检索结果-内蒙古大学图书馆

YOLOv8n-CGW: A novel approach to multi-oriented vehicle detection in intelligent transportation systems

Multimedia Tools and Applications 2025年第7期84卷 3809-3840页

作者： Berwo, Michael Abebe Fang, Yong Sarwar, Nadeem Mahmood, Jabar Aljohani, Mansourah Elhosseini, Mostafa School of Information and Engineering Chang’an University Shaanxi Xi’an710064 China Department of Computer Science Bahria University Lahore Campus Punjab Lahore54600 Pakistan Department of Information Technology Faculty of Computing and Information Technology University of Sialkot Punjab Sialkot51040 Pakistan College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

In the context of Intelligent Transportation systems (ITS), the role of vehicle detection and classification is indispensable for streamlining transportation management, refining traffic control, and conducting in-depth accident analyses. However, the intricate task of accurately detecting multi-oriented vehicles in diverse scenarios remains a challenge, even with the advancements in ITS. Factors such as vehicle morphology, design, road conditions, structural details, and climatic variables provide a significant part in the detection. To address this, our study introduces an advanced YOLOv8n model, specifically the YOLOv8n-CGW, which is built upon pre-trained deep learning frameworks. This model is meticulously tailored to enhance the detection capabilities for multi-oriented vehicles. Comprehensive evaluations on esteemed datasets like MtV, MERGED, Custom dataset, DAWN, WEDGE, and UA-DETRAC underscore the superiority of our approach over existing models. Notably, our YOLOv8n-CGW model achieves a remarkable mAP of 83.3% and boasts a swift inference time of 0.0019s, setting a new benchmark in the domain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid-Optimized Model for Deepfake Detection

引用

International Journal of Advanced computer Science and Applications 2025年第4期16卷 148-160页

作者： Mancy, H. Elpeltagy, Marwa Eldahshan, Kamal Ismail, Aya Department of Computer Science College of Engineering and Computer Sciences Prince Sattam Bin Abdulaziz University Alkharj11942 Saudi Arabia Al-Azhar University Cairo Egypt Systems and Computers Department Al-Azhar University Egypt Mathematics Department Faculty of Science Al-Azhar University Egypt Mathematics Department Tanta University Egypt

The advancement of deep learning models has led to the creation of novel techniques for image and video synthesis. One such technique is the deepfake, which swaps faces among persons and then produces hyper-realistic videos of individuals saying or doing things that they never said or done. These deepfake videos pose a serious risk to everyone and countries if they are exploited for extortion, scamming, political disinformation, or identity theft. This work presents a new methodology based on a hybrid-optimized model for detecting deepfake videos. A Mask Region-based Convolutional Neural Network (Mask R-CNN) is employed to detect human faces from video frames. Then, the optimal bounding box representing the face region per frame is selected, which could help to discover many artifacts. An improved Xception-Network is proposed to extract informative and deep hierarchical representations of the produced face frames. The Bayesian optimization (BO) algorithm is employed to search for the optimal hyperparameters' values in the extreme gradient boosting (XGBoost) classifier model to properly discriminate the deepfake videos from the genuine ones. The proposed method is trained and validated on two different datasets;CelebDF-FaceForencics++ (c23) and FakeAVCeleb, and tested also on various datasets;CelebDF, DeepfakeTIMIT, and FakeAVCeleb. The experimental study proves the superiority of the proposed method over the state-of-the-art methods. The proposed method yielded %97.88 accuracy and %97.65 AUROC on the trained CelebDF-FaceForencics++ (c23) and tested CelebDF datasets. Additionally, it achieved %98.44 accuracy and %98.44 AUROC on the trained CelebDF-FaceForencics++ (c23) and tested DeepfakeTIMIT datasets. Moreover, it yielded %99.50 accuracy and %99.21 AUROC on the FakeAVCeleb visual dataset. © (2025), (Science and Information Organization). All Rights Reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM 3

Hybrid Approach for Electricity Price Forecasting using Alex...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Sambana, Bosubabu Devi, Kotamsetty Geethika Reddy, Bandi Rajeswara Hussain, Galeti Mohammad Siddartha, Gownivalla School of Computing Mohan Babu University Tirupati India Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798331527549

