检索结果-内蒙古大学图书馆

Attention-based neural machine translation with quality analysis on low-resource Digaru-English Pairs

International Journal of Information technology (Singapore) 2025年第1期17卷 575-589页

作者： Rushanti, Kri Kakum, Nabam Sambyo, Koj Department of Computer science and Engineering National Institute of Technology Jote Arunachal Pradesh India

Attention-based neural machine translation (NMT) has significantly improved translation quality for well-resourced language pairs. However, enhancing translation accuracy for low-resource languages remains a challenge due to limited datasets and technical constraints. Despite these challenges, the latest NMT method has notably improved translation precision for language combinations with limited data by employing techniques aimed at boosting the training models. This study focuses on improving translations for the low-resource North-East Indian language, Digaru. We utilize attention-based NMT and the Transformer model with hyperparameter tuning, experimenting with datasets of 5k, 10k, and 50k sentences. Our optimized model shows a notable improvement in BLEU scores over the base models, resulting in significantly better translation accuracy. Additionally, human evaluations and multidimensional quality metrics (MQM) confirm the enhanced translation quality. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： BLEU Global attention Hyper-parameter optimization MQM Transformer

来源：评论

学校读者我要写书评

暂无评论

Severity of natural calamities and crop yield prediction using hybrid deep learning model in Uttar Pradesh

World Water Policy

引用

World Water Policy 2024年第1期10卷 244-279页

作者： Kumar, Rajneesh Mahapatra, Rajendra Prasad Department of Computer Science and Engineering SRM Institute of Science and Technology Uttar Pradesh Ghaziabad India

Crop yield prediction has gained major potential for global food production. Predicting crop yields based on specific parameters like soil, environment, crop, and water has been an interesting research topic in recent decades. To accurately predict crop yields, measuring the severities of natural calamities including water level is mainly required. However, the existing studies failed to predict crop yields accurately because of various issues like overfitting problems, difficulty in training, inability to handle large data, and reduced learning capability. Thus, the proposed study develops an efficient mechanism for accurately predicting crop yields by analyzing several natural calamities. Here, the input samples are initially pre-processed to remove unwanted noises using data normalization and standardization. To enhance the performance of crop yield prediction, natural calamities are computed by using an Extreme Gradient Boosting (XGBoost) model based on parameters like the Palmer Drought Severity Index (PDSI), Severe Hail Index (SHI), and Storm Severity Index (SSI). Also, the hyperparameters of XGBoost model are tuned by utilizing Sheep Flock Optimization Algorithm (SFOA). Finally, the crop yield is predicted by proposing a new one-dimensional convolutional gated recurrent unit neural network (1D-CGRU). The proposed classifier predicts the crop yields with reduced error rates like mean square error (MSE) of 0.4363, root mean square error (RMSE) of 0.1904, normalized root mean squared error (NRMSE) of 0.00101, mean absolute error (MAE) of 0.2437, and R-squared (R²) of.2756. Also, the significant findings of the proposed study positively indicate that this study can be applicable to real-time agricultural practices and is highly suitable for water quality predictions. Also, it can assist farmers and farming businesses in predicting the yield of crops in a specific season when to harvest and crop a plant for attaining improved crop yields. © 2024 Policy

关键词： crop yield prediction deep learning network extreme gradient boosting Palmer Drought Severity Index Severe Hail Index Storm Severity Index

来源：评论

学校读者我要写书评

暂无评论

NeuroProbe: A Performance Profiling Feed Forward Neural Network Simulator for Hardware Interaction Analysis

引用

SN computer science 2025年第5期6卷 1-22页

作者： Ayyappan, Binu Kumar, G. Santhosh Department of Computer Science Cochin University of Science and Technology Kochi India Department of Artificial Intelligence and Data Science Rajagiri School of Engineering & Technology Kochi India

