检索结果-内蒙古大学图书馆

9th IEEE International Conference on Computing, engineering and Design, ICCED 2023

作者： Fariza, Arna Asmara, Rengga Rojaby, Muhammad Oktavian Fajar Astuti, Eha Renwi Putra, Ramadhan Hardani Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia Universitas Airlangga Department of Dentistry Surabaya Indonesia

ISBN: (纸本)9798350370126

Accurate tooth numbering is essential for dental procedures, treatment planning, and patient record management. Automatic tooth enumeration in dental panoramic radiographs is crucial in modern dental image analysis and diagnosis. Tooth enumeration in panoramic radiographs has relied on handcrafted features and traditional image processing techniques. Still, these methods often lack the accuracy and robustness required for complex cases and varied image qualities. Despite the advancements in deep learning-based object detection algorithms, a significant research gap remains in the specific domain of automatic tooth enumeration on panoramic radiographs. This research paper presents an innovative approach for automatic tooth enumeration on panoramic radiographs using the state-of-the-art You Only Look Once (YOLO) object detection framework focused on implementing the YOLOv5 library. The YOLOv5 model is evaluated as an efficient system capable of accurately detecting and enumerating individual teeth from panoramic radiographs. The 612 panoramic radiograph images evaluation shows the bounding-box results show the best tooth detection rate in the YOLOv5x model. The YOLOv5 model is generally very good at predicting tooth enumeration on panoramic radiographs in a relatively small dataset. This advancement is expected to enhance dental diagnosis and treatment planning, benefiting dental professionals and patients. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Sentiment Polarity Analysis of Bangla Food Reviews Using Machine and Deep Learning Algorithms 3

Sentiment Polarity Analysis of Bangla Food Reviews Using Mac...

引用

3rd International Conference on Advancement in Electrical and Electronic engineering, ICAEEE 2024

作者： Amin, Al Sarkar, Anik Islam, Md Mahamodul Miazee, Asif Ahammad Islam, Md Robiul Hoque, Md Mahmudul Uttara University Department of Computer Science and Engineering Dhaka Bangladesh National Institute of Technology Silchar India University of Oslo Department of Informatics Oslo Norway Maharishi International University Department of Computer Science Iowa United States CCN University of Science & Technology Department of Computer Science and Engineering Comilla Bangladesh

ISBN: (纸本)9798350388282

The Internet has become an essential tool for people in the modern world. Humans, like all living organisms, have essential requirements for survival. These include access to atmospheric oxygen, potable water, protective shelter, and sustenance. The constant flux of the world is making our existence less complicated. A significant portion of the population utilizes online food ordering services to have meals delivered to their residences. Although there are numerous methods for ordering food, customers sometimes experience disappointment with the food they receive. Our endeavor was to establish a model that could determine if food is of good or poor quality. We compiled an extensive dataset of over 1484 online reviews from prominent food ordering platforms, including Food Panda and HungryNaki. Leveraging the collected data, a rigorous assessment of various deep learning and machine learning techniques was performed to determine the most accurate approach for predicting food quality. Out of all the algorithms evaluated, logistic regression emerged as the most accurate, achieving an impressive 90.91% accuracy. The review offers valuable insights that will guide the user in deciding whether or not to order the food. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Job Resumes Recommendation using Integration of Fuzzy Discernibility Matrix Feature Selection and Convolutional Neural Network Multi-label Text Classification

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第13期49卷 49-58页

作者： Hayami, Regiolina Yusoff, Nooraini Daud, Kauthar Mohd Fatma, Yulia Department of Informatics Engineering Faculty Computer Science Universitas Muhammadiyah Riau Indonesia Faculty of Data Science and Computing Universiti Malaysia Kelantan 16100 Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and Technology Universiti Kebangsaan Malaysia 43600 Malaysia

