检索结果-内蒙古大学图书馆

Predicting physicochemical properties of papayas (Carica papaya L.) using a convolutional neural networks model approach

引用

JOURNAL OF FOOD SCIENCE 2024年第11期89卷 7861-7871页

作者： An, Sujin Oh, Geuncheol Lee, Dongyoung Baek, Kyungim Jun, Soojin Univ Hawaii Manoa Dept Human Nutr Food & Anim Sci Honolulu HI 96822 USA Cobslab Goyang South Korea Univ Hawaii Manoa Dept Mol Biosci & Bioengn Honolulu HI USA Univ Hawaii Manoa Dept Informat & Comp Sci Honolulu HI USA

The current state of quality assessment methods for agricultural produce, particularly fruits, heavily relies on manual inspection techniques, which could be subjective, time-consuming, and prone to human errors. Consequently, there have been emerging trends and needs for non-destructive methods to evaluate fruit quality accurately and practically. This research aimed to develop a novel approach for predicting the physicochemical properties of papayas using a convolutional neural network (CNN) model that combines image analysis and weight assessment. This study involved capturing images of papayas at different ripening stages, measuring papaya weights, and determining various physicochemical properties such as texture, pH, total soluble solids, and seed weight. A total of 532 images were obtained from 132 papayas, and an additional 1064 images were generated through image augmentation. The dataset was divided into three sets with an 8:1:1 ratio for training, validation, and testing. The CNN model was trained using papaya images and weights as input values to predict and estimate the physicochemical property values. Model performance was evaluated using mean squared error (MSE) and the coefficient of determination (R2) as metrics. The CNN model, integrated with image processing, could predict the diverse physicochemical properties of papayas with high accuracy. The MSE values estimated for the training and validation sets were 0.0284 and 0.1729, respectively. The R2 values for the test dataset ranged from 0.71 to 0.94. These findings demonstrate that CNN-based models could provide detailed and quantitative insights, facilitating improved understanding and management of papaya quality while enhancing predictive modeling accuracy in agriculture.

关键词： convolutional neural network deep learning fruit assessment machine learning papaya

来源：评论

学校读者我要写书评

暂无评论

Optimization of Temporal Convolutional Network for Remaining Useful Life Prediction of LithiumIon Battery Using Separable Convolution 1

Optimization of Temporal Convolutional Network for Remaining...

引用

1st International Symposium on Parallel Computing and Distributed Systems, PCDS 2024

作者： Miyawaki, Atsushi Kobayashi, Nobuaki Nihon University Precision Machinery Engineering Graduate School of Science and Technology Chiba Japan College of Science and Technology Nihon University Department of Precision Machinery Engineering Chiba Japan

ISBN: (纸本)9798350349658

Predicting the remaining useful life (RUL) of lith-ium-ion batteries is crucial in battery management and mainte-nance for electric vehicles (EVs) and industrial machinery [1]. In this prediction, a data-driven approach using deep learning, which has demonstrated high performance in image recognition and natural language processing, has been developed, but there are still some issues to be solved. In particular, these include the increase in computational complexity in the hidden layers when introducing deep learning [3], as well as the improvement of accuracy and the practicality of attaching deep learning to battery-powered devices [3]. Therefore, in this study, we will solve the above problems by introducing a temporal convolutional network (TCN), which has numerous advantages for time-series data, and by devising the configuration of the network. First, we propose using depthwise separable convolution layers to reduce computational complexity and the number of parameters. These layers have been used in mobile application networks in recent years. In addition, we further improve computational efficiency by adopting bottleneck architecture centered on the pointwise convolution layers for the residual blocks in TCN. In this study, we performed RUL prediction for these networks using the NASA Ames Prognostics Centers of Excellence (PCOE) dataset and compared the models' accuracies and complexities using mean square error and other evaluation metrics. Therefore, while there was no degradation in the models' accuracies, the computational complexity and number of parameters were reduced by a factor of 10 using the separable convolution layers, and by a factor of 20 using the bottleneck architecture. © 2024 IEEE.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Identifying High-Risk Patients for Diabetes using Machine learning 8

Identifying High-Risk Patients for Diabetes using Machine Le...

