检索结果-内蒙古大学图书馆

2024 International Conference on Big Data Analytics in Bioinformatics, DABCon 2024

作者： Banerjee, Sumit Kumar Chakraborty, Priyanka Nath, Sayan Computer Science and Engineering Guru Nanak Institute of Technology Kolkata India

ISBN: (纸本)9798350378047

It is critical to identify and then classify diseases in pomegranate fruits to ensure a high-quality yield and reduce agricultural losses. Regretfully, large-scale monitoring is difficult since traditional methods of identifying illnesses are time-consuming and often require specialist knowledge. Advanced methods for automated disease classification have been made possible in recent years by machine learning (ML) and deep learning (DL). Transfer learning (TL), one of these approaches, has proven to be successful in addressing particular agricultural issues with sparse data by utilizing pre-trained models on big datasets. Here a method for classifying pomegranate fruit problems called Hybrid Transfer Learning (HTL) is proposed. This approach integrates domain-specific feature extraction with the benefits of TL and fine-tuning approaches. Images of both healthy and sick pomegranate fruit are fed into pre-trained convolutional neural networks (CNNs), such as ResNet, Inception, and VGG, to extract generalized visual information. Following this, a process of fine-tuning combines these features with a specially designed disease categorization module that is tailored to the distinct qualities of pomegranate disorders. Affected crops have caused the agricultural field to suffer and also affects the economy. However, the reason behind the infected crops may be crop diseases. To resolve this issue, Pomegranate fruit disease classification based on hybrid transfer learning is chosen. Different machine learning algorithms such as Random Forest Classifier, K-Nearest Neighbors algorithm with custom deep learning algorithms are used. Our run-time training precision is 96% and run-time validation precision is 93% respectively. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Single-Frame Image Based Multi-variant Bird Species Identification and Classification 5th

Single-Frame Image Based Multi-variant Bird Species Identifi...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Adhikari, Nilanjana Bhattacharya, Suman Sultana, Mahamuda Department of Computer Science and Engineering Guru Nanak Institute of Technology Kolkata700114 India

ISBN: (纸本)9789819771776

The increasing demand for advanced ornithological tools and techniques aimed at accurately identifying and classifying multiple bird species within a single-frame image has led us to develop a framework for researchers, environmentalists, and bird enthusiasts. Traditional methods often struggle to handle the complexity of diverse avian variants present in each scene, particularly when capturing images in real-world, uncontrolled environments. Single-frame images, such as those obtained through wildlife monitoring cameras or handheld devices, offer a practical and common means of avian observation. Our work centered on the automated detection and classification of a group of multi-variant bird species using a Deep Learning (DL) framework. The You Only Look Once (YOLO) version 5 networks were deployed in this study. Each object within the image frame was detected, annotated, and captured in a bounded box. Subsequently, each bounded object underwent scrutiny and recognition. The manually collected dataset comprises five mutually exclusive local bird species native to India. The developed model demonstrated satisfactory performance in terms of Precision, Recall, mAP, and F1 values, achieving scores of 0.87, 0.81, 0.82, and 0.826, respectively. This system can work as an automated bird species detection, recognition and classification tool for numerous individuals encountering difficulty recognizing multiple birds within a single image frame. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Performance optimization in ddos prediction with ensemble based approach

引用

Multimedia Tools and Applications 2025年第12期84卷 10631-10644页

作者： Dogra, Amit Taqdir Department of Computer Science and Engineering SoET BGSB University Rajouri India Department of Computer Science Engineering and Technology Guru Nanak Dev University Regional Campus Gurdaspur India

Distributed Denial of Service (DDoS) attacks pose a significant threat to network infrastructures, leading to service disruptions and potential financial losses. In this study, we propose an ensemble-based approach for DDoS attack detection, leveraging the strengths of three different classifiers: Adaboost, K-Nearest Neighbors (KNN), and Random Forest. We apply data normalization during pre-processing, utilize a Multi-Layer Perceptron (MLP) for feature extraction, and combine the classifiers using an ensemble approach. The performance of each individual classifier and the ensemble is extensively evaluated, and the results demonstrate the effectiveness of the proposed ensemble in accurately identifying and mitigating DDoS attacks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Optimal trained ensemble of classification model for satellite image classification

引用

Multimedia Tools and Applications 2025年第7期84卷 3745-3766页

作者： Singh, Sarabjeet Kundra, Harish Kundra, Sheetal Pratima, P. Venkata Devi, M. V. Anjana Kumar, Sushil Hassan, Mariya Department of Computer Science and Engineering Chandigarh College of Engineering and Technology Chandigarh160019 India Department of Computer Science and Engineering Guru Nanak Institutions Technical Campus Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Artificial Intelligence and Data Science Guru Nanak Institute of Technology Ranga Reddy District Telangana Ibrahimpatnam501506 India Department of Computer Science and Engineering Central University of Haryana Jant-Pali Mahendergarh123031 India

