检索结果-内蒙古大学图书馆

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

Density of Ham- and Lee- non-isometric k-ary Words 24

Density of Ham- and Lee- non-isometric k-ary Words

引用

24th Italian Conference on Theoretical computer science, ICTCS 2023

作者： Anselmo, Marcella Flores, Manuela Madonia, Maria Dept.of Computer Science University of Salerno Italy Dept. of Mathematics and Computer Science University of Palermo Italy Dept.of Mathematics and Computer Science University of Catania Italy

Isometric k-ary words have been defined referring to the Hamming and the Lee distances. A word is non-isometric if and only if it has a prefix at distance 2 from the suffix of same length;such a prefix is called 2-error overlap. The limit density of isometric binary words based on the Hamming distance has been evaluated by Klavžar and Shpectorov, obtaining that about 8% of all binary words are isometric. In this paper, the issue is addressed for k-ary words and referring to the Hamming and the Lee distances. Actually, the only meaningful case of Lee-isometric k-ary words is when k = 4. It is proved that, when the length of words increases, the limit density of quaternary Ham-isometric words is around 17%, while the limit density of quaternary Lee-isometric words is even bigger, it is about 30%. The results are obtained using combinatorial methods and algorithms for counting the number of k-ary isometric words. © 2023 CEUR-WS. All rights reserved.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Distributed Scheduler for Computing on the Edge 1

A Dynamic Distributed Scheduler for Computing on the Edge

引用

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

作者： Hu, Fei Mehta, Kunal Mishra, Shivakant Almutawa, Mohammad University of Colorado Dept. of Computer Science United States Kuwait University Dept. of Computer Science Kuwait

ISBN: (纸本)9798350349658

Edge computing is crucial for IoT applications, especially those needing quick, private data handling. However, these applications are resource-intensive, and edge computing resources are limited compared to cloud capabilities. Efficiently using these limited resources is essential to meet all application demands, including latency, privacy, and cost. Due to the dynamic and hybrid nature of IoT environments, static scheduling systems often falls short in meeting these diverse constraints. This paper describes the design, implementation, and evaluation of a dynamic distributed scheduler for the edge. This scheduler schedules the execution of various computing tasks across all computing resources available at the edge in order to satisfy the diverse constraints of an IoT application. The key characteristic of this scheduler is that it constantly monitors the current state of the IoT infrastructure and dynamically adjusts the scheduling of various computing tasks based on the current environmental context as well as the current computing and network conditions. The scheduler utilizes a predictive profiling method to manage the hybrid and variable nature of edge computing resources and tasks. A prototype of this scheduler has been implemented and the paper demonstrates its practicality via an augmented reality application. © 2024 IEEE.

关键词： Augmented Reality Applications De-vice Profile Dynamic Distributed Scheduler Edge Computing Parallel Com-puting

来源：评论

学校读者我要写书评

暂无评论

Efficient Spectral Attention Block for Cascaded Hyperspectral Image Super-Resolution Architectures 14

Efficient Spectral Attention Block for Cascaded Hyperspectra...

引用

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

IoT IN EDUCATION - PHOTOVOLTAIC PANEL SYSTEMS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2024年第1期86卷 329-342页

作者： Oprea, Marin Mocanu, Mariana The National University of Science and Technology POLITEHNICA Bucharest Romania Dept. of Computer Science The National University of Science and Technology POLITEHNICA Bucharest Romania

In this paper we presented a synthesis of the design, construction and implementation activities, at the school level, of an intelligent system for transforming solar energy into electricity based on photovoltaic panels, with the possibility of real-time monitoring, via Internet, of its functional parameters: voltage (U), current (I), power (P) and electrical energy (W) produced. Since the purpose of the project was educational, we started the activities with the design and realization of a didactic solar panel, composed of polycrystalline solar cells. To determine its functional parameters, we used an experimental method different from the classical method (based on measurements made with multimeters). This new method was based on the INA219 current-voltage sensor connected to an Arduino Uno board and allowed real-time representation of the I-U and P-U characteristics of the panel using the Excel add-in Data Streamer. The technical parameters of the panel were studied in different lighting conditions (artificial light and natural light). After the realization and functional testing of this didactic panel, we included in the scope of the experimental activities some solar panels of commercial origin, of low and medium power. These activities prepared the framework for the realization of an IoT monitored photovoltaic system. The functional parameters of the panel were monitored through the open source IoT platform-ThingSpeak. The remote control of the consumers was realized both via Bluetooth and WiFi connection. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Solar panels

