检索结果-内蒙古大学图书馆

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Gupta, Kavya Kumar Tayal, Devendra Jain, Aarti Indira Gandhi Delhi Technical University for Women Department of Computer Science and Engineering Delhi India Netaji Subhas University of Technology Department of Electronics and Communication Engineering East Campus Delhi India

ISBN: (纸本)9781665437899

Wireless sensor networks are an active research area due to their wide range of applications in almost every aspect of life and their associated challenges, including energy conservation, longer life cycle, and better utilization of resources. Their presence in such large quantities also leads to a tremendous amount of sensor data to be stored and processed efficiently. This poses a new challenge as the sensor nodes are often deployed in harsh environments, where cheaper resources are needed to collect and process data. Data reduction is one such technique that helps in reducing the amount of sensor data. In this paper, a review of data reduction techniques has been presented. An analysis of various data reduction techniques proposed over the years, their benefits and challenges, how they help, their pros and cons, and if the employment of data reduction techniques is worthy in such resource-constrained environments has been presented. © 2022 IEEE.

关键词： Data integration

来源：评论

学校读者我要写书评

暂无评论

Prediction of impact response of square reinforced concrete (RC) slab with square/circular opening under drop-weight impact using FEM simulation

引用

Asian Journal of Civil engineering 2024年第2期25卷 2189-2208页

作者： Anas, S.M. Alam, Mehtab Saidani, Messaoud Department of Civil Engineering Jamia Millia Islamia (A Central University) New Delhi 110 025 India Department of Civil Engineering Netaji Subhas University of Technology New Delhi 110 073 India Research Institute for Clean Growth and Future Mobility Coventry University Coventry England CV1 5FB United Kingdom

Gravity load-carrying members of a structure are often subjected to low-velocity impact during construction and subsequent service life. In contrast to quasi-static situations, dynamic impacts introduce impulsive loading that must be carefully addressed by considering the strain-rate characteristics of materials. The performance of reinforced concrete (RC) slabs with opening(s) subjected to such loading is an important topic of considerable interest from the structural design point of view. The present study investigates the response of an RC slab with an opening under drop-weight impact loading and therefore analysis sets out via an explicit platform of Abaqus software. Damage plasticity models built into the ABAQUS software are used to incorporate materials’ nonlinearity in the analysis. The slab that does not have any openings is regarded as the baseline slab, and its response to impact load is compared to the findings of Sadraie et al. (Eng Struct 191, 62–81, 2019). Following validation, square and circular openings of 1/8th of the size of the slab (≈125 mm) at diagonally and mid-span eccentric farthest possible locations in the middle strip of the slab are considered and analysed to evaluate its impact response under the same drop load. Slab performance is found invariably almost identical in terms of maximum displacement for the location and geometry of the opening of the same size. However, the slab with a circular opening displays improved performance against damage and cracking than with a square opening along the diagonally eccentric location of the slab. The novelty of this research lies in the determination of the optimal geometry and diagonal positioning of opening/s in the RC slab to enhance its anti-damage performance. © 2023, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Damage Finite element method (FEM) Impact loading Low-velocity impact Openings Response prediction Slabs

来源：评论

学校读者我要写书评

暂无评论

Children’s Ability to Read from computers and Smartphones

引用

Journal of Educational technology Systems 2022年第4期50卷 521 - 539页

作者： Savita Yadav Pinaki Chakraborty Lokesh Meena Deepanshu Yadav Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India

Children now use digital devices for learning and leisure activities. The study assessed children's ability to read from computers, smartphones and printed sheets. We provided 60 children aged seven to ten years with reading material and recorded the time taken by them to complete reading and their navigation pattern and eye movements using software developed by us. There was no significant difference in the time taken to complete reading and the ability to recall the content when the children read from the three mediums (P > .05). The average eye fixation duration was however significantly higher when the children read from a smartphone (P < .05). Children aged nine and ten years used hyperlinks more often while reading from a smartphone than a computer (P < .05). We concluded that children can read fluently from all the three mediums by the age of seven years, and navigate hypertext effectively on smartphones by nine years of age.

关键词： hypertext children digital content smartphone typeface

来源：评论

学校读者我要写书评

暂无评论

Enhancing transparency in global horizontal irradiance estimation with tree based machine learning algorithms and Shapley additive explanations framework

引用

International Journal of Ambient Energy 2025年第1期46卷

作者： Gupta, Rahul Ganvir, Chaitanya Jha, S.K. Singh, Rahul Baghel, Raj Kumar Department of Electrical and Electronics Engineering G L Bajaj Institute of Technology and Management Greater Noida India Department of Instrumentation and Control Engineering Netaji Subhas University of Technology Dwarka India Department of Electrical Engineering Indian Institute of Technology Ropar Rupnagar India