Satellite image classification is the most significant remote sensing method for computerized analysis and pattern detection of satellite data. This method relies on the image's diversity structures and necessitates a thorough validation of the training data using the chosen classification algorithm. The classifying of remotely sensed images refers to the process of classifying pixels into a fixed set of distinct classes based on their data values. The pixel is categorized into that class if it complies with a specific set of requirements. A new SIC scheme is suggested in this work, where, Contrast limited adaptive histogram equalization (CLAHE) is deployed for pre-processing the image. Further, statistical features, Vegetation Indices (VI) and Improved Hybrid Vegetation Index (IHVI) are extracted from the preprocessed image. Then, we deploy 2 phase classification process for classifying the image. In the first phase, Bi-Directional Gated Recurrent Unit (BI-GRU), Convolutional Neural Network (CNN) and Deep Max Out (DMO) are used. In 2nd phase, optimized RNN is used for determining the final classification result. Also, the training of the model is done by the new Chaotic Opposition Behavior Improvised Coot Algorithm (COBI-CA) optimization via tuning the optimal weights. The COOT method has been enhanced and is now the suggested algorithm. Lastly, we conduct an analysis to compare the suggested Satellite Image Classification (SIC) model's performance to the traditional approaches in terms of statistical analysis, precision, accuracy, and error measure. In comparison to other conventional methods, the accuracy of the suggested model is 97%. © This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Advances in AI-based genomic data analysis for cancer survival prediction

引用

Multimedia Tools and Applications 2025年第14期84卷 14139-14166页

作者： Deepali Goel, Neelam Padmavati Khandnor University Institute of Engineering and Technology Panjab University Chandigarh160014 India Chandigarh160012 India Department of Computer Science Guru Nanak College Budhlada151502 India

Problem: Cancer is one of the deadliest diseases prevalent in the world. Survivability, early diagnosis, and accurate prognosis are of utmost importance for the therapeutics and clinical management of cancer patients. To achieve accurate and timely prediction of the survival of cancer patients, several machine-learning models based on genomic data have been proposed but a comprehensive review of recent applications in cancer survival prediction is lacking. This paper represents a review of the most recent application of machine learning and deep learning on cancer survival prediction, with a particular focus on the use of genomic data. It specifically targets the most prominent cancer types such as breast cancer, glioblastoma, lung cancer, renal cell cancer, and oral cancer. Methods: A systematic review approach is employed to analyze recent studies on machine learning techniques applied to cancer survival prediction. Emphasis is placed on methodologies utilizing genomic data due to its effectiveness in predicting survival outcomes. Results: This review highlights the efficacy of different machine/deep learning-based techniques in predicting survival outcomes for different cancer types with genomic data. It also provides a summary of the contributions made by different research groups, critically examines the associated challenges, and suggests potential areas for further investigation. Conclusion: Machine learning and deep learning techniques, especially those utilizing genomic data, hold significant promise for accurate cancer survival prediction across diverse cancer types. Despite advancements, challenges such as data heterogeneity and model interpretability still persist. Further research is warranted to address these challenges and develop a comprehensive framework for cancer survival prediction applicable to various cancer types. This review lays the foundation for future investigations in the area of cancer research. © The Author(s), under exclusive licence

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Identification of Bird via Acoustics for Bird Species Population Monitoring and Conservation

Identification of Bird via Acoustics for Bird Species Popula...

引用

2024 International Conference on Big Data Analytics in Bioinformatics, DABCon 2024

作者： Adhikari, Nilanjana Bhattacharya, Suman Sultana, Mahamuda Maiti, Ananjan Sengupta, Diganta Guru Nanak Institute of Technology Jis Computer Science and Engineering West Bengal Kolkata India

ISBN: (纸本)9798350378047

Nowadays, bird conservation has become a crucial part of the study. The paramount peril confronting avian species in jeopardy pertains to the degradation of their habitats. The chirping sound of birds can be heard with lots of noise and environmental sounds. So, monitoring and identification of bird sounds are more challenging. This study proposes meticulous monitoring and identifying bird sounds to ensure bird species' conservation and automate the remote monitoring of bird populations. Firstly, the data frame was generated from the acquired recorded dataset. Then, the data frames were segmented into slices of 0.5-second intervals so that the silent zones of the recorded dataset could be removed. Following this, unwanted noise was removed using the filter. Then, the Mel Frequency Cepstral Coefficients (MFCCs) spectrogram was generated using feature extraction methodology. From this spectrogram, a sound vector is generated. Monitoring and tuning different hyperparameter constraints using Principal Component Analysis (PCA), the model was subsequently trained using Dense Neural Network. The test demonstrates exceptional precision and reliability with a nominal margin of error. © 2024 IEEE.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Watermarking technique for document images using discrete curvelet transform and discrete cosine transform

引用

Multimedia Tools and Applications 2024年第40期83卷 87647-87671页

作者： Singh, Balkar Sharma, M.K. Post Graduate Department of Computer Science Gujranwala Guru Nanak Khalsa College Punjab Ludhiana India School of Mathematics Thapar Institute of Engineering and Technology Punjab Patiala India

