检索结果-内蒙古大学图书馆

IWF-ECTIC: Improved Wiener filtering and ensemble of classification model for tourism image classification

Multimedia Tools and Applications 2024年 1-38页

作者： Bhosale, Tejaswini A. Pushkar, S. Department of Computer Science and Engineering Birla Institute of Technology Jharkhand Mesra835215 India Birla Institute of Technology Ranchi Mesra835215 India

Social media is so widely used;travelers frequently post texts, photos, and videos about their experiences online. These user-generated content (UGCs) significantly affect how travelers perceive Tourist Destination Image (TDI) and directly influence their decision-making. UGC photos represent passengers' visual preferences for a certain place. Considering the significance of photographs, a lot of researchers have tried to analyze them using machine learning methods. Nevertheless, a limitation of research efforts employing these techniques for tourism image analysis is that they cannot precisely categorize the unique photos found in specific tourist destinations using predetermined images. In order to get rid of these challenges, this work proposes a Tourism image classification model termed as Improved Weiner Filtering and Ensemble of Classification model for Tourism Image Classification (IWF-ECTIC) model which includes steps like preprocessing, segmentation, feature extraction, and classification. The preprocessing is done via improved wiener filtering which provides a more robust assessment of image quality. The segmentation is done by the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) model which can effectively handle outliers and noisy points. Subsequent to the segmentation, MLGBPHS (Modified Local Gabor Binary Pattern Histogram Sequence), MBP (Median Binary Pattern), color, shape and Improved Entropy-based features are extracted in the feature extraction stage to reduce the dimensionality of the data. Finally, ensemble classification is done by combining the Multihead Convolutional Neural Network with Attention Mechanism (MHCNN-AM), Bidirectional Long Short-Term Memory (Bi-LSTM), and Recurrent Neural Network (RNN) classifiers to classify the images. To improve the classification accuracy, optimal training will be done in MHCNN-AM, Bi-LSTM, and RNN classifier using the proposed Cuckoo Updated Chimp Optimization (CUCO) algorit

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Noise Robust ASV Spoof Detection Using Integrated Features and Time Delay Neural Network

引用

SN computer Science 2023年第2期4卷 127页

作者： Chakravarty, Nidhi Dua, Mohit Department of Computer Engineering National Institute of Technology Kurukshetra India

Recent advancements in research for development of countermeasure systems for Spoofed Audio detection has helped in building more robust Automatic Speaker Verification (ASV) System. However, available countermeasure systems are not able to generalize well against unknown attacks. The lack of context-dependent information extracted from the given speech at fine grained level is the dominating reason for poor performance of these systems against unknown attacks. To build a noise robust anti-spoof system, in this paper, we propose a Time Delay Neural Network (TDNN)-based countermeasure system that captures context-dependent information well. We devise a three-stage design where at first audio is pre-processed to extract useful information using three different types of features, that are, Mel Frequency Cepstral Coefficients (MFCC), noise robust Gammatone Cepstral Coefficients (GTCC) features and integration of MFCC-GTCC features. These features are then input to proposed Deep Neural Network (DNN) model that uses Long Short-Term Memory (LSTM) network for recurrent aggregation of layer wise generated shallow features in TDNN. Finally, the output is passed through context-dependent pooling layer to generate fixed-length representation that is further used at third stage to classify speech as genuine or spoofed. The proposed system is tested on Logical Access (LA) track of ASV Spoof 2019 dataset, and achieves performance improvement of about 59.7% and 65.9% relative to earlier proposed Linear-Frequency Cepstral Coefficients-Gaussian Mixture Model (LFCC-GMM) and Constant Q Cepstral Coefficients-Gaussian Mixture Model (CQCC-GMM) baseline models, respectively. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： ASV Deep neural network GTCC LSTM MFCC X-vector

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Based Framework For Bankruptcy Prediction In Corporate Finances Using Explainable AI Techniques

