检索结果-内蒙古大学图书馆

R-UNET: Improving performance of rumex detection using unet based selective regions

Inteligencia Artificial 2025年第75期28卷 186-198页

作者： Nazal, Saleh Al-Dulaimi, Khamael Al-Nahrain University College of Science Department of Computer Science Baghdad Iraq Queensland University of Technology School of Electrical Engineering and Robotics Australia

In particular, Rumex weed detection is regarded as a crucial step in real-world data under many circumstances. The detection task suffers from several issues, such as overlapping weeds, occlusion, varying leaf colour distributions, leaf size and shape, and growth stage. Many machine learning techniques have been proposed to detect weeds in plants. These techniques suffer from locating weed with precise bounding boxes because they may contain multiple bounding boxes in a certain region. Researchers have used the R-CNN based weed identification system, but it continues to have a low detection rate because of the issues mentioned above. In order to detect Rumex weeds under various conditions, particularly overlapping, occlusion, and size, as well as containing multiple bounding boxes, this paper is developed the R-CNN model by using UNet instead of the CNN model to become R-UNet. The proposed model is used due to its novelty of using a UNet classifier with selective regions which boosts the detection capabilities by extracting the most helpful features more effectively than the CNN network. The proposed method uses Intersection over Union (IoU) to assess the detection rate using real-world data. We compare and benchmark the evaluation of the detection performance of this work with different models, including Single-Shot Detector (SSD), hybrid CNNs, AlexNet, and adapted NMS methods. The proposed model yields the highest IoU values compared with other methods. © IBERAMIA and the authors.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhanced MADM Strategy with Heptapartitioned Neutrosophic Distance Metrics

引用

Neutrosophic Sets and Systems 2025年 78卷 74-96页

作者： Eassa, Mohamed Myvizhi, M. Elkholy, Mohamed Abdelhafeez, Ahmed Elbehiery, Hussam Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Mathematics KPR Institute of Engineering and Technology Tamilnadu Coimbatore India Faculty of Computer Science& Engineering Alamein International University Egypt

In this work, a novel methodological approach to multi-attribute decision-making problems is developed and the notion of Heptapartitioned Neutrosophic Set Distance Measures (HNSDM) is introduced. By averaging the Penta-Partitioned Neutrosophic Distance Measures under particular conditional criteria, the suggested technique ranks the options. Additionally, we explore the fundamental characteristics of HNSDM and provide several illustrative theorems. The Heptapartitioned Neutrosophic Set Distance Measures are formulated based on the Hepta Neutrosophic Set. Lastly, a practical numerical example is provided to illustrate the efficacy of the suggested methodology. © 2025, university of New Mexico. All rights reserved.

关键词： Heptapartitioned Neutrosophic set Heptapartitioned Neutrosophic set and MADM strategy Heptapartitioned set Neutrosophic sine distance measure

来源：评论

学校读者我要写书评

暂无评论

qLIF: Mitigating the memory and computation overhead to implement spiking convolutional neural networks

引用

Neural Computing and Applications 2025年第15期37卷 9011-9024页

作者： Li, Silong Wang, Ningning Kang, Xinyu Yu, Chunlin Ye, Terry Tao Department of Electronic and Electrical Engineering Southern University of Science and Technology Xueyuan Avenue Guangdong Shenzhen518055 China Institute of Nanoscience and Applications Southern University of Science and Technology Xueyuan Avenue Guangdong Shenzhen518055 China

Spiking neural networks (SNNs) have many advantages in achieving lower power neuromorphic computation. In this paper, we propose new methods that can further mitigate the memory spaces and computation resources that are needed for spiking convolutional neural networks (SCNNs) implementation. Traditional leaky-integrate-and-fire (LIF) mechanism, which is widely adopted in SNN, demands large memory spaces to store the membrane potentiation values for integration, through experiments, we find out that for many layers, the potentiation values can be quickly leaked (qLIF) and no extra memory spaces are needed to store the values from past events. With the adoption of qLIF mechanism, convolution between the input matrix and the kernel matrix can be simplified into a look-up-table (LUT) operation (called ConvLUT in this paper), without the need of computation resources to perform the dot-product. Through experiments on MNIST, CIFAR-10, CIFAR-100 and DVS128-Gesture datasets with SCNNs, we have verified that both qLIF mechanism and ConvLUT method can greatly reduce the memory spaces as well as computation resources in SCNN, the computation latency can also be improved. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

