检索结果-内蒙古大学图书馆

A Bayesian-based approach for extracting the pion charge radius from electron-electron scattering data

Chinese Physics C 2021年第8期45卷 12-27页

作者： Alam A Hidayat Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara UniversityJakarta 11480Indonesia Computer Science Department BINUS Graduate Program-Master of Computer ScienceBina Nusantara UniversityJakarta 11480Indonesia

In this study,we utilize a potentially versatile Bayesian parameter approach to compute the value of the pion charge radius and quantify its uncertainty from several experimental e^(+)e^(-) datasets for the pion vector form *** employ dispersion relations to model the pion vector form factor to extract the *** model selection is used to determine the order of polynomial appearing in the form factor formulation that can be supported by the data,adapting the computation of Bayes evidence and Bayesian effective complexity based on Occam's *** findings indicate that five out of six used datasets favor the nine-parameter model for radius extraction,and accordingly,we average the radii from the *** some inconsistencies with the most updated radius values,our approach may serve as a more intuitive method of addressing parameter estimations in dispersion theory.

关键词： Bayesian complexity dispersion hadron pion

来源：评论

学校读者我要写书评

暂无评论

The Utilization of DistilBERT Features Space for Topics Suggestion in the Context of Learning Content

The Utilization of DistilBERT Features Space for Topics Sugg...

引用

Artificial Intelligence and Image Processing (IWAIIP), International Workshop on

作者： Kenny Jingga Hidayaturrahman Hidayaturrahman Computer Science Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Recommender system is one of the popular topics in artificial intelligence fields as it can widely be used in the *** service provider, e-commerce, e-learning, and many other fields can utilize recommender system to give the personalization for the users. This research will try to use recommender system to provide the recommended topics that are suitable to each learning content. As part of developing the most suitable recommender system, this research will also focus on the data pre-processing,as the data is still raw and contains too much unused information yet. Text vectorization or the embedding process was conducted to the dataset using DistilBERT, pre-trained BERT model. After the vectorization, the recommender system used cosine similarity from the result to discover the largest cosine similarity, which was used to determine the recommendation. Based on the experiment, using cosine similarity could do the recommendation well enough by giving the appropriate topics recommendation based on the content. For example, given the content: “Chapter 2: Comments Chapter 2 of the book on C programming”, the top 5 recommended topics were: “Objective-C”, “C++”, “MATLAB”,”VBA”, and “Perl”. Based on the results, it can be considered that the recommender system had performed as expected. However,it still had a lot of areas that could be improved for the future research, especially in the data preprocessing. Other text vectorization models can be considered to be used, such as: BERT Multilingual, RoBERTa, and SpanBERT. Other consideration is the content preparation that will be used as the input for the system. Combination of DistilBERT and cosine similarity as the recommender system can be considered to be implemented for other areas.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding the limits of vision language models through the lens of the binding problem 24

Understanding the limits of vision language models through t...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Declan Campbell Sunayana Rane Tyler Giallanza Nicolò De Sabbata Kia Ghods Amogh Joshi Alexander Ku Steven M. Frankland Thomas L. Griffiths Jonathan D. Cohen Taylor Webb Princeton Neuroscience Institute Department of Psychology Princeton University Department of Computer Science EPFL Department of Cognitive Science Dartmouth College Department of Psychology and Department of Computer Science Princeton University Princeton Neuroscience Institute and Department of Psychology Princeton University Microsoft Research

ISBN: (纸本)9798331314385

Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models are able to describe and generate a diverse array of complex, naturalistic images, yet they exhibit surprising failures on basic multi-object reasoning tasks - such as counting, localization, and simple forms of visual analogy - that humans perform with near perfect accuracy. To better understand this puzzling pattern of successes and failures, we turn to theoretical accounts of the binding problem in cognitive science and neuroscience, a fundamental problem that arises when a shared set of representational resources must be used to represent distinct entities (e.g., to represent multiple objects in an image), necessitating the use of serial processing to avoid interference. We find that many of the puzzling failures of state-of-the-art VLMs can be explained as arising due to the binding problem, and that these failure modes are strikingly similar to the limitations exhibited by rapid, feedforward processing in the human brain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Racial Bias in Pain Detection with a computer Vision Model 44

Exploring the Racial Bias in Pain Detection with a Computer ...