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第15期49卷 15-26页

作者： Maktum, Tabassum Pulgam, Namita Chandgadkar, Vaishnavi Pathak, Prachi Solanki, Aditya Department of Computer Engineering School of Engineering & Technology Anjuman I Islam’s Kalsekar Technical Campus Maharashtra New Panvel India D J Sanghvi College of Engineering Maharashtra Mumbai India Department of Computer Engineering Ramrao Adik Institute of Technology D Y Patil Deemed to be University Maharashtra Navi Mumbai India

Forecasting bankruptcy within corporate finances is an indispensable endeavor crucial for sustaining business growth and fostering stability. The paper presents a methodology to redefine the conventional approach to bankruptcy prediction within corporate finance. Through the adept utilization of advanced machine learning techniques, notably classification models, a dynamic and adaptable framework is established, enabling the systematic categorization of companies based on their bankruptcy risk profiles. Moreover, the methodology addresses the inherent challenge of data bias by integrating oversampling techniques like the Synthetic Minority Over-sampling Technique (SMOTE), thereby ensuring a more equitable representation of minority class samples and bolstering the model’s predictive accuracy. The resulting model delivers timely and precise forecasts of bankruptcy risk, fortified by crucial recommendations such as the Altman Z-Score for vulnerability assessment, Debt-to-Equity Ratio for insights into leverage, Quick Ratio for assessing liquidity, and Explainable AI Techniques like SHapley Additive exPlanations (SHAP) analysis for transparent interpretations. This comprehensive approach equips stakeholders with tailored recommendations, empowering them to proactively safeguard their organizations’ financial well-being and avert the perils of bankruptcy. The comparative analysis presented in paper demonstrates that the proposed method assesses the bankruptcy risk more accurately. The integration of Explainable AI techniques and key financial metrics helps the stakeholders to take vital decisions about corporate finances. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Image-based Plant Diseases Detection using Deep Learning

引用

Materials Today: Proceedings 2023年 80卷 3500-3506页

作者： Panchal, Adesh V. Patel, Subhash Chandra Bagyalakshmi, K. Kumar, Pankaj Khan, Ihtiram Raza Soni, Mukesh Department of Computer Science & Engineering GEC Patan India School of Computer Science and Engineering VIT Bhopal University Sehore MP Bhopal India Electrical and Electronics Engineering SRI Ranganathar Institute of Engineering and Technology Coimbatore India Department of Computer Science & Engineering Institute of Engineering & Technology Uttar Pradesh Greater Noida India Jamia Hamdard Computer Science Department Delhi India Jagran Lakecity University Bhopal India

Agriculture plays a major role in developing countries like India, however the food security still remains a vital issue. Most of the crops get wasted due to lack of storage facility, transportation, and plant diseases. More than 15% of the crops get wasted in India due to diseases and hence it has become one of the major concern to be resolved. There is a need of automatic system that can identify these diseases and help farmers to take appropriate steps to get rid of crop loss. Farmers have followed the conventional method of identifying the plant disease with their naked eyes, and it not possible for all the farmers to identify these diseases the same way. With the advance in Artificial Intelligence, there is a need to incorporate the facilities of the computer vision in the field of agriculture. Deep Learning rich libraries and user as well as developer friendly environment to work with, all these qualities make Deep Learning as the favorable method to get started with this problem. In this paper we have used Deep Learning because of the advantages it offers to work with images especially in image classification to get improvised results. The methodology includes taking leaves of infected crops and label them as per the disease pattern. The images of infected leaves are processed pixel based operations are applied to improve the information from the image. As a next step feature extraction is done followed by image segmentation and at the last classification of crop diseases based on the patterns extracted from the diseased leaves. The CNN (Convolutional Neural Network) is used for the classification of diseases, for the demonstration purpose the public dataset is used consisting of around 87 K images (RGB type images) including healthy as well as diseased leaves. © 2021

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

KGFakeNet: A Knowledge Graph-Enhanced Model for Fake News Detection 31

KGFakeNet: A Knowledge Graph-Enhanced Model for Fake News De...

