检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Intelligent systems, Smart and Green Technologies, ICISSGT 2024

作者： Padmaja, Chinimilli Venkata Rama Lakshminarayana, S. Institute of Aeronautical Engineering Computer Science & Engineering Hyderabad India Andhra University Computer Science & Systems Engineering Visakhapatnam India

ISBN: (纸本)9798350304329

In recent years, language models have undergone significant advancements with models like GPT-3, showcasing impressive abilities in natural language processing and generation. However, these models often experience from issues such as generating biased or unreliable content, producing inappropriate responses, or failing to fulfill specific user needs. To address these challenges, prompt engineering emerged as a promising approach by providing explicit guidance to language models. It refers to the process of designing and constructing effective prompts or instructions to guide language models like GPT-3 in generating desired outputs. In this article an attempt was made to address the role of prompt engineering, its techniques, and its potential impact on enhancing the performance and reliability of language models. © 2024 IEEE.

关键词： ChatGPT Language Models Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

Occlusion robust sign language recognition system for indian sign language using CNN and pose features

引用

Multimedia Tools and Applications 2024年第36期83卷 84141-84160页

作者： Das, Soumen Biswas, Saroj Kr. Purkayastha, Biswajit Computer Science Engineering National Institute of Technology Silchar NIT Road Assam Silchar788010 India

The Sign Language Recognition System (SLRS) is a cutting-edge technology that aims to enhance communication accessibility for the deaf community in India by replacing the traditional approach of using a human interpreter. However, the existing SLRS for Indian Sign Language (ISL) do not focus on some major problems including occlusion, similar hand gesture, multi viewing angle problem and inefficiency due to extracting features from a large sequence of frame that contains redundant and unnecessary information. Therefore, in this research paper an occlusion robust SLRS named Multi Featured Deep Network (MF-DNet) is proposed for recognizing ISL words. The suggested MF-DNet uses a histogram difference based keyframe selection technique to remove redundant frames. To resolve occlusion, similar hand gesture, and multi viewing angle problem the suggested MF-DNet incorporates pose features with Convolution Neural Network (CNN) features. For classification the proposed system uses Bi Directional Long Shor Term Memory (BiLSTM) network, which is compared with different classifier such as LSTM, ConvLSTM and stacked LSTM networks. The proposed SLRS achieved an average classification accuracy of 96.88% on the ISL dataset, 99.06% on the benchmark LSA64 dataset and 99.85% on the WLASL dataset. The results obtained from the MF-DNet is compared with some of the existing SLRS where the proposed method outperformed the existing methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Novel and Optimized Collaborative Diversity-Driven Routing Mechanism in MANETs

引用

SN computer science 2024年第1期5卷 22页

作者： Malyadri, Neelam Ramakrishna, M. Department of Computer Science and Engineering Vemana Institute of Technology VTU Belagavi India School of Computer Science and Engineering REVA University Karnataka Bengaluru India Department of Computer Science and Engineering Vemana Institute of Technology Karnataka Bengaluru India

Wireless networks such as MANETs present unique challenges due to their dynamic and decentralized nature. Efficient routing protocols are essential for achieving reliable and robust communication in such networks. In this research, we propose a novel routing mechanism called collaborative diversity-driven routing (CollabNet) that integrates collaborative diversity to enhance the routing process in ad hoc networks. CollabNet utilizes a collaborative approach to address the challenges posed by dynamic network environments. CollabNet incorporates collaborative power control, adaptive power allocation, and energy-efficient routing to automatically adjust the dynamic power of nodes. By promoting collaborative behavior and optimizing power levels. It fosters collaborative behavior among nodes by establishing cooperation groups and leveraging multiple relay nodes. Through collaborative multipath diversity CollabNet facilitates the transmission of packets toward the destination via multiple paths within the transmission range. This approach increases the probability of successful packet delivery by establishing redundant connections. By promoting collaboration among nodes, CollabNet improves the reliability and connectivity of wireless ad hoc networks. The mechanism leverages the strength of collaborative diversity to enhance the overall performance of routing protocols. Extensive simulations demonstrate that CollabNet outperforms traditional routing protocols in terms of network connectivity, reliability, and efficiency. The proposed mechanism offers a promising solution for efficient routing in MANETs contributing to the advancement of wireless communication in dynamic ad hoc network environments. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Collaborative diversity Collaborative diversity-driven routing MANETs Routing protocols Wireless ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of EfficientNet Models in Grape Leaf Disease Classification 1

Performance Evaluation of EfficientNet Models in Grape Leaf ...

