检索结果-内蒙古大学图书馆

International Journal of Systematic Innovation 2023年第6期7卷 12-19页

作者： Kumar, R. Senthil Barnwal, Rajesh P. Department of Computer Science with Cognitive Systems Dr. N.G.P. Arts and Science College Coimbatore India Information Technology Group CSIR-Central Mechanical Engineering Research Institute Durgapur India

Object detection plays a vital role in remote-sensing datasets which trains the image or things and helps in classifying the images into their classes. Instance segmentation is the avant-garde technique used for object detection in Deep Learning. There are many instance segmentation models which can produce significant results. Object detection, segmentation, and RGB analysis in images taken from Unmanned Aerial Vehicles (UAV) are difficult with the desired level of performance. Instance segmentation is a powerful method that extracts each object and its location with the predicted label for pixels in the input image. In this paper, a study has been carried out on the implementation of Mask R-CNN for instance segmentation with different optimization algorithms to obtain a more accurate result for UAV images. The training has been carried out with Mask R-CNN for object detection using ResNet50 and ResNet101 as the backbone. After extensive experiments, it has been observed that the optimization algorithm plays a vital role in the overall computational process and can improve the accuracy level with a reduction in the training/validation loss. The experiment has been conducted on publicly available UAV datasets. The paper further presents the results in terms of different performance parameters © 2023, International Journal of Systematic Innovation. All Rights Reserved.

关键词： Deep learning Instance Segmentation Mask R-CNN Optimization algorithm UAV Images

来源：评论

学校读者我要写书评

暂无评论

Objective Sleep Quality Measurement based on Fuzzy Logic and Wearable Device 8

Objective Sleep Quality Measurement based on Fuzzy Logic and...

引用

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Wijaya, Jason A. Andersen, Pauw D. Surantha, Nico Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Department of Electrical Electronic and Communication Engineering Tokyo City University Japan

Sleep is the natural state of relaxation for human being. Sleep quality is an essential yet frequently neglected aspect of sleep in general. Sleep quality is essential because it allows the body to restore itself and prepare for the next day. The standard method for evaluating sleep quality was subjective evaluation. Actigraphy devices, which can measure the sleep cycle, are now widely available. This study developed a method using Fuzzy Logic and an actigraphy device to measure and classify sleep quality. The fuzzy logic method was developed in several stages, which are determining the sleep quality measurement parameters, constructing the fuzzy set for each input variable, and developing the fuzzy rules. To evaluate the proposed fuzzy model, five individuals were invited to participate in the experiment and required to complete the PSQI subjective sleep questionnaire. The evaluation result shows that our proposed Fuzzy model achieves lower error compared to the existing method. © 2023 The Authors. Published by Elsevier B.V.

关键词： actigraphy artificial intelligences fuzzy logic sleep sleep quality

来源：评论

学校读者我要写书评

暂无评论

Diffusion-Based Gray-White Matter Mapping for Quantitative Tractography in Glioma Patients 15th

Diffusion-Based Gray-White Matter Mapping for Quantitative T...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Smolders, Lars Chamberland, Maxime Rutten, Geert-Jan De Baene, Wouter van der Hofstad, Remco Florack, Luc Department of Neurosurgery Elisabeth-Tweesteden Ziekenhuis Tilburg Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands Department of Cognitive Neuropsychology Tilburg University Tilburg Netherlands

ISBN: (纸本)9783031869198

Gliomas are malignant brain tumors whose potential to infiltrate healthy white matter (WM) necessitates a careful approach during surgical treatment. While tractography is clinically widely used in a qualitative manner to visualise WM bundles during surgery planning, quantifying the integrity of such bundles in glioma patients is a difficult challenge. Quantitative measures currently used in group-level studies are biased or heavily dependent on tractography parameters. In most populations, Anatomically Constrained Tractography (ACT) in combination with Spherical-deconvolution Informed Filtering of Tractograms (SIFT) successfully estimates WM connectivity in whole-brain tractograms. However, a critical segmentation step used in ACT typically overestimates the presence of gray matter (GM) in glioma patients due to the properties of glioma tissue on T1-weighted MRI. This leads to an incorrect derivation of the interface between GM and WM, which is used to define a seed and target region of interest (ROI) in ACT. While workarounds exist, we argue that these may bias SIFT by either under- or overestimating fiber reconstructions in and around the tumor. In this work, we present an alternative GM-WM segmentation method based on diffusion-weighted MRI using multi-tissue Constrained Spherical Deconvolution (CSD) and derive GM-WM interfaces from these novel segmentations. We demonstrate that this method results in a more accurate GM-WM interface in and around tumors in three glioma patients, and that the resulting quantitative tractograms better identify WM disconnections induced by surgery. This method represents a step towards quantitative tractography in glioma patients, and towards improved surgical decision-making in clinical practice. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Transplants

来源：评论

学校读者我要写书评

暂无评论

PentaPen: Combining Penalized Models to Identify Important SNPs on Whole-genome Arabidopsis thaliana Data 24

PentaPen: Combining Penalized Models to Identify Important S...

