检索结果-内蒙古大学图书馆

iCrop: a framework for identification of millet crop diseases via segmentation and feature extraction

Indian Phytopathology 2023年第3期76卷 803-812页

作者： Singh, Sonal Dashore, Swastik Prasad, Jatin Naik, Nenavath Srinivas Data Science and Artificial Intelligence International Institute of Information Technology Chhattisgarh Naya Raipur 493661 India Computer Science and Engineering Indian Institute of Information Technology Design and Manufacturing (IIITDM) Kurnool Andhra Pradesh Kurnool 518008 India

Crop diseases are important in agricultural productivity and quality. It is essential to recognise and diagnose these diseases. Deep learning’s ability to correctly classify small data sets is a major research challenge. This work proposes an approach using image segmentation, feature extraction and deep learning techniques to develop a multi-class classifier for millet crop disease identification. The proposed image processing approach and use of Artificial Neural Networks demonstrate disease classification over 2632 images with a training accuracy of 97.25% and a testing accuracy of 96.88%. Compared with the pre-trained model MobileNet V3, the implemented model achieved better training and validation accuracy over 100 epochs and required less training time. The proposed model’s simplicity makes crop disease detection in agriculture fast and efficient. As a result, the suggested method paves the way for large-scale crop disease diagnosis. © 2023, Indian Phytopathological Society.

关键词： Artificial neural networks Deep learning Feature extraction Image segmentation Millet crop disease

来源：评论

学校读者我要写书评

暂无评论

Classification of EEG Signals on SEED Dataset Using Improved CNN 2

Classification of EEG Signals on SEED Dataset Using Improved...

引用

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Ramar, B. Ramalakshmi, R. Gandhi, Vaibhav Pandiselvam, P. Kalasalingam Academy of Research and Education Department of Computer Applications Tamilnadu Krishnankoil India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu Krishnankoil India Middlesex University Department of Design Engineering and Maths Education London United Kingdom

ISBN: (纸本)9798350347579

The proposed research introduces an Improved Convolutional Neural Network (ICNN) to construct EEG-based emotion detection models. This study has utilized an EEG dataset of 15 subjects available from a BCMI laboratory. In our work, differential entropy characteristics obtained from multichannel EEG data are used to train the Improved CNN. The best classification accuracy is 95.67% which is significantly higher than that of the original 62 channels. The most important channels and frequency bands are identified by Improved CNN. The outcomes of our study also demonstrate the existence of neuronal signatures linked to various emotions, which are consistent between sessions and people. Finally, the effectiveness of deep and shallow models are compared and also the performance of improved CNN is compared with benchmark algorithms. © 2023 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

JMCD Dataset for Brain Tumor Detection and Analysis Using Explainable Deep Learning

引用

SN computer science 2023年第6期4卷 1-14页

作者： Verma, Aryan Gupta, Nidhi Bhatele, Pushpraj Khanna, Pritee Department of Computer Science and Engineering National Institute of Technology HP Hamirpur 177005 India Department of Computer Applications National Institute of Technology HR Kurukshetra 136119 India NSCB Medical College MP and MRI Scan Centre Nagpur Road MP Jabalpur 482003 India Computer Science and Engineering Discipline PDPM Indian Institute of Information Technology Design and Manufacturing MP Jabalpur 482005 India

The growth of abnormal cells in the brain gives rise to a deadly form of cancer known as a brain tumor. The mass of brain tumors proliferates and rises very fast, and if not appropriately treated, the patient’s survival rate is less or can rapidly lead to death. A very exigent task for radiologists is early brain tumor detection which may help to evaluate the tumor and plan treatment for an effective prognosis. In this work, we used deep learning to detect and localize brain tumors from MRI slices. After the detection of the tumor, we generate a color heatmap to show the tumor’s location, severity, and possible affected regions. Our novel image processing algorithm swiftly segments the skull region from the background of MR images, augmented over heatmap for better observation. We analyzed the performance of VGG 16, Resnet 50, and EfficientNet deep learning architectures. Transfer learning on Resnet 50 model with custom top layers achieved excellent performance with 99.37% accuracy, 99.68% precision, and 99.69% specificity, which is better than most of the works in brain tumor detection using machine learning. Expert radiologists critically examined our model outcomes in detail. They found our method effective to triage people with brain tumors and helpful in decision making for the clinicians by severity indication through heatmaps. They observed the prime cause for false positives to be unbalanced contrast in some MR images. Through this work, we also made the novel dataset named as JMCD (Jabalpur Medical College Dataset) publicly available for research which contains all four MR pulse sequences annotated by expert radiologists for 140 patients. Each patient has 15–20 sequences containing 250 images. Through this work and accompanying data, we aim to give better methods for brain tumor detection and help research in the same field. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Brain tumor Deep learning Glioma Medical image analysis MRI

来源：评论

学校读者我要写书评

暂无评论

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Similarity Computation Model Based on Optimised SBERT

SMGC-SBERT: A Multi-Feature Fusion Chinese Short Text Simila...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Zhao, Shuo Gu, Qiliang Zhang, Jianqiang Song, Gongpeng Lu, Qin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (纸本)9781665410205