引用

1st International Conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Subramanya, S.G. Parkavi, A. Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bengaluru India Ramaiah Institute of Technology Department of Computer Science and Engineering Bengaluru India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529246

Grape farming is a globally significant agricultural practice, but grapevines frequently encounter viral, fungal, and bacterial infections that compromise crop quality and yield. Conventional disease detection methods are labor-intensive and require significant expertise. This study investigates deep learning techniques, focusing on EfficientNet models, to automate grape leaf disease identification and classification. The transfer learning approach was applied to train and fine-tune EfficientNet models on a publicly available dataset with four classes: black rot, leaf blight, esca, and healthy leaves. A model performance was measured through accuracy and loss metrics. EfficientNetB0 achieved accuracy of 92.45% and 96.73%, and loss of 0.197 and 0.098, on training and validation data, respectively. However, EfficientNetB5 and EfficientNetB7 gave validation accuracies of 96.07% and 96.39%, respectively. The accuracy and loss trends demonstrate that EfficientNetB0 outperforms the other two counterparts. This approach highlights the potential of EfficientNetB0 for accurate, efficient grape disease detection and classification. © 2025 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Nanoimprint lithography-assisted block copolymer self-assembly for hyperfine fabrication of magnetic patterns based on L10-FePt nanoparticles

引用

science China Chemistry 2025年第5期68卷 2027-2034页

作者： Jie Zhang Yi Chen Guijun Li Zelin Sun Zhengong Meng Wai-Yeung Wong Department of Applied Biology and Chemical Technology and Research Institute for Smart Energy The Hong Kong Polytechnic University The Hong Kong Polytechnic University Shenzhen Research Institute Division of Integrative Systems and Design and Department of Electronic and Computer EngineeringThe Hong Kong University of Science and Technology School of Flexible Electronics (Future Technology) and Institute of Advanced Materials (IAM) Nanjing Tech University

L10-FePt-type bit-patterned media has provided a promising alternative for ultrahigh-density magnetic recording systems in the current digital era, but rapid fabrication of magnetic patterns with hyperfine bit islands is still challenging, especially with the target for miniaturization and scalable production simultaneously. Herein, Fe,Pt-containing block copolymers were utilized as single-source precursors for solution-processable patterning and subsequent generation of the demanding magnetic FePt dots by in situ pyrolysis. High-throughput nanoimprint lithography was initially employed to fabricate the predefined bit cells precisely,and then the intrinsic self-assembly of phase-separated block copolymers further drove the formation of accurate bit *** from the synergistic effect of top-down lithographic approach and bottom-up self-assembly, the customizable patterns could be achieved for large-scale mass production in targeted areas, but high-density isolated dots could also be accurately aligned along the patterned features after subsequent self-assembly. This reliable strategy would provide a good avenue to precisely construct ultrahigh-density magnetic data storage devices.

关键词： organometallic precursor magnetic nanoparticles block copolymer self-assembly nanoimprint lithography

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Lightweight Sign Language Recognition Leveraging Google Mediapipe and Deep Neural Net 1

A Novel Approach for Lightweight Sign Language Recognition L...

引用

1st International Conference on Software, systems and Information technology, SSITCON 2024

作者： Siju, Ijas Selvam, Prabu Vellore Institute of Technology School of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Department of Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350352931

The advent of technologies like Deep Learning has revolutionized human interaction, transcending language and disability barriers. Sign Language Recognition (SLR) systems have emerged as vital tools, facilitating seamless communication between individuals and between humans and machines through Interfaces. However, existing SLR systems pose significant challenges, including the demand for high accuracy, low latency, simplicity in development and deployment, lightweight design for edge compatibility, and efficient resource utilization during training. Addressing these challenges necessitates developing a system that balances training data accuracy, ease of training, and resource efficiency. Conventional Deep learning approaches often rely on high-dimensional image datasets for training HGR models, resulting in trade-offs between latency, accuracy, complexity, and resource requirements. To mitigate these challenges, this paper harnesses the capabilities of Google Mediapipe to extract a 21-point hand landmark vector from each training image. By leveraging this low-dimensional data, we train model that are accurate, lightweight, less complex, and exhibit low latency, making them compatible with edge devices. The hand gesture images were collected for several gestures, such as peace, okay, and stop. These images will be converted to landmark vectors using Mediapipe. These landmark points were used to train the Deep Neural Network architecture developed in Tensorflow. The model was trained with each hand gesture assigned with a common word in English and the proposed model was tested with a live webcam stream. The proposed model is developed in Python in the Google Colab IDE with the help of libraries and frameworks like OpenCV, Tensorflow and Google Mediapipe. The proposed model outperforms current state-of-the-art approaches by achieving an accuracy of 9 4. 8 8 %. © 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

Hybrid deep learning based digital image watermarking using GAN-LSTM and adaptive gannet optimization techniques

引用

Multimedia Tools and Applications 2024年 1-31页

作者： Shedole, Sambhaji Marutirao Santhi, V. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Katpadi Vellore632014 India