引用

16th International Conference on Bioinformatics and Biomedical Technology, ICBBT 2024

作者： Kohli, Nikita Tomal, Jabed H. Lin, Wenjun Yan, Yan Program of Data Science Thompson Rivers University KamloopsBC Canada Department of Mathematics and Statistics Thompson Rivers University KamloopsBC Canada School of Computer Science and Technology Algoma University BramptonON Canada School of Computer Science University of Guelph GuelphON Canada

ISBN: (纸本)9798400717666

In the rapidly advancing field of genomics, the identification of Single Nucleotide Polymorphisms (SNPs) plays a crucial role in understanding complex phenotypic *** study introduces "PentaPen", an innovative computational workflow which combines the strengths of five penalized models to achieve improved accuracy in SNP *** compare the performance of PentaPen with existing models, highlighting its advantages in solving problems arising from when the number of predictors exceeds the number of *** model comparison, we provide insights into PentaPen's effectiveness in utilizing all SNPs as input, streamlines data pre-processing, and leverages parallel computation, enabling the workflow a considerable stride in SNP ***, a thorough evaluation and comparison of computational complexities signifies competitive edge of the workflow over individual penalized *** future research directions, we propose applications of PentaPen to plant-specific characteristics and suggest further explorations to assess the robustness of its *** summary, this manuscript presents the genomics community with a tool that combines computational efficiency with high-precision SNP detection, making a strong contribution to the field of genomic research. © 2024 Copyright held by the owner/author(s).

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Children to Learn BISINDO Sign Language 6

Mobile Application for Children to Learn BISINDO Sign Langua...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Andreas, Raynaldo Maria, Sarah Satyadhana, Alexander Khrisna Warnars, Harco Leslie Hendric Spits Ramadhan, Arief Muyeba, Maybin K. Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Indonesia Computer Science Bina Nusantara University Jakarta11480 Indonesia Telkom University Bandung40257 Indonesia MIST Consulting ManchesterM410SA United Kingdom

ISBN: (纸本)9798350398496

Sign language is the most commonly used communication medium for people who are deaf and mute. By using body movements, they can convey meaning through visual cues, not vocal cues. This type of language is learned almost exclusively by people who are deaf or dumb and those who interact with them on a daily basis. Most people do not learn it because sign language is not part of basic education, and the lack of need to use it, especially from a young age. Most of the spoken languages in the world usually have sign language variants according to the language of their respective countries. In this study, a mobile application is developed for children to learn Indonesian sign language where the process model is designed using use case diagrams, and the database design is modeled with class diagrams. As for the implementation, the Android Studio software is used for the application, and the MySQLdatabase is for database storage. © 2023 IEEE.

关键词： Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Exploring Recurrent Neural Network Models for Depression Detection Through Facial Expressions: A Systematic Literature Review 6

Exploring Recurrent Neural Network Models for Depression Det...

引用

6th International Conference on computer and Informatics Engineering, IC2IE 2023

作者： Rumahorbo, Brilyan Nathanael Pardamean, Bens Elwirehardja, Gregorius Natanael Bina Nusantara University Binus Graduate Program - Master of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia

ISBN: (纸本)9798350345162

Major Depressive Disorder (MDD) is a prevalent mental disorder, affecting a significant number of individuals, with estimates reaching 300 million cases worldwide. Currently, the diagnosis of this condition relies heavily on subjective assessments based on the experience of medical professionals. Therefore, researchers have turned to deep learning models to explore the detection of depression. The objective of this review is to gather information on detecting depression based on facial expressions in videos using deep learning techniques. Overall, this research found that RNN models achieved 7.22 MAE for AVEC2014. LSTM models produced 4.83 MAE for DAIC-WOZ, while GRU models achieved an accuracy of 89.77% for DAIC-WOZ. Features like Facial Action Units (FAU), eye gaze, and landmarks show great potential and need to be further analyzed to improve results. Analysis can include applying feature engineering techniques. Aggregation methods, such as mean calculation, are recommended as effective approaches for data processing. This Systematic Literature Review found that facial expressions do have relevant patterns related to MDD. © 2023 IEEE.

关键词： deep learning facial expression GRU LSTM major depressive disorder

来源：评论

学校读者我要写书评

暂无评论

3D Facial Reconstruction Applied to Medical Cosmetology 5

3D Facial Reconstruction Applied to Medical Cosmetology

引用

5th IEEE Eurasia Conference on Biomedical Engineering, Healthcare and Sustainability, ECBIOS 2023

作者： Hsieh, Sheng-Hsien Lin, Ming-Yi Chen, Ching-Han National Pingtung University of Science and Technology Program of Artificial Intelligence and Mechatronics Pingtung Taiwan Yuan Ze University Department of Computer Science and Engineering Taoyuan Taiwan National Central University Department of Computer Science and Engineering Taoyuan Taiwan

