检索结果-内蒙古大学图书馆

14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024

作者： Patibandla, Tarun Pv, Arun Porwal, Alok IIIT Sri City Computer Science Dept. India IIT Bombay Computer Science Dept. India

ISBN: (纸本)9798331513139

Hyperspectral image (HSI) super-resolution has seen significant advancements with the emergence of diffusion models, demonstrating impressive results in prior works. However, existing approaches often take up cascaded architectures for feature extraction, often suffering from high computational costs, gradient instability, and training difficulties. This paper introduces a novel Efficient Spectral Attention Block (ESAB) that addresses these challenges by leveraging atrous convolutional blocks and channel attention within a multiscale feature extraction strategy. ESAB enables effective spectral feature extraction while maintaining computational efficiency, leading to improved performance. Furthermore, a unique loss function is proposed to enhance spectral fidelity by comparing the spectral slopes of the ground truth and predicted image pixels. Experimental results demonstrate that the proposed approach achieves great performance in super-resolving HSIs, achieving high spectral fidelity with reduced model complexity. © 2024 IEEE.

关键词： Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Coexistence of 802.11 WLAN and 5G Networks using a Multi-Task Learning with Convolutional Neural Network Model 2

Enhancing the Coexistence of 802.11 WLAN and 5G Networks usi...

引用

2nd International Symposium on Information Technology and Digital Innovation, ISITDI 2024

作者： Putra, Dody Ichwana Ekariani, Shelvi Universitas Andalas Dept. of Computer Engineering Padang Indonesia Universitas Andalas Dept. of Mathematics and Data Science Padang Indonesia

ISBN: (纸本)9798350389241

The increasing need for high-speed internet for wireless devices has driven the development of 5G New Radio (NR) technology. The 5G NR operates in various spectrums such as sub-1 GHz, sub-6 GHz, and millimeter wave (mmWave) in the 26-28 GHz range. Conversely, the new standard Wi-Fi 6E operates on the unlicensed band and currently utilizes 2.4 GHz, 5 GHz, and 6 GHz. The coexistence of 5G NR sub-6 GHz and Wi-Fi 6E networks can result in interference and reduced performance for both technologies. To address this challenge, we introduce a Multi-Task Learning (MTL) approach using Convolutional Neural Networks (CNN) to improve the coexistence of 5G and Wi-Fi 6E networks. This proposes identifying and classifying packets transmitted and its modulation over both types of networks. The MTL-CNN model is trained to classify packets based on their type (e.g., 5G or Wi-Fi) and to identify the specific protocol used within each packet. We confirm the accuracy of this method with Wi-Fi and 5G signals produced by the MATLAB waveform simulator and subsequently deploy it on a hardware testbed using SDR. Our experimental results show that this method improves the accuracy of packet identification and classification, thus enhancing the coexistence between 5G and Wi-Fi 6E networks. MTL-CNN potentially leads to more efficient use of the wireless spectrum and improves the overall performance of wireless communication systems. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Malignant Lymphoma Cancer Using Hybrid Optimized Techniques Based on Dense Neural Networks

Diagnosis of Malignant Lymphoma Cancer Using Hybrid Optimize...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Aly, Salah A. Bakhiet, Ali Balat, Mazen Badya University Faculty of Computing & Data Science Giza Egypt Fayoum University Faculty of Science Computer Science Dept. Fayoum Egypt Computer Science Dept. October 6th City Giza Egypt E-Japanese University of Science & Tech. Cs & It Dept. Alexandria Egypt

ISBN: (纸本)9798350367560

Lymphoma diagnosis, particularly distinguishing between subtypes, is critical for effective treatment but remains challenging due to the subtle morphological differences in histopathological images. This study presents a novel hybrid deep learning framework that combines DenseNet201 for feature extraction with a Dense Neural Network (DNN) for classification, optimized using the Harris Hawks Optimization (HHO) algorithm. The model was trained on a dataset of 15,000 biopsy images, spanning three lymphoma subtypes: Chronic Lymphocytic Leukemia (CLL), Follicular Lymphoma (FL), and Mantle Cell Lymphoma (MCL). Our approach achieved a testing accuracy of 99.33%, demonstrating significant improvements in both accuracy and model interpretability. Comprehensive evaluation using precision, recall, F1-score, and ROC-AUC underscores the model's robustness and potential for clinical adoption. This framework offers a scalable solution for improving diagnostic accuracy and efficiency in oncology. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A web-based biometric system for e-voting

A web-based biometric system for e-voting

引用

2024 International Conference on science, Engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Abiodun, Moses Kazeem Adeniyi, Jide Kehinde Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Aremu, Dayo Rueben Samuel, Olabode Adebiyi, Ayodele A Atanda, Oladayo G. Landmark University Dept. of Computer Science Omu-Aran Nigeria Bowen University Dept. of Computer Science Iwo Nigeria University of Ilorin Dept. of Computer Science Ilorin Nigeria

