检索结果-内蒙古大学图书馆

6th International Conference on Smart Computing and Informatics, SCI 2024

作者： Digumarthi, Suseela Diddi, Sattibabu Potla, Lavanya Pantham, Siva Jyothi Venkatesan, K.G.S. Department of Computer Science and Engineering Godavari Institute of Engineering and Technology (A) Rajamahendravaram India Department of Computer Science and Engineering Megha Institute of Engineering and Technology for Women Telengana Hyderabad India

ISBN: (纸本)9789819619801

Identifying and classifying twins pose challenges, yet hold significant applications in medical research, forensic science, and social science. In recent years, machine learning has emerged as a promising approach to twins identification and classification. Leveraging the unparalleled genetic similarity of identical twins, it is unsurprising that their fingerprints exhibit the highest degree of resemblance, rendering DNA ineffective for discrimination. Face recognition, a burgeoning field of image analysis and understanding, has garnered significant interest, especially in recent years. This study delves into the potential of both traditional decision trees and cutting-edge Convolutional Neural Networks (CNNs) within machine learning (ML) for accurate twin identification and classification. Key metrics like specificity, sensitivity, and accuracy are employed to gauge performance. The results unveil the superiority of CNNs over decision trees in every aspect, achieving exceptional accuracy in twin recognition. MATLAB development tool will be used to demonstrate the. The ultimate objective is to establish a robust system that capitalizes on inherent characteristics to distinguish between individual twins with unparalleled precision. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks (CNN) Face recognition Forensic investigation Machine learning Twins identification

来源：评论

学校读者我要写书评

暂无评论

Identification of Human Activity from Video Streaming Smartphone Data Using Intensified VGG16

引用

International Journal of engineering, Transactions B: Applications 2025年第6期38卷 1340-1352页

作者： Yadav, R.K. Daniel, A. Semwal, V.B. Department of Computer Science and Engineering Amity University Gwalior India Data Science and Engineering Manipal University Jaipur India Department of Computer Science and Engineering Maulana Azad National Institute Technology Bhopal India

Human activity recognition (HAR) techniques pick out and interpret human behaviors and actions by analyzing data gathered from various sensor devices. HAR aims to recognize and automatically categorize human activities using patterns and attributes taken from sensor data. HAR is complex in implementing the algorithm for a self-recorded dataset, including challenges such as age variation, wearing different clothes, environment and surface, the direction of the smartphone camera, and many more. The paper aims to propose a VGG16 deep learning framework including an activation function and different optimizers for classifying human activity from the real-time captured dataset;further, we compare the evaluated results with existing results. The proposed methods achieved 99.88% accuracy with excellent precision, recall, and F_measure values. Comparing the evaluated result with existing outcomes over the WISDM and UCI-HAR datasets. The new things in the article are a self-captured dataset of various aged male, female, and healthy volunteers to perform seven activities. Furthermore, this research uses Tensor Processing Units (TPU) available on Kaggle to improve classification accuracy while reducing error rates and speeding up execution. ©2025 The author(s).

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

ResdenseNet: a lightweight dense ResNet enhanced with depthwise separable convolutions and its applications for early plant disease classification

引用

Neural Computing and Applications 2025年第8期37卷 6305-6326页

作者： Nagpal, Jyoti Goel, Lavika Department of Computer Science & Engineering The NorthCap University Gurugram122017 India Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India