The manual analysis of job resumes poses specific challenges, including the time-intensive process and the high likelihood of human error, emphasizing the need for automation in content-based recommendations. Recent advancements in deep learning, particularly Convolutional Neural Networks (CNN) for Multi-label Text Classification (MLTC), offer a promising solution for addressing these challenges through artificial intelligence. While CNN is renowned for its robust feature extraction capabilities, it faces specific challenges such as managing high-dimensional data and poor data interpretability. To address these limitations, this study employs the Fuzzy Discernibility Matrix (FDM) feature selection technique to determine the relevance of skills for each job vacancy. FDM assigns weights to the features of each job category and ranks their relevance based on the highest scores, which are then utilized in the MLTC CNN model. The integration of FDM and MLTC CNN serves as the foundation for generating content-based recommendations derived from key features in job resumes. This study produces a content-based job recommendation system that displays the top three job categories, accompanied by explanations of the skills supporting each selected category. These recommendations also consider cosine similarity values between analyzed items and the integrated results of FDM and MLTC CNN. The application of FDM for feature weighting has been proven to enhance multi-label text classification outcomes by providing better insights during the feature selection process. With a recall of 97.26%, precision of 94.81%, and accuracy of 98.58%, the MLTC model integrating FDM feature selection and CNN demonstrates robust performance characteristics in content-based job recommendation tasks. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Facial Palsy Detection Through Changes in Facial Muscle Functionality Using CNN Algorithm 6

Facial Palsy Detection Through Changes in Facial Muscle Func...

引用

6th International Conference on computer and informatics engineering, IC2IE 2023

作者： Sari, Chindy Aulia Bachtiar, Fitra Abdurrachman Muflikhah, Lailil Widayati, Aris University of Brawijaya Faculty of Computer Science Informatics Engineering Department Malang Indonesia University of Brawijaya Faculty of Medicine Malang Indonesia

ISBN: (纸本)9798350345162

Facial palsy is a common condition in the medical field that results from facial nerve disorders, leading to weakened facial motor functions. Detecting facial palsy typically involves observing the functional ability of facial muscles, a process currently performed manually by healthcare professionals relying on visual cues. However, manual detection is prone to errors, this needs for early and automated facial palsy detection. Overall, our research aims to improve the detection of facial palsy by leveraging deep learning techniques. By automating the detection process, we hope to provide a more accurate and efficient approach for early identification of this condition. In this research, we aim to develop a facial palsy detection system using the Convolutional Neural Network (CNN) algorithm. We utilize three datasets, namely CK+, JAFFE, and YouTube Facial Palsy, which are organized into normal and dysfunctional classes. The dataset is divided into training and testing data in an 80:20 ratio, and preprocessing techniques such as image resizing and grayscale conversion are applied. To find the optimal parameters for our model, we employ k-fold cross validation during the training process. The evaluation results show that the best model achieved optimal performance with the following parameters: 3 hidden layers, a fully connected layer (fc)-1 with a hidden size of 128, fc-2 with a hidden size of 16, and fc-3 with a hidden size of 32. The optimizer used was Adam, with a learning rate of 0.001, a batch size of 64, and trained for 10 epochs. This best model attained an average training accuracy of 0.958, testing accuracy of 1, recall of 1, and precision of 0.99. © 2023 IEEE.

关键词： CNN deep learning face detection facial palsy

来源：评论

学校读者我要写书评

暂无评论

SGCL-LncLoc:An Interpretable Deep Learning Model for Improving IncRNA Subcellular Localization Prediction with Supervised Graph Contrastive Learning

引用

Big Data Mining and Analytics 2024年第3期7卷 765-780页

作者： Min Li Baoying Zhao Yiming Li Pingjian Ding Rui Yin Shichao Kan Min Zeng School of Computer Science and Engineering Central South UniversityChangsha 410083China Center for Artificial Intelligence in Drug Discovery Case Western Reserve UniversityClevelandOH 44106USA Department of Health Outcomes and Biomedical Informatics University of FloridaGainesvilleFL 32603USA

Understanding the subcellular localization of long non-coding RNAs(IncRNAs)is crucial for unraveling their functional *** previous computational methods have made progress in predicting IncRNA subcellular localization,most of them ignore the sequence order information by relying on k-mer frequency features to encode IncRNA *** the study,we develope SGCL-LncLoc,a novel interpretable deep learning model based on supervised graph contrastive ***-LncLoc transforms IncRNA sequences into de Bruijn graphs and uses the Word2Vec technique to learn the node representation of the ***,SGCL-LncLoc applies graph convolutional networks to learn the comprehensive graph ***,we propose a computational method to map the attention weights of the graph nodes to the weights of nucleotides in the IncRNA sequence,allowing SGCL-LncLoc to serve as an interpretable deep learning ***,SGCL-LncLoc employs a supervised contrastive learning strategy,which leverages the relationships between different samples and label information,guiding the model to enhance representation learning for *** experimental results demonstrate that SGCL-LncLoc outperforms both deep learning baseline models and existing predictors,showing its capability for accurate IncRNA subcellular localization ***,we conduct a motif analysis,revealing that SGCL-LncLoc successfully captures known motifs associated with IncRNA subcellular *** SGCL-LncLoc web server is available at http://***:8000/*** source code can be obtained from https://***/CSUBioGroup/SGCL-LncLoc.