ISBN: (纸本)9798350358155

Voting is an important activity, and it is an inevitable event in our everyday life. Voting has been conducted in various ways some of which are the use of ballot papers or raising of hands and further collating its statistics manually. The election process in Nigeria has a lot of vulnerabilities, ranging from when the users are casting their votes manually to when the votes are being counted by officials. In previous years Nigerian elections has had a lot of controversy concerning its accuracy and *** major reason for this research is to reduce the rate of corruption in voting and further make it easier for citizens of Nigeria to cast their votes. An electronic voting system is proposed that make use of two-level authentication system, the National Identification Number (NiN) and the facial recognition of voters. The system was implemented using technologies like HTML (Hypertext Markup Language), CSS (Cascade Styling Sheet), JS (JavaScript) language used for the client-side and node JS (JavaScript) used on the server-side. Mongo DB was used as the *** results of evaluation of the system are very encouraging, 87.7% of the respondent attest to how the integration of the application and its functionality. There was a positive respond for determining the speed of page transition. 87.7% says the loading time of the web application is very *** on the evaluation of this system and its performance, the e-voting system is therefore recommended to be used in Nigeria for next election. © 2024 IEEE.

关键词： Markup languages

来源：评论

学校读者我要写书评

暂无评论

The Utilization of Google Cloud in the Healthcare Industry 2

The Utilization of Google Cloud in the Healthcare Industry

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Kapse, Rishikesh Gourshettiwar, Palash Faculty of Engineering and Technology Dept. of Artificial Intelligence and Data Science Maharashtra Wardha India Faculty of Engineering and Technology Dept. of Computer Science And Medical Engineering Maharashtra Wardha India

ISBN: (纸本)9798331505745

This essay's primary focus is on Google Cloud's use in healthcare and how it affects data management, teamwork, and cost-effectiveness. With a focus on Google Cloud, which improves the processing, storing, and accessibility of medical data, the study examines the trends, advantages, and persistent challenges that come with the increasing usage of cloud computing technology. These consist of remote patient monitoring, 'artificial intelligence,' and 'machine learning' applications in diagnostics, diagnostics, and personalized medicine. data privacy, security issues, and concerns with the HIPAA incident are among the problems that are discussed along with all the significant elements that could facilitate the cloud migration of healthcare. © 2025 IEEE.

关键词： Theranostics

来源：评论

学校读者我要写书评

暂无评论

Development of An Android-Based Expert System for Malaria Diagnosis

Development of An Android-Based Expert System for Malaria Di...

引用

2024 International Conference on science, Engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adebiyi, Marion Adebiyi, Ayodele Ariyo Victoria Oluwaseyi, Adebayo-Ajayi Abiodun, Moses Kazeem Emmanuel, Abidemi Raphael, Adeyemo Bamidele Ojo Adekunle, Kolawole Osang, Francis B. Landmark University Dept. of Computer Science Omu-Aran Nigeria Bowen University Dept. of Computer Science Iwo Nigeria Federal Polytechnic Dept. of Computer Science Ile-Oluji Nigeria National Open University Dept. Computer Science Abuja Nigeria

ISBN: (纸本)9798350358155

Malaria, a widespread and potentially deadly disease affecting millions annually, underscores the urgent need for early detection to mitigate its impact on individuals and communities. Harnessing the ubiquitous presence of smartphones, an Android-based expert system emerges as a promising solution. This research endeavors to develop such a system using Android Studio, aimed at aiding healthcare professionals in malaria *** Android-based expert system offers a timely and precise diagnosis by leveraging patient-reported symptoms and medical history. Additionally, it furnishes educational materials on malaria prevention and management, bolstering public awareness and proactive measures against the disease. Through rigorous evaluation, this study advocates for the widespread adoption of the malaria expert system, under the supervision of medical practitioners, to expedite diagnosis and streamline healthcare delivery. Future iterations of this research should delve into refining the system's capability to discern the specific type of malaria infection afflicting the user. In conclusion, the creation of an Android-based expert system for malaria detection is a noteworthy advancement in the use of technology to battle a widespread health risk. Embracing this innovative approach stands to enhance early detection efforts and ultimately alleviate the burden of malaria on global health systems and communities. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Small object detection in diverse application landscapes: a survey

引用

Multimedia Tools and Applications 2024年第41期83卷 88645-88680页

作者： Iqra Giri, Kaisar J. Javed, Mohammed Department of Computer Science Islamic University of Science & Technology Pulwama India Computer Vision & Biometrics Lab Dept. of IT Indian Institute of Information Technology Allahabad India