引用

2025 Workshop on Generative AI and Knowledge Graphs, GenAIK 2025, co-located with the 31st International Conference on Computational Linguistics, COLING 2025

作者： Kumar, Anuj Kumar, Pardeep Yadav, Abhishek Ahlawat, Satyadev Prasad, Yamuna Department of Computer Science & Engineering Indian Institute of Technology Jammu India Department of Electrical Engineering Indian Institute of Technology Jammu India

ISBN: (纸本)9798891762121

The proliferation of fake news on social media has intensified the spread of misinformation, promoting societal biases, hate, and violence. While recent advancements in Generative AI (GenAI), particularly large language models (LLMs), have shown promise, these models often need more structured representation for accurate verification, as they rely on pre-trained data patterns without access to real-time or validated information. This study presents a framework that utilizes Open Information Extractor 6 (OpenIE6) to extract triplet relationships (subject-predicate-object) from statements and justifications to compute the cosine similarity between the Knowledge Graphs (KGs) of the statements and their supporting justification to precisely measure the relevance and alignment between them. This similarity feature is integrated with an attention mechanism over GenAI-generated embeddings to enhance the model’s ability to capture semantic features accurately. In addition, a Multi-Layer Perceptron (MLP) classifier is employed to integrate all features, resulting in a 4% improvement in accuracy and a 5% increase in F1-score over state-of-the-art LLM-based approaches. ©2025 International Committee on Computational Linguistics (ICCL)

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Grape Leaf Diseases using EfficientNet Model

Detection and Classification of Grape Leaf Diseases using Ef...

引用

2024 IEEE International Conference on Recent Advances in Science and engineering technology, ICRASET 2024

作者： Subramanya, S.G. Parkavi, A. Ramaiah Institute of Technology affiliated to Visvesvaraya Technological University Department of Computer Science and Engineering Bengaluru India Ramaiah Institute of Technology Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350388602

Viticulture or grape cultivation is a significant horticulture method all over the globe. Often, grapevines suffer from many viral, fungal, and bacterial infections that affect production quantity and quality. Farmers worldwide use traditional methods to detect and treat these diseases. However, they are time-consuming, labor intensive, and require significant expertise. The EfficientNetB0 model is implemented for automating the diagnosis of grape leaf diseases. The transfer learning (TL) approach is leveraged to train and fine-tune the EfficientNetB0 model using Kaggle grapevine disease dataset. The leaf image dataset represents four classes - black rot, esca, leaf blight, and healthy samples. The model's performance is evaluated based on metrics like accuracy and loss. The result shows that EfficientNetB0 gave accuracies of 92.45% and 96.73% on training and validation datasets, respectively. The model achieves better results in disease classification while maintaining computational efficiency. © 2024 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Early Diabetics Prediction Using Multi Model Approaches in Machine Learning 9

Early Diabetics Prediction Using Multi Model Approaches in M...

引用

9th International Conference on Science, technology, engineering and Mathematics, ICONSTEM 2024

作者： Renugadevi, G. Sasi Kala Rani, K. Oswalt Manoj, S. Saranya, N. Goudhaman, M. Sri Krishna College of Engineering And Technology Department of Computer Science And Engineering Chennai India Dr Ngp Institute of Technology Department of Computer Science And Engineering Chennai India Jeppiaar Engineering College Department of Computer Science And Engineering Chennai India

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365092

Diabetics is the maximum common non-transmissible disease and the deadliest disease worldwide, affecting five hundred and thirty-seven mountain individuals. Diabetics container be carried on by a variety of sources, with an unhealthy diet, high BP, abnormal cholesterol, a personal antiquity of the disease, and inactivity. Early diabetes prediction using IoT can be done by monitoring various health parameters and identifying patterns that may indicate the development of diabetes. In Proposed work, Mendeley Data Repository is a real-time data have been taken for early diabetes prediction. The Proposed hybrid Backward elimination method with Maximum Relevance, Minimum Redundancy (BE-MRMR) algorithm When integrating backward elimination and the MRMR algorithm, you can use the strengths of both strategies to identify a small but informative set of features for early diabetic prediction, potentially enhancing model interpretability and generalisation. Finally, after eliminating features, left with a subdivision of structures that subsidize most to the replica's performance. This feature given to various machine learning classifiers RF, ANN, SVM to predict early diabetics. These models produce performance matrices is calculated in terms of accuracy, specificity, precision and sensitivity. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adversarial Robustness in DeepFake Detection: Enhancing Model Resilience with Defensive Strategies 4

Adversarial Robustness in DeepFake Detection: Enhancing Mode...