The recent development of advanced machine learning methods for hybrid models has greatly addressed the need for the correct prediction of electrical prices. This method combines AlexNet and LSTM algorithms, which are used to introduce a new model with higher accuracy in price forecasting. Despite RNN and ANN being effective, they often fail to deal with forex time sequence data. The traditional methods do not accurately forecast the prices. These traditional methods only focus on demand and price which leads to insufficient analysis of data. To address this issue, using the hybrid approach, which focuses on external variables that also effect the predicted prices. Nevertheless, due to AlexNet's excellent feature extraction and LSTM's learning sequential patterns, the prediction accuracy is vastly increased. The model is built on the past data, which has been supplied with the most significant elements like demand, temperature, sunlight, and rain. For example, the model applies methods, such as minimum-maximum scaling and a time window, to predict the electricity prices of the future. The results show that this hybrid model is good than the standalone ones in terms of accuracy. Although we got our accuracy rating of 97.08, it shows higher accompaniments than remaining models RNN and ANN with accuracies of 96.64 and 96.63 respectively. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

DeepLeaf: an optimized deep learning approach for automated recognition of grapevine leaf diseases

引用

Neural Computing and Applications 2025年第15期37卷 8799-8823页

作者： Talaat, Fatma M. Shams, Mahmoud Y. Gamel, Samah A. ZainEldin, Hanaa Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Faculty of Engineering Horus University Damietta Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt

Plant diseases can cause severe losses in agricultural production, impacting food security and safety. Early detection of plant diseases is crucial to minimize crop damage and ensure agricultural sustainability. Manual monitoring is often impractical due to the complexity and time involved, making automated disease recognition essential. This study presents a new Plant Disease Detection Algorithm (PDDA) called DeepLeaf focused on identifying four common grapevine diseases: leaf blight, black rot, stable, and black measles. The PDDA integrates three key modules: an Image Preprocessing Module, a Feature Extraction Module, and an Optimized Convolutional Neural Network (OCNN)-based Classification Module. The OCNN forms the core of the classification system, with its hyperparameters fine-tuned using fuzzy optimization to enhance performance. Preprocessing techniques are applied to analyze diseased leaves, and a logistic regression algorithm is used to downsample the features for better analysis. The CNN is trained on images from the Plant Village dataset, allowing it to detect and classify grapevine leaf diseases accurately. The proposed model's efficiency in the automated diagnosis of grapevine diseases is demonstrated by its remarkable 99.7% accuracy rate. This high accuracy indicates that the PDDA may help with more effective and scalable plant disease monitoring, which will ultimately allow better agricultural practices. © The Author(s) 2025.

关键词： CNN Detection of leaf disease Extracting features Plant disease

来源：评论

学校读者我要写书评

暂无评论

Monolithic 3-D Integration of Diverse Memories: Resistive Switching (RRAM) and Gain Cell (GC) Memory Integrated on Si CMOS

引用

IEEE Transactions on Electron Devices 2025年第5期72卷 2685-2690页

作者： Liu, Shuhan Radway, Robert M. Wang, Xinxin Moro, Filippo Nodin, Jean-Francois Jana, Koustav Yan, Lixian Du, Shuting Upton, Luke R. Chen, Wei-Chen Kang, Jimin Chen, Jian Li, Haitong Andrieu, Francois Vianello, Elisa Raina, Priyanka Mitra, Subhasish Wong, H.-S. Philip Stanford University Department of Electrical Engineering StanfordCA94305 United States University of Pennsylvania Department of Electrical and Systems Engineering School of Engineering and Applied Science PhiladelphiaPA19104 United States Université Grenoble Alpes CEA-Leti Grenoble38058 France Purdue University Department of Electrical and Computer Engineering West LafayetteIN47907 United States