Chinese short text similarity computation stands as a pivotal task within natural language processing, garnering significant attention. However, existing models grapple with limitations in handling intricate semantic relationships, such as the challenge of discerning subtle semantic nuances in text, inadequacies in effectively integrating diverse levels of semantic information, and the struggle to capture polysemous meanings accurately. In addressing these issues, this paper introduces an innovative Chinese short text similarity computation model, SMGC-SBERT. This model addresses shortcomings of the existing models by employing a multi-module fusion strategy, thereby enabling a more precise measurement of semantic similarity between texts. Primarily, the model incorporates SAT embedding to acquire phrase-level semantic information and leverages the MS-BERT model to encode text, improving the model's comprehension of textual polysemy and obtaining richer semantic representation. Then, the fusion of module features, including multi-branch convolutional networks and mix pooling, enables the extraction of textual features from varied levels, bolstering the model's representational capacity. Additionally, to further reduce overfitting risks while improving accuracy and other performance, a multi-layer feature adjustment network is utilized for short text similarity calculation. The final resultant experimental findings showcase the superiority of the SMGC-SBERT model over other neural network models, demonstrating significant advancements across both Chinese-SNLI and CCKS2018_Task3 Chinese short text datasets. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Critical Tools for Machine Learning: Working with Intersectional Critical Concepts in Machine Learning Systems design 22

Critical Tools for Machine Learning: Working with Intersecti...

引用

5th ACM Conference on Fairness, Accountability, and Transparency, FAccT 2022

作者： Klumbyte, Goda Draude, Claude Taylor, Alex S. Faculty of Electrical Engineering and Computer Science University of Kassel Germany Centre for Human-Computer Interaction Design City University of London United Kingdom

ISBN: (纸本)9781450393522

This paper investigates how intersectional critical theoretical concepts from social sciences and humanities research can be worked with in machine learning systems design. It does so by presenting a case study of a series of speculative design workshops, conducted in 2021. These workshops drew on intersectional feminist methodologies to construct interdisciplinary interventions in the design of machine learning systems, towards more inclusive, accountable, and contextualized systems design. The concepts of "situating/situated knowledges", "figuration", "diffraction", and "critical fabulation/speculation"were taken up as theoretical and methodological tools for concept-led design workshops. This paper presents the design framework of the workshops and highlights tensions and possibilities with regards to interdisciplinary machine learning systems design towards more inclusive, contextualized, and accountable systems. It discusses the role that critical theoretical concepts can play in a design process and shows how such concepts can work as methodological tools that nonetheless require an open-ended experimental space to function. It presents insights and discussion points regarding what it means to work with critical intersectional knowledge that is inextricably connected to its historical and socio-political roots, and how this reframes what it might mean to design fair and accountable systems. © 2022 Owner/Author.

关键词： Systems analysis

来源：评论

学校读者我要写书评

暂无评论

Medical Image Classification Using Thermal Images and Diagnosis of Carcinogen

Medical Image Classification Using Thermal Images and Diagno...

引用

2024 IEEE International Conference on Innovation and Novelty in engineering and Technology, INNOVA 2024

作者： Govinda Rajulu, G. Sharmila, L. Venkatesan, D. Srinivas, K. Krishnaiah, Nallam Kumar, K. Laxman Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Tamil Nadu Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamil Nadu India Dept. of Artificial Intelligence and Machine Learning St. Martin’s Engineering College Hyderabad India St. Martin’s Engineering College Hyderabad India Department of IT St. Martin's Engineering College Dhulapally Telangana Secunderabad India Deptartment of Computer Science and Design St. Martin’s Engineering College Hyderabad India

ISBN: (纸本)9798331505134

Lung and Colon (L&C) tumors are lethal sicknesses that can foster in a few organs all the while and, in specific circumstances, jeopardize human existence. Even though it is highly unlikely that these two types of cancer will develop simultaneously, delaying diagnosis significantly increases the likelihood of metastasis between the organs that are affected. To really treat specific sorts of malignant growth, histological determination is fundamental. In the past, doctors had to go through a long and difficult process to look at thermal images and figure out if a patient had cancer;however, this procedure may now be completed much more quickly thanks to the new technology options. Histological images of L&C tumors were classified using a hybrid Deep Learning (DL) model with an attention mechanism and a multipath network in this study. To zero in on the main attributes and negligence the less significant ones, a consideration component was utilized. In a multipath network, data travels over a number of channels before each channel is converted and the output from all of the branches is combined. The multipath network is similar to grouped convolution when simplified. The five thermal image categories of the LC25000 dataset were utilized. Among these classes were two for colon disease and three for cellular breakdown in the lungs. The proposed model was compared to a number of well-known DL models, such as ResNet-50, VGG-16, and AlexNet. The proposed approach showed the best exhibition concerning exactness (99.2%), particularity (99.12%), responsiveness (99.28%), accuracy (99.12%), and F1 score (99.2%), as indicated by the exploratory discoveries. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for Image-text Matching 30

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhang, Yu Zhang, Jianqiang Song, Gongpeng Lu, Qin Zhao, Shuo Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (纸本)9798331515966

Image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method. © 2024 IEEE.