The importance of object detection within computer vision, especially in the context of detecting small objects, has notably increased. This thorough survey extensively examines small object detection across various applications, consolidating and outlining the available methodologies. Traditional papers on small object detection have focused on specific domains. However, this survey paper incorporates insights from a multitude of domains, providing a comprehensive understanding of the versatility and applicability of small object detection techniques. This paper sheds light on the key challenges faced and delves into potential solutions to address the challenges, offering insights into viable solutions to enhance small object detection performance, setting it apart from existing literature. The strategies identified in our survey encompass a spectrum of approaches, categorized as transformer-based, CNN, and traditional methods. Also, this paper collates prevalent datasets relevant to small object detection, simplifying access to these resources. Further, it provides a succinct overview of diverse evaluation metrics used for performance assessment in this field, enhancing understanding of the effectiveness and proficiency of these methods. This survey paper not only consolidates established knowledge but also highlights innovative viewpoints, providing a comprehensive and enlightening compilation that contributes to the advancement of small object detection in the field of computer vision. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Human Factors in Malware Attacks

An Analysis of Human Factors in Malware Attacks

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Alotaibi, Jawza Al Ja'am, Jihad M. Hoda, Mohammed Oryx Universal College in Partnership with Liverpool John Moores University Dept. of Computing and Data Science Doha Qatar Kuwait College of Science and Technology Dept. of computer Science and Engineering Doha Kuwait

ISBN: (纸本)9798350367560

This research study investigates human responses to malware attacks, focusing on attacker motivations, individual reactions, and key factors influencing user vulnerability and resilience. Using a structured survey questionnaire, the study gathered data from 104 participants with diverse demographics across various occupations. The data was analyzed using SPSS statistical software and Python-based machine learning algorithms. The survey included demographic information and responses to cybersecurity-related questions about human behavior and experience. Machine learning techniques identified ten critical factors as significant predictors of vulnerability to malware attacks. The prediction model indicated that 55 out of 104 participants were vulnerable, with higher vulnerability observed among female participants and those in non-IT professions. This study contributes valuable insights into the human factors influencing cybersecurity resilience, providing a foundation for developing effective strategies to mitigate malware attack vulnerability. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Skin Melanoma diagnosis using machine learning and ABCD rule 4

Skin Melanoma diagnosis using machine learning and ABCD rule

引用

4th International Conference of science and Information Technology in Smart Administration, ICSINTESA 2024

作者： Kadeem, Zahra B. Mosa, Qusay O. College of Computer Science and Information Technology Dept. Computer Science Diwaniyah Iraq

ISBN: (纸本)9798350376111

Skin cancer, being the most predominant type of malignant growth, represents more than half of all cancer instances. While melanoma is less common than other skin cancers, it poses the highest risk due to its tendency to metastasize and potentially result in mortality. Nonetheless, early detection significantly increases the chances of curing melanoma. The detection of melanoma poses a considerable challenge, primarily attributed to the minimal interclass variance observed between images of melanoma and non-melanoma, alongside the heightened interclass variance within melanoma images. Hence, it is imperative to formulate a computer-aided Diagnosis (CAD) to identify such lesions and facilitate early disease diagnosis to enhance the probability of patient survival. The proposed methodology consists of a sequence of four distinct phases. The initial stage involves preprocessing, which incorporates the application of filtering and contrast enhancement algorithms such as the Median filter, Dull razor, and Histogram Equalization. The segmentation process proceeds by utilizing Otsu methods in order to detect any anomalies. Subsequently, the following phase involves the extraction of features through GLCM for textural attributes and ABCD base parameters, encompassing asymmetry, border irregularity, color, and diameter. Following this, a model based on artificial neural networks (ANN) is developed by leveraging these extracted traits to discern instances of skin cancer within the provided dataset. This methodology achieves a commendable overall accuracy rate of 99%. Dermatologists may derive significant assistance in their clinical decision-making procedures from this promising breakthrough. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric

Enhancing Argument Summarization: Prioritizing Exhaustivenes...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Khosravani, Mohammad Huang, Chenyang Trabelsi, Amine Dept. of Computer Science Lakehead University Canada Amii Dept. of Computing Science University of Alberta Canada Dept. of Computer Science Université de Sherbrooke Canada

ISBN: (纸本)9798891761148

The proliferation of social media platforms has given rise to the amount of online debates and arguments. Consequently, the need for automatic summarization methods for such debates is imperative, however this area of summarization is rather understudied. The Key Point Analysis (KPA) task formulates argument summarization as representing the summary of a large collection of arguments in the form of concise sentences in bullet-style format, called key points. A sub-task of KPA, called Key Point Generation (KPG), focuses on generating these key points given the arguments. This paper introduces a novel extractive approach for key point generation, that outperforms previous state-of-the-art methods for the task. Our method utilizes an extractive clustering based approach that offers concise, high quality generated key points with higher coverage of reference summaries, and less redundant outputs. In addition, we show that the existing evaluation metrics for summarization such as ROUGE are incapable of differentiating between generated key points of different qualities. To this end, we propose a new evaluation metric for assessing the generated key points by their coverage. Our code can be accessed online. © 2024 Association for Computational Linguistics.

关键词： Quality control

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：