REGAC: Multi-Class Offensive Content Identification Using Graphical Approach

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2025年第4期52卷 931-952页

作者： Chinivar, Sneha Roopa, M.S. Arunalatha, J.S. Venugopal, K.R. Department of Computer Science and Engineering Bangalore University K R Circle Karnataka Bengaluru India Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Karnataka Bengaluru India Department of Computer Science and Engineering Bangalore University K R Circle Karnataka Bengaluru India Karnataka Bengaluru India

Online offensive behaviour continues to rise with the increasing popularity and use of social media. Various techniques have been used to address this issue. However, most existing studies consider offensive content identification as a binary or ternary problem, disregarding the potential for multi-class classification of derogatory content. In this work, we propose RoBERTa Embedding-based Graphical Approach Classifier (REGAC), which aims to designate the identified offensive content into varied classes,like age, gender, ethnicity, religion, and others to understand what exact qualities the bully usually targets in their victim so that pertinent measures can be taken to battle them. Additionally, the models’ efficiency is evaluated using an unbalanced dataset to identify types of offensive content. The word embeddings are generated for a balanced dataset using RoBERTa embedding model to bring out the best-fitting vectors. These vectors are then input into traditional Machine Learning algorithms (SVM, KNN, Logistic Regression, Random Forest, and XGBoost) and graph-based algorithms (Graph Convolution Network (GCN), GraphSAGE, and Graph Attention Network (GAT)) for fine-grained categorization of offensive textual content. The experimental results demonstrate the efficiency of combating social media’s offensive content of the proposed work with higher Precision, Recall, F1-Score, and Accuracy compared with most state-of-art approaches. © (2025.0), (International Association of Engineers). All Rights Reserved.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Cyber-attack detection based on a deep chaotic invasive weed kernel optimized machine learning classifier in cloud computing

引用

Soft Computing 2025年第4期29卷 2015-2030页

作者： Indrasena Reddy, M. Siva Kumar, A.P. Subba Reddy, K. Department of Computer Science and Engineering BVRIT Hyderabad College of Engineering for Women Hyderabad500090 India Department of Computer Science and Engineering Jawaharlal Nehru Technological University Ananthapuramu Andhra Pradesh Ananthapuramu India Department of Computer Science and Engineering Rajeev Gandhi Memorial College of Engineering and Technology Andhra Pradesh Nandyala India

Nowadays, Cloud Computing has attracted a lot of interest from both individual users and organization. However, cloud computing applications face certain security issues, such as data integrity, user privacy, and service availability. The only better solution to such issues is to identify and prevent cyber threats before they can cause seriously harm the cloud computing system. Several methods have been suggested so far to detect the attack in cloud computing (CC), but no one method attains satisfactory results. To overwhelm these drawbacks, a Cyber Security Attack Detection using Deep Kernel Machine Learning optimized with Chaotic Invasive Weed Optimization algorithm is proposed in this paper for Cloud Computing. Here, the data is amassed from CSE-CIC-IDS2018 and Bot-IoT datasets. Subsequently, a pre-processing step involving redundancy reduction and missing value replacement for uncertainty removal is achieved through the Developed Random Forest with Local Least Squares (DRFLLS) method. By utilizing Entropy-Kurtosis based feature selection approach, the pre-processing data is given to the feature selection to identify the optimal features. The selected features are supplied to the Deep Kernel Machine Learning classifier (DK-ML), which is optimized using the Chaotic Invasive Weed Optimization algorithm (Chaotic-IWOA) for classification. This classification process classifies the data as normal or anomalous categories with anomalies encompassing, like DoS, DDoS, Theft attacks, and normal attacks. The proposed technique is activated in MATLAB. The proposed technique achieves 24.88%, 17.98%, 45.65%, 35.95% better accuracy for CSE-CIC-IDS2018 dataset, and 23.93%, 13.94%, 32.94%, and 29.04% better accuracy for Bot-IoT dataset. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of LIME and SHAP Interpreters With Explainable ML-Based Diabetes Predictions