关键词： cross-modal retrieval feature enhancement image-text matching relationship interaction

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Overview of Gas and Bio-Sensors Enabling Artificial Intelligence in Healthcare

Comprehensive Overview of Gas and Bio-Sensors Enabling Artif...

引用

Artificial Intelligence in Education and Industry 4.0 (IDICAIEI), DMIHER International Conference on

作者： Yashasvi Raut Shiv Nath Chaudhri Department of Computer Science and Engineering Faculty of Engineering and Technology DMIHER (DU) Maharashtra India Department of Computer Science and Design Faculty of Engineering and Technology DMIHER (DU) Maharashtra India

ISBN: (数字)9798331528713

ISBN: (纸本)9798331528720

Gas and biosensors are crucial in the modern healthcare system, enabling non-invasive monitoring and diagnosis of various medical conditions. These sensors are used in various applications, including smart home health monitoring devices and critical care units. Common non-imaging sensor types include gas or VOC sensors, diagnostic ECG sensors, blood glucose sensors, pulse oximeters, blood pressure sensors, body temperature sensors, EEG sensors, accelerometers, and imaging sensors like X-rays, MRIs, CT scans, and ultrasounds. Healthcare-related sensors offer numerous advantages, including diagnosing and treating medical conditions, monitoring vital signs, enabling remote patient monitoring, personalized healthcare, and early detection and prevention. However, issues like data accessibility, privacy, comfort, security, and accuracy must be considered when installing sensors in homes. Efficient data sharing and analysis require devices, sensors, and platforms to communicate effectively. Real-time data processing is essential for prompt diagnosis and intervention. In this article, we have put it briefly: medical sensors are transforming the way we track, identify, and manage adverse health conditions.

关键词： Temperature sensors Image sensors Medical conditions Ultrasonic imaging X-rays Sensors Biosensors Artificial intelligence Intelligent sensors Gas detectors

来源：评论

学校读者我要写书评

暂无评论

SPECTRA: Personalizable Sound Recognition for Deaf and Hard of Hearing Users through Interactive Machine Learning 25

SPECTRA: Personalizable Sound Recognition for Deaf and Hard ...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Goodman, Steven M. McDonnell, Emma J Froehlich, Jon E. Findlater, Leah Human Centered Design and Engineering University of Washington SeattleWA United States Paul G. Allen School of Computer Science & Engineering University of Washington SeattleWA United States

ISBN: (纸本)9798400713941

We introduce SPECTRA, a novel pipeline for personalizable sound recognition designed to understand DHH users' needs when collecting audio data, creating a training dataset, and reasoning about the quality of a model. To evaluate the prototype, we recruited 12 DHH participants who trained personalized models for their homes. We investigated waveforms, spectrograms, interactive clustering, and data annotating to support DHH users throughout this workflow, and we explored the impact of a hands-on training session on their experience and attitudes toward sound recognition tools. Our findings reveal the potential for clustering visualizations and waveforms to enrich users' understanding of audio data and refinement of training datasets, along with data annotations to promote varied data collection. We provide insights into DHH users' experiences and perspectives on personalizing a sound recognition pipeline. Finally, we share design considerations for future interactive systems to support this population. © 2025 Copyright held by the owner/author(s).

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing’s Effect on Video Games Streaming 2

Cloud Computing’s Effect on Video Games Streaming

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Komathi, A. Lenin, J. Asha, S. Suresh, A. Suguna, M. Srinivasan, C. Department of Computer Science Nadar Saraswathi College of Arts and Science College Tamilnadu Theni India Department of ComputerScience and Engineering Alliance College of Engineering and Design Alliance University Karnataka Bengaluru India Department of Information Technology S.A. Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Siddharth Institute of Engineering & Technology Andhra Pradesh Puttur India Tamil Nadu Salem India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350340235

The disruptive power of cloud computing is altering the gaming industry. Real-time gaming is now feasible because to advancements in streaming algorithms, further blurring the lines between the digital and physical worlds. Understanding the potential of Cloud computing to change the gaming industry is the emphasis which investigates the complicated relationship between numerous technologies. By using cutting-edge streaming protocols and techniques like Adaptive Bitrate Streaming (ABS), buffering, caching, and compression, users may have uninterrupted, high-quality gaming experiences. The study's findings herald a new era of interactive entertainment and shed light on the transformative possibilities of these technologies. Asynchronous Bit-Rate (ABR) encoding, buffering, caching algorithms, video compression standards, and streaming protocols are just few of the numerous digital components that work together to provide uninterrupted data transmission. The rapid progress of ABR algorithms has made it possible to dynamically alter video quality to maximize the user experience across a broad variety of network scenarios. Buffering and caching algorithms play crucial roles by proactively managing data flow and storage to avoid disruptions in the streaming experience. © 2023 IEEE.

关键词： Autism buffering algorithms caching methods Cloud Computing Impact Interactive Entertainment Standards for video compression Streaming Algorithms streaming protocols Video Games

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：