引用

8th IEEE International Conference on image and Signal processing and their Applications, ISPA 2024

作者： Dib, Wassila Kerdjidj, Oussama Zergoug, Nabila Allaoui, Maroua Centre for Development of Advanced Technologies Algiers Algeria University of Algiers Benyoucef Benkhedda Algiers Algeria

ISBN: (纸本)9798350309249

Diabetes is a chronic disease that represents a major challenge for global health. However, current technological advances allow us to monitor blood glucose levels in real time throughout the day, enabling better monitoring and faster intervention when needed. In this work, we aim to improve current methods of classifying patients at risk of diabetes using glycated hemoglobin test (HbA1c). The eleven features extracted from synthetic continuous glucose monitoring (CGM) data were used with two classifiers, namely decision tree (DT) and Random Forest (RF), to classify patients into four categories: healthy, moderate pre-diabetic, severe pre-diabetic and diabetic. The results obtained are promising, with an overall accuracy of around 92%. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Enhanced CNN-DCT Steganography: deep learning-Based image Steganography Over Cloud

引用

SN Computer Science 2024年第4期5卷 408页

作者： Ahmad, Shahnawaz Ogala, Justin Onyarin Ikpotokin, Festus Arif, Mohd. Ahmad, Javed Mehfuz, Shabana School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida 201310 India Department of Cyber Security University of Delta Agbor Nigeria Department of Computer Science Ambrose Alli University Edo State Ekpoma Nigeria Department of CSE School of Computing Science and Engineering Galgotias University Uttar Pradesh Greater Noida 203201 India Department of Computer Science and Engineering Sharda School of Engineering and Technology Sharda University Uttar Pradesh Greater Noida 201310 India Department of Electrical Engineering Jamia Millia Islamia New Delhi 110025 India

image steganography plays a pivotal role in secure data communication and confidentiality protection, particularly in cloud-based environments. In this study, we propose a novel hybrid approach, CNN-DCT Steganography, which combines the power of convolutional neural networks (CNNs) and discrete cosine transform (DCT) for efficient and secure data hiding within images over cloud storage. The proposed method capitalizes on the robust feature extraction capabilities of CNNs and the spatial frequency domain transformation of DCT to achieve imperceptible embedding and enhanced data-hiding capacity. In the proposed CNN-DCT Steganography approach, the cover image undergoes a two-step process. First, feature extraction using a deep CNN enables the selection of appropriate regions for data embedding, ensuring minimal visual distortions. Next, the selected regions are subjected to the DCT-based steganography technique, where secret data is seamlessly embedded into the image, rendering it visually indistinguishable from the original. To evaluate the effectiveness of our approach, extensive experiments are conducted using a diverse dataset comprising 500 high-resolution images. Comparative analysis with existing steganography methods demonstrates the superiority of the proposed CNN-DCT Steganography approach. The results showcase higher data hiding capacity, superior visual quality with an MSE of 112.5, steganalysis resistance with a false positive rate of 2.1%, and accurate data retrieval with a bit error rate of 0.028. Furthermore, the proposed method exhibits robustness against common image transformations, ensuring the integrity of the concealed data even under various modifications. Moreover, the computational efficiency of our approach is demonstrated by a competitive execution time of 2.3 s, making it feasible for real-world cloud-based applications. The combination of deep learning techniques and DCT-based steganography ensures a balance between security and visual qual

关键词： Cloud storage CNN Data hiding DCT deep learning image steganography Visual fidelity

来源：评论

学校读者我要写书评

暂无评论

Enhanced Lung Tumor Detection via deep learning Techniques in CT Imaging 10

Enhanced Lung Tumor Detection via Deep Learning Techniques i...