引用

IEEE Access 2025年 13卷 37370-37388页

作者： Ahmed, Shamim Kaiser, M. Shamim Shahadat Hossain, Mohammad Andersson, Karl Jahangirnagar University Institute of Information Technology Savar Dhaka1342 Bangladesh University of Chittagong Department of Computer Science and Engineering Chattogram4331 Bangladesh Luleå University of Technology Electrical and Space Engineering Department of Computer Science Skellefteå931 87 Sweden

Explainable artificial intelligence is beneficial in converting opaque machine learning models into transparent ones and outlining how each one makes decisions in the healthcare industry. To comprehend the variables that affect decision-making regarding diabetes prediction that can be accounted for by model-agnostic techniques. In this project, we investigate how to generate local and global explanations for a machine-learning model built on a logistic regression architecture. We trained on 253,680 survey responses from diabetes patients using the explainable AI techniques LIME and SHAP. LIME and SHAP were then used to explain the predictions produced by the logistic regression and Random forest-based model on the validation and test sets. With a discussion of future work, the comparative analysis and discussion of various experimental findings between LIME and SHAP are provided, along with their strengths and weaknesses in terms of interpretation. With a high accuracy of 86% on the test set, we used LR architecture with a spatial attention mechanism, demonstrating the possibility of merging machine learning and explainable AI to improve diabetes prediction, diagnosis, and treatment. We also focus on various applications, difficulties, and probable future directions of machine learning models for LIME and SHAP interpreters. © 2013 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Closed-Loop Placement Planning for Regrasping and Reconstruction With Single-View RGB-D Images

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 14084-14095页

作者： Chen, Zhiyuan Liu, Jiangshan Chen, Ronghao Wang, Jiankun Southern University of Science and Technology Shenzhen Key Laboratory of Robotics Perception and Intelligence Department of Electronic and Electrical Engineering Shenzhen518055 China Southern University of Science and Technology Jiaxing Research Institute Jiaxing030024 China

In robotic reorientation, achieving certain positions or orientations within a workspace can be difficult due to collisions and interference between objects and the environment. Regrasping is a technology that overcomes limitations on object reorientation using multiple pick-and-place actions. However, constructing a regrasping graph, which consists of predicted intermediate placements, is challenging with only partial observations of unknown objects. To address this challenge, we design a closed-loop placement planning system using single-view RGB-D images. This system seamlessly integrates perception and manipulation processes, capturing RGB-D images for object reconstruction while predicting intermediate placements for constructing regrasping graphs simultaneously. To optimize the regrasping graph construction, we propose a Truncated Signed Distance Function (TSDF)-based placement evaluation algorithm that selects the next-best-placement by estimating the information gain and retention of the placements. Additionally, we adopt a novel data fusion method based on predicted intermediate placements to enhance object reconstruction and TSDF updates, effectively mitigating in-hand errors. Our system surpasses baselines in accuracy and diversity of placement predictions. It demonstrates superior performance in object reconstruction, excelling in quantitative analysis and visualization. Real-world experiments validate the effectiveness of our system in reorientation and reconstruction tasks on real industrial parts, demonstrating its robustness and applicability in practical scenarios. © 2004-2012 IEEE.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Composite spectral spatial pixel CNN for land-use hyperspectral image classification with hybrid activation function

引用

Multimedia Tools and Applications 2025年第12期84卷 10527-10550页

作者： Banerjee, Anasua Swain, Satyajit Rout, Minakhi Bandyopadhyay, Mainak School of Computer Engineering Kalinga Institute of Industrial Technology-Deemed-to-be-University Bhubaneswar India Department of Computer Science and Engineering National Institute of Technology Silchar India