引用

44th Annual Meeting of the cognitive science Society: cognitive Diversity, CogSci 2022

作者： Fabi, Sarah Xu, Xiaojing de Sa, Virginia R. Department of Cognitive Science Halicioglu Data Science Institute University of California San Diego United States Neuro-Cognitive Modeling Group University of Tübingen Germany Department of Electrical and Computer Engineering University of California San Diego United States

People detect painful expressions more easily in members of their racial ingroup than outgroup. Here, we wanted to investigate this racial bias with a machine learning model trained to detect activations of different action units of painful facial expressions. We examined whether the model detected higher action unit activation for European than African faces when trained on datasets with mostly White faces. To control for confounding variables, pictures of faces were generated with the FaceGen Modeller. Results revealed that there exist differences in the visual detectability of some facial muscle activations due to skin color or other race-dependent facial features. Despite the bias towards European looking faces in the training data, some activations were more easily detectable in African faces. Thus, neither the perceptual detectability, nor the larger exposure to own-race faces seems to solely explain the racial bias in pain detection. © 2022 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Tree Counting with Deep Forest Algorithm for Kulon Progo District in Yogyakarta, Indonesia Using Pleiades Satellite Imagery

Tree Counting with Deep Forest Algorithm for Kulon Progo Dis...

引用

ICT Conference (AICTC), Arab

作者： David Wijaya Ibrahim Seto Aditama Stanley Armando Austen Calvin Surya Widjaja Bakti Amirul Jabar Edy Irwansyah Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Tangerang Selatan Indonesia Computer Science Department School of Computer Science Bina Nusantara University Bandung Indonesia BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350342086

ISBN: (纸本)9798350342093

Trees are one of the most important living things on the planet. Trees help by being one of the largest producers' oxygens on planet, by absorbing groundwater and by maintaining soil fertility. Trees can also be one of the keys to reducing existing air pollution. Therefore, the number of existing trees must be maintained. The first step in maintaining the number of existing trees is to count or map them. One of the easiest ways is to do this use an algorithm. This study uses a tree-counting algorithm called Deep Forest. Deep Forest is a Python package that can detect trees through RGB satellite imagery. This study used satellite imagery from Pleiades on an area in Kulon Progo district, Yogyakarta, Indonesia for the image-one of the four regencies within Yogyakarta Province in Indonesia. In addition to the Deep Forest algorithm, this research also used an application provided by Esri called ArcGIS Pro. With this application, data preprocessing such as labeling the data and creating the deep learning dataset for research is much easier, while ArcGIS Pro provides tools for labeling and exporting the data to jupyter notebook. The result obtained using the Deep Forest algorithm is the F1 score with an accuracy of 0.76 for the first experiment, 0.774 for the second experiment, and 0.779 for the final experiment.

关键词： Deep learning Training Codes Planets Vegetation Soil Regression analysis Satellite images Labeling Random forests

来源：评论

学校读者我要写书评

暂无评论

Enhancing Student Dropout Prediction Using Chi-Square, SMOTE-ENN, and Hyperparameter Tuning of Random Forest

Enhancing Student Dropout Prediction Using Chi-Square, SMOTE...

引用

International Conference on Informatics and Computing (ICIC)

作者： Andri Roni Yunis Djoni Ng Poi Wong Robin Darwin Program of Computer Science Department Universitas Mikroskil Medan Indonesia Program of Information Systems Department Universitas Mikroskil Medan Indonesia Program of Computer Science Department University of Pelita Harapan Tangerang Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Reducing dropout rates is crucial for enhancing human capital and education standards. Existing methods, such as Random Forest with Chi-Square and SMOTE-ENN, effectively addressed class imbalance and improved prediction accuracy for dropout data. However, there is still a research gap in achieving optimal model performance. This study addresses the gap by incorporating hyperparameter tuning alongside ChiSquare for feature selection and SMOTE-ENN for handling class imbalance. The dataset was segmented into training and evaluation subsets through the implementation of 10 -fold cross-validation. The testing was conducted with seven variations, namely building and implementing a Random Forest model using the default parameters from the Weka tool and applying six different hyperparameter tuning techniques. The results showed that Hyperband, along with other techniques like TPE, RandomSearch, and BO-TPE, led to substantial improvements in model accuracy, precision, and F-measure, and achieved perfect AUC scores. However, BO-GP and Nevergrad did not improve model performance. These findings suggest that the combination of SMOTE-ENN, Chi-Square, and hyperparameter tuning can enhance the effectiveness of dropout prediction models, with potentially positive implications for early intervention strategies in educational institutions.