引用

10th International Conference on Biosignals, images and Instrumentation, ICBSII 2024

作者： Bose, S Rubin Karrthik Kishore, V. Abishek, K.R. Chalwin Ajay, J. Angelin Jeba, J. Regin, R. Srm Institute of Science and Technology Department of Ece Chennai India Anna University Department of Ece CEG Campus Chennai India

ISBN: (纸本)9798350350951

Lung cancer is one of the most common causes of cancer-related death worldwide. Early detection is essential for better patient outcomes. Both the YOLOv8 algorithm and Convolutional Neural Networks (CNNs) have demonstrated promise in the field of medical image processing and object detection, respectively. In this research, we present an innovative method for the detection of lung cancer utilising a CNN model and the YOLOv8 algorithm, integrated into a mobile application developed in Kotlin for enhanced accessibility. Our system takes advantage of the YOLOv8 algorithm's real-time object detection capabilities to recognise nodules of lung cancer using CT scans. The CNN model is trained on a dataset of CT scans and is capable of differentiating between benign and malignant nodules. The mobile application provides a user-friendly interface for uploading CT scans and receiving real-time diagnostic results. The proposed system intends to improve lung cancer early detection by providing a convenient and efficient tool for healthcare professionals and patients. By utilising the strength of CNNs and YOLOv8, this technology has the capacity to reduce false negatives and improve overall diagnostic accuracy, ultimately contributing to better patient care and outcomes. Our model performs well overall, with 98.06% precision, 96.57% recall and 97.31% F1 score when test on a benchmark dataset of images of lung cancer. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Roadway and Traffic Control Conditions Using On-Board image processing 17

Automated Detection of Roadway and Traffic Control Condition...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Sivakumar, Ashmitha Jaysi Pragati, L. Roy, Sambhavi Vanajakshi, Lelitha Devi Indian Institute of Technology Madras Department of Civil Engineering Chennai India

ISBN: (纸本)9798331531195

Accurate detection of roadway and traffic control conditions is crucial for enhancing Advanced Driver Assistance Systems (ADAS) in dynamic environments. This study aims to leverage deep learning techniques, specifically YOLO series, for their identification in real-world scenarios. Detection of traffic signs, markings and signal along with road conditions such as potholes, and speed breakers are considered. The YOLO models perform well and demonstrates effective and real-time detection capacities. © 2025 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

FUSION OF MULTI-RESOLUTION SEISMIC TOMOGRAPHY MAPS WITH PHYSICS-INFORMED PROBABILITY GRAPHICAL MODELS 49

FUSION OF MULTI-RESOLUTION SEISMIC TOMOGRAPHY MAPS WITH PHYS...

引用

49th IEEE International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Zhou, Zheng Gerstoft, Peter Olsen, Kim Univ Calif San Diego San Diego CA 92103 USA San Diego State Univ San Diego CA USA

ISBN: (纸本)9798350344868;9798350344851

We propose an approach to fuse multiresolution seismic tomography models with physics-informed probability graphical models (PIPGMs), which consider the physical information (ray-path density). To evaluate the efficacy of the PIPGM fusion method, we use both synthetic checkerboard models and real fault zone structures imaged from 2019 Ridgecrest, CA, earthquake sequence. The proposed method improves the combined models in terms of travel time residual, image quality, and peak signal-to-noise ratio, compared to those obtained by multiple conventional methods. The proposed fusion method can merge any type of gridded multi-resolution velocity model, a valuable tool for computational imaging.

关键词： Multi-resolution model fusion Markov Random Fields physics-informed machine learning.

来源：评论

学校读者我要写书评

暂无评论

AI on the Edge: A Novel Approach to Detect Waste on Water Bodies 8

AI on the Edge: A Novel Approach to Detect Waste on Water Bo...

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Prasad, Ishan Shekhar Sanketh, Medha Chandra Kumar, R. R.V College of Engineering Department of Artificial Intelligence and Machine Learning Bengaluru India R.V College of Engineering Department of Mechanical Engineering Bengaluru India

ISBN: (纸本)9798331505462

Marine environments are being increasingly burdened by waste from heavy industries and the large scale disposal of electronics and plastics into waterways that flow into the oceans. Recent advancement in technologies like real time image processing, machine learning and edge computing has made it feasible to develop commercially viable solutions for automated identification of garbage on water bodies. This paper explores image processing as a targeted approach for the on-field identification of water pollutants. A unique aspect of this approach was to demonstrate the effectiveness of its implementation on standalone edge devices viz. ones that could be used in remote locations with limited compute capabilities and no wireless connectivity. The study demonstrates this use-case with TensorFlow as an AI framework and Raspberry Pi 4B as an edge device. The model achieved a mean Average Precision (mAP) of 51.20%, validating its performance in identifying water pollutants. © 2024 IEEE.