In this paper, a watermarking technique based on discrete curvelet transform and discrete cosine trans- form is proposed to protect the color document images. The six layers of the document image are created using the Discrete Curvelet Transform (DCuT). The sixth layer is chosen for the embedding process, while the remaining layers are discarded. Discrete Cosine Transform (DCT) is applied on the 8 × 8 blocks of the real part of sixth layer. DCT coefficients from low to medium are selected for the embedding process, excluding the first one. To choose the Direct Current (DC) coefficients of DCT to embed the watermark bits, a zigzag function is used. The same process is applied on the receiver side watermark image is extracted. Since this is a non-blind method, we require both a cover image and a watermarked image. DCT of watermarked image and the cover image are compared to extract the watermark image. The resistivity of the watermarked image against image processing attacks is measured using the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Mean Square Error (MSE), Normalization Correlation (NC), Bit Error Rate (BER) and Universal Quality Index (UQI). © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Threats to medical diagnosis systems: analyzing targeted adversarial attacks in deep learning-based COVID-19 diagnosis

引用

Soft Computing 2025年第3期29卷 1879-1896页

作者： Haque, Sheikh Burhan Ul Zafar, Aasim Haq, Sheikh Riyaz Ul Haque, Sheikh Moeen Ul Ahmad, Mohassin Roshan, Khushnaseeb School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India Department of Computer Science Aligarh Muslim University Uttar Pradesh Aligarh202002 India Department of Computer Science Engineering Guru Nanak Institution Ibrahimpatnam Telangana Hyderabad501506 India Department of Electronics and Communication Guru Nanak Institution Ibrahimpatnam Telangana Hyderabad501506 India

Deep and machine learning models have become pivotal in medical image analysis, especially for diagnosing COVID-19 using X-rays and CT scans. While these models, including transfer learning-based approaches, have achieved high accuracy, they remain highly vulnerable to adversarial attacks, which can manipulate input data and cause misclassification, posing critical risks in clinical applications. This study introduces a novel approach to addressing this issue by systematically evaluating the impact of adversarial attacks on COVID-19 diagnosis models built with two leading architectures, VGG-16 and DenseNet-121, using the Fast Gradient Sign Method (FGSM). The FGSM attack causes a dramatic drop in accuracy, reducing VGG-16’s accuracy from 95.12 to 9.97% and DenseNet-121’s from 96.51 to 10.13%. To counter these vulnerabilities, we propose a novel defense mechanism that combines adversarial training with Gaussian noise data augmentation, a dynamic approach that generates perturbations across various epsilon values during the training phase. This innovative method significantly enhances model robustness, restoring accuracy to over 92% on adversarial examples. These findings emphasize the need for strong defense mechanisms in deep learning models for COVID-19 diagnosis, ensuring reliability and security against adversarial threats in clinical environments. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

HMM-Based Secure Framework for Optical Fog Devices in the Optical Fog/Cloud Network

引用

Journal of Optical Communications 2023年第4期44卷 475-483页

作者： Sood, Sandeep K. Deep Singh, Kiran Department of Computer Science & Engineering Khalsa College of Engineering & Technology Amritsar India Department of Computer Science & Engineering Guru Nanak Dev University Regional Campus Punjab Gurdaspur India

In the present optical fog/cloud computing environment, optical line terminals and optical network units are used as the most promising optical fog devices (OFDs). The inherent characteristics of fog computing provide certain granted privileges to the attacker to hack devices and make them malicious. Also, existing security solutions generate false alarms that affect the performance of the underlying network. In this paper, a secure framework is proposed that not only predicts the malicious OFDs but also reduces false alarms. Hidden Markov model and intrusion detection system are used to detect the malicious one by computing the probability of shifting (POS) and then shift it to the virtual honeypot which is kept hidden by deploying it at the optical fog layer. In addition, it also reduces the generation of false alarm and logs all malicious activities for further analysis. In the experiment section, Python is used to validate the proposed framework. Further, HMM is simulated and tested in the MATLAB to reduce the false alarm rate. Results show that the proposed framework effectively reduces the false alarms and detects the malicious one and then shifts it onto the virtual honeypot efficiently. © 2019 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

IoV-fog-cloud framework for road anomalies detection using SVM-nAVDD approach

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第8期14卷 10899-10915页

作者： Kumar, Navin Sood, Sandeep Saini, Munish Department of Computer Engineering and Technology Guru Nanak Dev University Punjab Amritsar India Department of Computer Applications National Institute of Technology Haryana Kurukshetra India

The detection of road anomalies in highway management is a crucial yet manpower-demanding task. Although there have been many previous types of research based on visual and acceleration data collected from vehicles. However, to distinctively differentiate a pothole and speedbump from acceleration remains a challenge. The visual methods require high computation supported by expensive GPUs. This paper proposes a novel contribution to depth detection using angular velocity for pothole detection. The solution is accorded by three-layer architecture inclusive of fog-based cloud infrastructure where each layer performs a respective function based on computing capability. The data acquisition is accomplished using an IoV setup equipped with M8N GPS, and MPU-6050 mounted on an Arduino MEGA 2560. The results are compared with the state-of-art algorithms and methodologies. The proposed SVM-nAVDD achieved the precision of 0.9092–0.9123 for the tested datasets and depth/height detection with 92% accuracy. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Data acquisition

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：