The estimation of global horizontal irradiance (GHI) is crucial for assessing solar energy potential, especially for investment purposes in specific regions. This study employs two feature selection techniques such as recursive feature elimination (RFE) and least absolute shrinkage and selection operator (LASSO) to identify key variables from two datasets, which are then used to train four machine learning (ML) models such as Decision Tree (DT), Random Forest (RF), Extreme Gradient Boost (XGB), and Extra Trees (ET) regressors. The performance of these models is evaluated using three statistical metrics such as mean absolute error (MAE), root mean squared error (RMSE), and R-squared (R2). The results show that the ET regressor, when combined with LASSO, achieves the best predictive performance, with an MAE of 1.36 W/m² and an RMSE of 2.46 W/m2. The study further employs Shapley Additive Explanations (SHAP) to interpret the model, revealing that parameters like Diffuse Horizontal Irradiance, Solar Zenith Angle, and Direct Normal Irradiance significantly impact GHI prediction accuracy. The combination of feature selection, advanced ML models, and SHAP analysis offers a comprehensive and transparent framework for solar energy resource assessment, addressing the need for accuracy and interpretability in GHI estimation. © 2025 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Solar irradiance

来源：评论

学校读者我要写书评

暂无评论

BB-PATCH: BLACKBOX ADVERSARIAL PATCH-ATTACK USING ZEROTH-ORDER OPTIMIZATION

arXiv

引用

arXiv 2024年

作者： Kumar, Satyadwyoom Gupta, Saurabh Buduru, Arun Balaji Dept. of Electronics and Communication Engineering Netaji Subhas Institute of Technology Delhi India Dept. of Computer Science Engineering Indraprastha Institute of Information Technology Delhi India

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of these adversarial attack strategies assume that the adversary has access to the training data, the model parameters, and the input during deployment, hence, focus on perturbing the pixel level information present in the input image. Adversarial Patches were introduced to the community which helped in bringing out the vulnerability of deep learning models in a much more pragmatic manner but here the attacker has a white-box access to the model parameters. Recently, there has been an attempt to develop these adversarial attacks using black-box techniques. However, certain assumptions such as availability large training data is not valid for a real-life scenarios. In a real-life scenario, the attacker can only assume the type of model architecture used from a select list of state-of-the-art architectures while having access to only a subset of input dataset. Hence, we propose an black-box adversarial attack strategy that produces adversarial patches which can be applied anywhere in the input image to perform an adversarial attack. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A study on the estimation of global horizontal irradiance via deep learning technique

A study on the estimation of global horizontal irradiance vi...

引用

Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON), International Conference on

作者： Manisha Kumari Chandan Kumar Smriti Srivastava Department of Electrical Engineering Netaji Subhas University of Technology New Delhi India Department of Electrical Engineering Indian Institute of Technology Kanpur Kanpur India Department of Control and Instrumentation Engineering Netaji Subhas University of Technology New Delhi India

For grid-connected photovoltaic (PV) systems, accurate solar irradiance forecasting is crucial, especially in cases of intermittent environmental conditions, in order to ensure grid operation, scheduling, and grid energy management. Solar irradiance, temperature, and other meteorological factors significantly influence PV generation and also make it intermittent in nature. Time series analysis provides an efficient way to map temporal patterns, like hourly, monthly, yearly, and seasonal variations, and within solar irradiance data. In this paper, time series forecasting of 24hourly future observations of global horizontal irradiance (GHI) is done using a multilayer perceptron (MLP) of deep learning framework. Different hyperparameters like hidden layers, hidden units of each layer, activation function, optimizer, and lag observations/steps are tuned to develop the best model that fits the GHI historical data. Further dropout regularization is used to avoid overfitting the model. The model is validated using validation data that the model has never seen before. RMSE, MSE, MAE, and NRMSE errors, aiming at minimizing forecasting errors on test data, are used to select the optimal value of hyperparameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Algorithms for Pulse Jammer Detection

Comparative Analysis of Machine Learning Algorithms for Puls...

引用

International Symposium on Advanced Networks and Telecommunication Systems (ANTS)

作者： Srishti Srivastava Prerna Chaudhary Manav R. Bhatnagar Department of Electronics & Communication Engineering Netaji Subhas University of Technology Delhi India Department of Electrical Engineering Indian Institute of Technology Delhi New Delhi India

ISBN: (数字)9798350391725

ISBN: (纸本)9798350391732

This work compares various machine learning algorithms for predicting the presence of a random on/off jammer in wireless communication systems. We analyze four machine learning classification algorithms, Decision Trees, Support Vector Machines, K-nearest neighbors, and Random Forest. The study applies data pre-processing techniques to improve detection performance and assesses the algorithms using metrics such as accuracy, precision, recall, and F1 score. Among the tested methods, Random Forest and Decision Trees achieved the highest performance with an accuracy of 97.5%, precision of 1.00, recall of 0.95, and an $F 1$ score of 0.97. SVM demonstrated strong precision at 1.00 but slightly lower accuracy at $\mathbf{9 2. 5 \%}$, while KNN exhibited the lowest accuracy at 85%. These results highlight the effectiveness of Random Forest and Decision Trees for robust and efficient jammer detection. The findings have significant implications for enhancing the resilience of wireless communication systems against jamming attacks. In particular, we show the use-case of our analytical work in the classification-based application of wireless communication systems, specifically jammer detection.