关键词： Plastics industry

来源：评论

学校读者我要写书评

暂无评论

deep learning for Dermatological Diagnostics: A Comprehensive Study on Skin Disease Classification Using ResNet50 2

Deep Learning for Dermatological Diagnostics: A Comprehensiv...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Devi, Priyanka Gupta, deepanshu Thakur, Adarsh Kumar, Dhirendra Kumar, Aditya Budhiraja, Bhumi Chandigarh University Department of Computer Science Punjab Mohali India

ISBN: (纸本)9798331519056

The research is trying to move forward skin disease classification using a dataset consisting of 19,500 images of 23 distinct skin conditions retrieved from dermatology-pictures-skin-disease-pictures. The trial relies on ResNet50 structure, with a remarkable 97% clinical interpretation success. The images in JPEG format with different resolutions, at the beginning of processing, were divided into two groups and their size was changed in addition to standardization. time was devoted to intensive training covering tuning of hyperparameters as well as growing data variety. This research work contributes to the current knowledge on skin lesion classification, evaluating ResNet50 features that identify different skin problems. Everything about the high accuracy indicates that deep learning has a huge potential in dermatology. The paper herein presents both the model's strengths and weaknesses to set the path for future developments. This study is the milestone toward the automated skin diseases diagnosis and also the development of image analysis technologies. © 2024 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Automatic Flood Detection from Sentinel-1 Data Using a Nested UNet Model and a NASA Benchmark Dataset

引用

PFG-JOURNAL OF PHOTOGRAMMETRY REMOTE SENSING AND GEOINFORMATION SCIENCE 2024年第1期92卷 1-18页

作者： Ghosh, Binayak Garg, Shagun Motagh, Mahdi Martinis, Sandro GFZ German Res Ctr Geosci Dept Geodesy Sect Remote Sensing & Geoinformat D-14473 Potsdam Germany Univ Cambridge Dept Engn Future Infrastruct & Built Environm Cambridge England Leibniz Univ Hannover Inst Photogrammetry & GeoInformat IPI D-30167 Hannover Germany German Aerosp Ctr DLR Cologne Germany

During flood events near real-time, synthetic aperture radar (SAR) satellite imagery has proven to be an efficient management tool for disaster management authorities. However, one of the challenges is accurate classification and segmentation of flooded water. A common method of SAR-based flood mapping is binary segmentation by thresholding, but this method is limited due to the effects of backscatter, geographical area, and surface characterstics. Recent advancements in deep learning algorithms for image segmentation have demonstrated excellent potential for improving flood detection. In this paper, we present a deep learning approach with a nested UNet architecture based on a backbone of EfficientNet-B7 by leveraging a publicly available Sentinel-1 dataset provided jointly by NASA and the IEEE GRSS Committee. The performance of the nested UNet model was compared with several other UNet-based convolutional neural network architectures. The models were trained on flood events from Nebraska and North Alabama in the USA, Bangladesh, and Florence, Italy. Finally, the generalization capacity of the trained nested UNet model was compared to the other architectures by testing on Sentinel-1 data from flood events of varied geographical regions such as Spain, India, and Vietnam. The impact of using different polarization band combinations of input data on the segmentation capabilities of the nested UNet and other models is also evaluated using Shapley scores. The results of these experiments show that the UNet model architectures perform comparably to the UNet++ with EfficientNet-B7 backbone for both the NASA dataset as well as the other test cases. Therefore, it can be inferred that these models can be trained on certain flood events provided in the dataset and used for flood detection in other geographical areas, thus proving the transferability of these models. However, the effect of polarization still varies across different test cases from around the world in terms of

关键词： Flood detection NASA Synthetic aperture radar Transfer learning deep learning UNet plus plus UNet

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：