关键词： supervised contrastive learning long non-coding RNA(IncRNA) subcellular localization prediction deep learning Graph Convolutional Network(GCN)

来源：评论

学校读者我要写书评

暂无评论

Compiler-based Web Services code conversion model for different languages of mobile application 1

Compiler-based Web Services code conversion model for differ...

引用

1st International Conference of Intelligent Methods, Systems and Applications, IMSA 2023

作者： Mahmoud, Amira T. Muhammad, Ahmad A. Yousef, Ahmed H. Medhat, Walaa Zayed, Hala H. Selim, Sahar Nile University School of Information Technology and Computer Science Giza Egypt Egypt University of Informatics School of Engineering Cairo Egypt

ISBN: (纸本)9798350335569

Mobile applications are very popular nowadays. The two most common platforms depend on different languages to have native performance. Most trans-compiler-based converters between those languages didn't take webservices conversion into consideration. However, in recent years, mobile applications developers have used web services for lighter and more dynamic mobile applications. Therefore, it becomes crucial to include web services mapping to the trans-compiler-based code converters for mobile applications code. In this paper, we present a model for web service trans-compiler code mapper from swift for iOS to java for Android to be integrated to previous trans-pilers. The testing for the conversion accuracy is done for six different web services functions. The average accuracy of converting webservice calling from iOS to Android is 89.3%. In addition, due to the rise of generative language models and their capability to generate code, we compare OpenAI's chatGPT to our tool, evaluating its capabilities for code translation and exploring the potential of prompt engineering for seamless integration into our trans-compiler tool. © 2023 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence and Seeing The Invisible in Arts - From the Wane of axiality and Symmetry To the Wax of Invisibility and Emptiness

Artificial Intelligence and Seeing The Invisible in Arts - F...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Abdel Latif, Rasha Said Abou El-Seoud, M. Samir Dewidar, Khaled Mohamed Faculty of Energy and Environmental Engineering El-Sherouk City Cairo Egypt Faculty of Informatics and Computer Science El-Sherouk City Cairo Egypt Faculty Engineering El-Sherouk City Cairo Egypt

ISBN: (纸本)9798350367560

Function has been always an important driver in architectural design. It is the request to generate form directly from purpose and utility. In 1896, Louis Sullivan projected that 'form follows function' and that the beauty of a building derives directly from its function and not from references of the built heritage. The assumption was that beauty would naturally derive from design once functional requirements are met. Thus, fitness for purpose equals beauty. In 1908, Adolf Loos even went so far as to ask for the total abandonment of decoration. In 1947, Mies van der Rohe made his paradigm shift, function is the main language for design in Europe, creating a new built environment. However, with the advent of machine learning systems, and as seen in our deep learning approach, form indeed can literally follow function. In this paper, we presented a new design approach where we can interpret the unseen in visualizing the future. This can decompose the final design to its essentials to finally generate a conceptual new futuristic design. Using multiple types of tools, we showed how to merge art, sculpture and architecture in a principled manner to yield new compositions and how to generate interesting design variations thus reaching novel conceptual designs. Architecture is a complex spatial organization field, and one must consider it in its totality. There are not only functional considerations but also aesthetical and structural ones. Artificial intelligence is an exciting field of investigation that not only has the potential to fill the gap of computational resources for the conceptual design phases of architectural projects but also the capacity to address the wider needs of the profession for futuristic designs. It answers the ideas of the volume of space, and how space be visualized and built. Finally, architecture does not only deal with functional perfection but also need to respond to immaterial and contextual conditions and inevitably responding to aestheti

关键词： Conceptual design

来源：评论

学校读者我要写书评

暂无评论

Android and Desktop Based Ground Control Station (GCS) Interface Design for Unmanned Aerial Vehicle (UAV) Communication and Monitoring 24

Android and Desktop Based Ground Control Station (GCS) Inter...