引用

4th International Conference on Intelligent Cybernetics technology and Applications, ICICyTA 2024

作者： Pallavi, N. Pallavi, T.P. Bylaiah, Sushma Goutam, R. M S Ramaiah Institute of Technology Department of Computer Science and Engineering Karnataka India Karnataka India Atria Institute of Technology Department of Computer Science and Engineering Karnataka India

ISBN: (纸本)9798331506490

Detection of DeepFakes presents formidable challenges primarily due to adversarial attacks that can dramatically reduce model accuracy. Current detection models are reasonably effective in real scenarios;however, these detectors are vulnerable to adversarial attacks, resulting in misclassifications. The current study examines defensive approaches to strengthen the robustness of DeepFake detection approaches when facing adversarial attacks. Explored several alternatives, including adversarial training, input preprocessing, and model ensembles against a manipulated media dataset. The results demonstrate that the model has predicted image appropriately at average of 86.34% but after the adversarial attacks the prediction of the image was 99.8% inappropriate. although adversarial attacks greatly lower the effectiveness of a model, it is possible to improve the robustness of a model through defense methods, particularly adversarial training in combination with an ensemble method which predicted the image appropriately at an average of 52.06%. However, despite the improvement, the defense methods still fail to protect all adversarial examples. The results illustrate the importance of developing new methods of defense against DeepFake detection in light of future adjustments and variants of an attack. © 2024 IEEE.

关键词： adversarial attack attacks deepfake deeplearning detection system

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Cognitive Task and Seizure Classification with Hilbert–Huang Transform and Variational Mode Decomposition 3rd

Deep Learning for Cognitive Task and Seizure Classification ...

引用

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Jain, Shraddha Srivastava, Rajeev Department of Computer Science and Engineering Indian Institute of Technology BHU Varanasi India

ISBN: (纸本)9789819743582

Electroencephalography (EEG) signals are often utilized to study cognitive processes and brain diseases. The non-stationary and non-linear nature of EEG signals makes their analysis difficult. A deep learning framework that suggested classifying seizures based on scalp EEG signals and automating cognitive tasks. We use a pre-processing module based on the Hilbert–Huang Transform (HHT) and Variational Mode Decomposition (VMD) to extract features from raw EEG data. We present an approach that combines deep learning with HHT and VMD for rapid and precise seizure detection. Our method detects seizures with an astounding 98.40% accuracy. Our suggested techniques have great potential for quantifying brain wave patterns and advancing neuroscience research, even outside of classification applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Mitigating Risks in Vehicle Fires: An Integrated Approach for Early Detection and Real-Time Alert System 1

引用

4th International Conference on Smart IoT Systems: Innovations and Computing, SSIC 2023

作者： Suryawanshi, Ranjeetsingh Bhagat, Harshita Karande, Aryan More, Parth More, Vaishali Department of Computer Engineering Vishwakarma Institute of Technology Pune India Department of Information Technology Vishwakarma Institute of Technology Pune India

ISBN: (数字)9789819752003

ISBN: (纸本)9789819751990

Every year, there are about 170,000–220,000 car accidents each year that involve fire. The cause of the fire ranges from collision, engine malfunction, electric short circuits, and many more. Irrespective of the cause, the damage incurred is close to $2 billion in direct property damage and in severe accidents, even the passengers’ lives. The rapid detection and timely notification of fire incidents are crucial for minimizing property damage and ensuring public safety. The current vehicle fire safety system relies on manual notification, leading to delayed responses and potential risks, especially in low-density areas and nighttime scenarios. Additionally, the lack of proactive fire detection technology hinders early identification, increasing the likelihood of extensive damage and harm to passengers. This paper proposes an integrated alert system automatically notifies fire stations, hospitals, and police upon fire detection, streamlining coordination and reducing response times. Rigorous evaluations are undertaken to assess the system's accuracy, sensitivity, and reliability under various conditions, solidifying its efficacy in addressing vehicle fire incidents. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Fires

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：