ISBN: (纸本)9798350320978

We present a high-accuracy 3D facial reconstruction system with the following features: real-time 3D facial reconstruction using exposure synchronization multi-camera, feature alignment to quantify facial differences, a software system based on a naked eye 3D display, and medical records for a 3D face database. The proposed system is novel and practical, and the algorithm and the hardware/software architecture improve the current non-quantitative communication status in medical aesthetics. The system achieves preoperative expectations, real-time recording and feedback during surgery, and postoperative tracking analysis, thus making doctor-patient communication more efficient. The facial data database records personal and quantitative beauty data and its changes, providing accurate medical and aesthetic treatment analysis for individuals. In addition, the collected data of different genders, ages, injection sites, and dosages contribute to the development of more accurate medical materials. With artificial intelligence and cloud architecture, we provide reliable data for medical aesthetics customers, helping them understand their medical aesthetic needs. Doctors also provide stable medical care quality to consumers through cloud data, and medical aesthetic consultants do not need to exaggerate medical effects excessively. They can inform customers of specific differences before and after surgery through precise data and provide visual communication and customer expansion to improve consultation conversion rates. © 2023 IEEE.

关键词： Visual communication

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Threat Detection

Machine Learning for Threat Detection

引用

International Symposium on Networks, computers and Communications (ISNCC)

作者： Dustin Sutanto Febri Fransisca Steven Liem Andry Chowanda Yohan Muliono Zahra Nabila Izdihar Computer Science Department Cyber Security Program School of Computer Science Bina Nusantara Jakarta Indonesia Computer Science Department Computer Science Program School of Computer Science Bina Nusantara Jakarta Indonesia

ISBN: (数字)9798350364910

ISBN: (纸本)9798350364927

These days almost all people in the world use the Internet as the internet is constantly evolving. Cyber attack scale are increased thanks to cybercriminals that have become sophisticated in employing threats. Since the 1980s, Intrusion Detection Systems (IDS) have been developed to defend computer networks against malicious activity and unauthorized access. Companies choose to implement IDS the part of their Cyber Security strategy to protect their data and network from potential threats. in this case, IDS has played a crucial role in detecting abnormal traffic and protecting digital assets. furthermore, a high-accuracy IDS is needed in concern of having false positive feedback from the IDS machine itself that can cause various problems. to accompany the need for high accuracy and trainable IDS machines, we experimented with a hybrid system using machine learning that is combined with traditional IDS machines resulting in higher accuracy and lower error rate. By adjusting the parameter the accuracy improved and could achieve an accuracy of 99.66% of classifying the traffic.

关键词： Support vector machines Accuracy Machine learning algorithms Intrusion detection Telecommunication traffic Forestry Nearest neighbor methods Classification algorithms Random forests Tuning

来源：评论

学校读者我要写书评

暂无评论

Quantitative analysis of sign language translation using artificial neural network model

引用

Procedia computer science 2024年 245卷 998-1009页

作者： Fendy Wijaya Leonardo Dahendra Eko Setyo Purwanto Muhamad Keenan Ario Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Mobile Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Sign language is one of the technique to support communication with deaf and speech impaired people. Nowadays, human needs become more complex, so are the needs of people with those disabilities. Therefore, with the sophistication of modern technology in the field of computer science, it is necessary to have a sign language translation system which is capable to convert human gestures into words or spelling letters in a natural human language, especially Indonesian language and SIBI sign language. This research is conducted to analyze the capabilities of an Artificial Neural Network (ANN) system to translate SIBI sign language into Indonesian language. The analysis is performed quantitatively from the experiment results to gain a descriptive insights for the generated models. By creating two datasets containing alphabets and words in SIBI sign language, two models were generated to predict alphabets and words, respectively. The result shows that ANN model could effectively and efficiently perform a sign language translation with accuracy of alphabet prediction reached 96.15% and words prediction reached 99.45% in duration of prediction without exceeding 0.15 seconds. Regarding to the results, it can be concluded that ANN model quantitatively suitable to be implemented as an Indonesian sign language translator system.

关键词： sign language Artificial Neural Network SIBI prediction quantitative analysis

来源：评论

学校读者我要写书评

暂无评论

The future of virtual reality: Prospect and problems

引用

Procedia computer science 2024年 245卷 355-364页

作者： Andrew Alfonso Lie Owen Tamashi Buntoro Eko Setyo Purwanto Muhamad Keenan Ario Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Mobile Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480

Virtual Reality (VR) is a technology that allows users to interact with a simulated environment created by virtual reality capabilities through the intermediary of computers, simulator tools, and others, providing new experiences and can feel experiences that are not possible in the real world. This research aims to identify and analyze what challenges may occur such as technical, social, and ethical barriers in the development and application of VR technology. Using a mixed methods approach, we collected quantitative data from Kaggle's dataset and conducted in-depth interviews with active VR users. Our findings show that although VR has significant potential in various fields, such as education, healthcare, and entertainment, challenges such as motion sickness, high costs, and limited and engaging content hinder the widespread adoption of VR technology. The study also highlights the importance of improving technologies that need to be implemented such as visual capabilities, motion responsiveness, and audio quality to enhance the user experience when using VR. By overcoming these barriers, VR can maximize its positive impact and become a revolutionary tool in various sectors.

关键词： Virtual Reality immersive experience technical barriers social impact ethical considerations

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：