NeuroProbe is a simple neural network simulator designed by authors specifically for educational purposes focusing on simulating inference phase on a computationally capable embedded hardware, aiming to provide a deeper understanding of hardware interactions and performance improvement. This simulator incorporates performance profiling capabilities, allowing students and educators to analyze and optimize the performance of a simulated trained neural network. By simulating the intricate hardware interactions, NeuroProbe enables users to gain insights into how various components impact the overall performance of neural networks. Using this simulator, learners can experiment with different configurations and architectures, identify potential bottlenecks, and explore optimization strategies to enhance neural network performance before deploying the model on an Edge Computing environment. It also enriches computer science education by enabling learners to gain deeper insights into hardware interactions and performance improvement. By identifying performance bottlenecks, learners can refine their understanding of neural networks and develop skills in optimizing their models for enhanced performance. In conclusion, NeuroProbe empowers users to bridge the gap between theoretical knowledge and practical implementation of neural network on an embedded device, fostering a more comprehensive understanding of neural networks and their hardware requirements. Currently, it is focused solely on single-threaded CPU-based computation enabling SSE, AVX. At present, NeuroProbe does not support SIMD extensions such as AVX-FMA, AVX-512, multi-threaded computation, and accelerators such as NPU, TPU, and GPU. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Hardware–software interactions Neural network simulator NeuroProbe Performance bottlenecks Performance profiling Simulations

来源：评论

学校读者我要写书评

暂无评论

SignBERT+: Hand-Model-Aware Self-Supervised Pre-Training for Sign Language Understanding

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第9期45卷 11221-11239页

作者： Hu, Hezhen Zhao, Weichao Zhou, Wengang Li, Houqiang University of Science and Technology of China Department of Electronic Engineering and Information Science of Electrical and Computer Engineering Anhui Hefei230026 China

Hand gesture serves as a crucial role during the expression of sign language. Current deep learning based methods for sign language understanding (SLU) are prone to over-fitting due to insufficient sign data resource and suffer limited interpretability. In this paper, we propose the first self-supervised pre-trainable SignBERT+ framework with model-aware hand prior incorporated. In our framework, the hand pose is regarded as a visual token, which is derived from an off-the-shelf detector. Each visual token is embedded with gesture state and spatial-temporal position encoding. To take full advantage of current sign data resource, we first perform self-supervised learning to model its statistics. To this end, we design multi-level masked modeling strategies (joint, frame and clip) to mimic common failure detection cases. Jointly with these masked modeling strategies, we incorporate model-aware hand prior to better capture hierarchical context over the sequence. After the pre-training, we carefully design simple yet effective prediction heads for downstream tasks. To validate the effectiveness of our framework, we perform extensive experiments on three main SLU tasks, involving isolated and continuous sign language recognition (SLR), and sign language translation (SLT). Experimental results demonstrate the effectiveness of our method, achieving new state-of-the-art performance with a notable gain. © 1979-2012 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

An Investigation on Open-RAN Specifications:Use Cases,Security Threats,Requirements,Discussions

引用

computer Modeling in engineering & sciences 2024年第10期141卷 13-41页

作者： Heejae Park Tri-HaiNguyen Laihyuk Park Department of Computer Science and Engineering Seoul National University of Science and TechnologySeoul01811Republic of Korea Faculty of Information Technology School of TechnologyVan Lang UniversityHo Chi Minh City70000Vietnam

The emergence of various technologies such as terahertz communications,Reconfigurable Intelligent Surfaces(RIS),and AI-powered communication services will burden network operators with rising infrastructure ***,the Open Radio Access Network(O-RAN)has been introduced as a solution for growing financial and operational burdens in Beyond 5G(B5G)and 6G networks.O-RAN promotes openness and intelligence to overcome the limitations of traditional *** disaggregating conventional Base Band Units(BBUs)into O-RAN Distributed Units(O-DU)and O-RAN Centralized Units(O-CU),O-RAN offers greater flexibility for upgrades and network ***,this openness introduces new security challenges compared to traditional *** existing studies overlook these security requirements of the O-RAN *** gain deeper insights into the O-RAN system and security,this paper first provides an overview of the general O-RAN architecture and its diverse use cases relevant to B5G and 6G *** then delve into specifications of O-RAN security threats and requirements,aiming to mitigate security vulnerabilities *** providing a comprehensive understanding of O-RAN architecture,use cases,and security considerations,thisworkserves as a valuable resource for future research in O-RAN and its security.

关键词： O-RAN architecture use cases security issues security requirements security discussions

来源：评论

学校读者我要写书评

暂无评论

Proposed AES-based Obfuscation and Encryption Model for Cloud Data Security 1

Proposed AES-based Obfuscation and Encryption Model for Clou...