Deep learning methods have played a prominent role in the development of computer visualization in recent years. Hyperspectral imaging (HSI) is a popular analytical technique based on spectroscopy and visible imaging which examines the pattern of light in a target and recognizes objects based on varying spectral properties. However, in remote sensing, detecting surface material via HSI analysis is a critical and difficult task. The performance of spectral-spatial data exploitation is well established to outperform typical spectral pixel-wise techniques. Because of its great feature extraction ability, convolutional neural networks (CNN) have emerged as a potent deep learning approach. CNN translates the input features of an image into an equivalent CNN feature map, in addition to naturally combining spectral and spatial information. However, spectral-spatial properties when combined with pixel-wise extraction can learn more minute details of objects present on the earth’s terrain. In this paper, a noble Composite Spectral Spatial Pixel CNN model for the classification of hyperspectral data is presented which is an amalgamation of 3D-2D-1D CNN. While the 3D and 2D CNN exploit the spectral-spatial features effectively, 1D CNN works on pixel-wise feature extraction. Further, to optimize the classification performance of the proposed model, a new hybrid activation function Flatten-T Swish is also used which is the combination of ReLU and Swish function. The proposed model is compared with other state-of-the-art models based on three popular HSI datasets, and it is found that the proposed model performs better among others in terms of classification and computation time, giving 98.87% accuracy for Indian Pines, 99.92% accuracy for Pavia university, and 99.99% accuracy for Salinas Valley dataset. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

WSO-KELM: War Strategy Optimization-Based Kernel Extreme Learning Machine for Automatic Software Fault Prediction Model

引用

Journal of The Institution of Engineers (India): Series B 2025年第1期106卷 145-163页

作者： Elci, J. Brundha Nandagopalan, S. Department of Computer Science and Engineering Vemana Institute of Technology Visvesvaraya Technological University Karnataka Belagavi India Department of Information Science and Engineering Vemana Institute of Technology Visvesvaraya Technological University Karnataka Belagavi India

The software development projects’ testing part is usually expensive and complex, but it is essential to gauge the effectiveness of the developed software. Software Fault Prediction (SFP) primarily serves to detect faults within software components. The scale of software projects is getting larger, making it impossible and time-consuming to analyze the flaws manually. Artificial Intelligence (AI) techniques are mainly incorporated to solve this problem. The massive data retrieved from the software repositories helps in identifying the features that are highly correlated with fault prediction and the features that are not. This paper introduces a Kernel Extreme Learning Machine (KELM) for SFP. To optimize the hyperparameters of the classifier and also enhance the classification accuracy, the War Strategy Optimization (WSO) algorithm is employed here. The experimental evaluations are conducted using different baseline actual-world datasets of software programs such as Java-coded open-source and PROMISE datasets. The experimental outcomes are conducted using different performance metrics that include sensitivity, Accuracy, and F1-score with values of 0.96%, 0.97%, and 0.96%, respectively. The results show that KELM is beneficial, and the optimization provided by the WSO algorithm also helps us obtain higher classification accuracy for the SFP problem and improve the fault detection process. © The Institution of Engineers (India) 2024.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Deep Exclusion Unfolding Network for Single Image Reflection Removal

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第6期47卷 4957-4973页

作者： Huang, Jun-Jie Liu, Tianrui Chen, Zihan Liu, Xinwang Wang, Meng Dragotti, Pier Luigi National University of Defense Technology College of Computer Science and Technology Changsha China Hefei University of Technology School of Computer Science and Information Engineering Hefei China Imperial College London Department of Electrical and Electronic Engineering London United Kingdom

Single Image Reflection Removal (SIRR) is a canonical blind source separation problem and refers to the issue of separating a reflection-contaminated image into a transmission and a reflection image. The core challenge lies in minimizing the commonalities among different sources. Existing deep learning approaches either neglect the significance of feature interactions or rely on heuristically designed architectures. In this paper, we propose a novel Deep Exclusion unfolding Network (DExNet), a lightweight, interpretable, and effective network architecture for SIRR. DExNet is principally constructed by unfolding and parameterizing a simple iterative Sparse and Auxiliary Feature Update (i-SAFU) algorithm, which is specifically designed to solve a new model-based SIRR optimization formulation incorporating a general exclusion prior. This general exclusion prior enables the unfolded SAFU module to inherently identify and penalize commonalities between the transmission and reflection features, ensuring more accurate separation. The principled design of DExNet not only enhances its interpretability but also significantly improves its performance. Comprehensive experiments on four benchmark datasets demonstrate that DExNet achieves state-of-the-art visual and quantitative results while utilizing only approximately 8% of the parameters required by leading methods. © 1979-2012 IEEE.

关键词： Blind source separation

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：