The future memory is massive, diverse, and tightly integrated with computing. This research presents tight integration, both physically and architecturally, of two on-chip memory technologies, resistive switching random access memory (RRAM) and gain cell (GC) memory. HfO2 RRAM and indium tin oxide (ITO) GC memory are monolithically integrated on 130-nm Si CMOS technology to form a joint memory that enables low-energy training and low-standby-power inference for edge devices. High-bandwidth on-chip data transfer can have a bandwidth that is 90× state-of-the-art (SoTA) HBM3E and 211× PCIe 7.0, enabled by high-density monolithic 3-D interconnections between memory arrays and high-speed transfer circuit within the integrated joint memory macro. Fabricated atomic layer deposition (ALD) ITO FET exhibits positive VTH of 0.67 V, excellent subthreshold slope (SS) of 65 mV/dec, high ON-current of 20 μA/μm, and low OFF-current of 5 × 10-18 A/μm, as extracted from >5000 s retention. The joint memory macro consumes 78% less standby power and 95% less training energy for MobileBERT compared to SRAM with iso-capacity. This RRAM-GC joint memory facilitates efficient continual learning in edge devices, addressing the challenges of a resource-constrained environment while supporting adaptive artificial intelligence (AI) model updates. © 1963-2012 IEEE.

关键词： RRAM

来源：评论

学校读者我要写书评

暂无评论

Applications of Topological Data Analysis with Morphology Operators on Hypergraphs

Applications of Topological Data Analysis with Morphology Op...

引用

International Conference on Mathematics of Intelligent Computing and Data Science, ICMICDS 2022

作者： Ramkumar, P.B. Dhanya, P.M. Department of Mathematics Rajagiri School of Engineering and Technology Kerala Kakkanad India Department of Computer Science and Business Systems Rajagiri School of Engineering and Technology Kerala Kakkanad India

ISBN: (纸本)9789819615049

A hypergraph is a type of graph, H=(V,E) where V is the set of nodes and E is the set of hyperedges;where one edge consists of may nodes. Morphological operators are nonlinear operators which can be applied on images, graphs, hypergraphs etc. Dilation and erosion are morphological operators and other operators like opening, closing can be obtained by repeated application of these operators. Topological space consists of a set X together with topology τ defined on X, which satisfies the axioms namely Nullset, arbitrary union of opensets and finite intersection of opensets. Such a topological space S=(X,T) is compatible with a hypergraph H if X=VH∪EH where VH and EH are the vertex set and edge set respectively. The morphological operators induces several topology on hypergraph with its compatible topological space S=(X,T). Neighborhood of a node is defined in many ways which can be considered as open sets in the corresponding topological space. The purpose of this paper is to apply topological properties on hypergraphs using morphological operators. Separation axiom and closure function are illustrated using hypergraph structure. The work is extended to crime analysis, text processing and patient disease analysis. Topological feature extraction is done on Barcodes created from crime hypergraphs. This gives a better visualization of crime analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Bidirectional LSTM-Based Energy Consumption Forecasting:Advancing AI-Driven Cloud Integration for Cognitive City Energy Management

引用

computers, Materials & Continua 2025年第5期83卷 2907-2926页

作者： Sheik Mohideen Shah Meganathan Selvamani Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Wajdan Al Malwi Mohammad Tabrez Quasim Department of Computer Science and Engineering Srinivasa Ramanujan CentreSASTRA Deemed UniversityKumbakonam612001India Department of Computer Science and Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bangalore562112India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK University Centre for Research and Development Chandigarh UniversityMohali140413PunjabIndia Centre for Research Impact and Outcome Chitkara University Institute of Engineering and TechnologyChitkara UniversityRajpura140401PunjabIndia Department of Information Systems College ofComputer and Information SciencePrincessNourah bintAbdulrahmanUniversityP.O.Box 84428Riyadh11671Saudi Arabia College of Computer Science Informatics and Computer Systems Department King Khalid UniversityAbha61421Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia

Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and *** study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory(LSTM)*** a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear *** bidirectional LSTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LSTMs consider only a single temporal *** design,combined with dropout regularization,leads to a 20.6%reduction in RMSE and an 18.8%improvement in MAE over conventional unidirectional LSTMs,demonstrating a substantial enhancement in prediction accuracy and *** to existing models—including SVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing,significantly outperforming these *** results highlight the model’s superior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive *** integrating advanced machine learning techniqueswith IoT and cloud infrastructure,this research contributes to the development of intelligent,sustainable urban environments.

