were undertaken using benchmark datasets and with state-of-the-art models. The quality of the generated captions was evaluated using quantitative criteria such as BLEU, BLEUR, ROUGE and F1 score. Furthermore, a series of qualitative assessments were conducted, employing human evaluators, to measure the overall coherence, and fluency of the captions. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： computer vision

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：