关键词： Wireless communication Support vector machines Machine learning algorithms Accuracy Switches Nearest neighbor methods Classification algorithms Decision trees Jamming Random forests

来源：评论

学校读者我要写书评

暂无评论

Potato Leaf Disease Detection using CNN - A Lightweight Approach 6

Potato Leaf Disease Detection using CNN - A Lightweight Appr...

引用

6th Doctoral Symposium on Intelligence Enabled Research, DoSIER 2024

作者： Saha, Abhisek Musharraf, Syed Mohammed Dey, Anubhav Roy, Hiranmoy Bhattacharjee, Debotosh Netaji Subhash Engineering College Techno City Garia Ranabhutia West Bengal Kolkata700152 India Department of Information Technology RCC Institute of Information Technology Canal South Road Kolkata700015 India Department of Computer Science & Engineering Jadavpur University Kolkata700032 India

Detection of potato leaf diseases at an early stage is of great significance to the agricultural industry. The conventional tactics of disease identification that exist are either unreliable or very complex or costly making them not suitable as viable techniques. However, with a boom in the field of Artificial intelligence, many procedures have come up over the recent years to help solve this problem. Data being the fuel for such procedures, it is very important to source reliable and accurate data for the training purpose of the AI based models. The task of disease detection for potato leaves is quite challenging as the symptoms show a lot of variations depending upon the species, climate and environmental factors. The popular pretrained models used for this purpose are VGG16, Inception V3, ResNet50 which help us to classify diseases of plants. In our research we have tried to build a custom Convolutional Neural Network classification model which is more robust and light weight as compared to the existing approaches. The model is built with a very simple approach and is trained using two standard publicly available datasets namely "PlantVillage" and PLD. The correctness of the suggested model has shown promising and consistent output with accuracy of 99.3% and 99.23%, while implemented on the two datasets respectively. To achieve the said accuracy, we have used image Enhancement algorithm: CLAHE at the preprocessing stage after the data acquisition. © 2025 Copyright for this paper by its authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Prediction Evaluation of Machine Learning Models with PSO-Optimized K-Fold Cross-Validation

Heart Disease Prediction Evaluation of Machine Learning Mode...

引用

IEEE Region 10 Symposium

作者： Nikita Gupta Kuldeep Singh Jadon Preeti Soni Nitin Gupta Sanjay Kumar Dhurandher Department of Computer Science & Engineering NIT Hamirpur (HP) India Department of Information Technology Netaji Subhas University of Technology New Delhi National Institute of Electronics and Information Technology New Delhi India

ISBN: (数字)9798350364866

ISBN: (纸本)9798350364873

Heart disease prediction is a critical aspect of modern healthcare and demands accurate and efficient models for timely diagnosis. Machine learning models in heart disease prediction analyze patient data, with cross-validation ensuring reliable performance, aiding model selection, and optimizing parameters for enhanced accuracy. The k value in cross-validation determines the number of folds into which the dataset is divided for training and validation. In the proposed work, optimization of the k-value in cross-validation is done using Particle Swarm Optimization (PSO), which is utilized to improve the evaluation of the predictive accuracy of various models. PSO dynamically adjusts the k-value, balancing computational efficiency with accurate model evaluation. The result shows that among various ML models, Random Forest, with an 86.95% mean accuracy, emerges as the preferred choice, offering reliable predictions for improved diagnostics.

关键词： Heart Training Analytical models Accuracy Computational modeling Predictive models Data models Reliability Optimization Diseases

来源：评论

学校读者我要写书评

暂无评论

An Elliptic Curve Biometric Based User Authentication Protocol for Smart Homes Using Smartphone 1st

An Elliptic Curve Biometric Based User Authentication Protoc...

引用

1st International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2021

作者： Bagha, Amir Mohammadi Woungang, Isaac Dhurandher, Sanjay Kumar Traore, Issa Department of Computer Science Ryerson University TorontoON Canada Department of Information Technology Netaji Subhas University of Technology University of Delhi Delhi India Department of Electrical and Computer Engineering University of Victoria VictoriaB.C Canada

ISBN: (纸本)9783030933135

The Internet of Things (IoT) is one of the most prominent technologies which establishes the foundation of smart homes and cities by creating a communication method for physical objects over the Internet. In smart homes, devices (objects) are not fundamentally homogeneous in security protocols, computational power, topology, or communication. This heterogeneous nature of these objects leads to incompatibilities with common authentication methods and the security requirements of IoT standards. This paper proposes an enhanced version of the RSA-Biometric-based user Authentication Scheme for Smart Homes using smartphone (denoted RSA-B-ASH-S) by utilizing the Elliptic-curve Diffie–Hellman (ECDH) protocol to optimize the computational power. The formal security analysis of the proposed scheme is presented using the Burrows-Abadi-Needham (BAN) logic, demonstrating how the proposed scheme achieves a perfect forward secrecy (PFS) by taking advantage of a unique encryption key for each session. An informal security analysis of the proposed scheme is also presented, highlighting its computational time, communication overhead, and storage requirements. A proof of concept of the proposed scheme is also presented. © 2022, ICST institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Data privacy

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：