关键词： Deep learning bidirectional LSTM energy consumption forecasting time-series analysis predictive modeling machine learning in energy management

来源：评论

学校读者我要写书评

暂无评论

Prediction of Covid-19 Recovery Chances Using Supervised Machine Learning Classification 5th

Prediction of Covid-19 Recovery Chances Using Supervised Mac...

引用

5th International Conference on Innovative Product Design and Intelligent Manufacturing systems, ICIPDIMS 2023

作者： Dhanalakshmi, R. Nivashini, A. Vijayaraghavan, N. Centre for Cyber Physical Systems School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering MNM Jain Engineering College Chennai India Department of Mathematics KCG College of Technology Chennai India

ISBN: (纸本)9789819767311

Predictive analytics if combined with machine learning approaches have the potential to play a significant role in forecasting the spread of respiratory infections. Machine learning approaches aid in the mining of data to better assess and forecast the presence or absence of covid-19 infection. In this paper, XGBoost Ensemble Classification using a fine-tuned approach is being used. Various machine learning algorithms are being analyzed and XGBoost Ensemble Classification algorithm is used to forecast and predict the covid-19 infected patient recovery chances that is the possible outcome of a covid-19 infected patient along with the prediction probability of recovery. The suggested categorization model is applied to a variety of situations. When compared to other ensemble models like random forest, hybrid ensemble and other individual classifiers such as decision tree, logistic regression, K-nearest neighbor, support vector machine and Naive Bayes, the XGBoost Ensemble Classification model gave the highest accuracy. Predicting the correct class is important. Thus, the proposed system discusses the possibility of automated prediction for covid-19 infected patient recovery chances along with the probability of recovery and the effectiveness of such predictions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Private Inference in Quantized Models

引用

IEEE Transactions on Information Theory 2025年第5期71卷 3957-3973页

作者： Deng, Zirui Ramkumar, Vinayak Bitar, Rawad Raviv, Netanel Washington University in St. Louis Department of Computer Science and Engineering St. LouisMO63130 United States Tel Aviv University Department of Electrical Engineering-Systems Tel Aviv-Yafo6997801 Israel Institute for Communications Engineering Technical University of Munich Munich80333 Germany

A typical setup in many machine learning scenarios involves a server that holds a model and a user that possesses data, and the challenge is to perform inference while safeguarding the privacy of both parties. Private Inference has been extensively explored in recent years, mainly from a cryptographic standpoint via techniques like homomorphic encryption and multiparty computation. These approaches often come with high computational overhead and may degrade the accuracy of the model. In our work, we take a different approach inspired by the Private Information Retrieval literature. We view private inference as the task of retrieving inner products of parameter vectors with the data, a fundamental operation in many machine learning models. We introduce schemes that enable such retrieval of inner products for models with quantized (i.e., restricted to a finite set) weights;such models are extensively used in practice due to a wide range of benefits. In addition, our schemes uncover a fundamental tradeoff between user and server privacy. Our information-theoretic approach is applicable to a wide range of problems and robust in privacy guarantees for both the user and the server. © 1963-2012 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

PlantCare AI: An AI based Solution for Plant Disease Diagnosis and Assistance 6

PlantCare AI: An AI based Solution for Plant Disease Diagnos...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Ghogare, Snehal Dhupe, Shivkanya Kulkarni, Abhijit Shingane, Tanish Gound, Renuka Department of Computer Science and Business Systems JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune India

ISBN: (纸本)9798331522667

The advancement of Artificial Intelligence (AI) and machine learning (ML) has introduced trans- formative solutions in plant care. This review investigates the integration of deep learning and image recognition technologies for identifying and managing plant diseases. The proposed project focuses on developing a user-centric web application designed to detect plant diseases automatically, provide treatment recommendations, suggest nearby nurseries for obtaining necessary supplies, and offer chatbot assistance for user inquiries. Leveraging advanced image recognition techniques, this system aims to make plant care more efficient and accessible. The integration of Google Maps enhances navigation to local nurseries, further simplifying access to resources and promoting better plant care practices. This study outlines current methodologies, explores challenges and opportunities, and proposes a structured framework for creating an intelligent plant care platform to meet the evolving demands of farmers and horticulture professionals. © 2025 IEEE.

关键词： Convolutional neural networks

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：