In recent years, artificial intelligence has undergone robust development, leading to the emergence of numerous autonomous AI applications. However, a crucial challenge lies in optimizing computational efficiency and reducing training time while maintaining high accuracy with limited hardware resources. This paper introduces ResdenseNet, a model built upon the MobileNet, DenseNet, and ResNet architectures. ResdenseNet combines dense blocks and residual blocks from the DenseNet and ResNet architectures. In these dense blocks, the standard convolutional units are replaced by depthwise separable convolutional units, a significant part of the MobileNet architecture. The experimental outcomes are contrasted with established models and their iterations, including ResNet-50, ResNet-101, MobileNet-V1, MobileNet-V2, DenseNet-121, and DenseNet-169. The proposed model is tested on benchmark and proposed datasets, showcasing its efficiency in reducing computations and accelerating the training process. Emphasizing hyperparameter importance, ResdenseNet, optimized with a growth rate of 64, 6 layers, and ReLU activation, achieves an accuracy of (98.73%) and a F1-score of (98.20%) on the wheat and barley dataset. The results indicate that ResdenseNet significantly decreases the number of parameters to 0.72M and efficiently shortens training time to 5983.54 s. Particularly noteworthy is ResdenseNet’s superiority over other models in terms of having the fewest parameters, the shortest training time, and the highest accuracy, especially when dealing with wheat, barley, and maize datasets. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

SMART LAVATORY SOLUTION: INTEGRATING IOT AND DEEP LEARNING MODELS FOR ENHANCED HYGIENE

引用

Scalable Computing 2025年第3期26卷 1057-1070页

作者： Patel, Jigna Shah, Aeshwi Rushali, Chaudhari Patel, Jitali Ukani, Vijay Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad India

In the current era of smart technology, integrating the Internet of Things (IoT) with Artificial Intelligence has revolutionized several fields, including public health and sanitation. The smart lavatory solution proposed in this paper improves hygiene standards using deep learning models and IoT system. The proposed system collect real-time data from deployed sensors to monitor and assess hygiene conditions regularly. Proposed model consists of four consequent phases as hardware implementation, data preprocessing, application and user interface modules. Rasberry Pi based sensor integration at hardware layer, normalization based techniques at data preprocessing layer, LSTM and GRU based deep learning model at application development layer and mobile notification to the cleaning staff at user interface layer ensure efficiently cleaning and monitoring of lavatory systems. Prior to assessing the proposed model’s testing accuracy experiments on the activation functions, optimizer, learning rate, and number of epochs were selected to choose the best to prevent overfitting or underfitting problems. With an accuracy of 98.61%, the proposed system performs better than the conventional approaches. © 2025 SCPE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing Hierarchical Relationships and Quality of Embedding in Latent Space

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 843-858页

作者： Chatterjee, Ankita Mukherjee, Jayanta Das, Partha Pratim Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur721302 India

Existing learning models partition the generated representations using hyperplanes which form well defined groups of similar embeddings that is uniquely mapped to a particular class. However, in practical applications, the embedding space does not form distinct boundaries to segregate the class representations. There exists interaction among similar classes which cannot be visually determined in high-dimensional space. Moreover, the structure of the latent space remains obscure. As learned representations are frequently reused to reduce the inference time, it is important to analyse how semantically related classes interact among themselves in the latent space. Therefore, we propose a boundary estimation algorithm that minimises the inclusion of other classes in the embedding space to form groups of similar representations and compare the quality of these class embeddings for various models in an already encoded space. These groups are overlapping to denote ambiguous embeddings that cannot be mapped to a particular class with high confidence. The algorithm determines which representations to be included or discarded to form well defined regions, separating discriminating, ambiguous and rejected embeddings to depict a particular class. Later, we construct relation trees to evaluate the hierarchical relationships formed among the classes, and compare it with the WordNet ontology using phylogenetic tree comparison methods. © 2020 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

IWM-LSTM encoder for abstractive text summarization

引用

Multimedia Tools and Applications 2025年第9期84卷 5883-5904页

作者： Gangundi, Ravindra Sridhar, Rajeswari Department of Computer Science and Engineering National Institute of Technology Tamilnadu Tiruchirappalli620015 India