Nowadays, multimedia technology is progressing everyday. It is very easy to duplicate, distribute and modify digital images with online editing software. Image security and privacy are critical aspects of the multimedia revolution. Therefore, digital image watermarking offers an alternative way out for image authentication. Currently, watermarking methods are crucial for safeguarding digital images. Several traditional watermarking approaches have been developed to protect images using spatial domains and transformations. Watermarking techniques that are more traditional are less resistant to repeated attacks. Deep learning-based watermarking has recently gained traction, greatly improving the safety of visual images in a variety of common applications. This study presents a robust and secure digital watermarking method for multimedia content protection and authentication. The watermark image is first transformed using the hybrid wavelet transform, and then it is encrypted using a chaos encryption algorithm. The cover image is simultaneously subjected to neighborhood-based feature extraction. Leveraging these extracted features, a novel Adaptive Gannet Optimization algorithm (AGOA) is employed to determine the optimal embedding location. Subsequently, the watermarked image is seamlessly integrated and extracted using the hybrid Generative adversarial network-based long short-term memory (GAN-LSTM) approach within the identified optimal region. Decryption and Inverse transformation are then used to get the original watermark image. Several previous methods, such as DNN, Deep-ANN, and Deep-CNN, are used to evaluate the performance of the proposed method. This technique improves multimedia content protection and authentication by guaranteeing strong and secure watermarking. The proposed method for digital image watermarking produced a peak signal-to-noise ratio of 46.412 and a mean square error of 24.512. Therefore, the proposed method performs well in digital image wa

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation

引用

Research 2024年第2期6卷 29-40页

作者： Jiawen Deng Zhuang Chen Hao Sun Zhexin Zhang Jincenzi Wu Satoshi Nakagawa Fuji Ren Minlie Huang The CoAl group DCSTInstitute for Artificial InteligenceState Key Lab of Intelligent Technology and SystemsBeijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Graduate School of Information Science&Technology The University of Tokyo.Tokyo 1138654Japan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengduSichuan611731China

Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language *** data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English *** significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain *** alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language Dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model ***,we employ a multiteacher distillation framework to enhance detection performance with unsupervised *** is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to *** soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive *** conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.

关键词： COLD dealing limitations

来源：评论

学校读者我要写书评

暂无评论

Chi-Square Target Encoding for Categorical Data Representation: A Real-World Sensor Data Case Study

引用

SN computer science 2025年第3期6卷 1-22页

作者： Anitha, M. Savarimuthu, Nickolas Bhanu, S. Mary Saira Department of Computer Applications National Institute of Technology Trichy India Department of Computer Science and Engineering National Institute of Technology Trichy India

Feature engineering is critical for improving machine learning performance (ML), especially when handling categorical data. Traditional encoding methods, such as one-hot and label encoding, often result in challenges like high dimensionality and loss of category significance. To address these limitations, this study introduces a novel Chi-Square Target Encoding (CSTE) approach, which transforms categorical variables into numerical representations by leveraging the chi-square statistic to evaluate the association between categories and the target variable, preserving information effectively. Unlike conventional techniques, CSTE uses Chi-square test values to generate target-based encoded representations, ensuring reliable transformation without information loss. Comprehensive empirical evaluations were conducted on various datasets for binary classification, showcasing CSTE’s superiority over methods like regularized target encoding, basic target encoding, and fuzzification. A case study on real-world sensor data further validated its efficiency and scalability for large-scale data-driven applications. The proposed CSTE method achieved an average increment rate of 3.9447%, surpassing one-hot and fuzzification (1.0430%) and regularized target encoding (1.8308%). Classification outcomes demonstrated F1-scores exceeding 0.90 and AUC values nearing 0.99 across diverse datasets, highlighting its robustness. Furthermore, the reduced dimensionality significantly enhanced inference time while maintaining high accuracy. The CSTE method offers a robust framework for categorical data transformation, addressing limitations of traditional encoding techniques. It improves the interpretability and efficiency of categorical data representation, boosting ML performance. This innovative approach is well-suited for applications across various domains involving categorical data. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Categorical data encoding Chi- Square statistics Data distribution preservation Feature engineering Machine learning Target encoding

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Child Activity Recognition Using Machine Learning 5th

A Comparative Analysis of Child Activity Recognition Using M...

引用

5th International Conference on Advances in Information Communication technology and Computing, AICTC 2024

作者： Kumar, Narendra Arora, Shefali Aggrawal, Lakshay Computer Science and Engineering National Institute of Technology Punjab Jalandhar144008 India Computer Science and Engineering DAV Institute of Engineering and Technology Punjab Jalandhar144008 India

ISBN: (纸本)9789819761050

This research study aims to create a smart child activity recognition device combines a Raspberry Pi-pico, sensors for Internet of things (IoT). The system includes several sensors for monitoring human motion, pulse, and location parameters. Different types of machine learning and deep learning algorithm is used for analyzing data to identify various kinds of activities in children including sitting, standing, running, and climbing the stairs. This study utilizes a Raspberry Pi-pico, which is a cost-effective as well as tiny single-board computer central processing unit for an infant monitoring system. It can be easily integrated with various sensors and devices, which make it a suitable foundation for developing an IoT-based tracking system. It is able to link to the Internet through Wi-Fi, allowing for surveillance remotely. The dataset collected from 22 different children based on their features like sitting, standing, running, and climbing the stairs. The model was trained using a data of child mobility and behavior, distinguishing activities such as sitting, standing, running, and stair climbing. There are six different classifiers: LSTM, SVM, ANN, KNN, AdaBoost, and Logistic Regression. When applied to pre-processed data, SVM outperformed other classification methods. The classification accuracy reached 98.81%. The experimental results indicate that the proposed system may identify behavior and it will keep parents remotely. The technology continuously monitors and analyzes the child’s environment and behavior to ensure their safety and well-being. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Support vector machines

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：