引用

24th International Electronics Symposium, IES 2022

作者： Putra, Hafizh Irfansyah Bachtiar, Mochamad Mobed Ruswiansari, Maretha Politeknik Elektronika Negeri Surabaya Department of Informatics and Computer Engineering Surabaya Indonesia

ISBN: (数字)9781665489713

ISBN: (纸本)9781665489713

The Indonesian Flying Robot Contest (KRTI) is a competition organized by the National Achievement Center of the Indonesian Ministry of Education, Culture, Research, and Technology. One of the KRTI categories, Technology Development, competes with the work of Unmanned Aerial Vehicle (UAV) technology in the field of Ground Control Station (GCS). GCS serves to communicate and monitor the condition of the UAV in the air. Generally, GCS is only available in applications designed specifically for certain brands of UAVs, resulting in GCS not being able to be used for other types of UAVs. UAVs can experience wind disturbances as well as urgency due to depleted battery capacity. Based on the problems that have been outlined, in this research, a solution was created to design the interface of an Android and Windows-based GCS application for the communication and monitoring of UAVs. The built GCS provides an alternative communication medium with Radio Telemetry for long-distance coverage and Wi-Fi for short-range coverage. The constructed GCS analyzes the roll value movement of the IMU sensor with the linear regression method to inform the UAV stability condition and analyzes the data of GPS sensors, altitude sensors, and UAV battery capacity sensors with the fuzzy inference system method to inform the urgency of the UAV return time. GCS meets real-time needs running on the lowest versions of Windows 10 and Android 5.0 (Lollipop) with an average data runtime of 3.427 milliseconds for Windows and 16.724 milliseconds for Android. The usability of the GCS design is rated Excellent with an effectiveness rate of 84%. Round-Trip-Time USB UART communication media of 13.518 milliseconds at the test limit distance of 100 meters and Wi-Fi UDP Relay of 3.125 milliseconds at an optimal distance of 25 meters. © 2022 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Development of Algorithms for Mining Processes to Identify Abnormal Situations in the Operation of High-tech Equipment

Development of Algorithms for Mining Processes to Identify A...

引用

2022 Conference of Russian Young Researchers in Electrical and Electronic engineering, ElConRus 2022

作者： Khasanova, Adelya M. National Research Nuclear University Informatics and Computer Engineering MEPhI Moscow Russia

ISBN: (纸本)9781665409933

In the modern world, almost every large enterprises uses IT infrastructure to organize its activities. Companies are constantly face threats to the security of their infrastructure, so the task of detecting and eliminating various anomalous events (including security threats) in the activities of technological platforms is extremely urgent. Any incidents with such systems, including service interruptions and reduced quality of service, will lead to the failure of individual applications and, accordingly, to significant financial costs. In addition, malfunctions of digital equipment can lead to industrial accidents. An efficient approach to detect malfunctions and / or attacks on information resources of computer systems is the intelligent analysis of system event *** purpose of this work is to study and implement various technologies for intelligent analysis of processes (Process Mining) of high-tech digital equipment, using event logs, in order to detect abnormal or harmful events in the system serving this equipment. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A hybrid deep learning approach for phenotype prediction from clinical notes

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第4期14卷 4503-4513页

作者： Khalafi, Sahar Ghadiri, Nasser Moradi, Milad Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan84156-83111 Iran Institute for Artificial Intelligence Center for Medical Statistics Informatics and Intelligent Systems Medical University of Vienna Vienna Austria

Identifying patient cohorts from clinical notes in secondary use of electronic health records is a fundamental task in clinical information management. The patient cohort identification process requires identifying the patient phenotypes. However, the growing number of clinical notes makes it difficult to analyze the data manually. Therefore, automatically extracting clinical concepts is crucial to identify patient phenotypes correctly. This paper’s proposed hybrid model is based on a neural bidirectional sequence model (BiLSTM or BiGRU) and a Convolutional Neural Network (CNN) for identifying patients’ phenotypes in clinical notes. Furthermore, an extra CNN layer is run parallel to the hybrid proposed model to extract more features related to each phenotype. We used pre-trained embeddings such as FastText and Word2vec separately as the input layers to evaluate other embedding’s performance in identifying patient phenotypes. We also measured the effect of adding additional data cleaning steps on discharge reports to identify patient phenotypes using deep learning models. Results demonstrated the proposed hybrid model extracts more features than existing methods of patient phenotype extraction and provides a better F1-score. We show that complementing the proposed hybrid model with an extra CNN in identifying different phenotypes improves the F1 scores. In addition, eliminating punctuation, numbers, and stop words in discharge reports before training hybrid models increased model performance. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Embeddings

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：