Sequence-to-sequence models are fundamental building blocks for generating abstractive text summaries, which can produce precise and coherent summaries. Recently proposed, different text summarization models aimed to enhance summarization performance through the use of copying mechanisms, reinforcement learning, and multiple-level encoders. However, there has been limited research on improving the summarization output by modifying the structure of the long short-term memory (LSTM) cell. We introduced an improved version of LSTM called improved working memory LSTM (IWM-LSTM). IWM-LSTM removes the output gate and enhances the input and forget gates by incorporating cell state information into these gates. In our sequence-to-sequence model for text summarization, we replaced the LSTM encoder with a bi-directional IWM-LSTM, resulting in better summaries with minimal training time and less computational intensiveness. Additionally, we utilized Bidirectional encoder representations from transformers (BERT) embeddings to enhance the rouge score. The CNN/DailyMail dataset is used to train and test the model performance. The proposed model achieves better Recall-oriented understudy for gisting evaluation (ROUGE) scores than state-of-the-art models. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Network Security and Cryptography: Threats, Obstacles and Solutions-A Bibliometric Analysis

Recent Advances in Computer Science and Communications

引用

Recent Advances in computer science and Communications 2025年第2期18卷 83-101页

作者： Singh, Purushottam Dutta, Sandip Pranav, Prashant Department of Computer Science and Engineering Birla Institute of Technology Mesra Ranchi835215 India

Background: In the wake of escalating cyber threats and the indispensability of ro-bust network security mechanisms, it becomes crucial to understand the evolving landscape of cryptographic research. Recognizing the significant contributions and discerning emerging trends can guide future strategies and technological advancements. Our study endeavors to shed light on this through a bibliometric analysis of publications in the realms of Network Security and Cryptography. Method: To chronicle and synthesize the progression of research methodologies from their in-ception to the present day, we undertook a comprehensive Bibliometric Analysis of Network Security and Cryptography. Our data set was culled from the Clarivate Analytics Web of science Database, encompassing 3,897 papers, 603 sources, and 7,886 authors from across the globe. Results: Our analysis revealed a marked upsurge in cryptographic research since 1992, with China standing out as a dominant contributor in terms of publications. Notably, while 'security' and 'cryptography' emerged as recurrent research themes, there's an observable downtrend in international collaborations. Our study also highlights pivotal topics shaping the network security domain, offering insights into the trajectories of research source growth, structural variabil-ities in research relevance, and prospective intellectual and collaborative avenues as guided by authorship patterns. Conclusion: Cryptographic research is on an upward trajectory, both in volume and signifi-cance. However, the tapering of international collaborations and an evident need to concentrate on emergent challenges, such as data privacy and innovative network attacks, emerge as nota-ble insights. This bibliometric review serves as a compass, directing researchers and academi-cians towards areas warranting heightened attention, thereby informing the roadmap for future investigative pursuits. © 2025 Bentham science Publishers.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Extreme learning machine to foretell the deflection in plain cement, steel-reinforced, and bamboo-reinforced concrete beams

引用

Emerging Materials Research 2025年第1期14卷 12-27页

作者： Dubey, Saurabh Gupta, Deepak Mallik, Mainak Department of Civil Engineering National Institute of Technology Arunachal Pradesh India Department of Computer Science and Engineering Motilal Nehru National Institute of Technology Allahabad India

In mountainous regions, bamboo has gained popularity as a local reinforcement material for concrete due to its availability and cost-effectiveness. However, the lack of standardized design guidelines complicates the assessment of deflection behavior under varying loads. Challenges such as bond failure, shrinkage, corrosion, and material strength uncertainties further limit its structural application. To address these issues, this study employs an extreme learning machine to predict deflection in plain cement concrete beams, steel-reinforced cement concrete beams, and bamboo-reinforced concrete beams. The performance of extreme learning machine is compared with support vector regression and artificial neural networks. A total of 122 specimens were analyzed using input features such as cement content, water-cement ratio, fine aggregate, coarse aggregate, tensile strength, concrete compressive strength, percentage of reinforcement, applied load, cross-sectional area, and clear cover. The extreme learning machine method demonstrated satisfactory performance with a coefficient of deformation of 0.9975, Mean Square Error of 0.0003, Mean Absolute Error of 0.0052, Mean Absolute Percentage Error of 0.0998, and Root Mean Square Error of 0.01694. These results suggest that extreme learning machine is an efficient machine learning algorithm for predicting the deflection behavior of different reinforced concrete beams, providing a reliable alternative to traditional methods. © 2025 Emerald Publishing Limited: All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Attention enabled viewport selection with graph convolution for omnidirectional visual quality assessment