引用

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

作者： Singh, Prabhdeep Singh, Pawan Agarwal, Abhay Kumar Kumar, Anil Amity School of Engineering and Technology Department of Computer Science and Engineering Lucknow India Kamla Nehru Institute of Technology Department of Computer Science and Engineering Sultanpur India Amity University Amity School of Engineering and Technology Lucknow India

ISBN: (纸本)9798331529246

Cloud Computing (CC) offers a diverse range of services along with huge data storage across a network. CC has collaborated with varied emerging technologies like IoT because of its numerous advantages. Despite CC's benefits, cloud-based servers are not always trustworthy in real-world scenarios. Users' privacy will be compromised if they send their data straight to cloud platforms since crucial information will be exposed to cloud servers. Thereby, this work develops a data security model in the cloud with two stages, proposed secured data storage and proxy re-encryption. Initially, the data is stored securely in the cloud based on improved AES-based encryption as well as obfuscation-based encryption. Based on the request from the data user, proxy re-encryption is done using Kronecker product-based encryption. The enhanced AES achieved the lowest value of 0.025 for the CCA attack with a key size of 128 bits. Thus, the final encoded key is obtained. © 2025 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Empirical techniques for effort estimation in designing effective ML models

引用

International Journal of computers and Applications 2025年第2期47卷 226-234页

作者： Padmanabha Reddy, Y.C.A. Kosuru, Sai Sathwik Sirisalla, Nageswara Rao Vivekananda, G.N. Perala, Venkata Akanksha Department of Artificial Intelligence and Machine Learning Chaitanya Bharati Institute of Technology Telangana Hyderabad India Department of CSE B V Raju Institute of Technology Telangana Narsapur India Department of Computer Science and Engineering K.S.R.M. College of Engineering AP Kadapa India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

Machine Learning Research often involves the use of diverse libraries, modules, and pseudocodes for data processing, cleaning, filtering, pattern recognition, and computer intelligence. Quantization of Effort Required for the above cumulative processes is rarely discussed in the existing works and The time to reach the desired level of the model's functionality is essential to gauge the environment training for the model training and pre-deployment testing. In this study, we empirically defined the manual-cum-computational effort required for the model development in terms of 2-time factors: time-to-live (time until 1st code modification) and time-for-modification (time between 2 codebase changes) taken together in a mathematical model to compute Effort Factor(quantitative measure of determining effort needed to design ML algorithms). The study is novel in terms of how the effort required to create ML models is calculated with a particular focus on the manual effort direction. The results and the findings obtained can be used for determining the total time needed to synthesize ML models and frameworks in terms of code change cycles and implementation strategies marking a 25% performance increase in the current method above the Standard Pipeline. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Pipeline codes

来源：评论

学校读者我要写书评

暂无评论

A Meticulous Range of Forensics Tech Advancement in the field of IoT, IIoT and MIoT 5

A Meticulous Range of Forensics Tech Advancement in the fiel...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Matta, Priya Kamalraj, R. Saxena, Kumud Tula's Institute Department of Computer Science and Engineering Dehradun India Department of Computer Science and Information Technology Bangalore India Noida Institute of Engineering and Technology Department of Computer Science Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350383522

Wide application of millions of connected, intelligent, and flexible gadgets in critical infrastructures like medical facilities, public transit, sustainability, and home automation has been driven by latest expansions in intelligence technology and hardware. Clients profit from consistency and accessibility when data is transmitted across the internet deprived of the need for any kind of person to person or person-to-computer communication however this additionally creates new prospects for hackers and increases a number of complicated and challenging issues for the area of online forensics. Regardless of the fact that IoT records may be a valuable evidence source, forensics professionals must deal with a wide range of issues, starting the massive diversity of IoT devices and unrecognized setups to the multi-tenant platforms of cloud and the ensuing multijurisdictional lawsuits. Encryption at all levels, which compromises users' rights regarding confidentiality for the benefit of forensics study, is another difficulty. The aim of this work is to recognize and address the issues connected through the complex procedure of IoT based inquiries, particularly the privacy and security problems. The study also examines the application of IoT forensics across different industries. © 2024 IEEE.