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

Continual Pre-Training of Python Language Model to mT5

Computer Software

引用

computer Software 2023年第4期40卷 10-21页

作者： Kajiura, Teruno Souma, Nao Sato, Miyu Kuramitsu, Kimio Dept. of Mathematical and Physical Sciences Graduate School of Science Japan Women’s University Japan Dept. of Mathematics Physics and Computer Science Faculty of Science Japan Women’s University Japan

Recently, Transformer-based pre-trained language models have achieved great success in natural language processing methods. As a result, there is a growing interest in software development and programming to apply pre-trained language models to a large amount of programming code. For example, CodeT5, which is T5 pre-trained with programming code, has shown significant performance improvements in various software development tasks such as code generation, code summarization, and code classification. However, building these models requires a huge amount of computing resources and time, and not everyone can do it. We propose a method of continuted pretraining to multilingual T5 for adapting python. This study reports that the proposed method shows improved performance results in tasks such as code generation and error diagnosis. © 2023 Japan Society for Software science and Technology. All rights reserved.

关键词： Python

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

Improving Chinese-Vietnamese Prototype Neural Machine Translation with Irrelevant Word Detection Denoising 7

Improving Chinese-Vietnamese Prototype Neural Machine Transl...

引用

7th International Conference on Machine Learning and Natural Language Processing, MLNLP 2024

作者： Wang, Ting Yu, Zhiqiang Yu, Wenjie Sun, Wenzhuang Yunnan Minzu University Dept. School of Mathematics and Computer Science Kunming China

ISBN: (纸本)9798350354973

The prototype method is an effective approach to enhancing the performance of neural machine translation. However, incorporating prototype sequences may inadvertently introduce noise, especially in low-resource scenarios such as Chinese-Vietnamese translation. To address the problem, this paper proposes a translation method that leverages denoising prototype sequences. Firstly, the target-side prototype sequences are retrieved across languages;Secondly, irrelevant words in the prototype sequences are detected, and the noise information is marked to reduce noise interference;Finally, an additional encoder is introduced to process the prototype sequences. Experimental results conclusively demonstrate that the proposed model achieves significantly improved performance compared to the baselines. © 2024 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Privacy Through Time Aggregation of Load Profiles in Energy Management 8

Enhancing Privacy Through Time Aggregation of Load Profiles ...

引用

8th IEEE International Energy Conference, ENERGYCON 2024

作者： Varenhorst, Ivo A.M. Hoogsteen, Gerwin Gerards, Marco E.T. Hurink, Johann L. dept. of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands

ISBN: (纸本)9798350382150

Demand side management (DSM) applications rely on the exchange of load profiles to effectively manage the operation of energy systems. However, sharing detailed energy profile data raises substantial privacy concerns, such as potential misuse of personal information. To mitigate these concerns, we investigate the potential of time aggregation (TA), which involves merging multiple samples of a profile into a single value representing multiple intervals. TA reduces data exchange and computational requirements in energy management and helps preserve user privacy by reducing granularity of user data. We show that, for an effective implementation of TA in energy management, it is important to make the right choice of TA method. We compare and evaluate seven different TA methods. Furthermore, we perform TA across various time frames using an optimization based DSM approach. Our findings reveal that if we aggregate load profiles from 15 minutes to 4 hours, we obtain both enhanced privacy and a 21% decrease in the required number of iterations with the investigated DSM method, albeit at the cost of a 15% decrease in objective value performance. Based on this, we conclude that depending on the application needs, TA with a carefully selected aggregation method has the potential to bring value to energy management, even when aggregating to a considerable extent. ©2024 IEEE.

关键词： Energy management

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：