引用

Multimedia Tools and Applications 2025年第14期84卷 12925-12948页

作者： C, Nandhini M, Brindha Department of Computer Science and Engineering National Institute of Technology TamilNadu Tiruchirappalli620015 India

Omnidirectional images provide an immersive viewing experience in a Virtual Reality (VR) environment, surpassing the limitations of traditional 2D media beyond the conventional screen. This VR technology allows users to interact with visual information in an exciting and engaging manner. However, the storage and transmission requirements for 360-degree panoramic images are substantial, leading to the establishment of compression frameworks. Unfortunately, these frameworks introduce projection distortion and compression artifacts. With the rapid growth of VR applications, it becomes crucial to investigate the quality of the perceptible omnidirectional experience and evaluate the extent of visual degradation caused by compression. In this regard, viewport plays a significant role in omnidirectional image quality assessment (OIQA), as it directly affects the user’s perceived quality and overall viewing experience. Extracting viewports compatible with users viewing behavior plays a crucial role in OIQA. Different users may focus on different regions, and the model’s performance may be sensitive to the chosen viewport extraction strategy. Improper selection of viewports could lead to biased quality predictions. Instead of assessing the entire image, attention can be directed to areas that are more importance to the overall quality. Feature extraction is vital in OIQA as it plays a significant role in representing image content that aligns with human perception. Taking this into consideration, the proposed ATtention enabled VIewport Selection (ATVIS-OIQA) employs attention based view port selection with Vision Transformers(ViT) for feature extraction. Furthermore, the spatial relationship between the viewports is established using graph convolution, enabling intuitive prediction of the objective visual quality of omnidirectional images. The effectiveness of the proposed model is demonstrated by achieving state-of-the-art results on publicly available benchmark datasets, n

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

QoS-Aware Application Assignment and Resource Utilisation Maximization Using AHP in Edge Computing

引用

IEEE Internet of Things Journal 2025年第11期12卷 17717-17728页

作者： Koganti, Yasasvitha Sridhar, Vidhyuth Yadav, Ram Narayan Pratap, Ajay Iitram Department of Electrical and Computer Science Engineering Ahmedabad380026 India Indiana University Department of Computer Science and Engineering Bloomington United States Banaras Hindu University Indian Institute of Technology Department of Computer Science and Engineering Varanasi India

Edge computing has emerged as a promising technology to satisfy the demand for data computational resources in Internet of Things (IoT) networks. With edge computing, processing of the massive data-intensive tasks can be done in the proximity of IoT users. Thus, the required constraints related to tasks such as latency requirements, and the Quality Of Service (QoS) can be guaranteed. However, the question that how to determine the task offloading strategy under various constraints of resources, distance, and cost is still an open issue. In this paper, we study the task offloading problem from a matching perspective and propose an Edge-User Assignment Algorithm (EUAA) that aims to maximize the resource utilization of edge servers and maximize the number of assigned IoT users. The main concern, in any matching algorithm, is how to generate the preference order of either side. To generate preference orders for edge servers, we use the concept of the Analytical Hierarchy Process (AHP). We have considered the following criteria: distance from users to the server, latency, available resources, and pricing. This generates the priority of the users for matching to edge servers. From IoT users' perspective, we use cost, and QoS parameters to improve their satisfaction. We have used state-of-the-art schemes to compare the performance of the proposed algorithm under different simulation scenarios. We compare the performance using the number of assigned users, servers' profit, number of satisfied users, edge server resources used, and execution time. The simulation results confirm that significant profit and satisfied user can be achieved by the proposed algorithm. © 2014 IEEE.

关键词： Computation offloading

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：