关键词： IoT (Internet of things) IoT forensics privacy issues and digital forensics Security issues

来源：评论

学校读者我要写书评

暂无评论

A Novel Intelligent Task Offloading Scheme for Multi-Controller Environment in Software Defined Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第12期12卷 20018-20029页

作者： Hussain, Mir Wajahat Sangaiah, Arun Kumar Reddy, K. Hemant Kumar Roy, Diptendu Sinha Alenazi, Mohammed J.F. Javvaji, Pavan Kumar Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Karnataka Anekal562106 India International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan School of Engineering and Technology Sunway University Selangor Petaling Jaya47500 Malaysia University Centre for Research and Development Chandigarh University Punjab Mohali140413 India School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati522237 India Department of Computer Science and Engineering National Institute of Technology Meghalaya 793003 India College of Computer and Information Sciences Department of Computer Engineering King Saud University Riyadh11451 Saudi Arabia

The Internet of Vehicles (IoV), equipped with sensors, generates vast amounts of data, demanding rigorous computation and network. The cloud computing platform meets these stringent computation requirements, but it has a significant latency that fog computing effectively handles. Software Defined Network (SDN) has become the de facto standard for next-generation networking due to its unique and flexible features, which handle the network pre-requisites in an agile manner. Task Offloading (TO) is a crucial issue in Software Defined-IoV (SDIoV), particularly when the vehicle's resources are insufficient. Fog nodes schedule offloaded tasks;however, neglecting computational and network details during task scheduling can lead to longer completion times, thereby restricting the functionality of SD-IoV due to its time-sensitive nature. Therefore, this paper introduces two proactive Intelligent Task Offloading (ITO' and ITO) schemes. These schemes schedule tasks onto fog nodes with enhanced computational capabilities, dynamically enable the network through the ovs-ofctl SDN utility, and consider vehicle mobility during task scheduling. Experiments with Mininet show that the proposed (ITO' and ITO) schemes improve performance in terms of CPU availability, bandwidth, and throughput by 5.2 times, 50% and (30.7-13.9)% more than the existing scheme. They also reduce average packet loss, delay, Round Trip Time (RTT), and offloaded node time selection by (45.35-21.3)%, (50-33.3)%, (53.9-9.9)% and (43.2-26.06)% which demonstrates the efficacy of the proposed scheme. © 2025 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Advancing Bilingual SMS Spam Detection: A Comparative Exploration of Machine Learning and Deep Ensemble Techniques 3

Advancing Bilingual SMS Spam Detection: A Comparative Explor...

引用

3rd IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things, RAAICON 2024

作者： Sultana, Hafsa Tanvin, Jamal Uddin Sharmin, Nusrat Arefin, Mohammad Shamsul Rahman, Md. Mahbubur Military Institute of Science and Technology Mirpur Cantonment Department of Computer Science and Engineering Dhaka1216 Bangladesh Chittagong University of Engineering and Technology Department of Computer Science and Engineering Chittagong4349 Bangladesh

ISBN: (纸本)9798331534400

Spam messages are increasingly becoming a major issue in digital communication, creating significant challenges for both users and organizations. With the rise in text-based interactions, especially in low-resource languages like Bangla-English SMS, there is a growing need for more effective spam detection systems. This paper presents BESpam, a unique bilingual dataset that contains 5,730 Bangla-English SMS messages, specifically designed to address this challenge. In the literature, various machine learning and deep learning techniques align with feature extraction techniques from natural language processing used for spam SMS detection. Still, no studies have been found that focus on comparing deep and machine learning approaches. As a further contribution, we propose an ensemble model that combines advanced transformer architectures with FastText to improve the accuracy of spam classification. Our results demonstrate that this ensemble approach outperforms both traditional machine learning models and individual transformer-based methods. The stacking ensemble achieved an accuracy of 99%, exceeding the performance of standalone models such as mBERT (98%) and XLM-RoBERTa (98%), as well as traditional classifiers such as logistic regression and SVM, both of which also scored 98%. This work provides insight analysis of machine learning and deep learning in terms of bilingual SMS spam detection, in addition to advancing spam detection methodologies. © 2024 IEEE.

关键词： Contrastive 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：