关键词： Training Accuracy Training data Predictive models Feature extraction Reliability Tuning Random forests Standards Testing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Deep Learning Technologies

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Dee...

引用

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： El-Sheikh, Mohamed M. Bayoumy, Aya Ahmed, Nada M. Mohamed Eldeeb, Amany Rabea, Fatma I. Nawar, Amira A. Khattap, Mohamed G. Galal Eldeen Mohamed Ali Hassan, Hend Mostafa, Mariam Ibrahim, Nayra Ramadan, Reem Refaat, Yomna Khaled, Mennatallah Maher, Ali Abd Elaziz, Mohamed Gamal Abdellatif Ibrahim, Ahmed Radiology and Medical Imaging Faculty of Applied Health Sciences Galala University Suez435611 Egypt Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez435611 Egypt Air Defense College Department of Electronics and Electrical Communications Engineering Alexandria Egypt

ISBN: (纸本)9798350351408

This paper introduces an alternative technique for diagnosing Acute Ischemic Stroke within the IoMT environment. In the proposed approach, the collected data is transmitted to a cloud-based center where the technique utilizes EfficientNet, a deep learning model, designed to extract features from MRI images thereby enhancing the detection of acute ischemic infarctions. The performance of EfficientNet is compared against two other models, CNN and MobileNet, demonstrating its superior efficacy through metrics such as accuracy, precision, recall, and F1-score, which stand at 92.31%, 92.28%, 92.33%, and 92.30%, respectively. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Keypoint-Based Approach for Identifying Copy-Move Forgery in Digital Images 7

Enhanced Keypoint-Based Approach for Identifying Copy-Move F...

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Bisht, Girish Singh Jain, Arpit Bansla, Vandna Sharma, Khemraj Bhutia, Rudramani Kumar, Vikas Tula's Institute Department of Computer Science & Engineering Dehradun248001 India Koneru Lakshamaiah Education Foundation Department of Computer Science & Engineering A.P. Vadessahwaram India Shivalik Engineering College Dehradun248001 India Nanhua University Doctoral Program in Management Sciences Department of Business Administration Dalin Chiayi62248 Taiwan Koneru Lakshmaiah Education Foundation Department of Computer Science & Engineering A.P. India Dev Bhoomi Uttrakhand University School Engineering and Computing Uttrakhand Dehradun India

ISBN: (纸本)9798350350067

Copy-move forgeries often exploit homogeneous regions in images with large-scale attacks to either highlight or conceal target objects. These manipulations are simple to execute but challenging to notice. Forgery detection techniques like Copy-Move Forgery Detection (CMFD) cannot detect these forged documents because they are unable to identify a sufficient number of effective keypoints in homogeneous areas, leading to inaccurate and inefficient results. SURF stands for Speeded-Up Robust Features and is used in this paper along with A-KAZE and Scale-Invariant Feature Transforms. According to our experiment, A-KAZE offers superior detection performance under diverse attacks, especially when it comes to large-scale attacks targeting homogeneous regions. A-KAZE is found to be more accurate than SIFT, SURF, and A-KAZE when applied to the NB-CASIA dataset, achieving detection accuracies of 89.2%, 93.9% and 98.98%.) © 2024 IEEE.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring EfficientNet Variants for Image Encoding in Auxiliary Signal Guided Knowledge Encoder-Decoder Framework

引用

Procedia computer science 2024年 245卷 391-398页

作者： Matthew Martianus Henry Nur Adhianti Heryanto Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia 11480

The growing number of medical images has led to radiologist burnout, which seriously impacts the radiologist's performance. To address the previously mentioned issue, an Auxiliary Signal Guided Knowledge (ASGK) multimodal encoder-decoder framework was designed to automatically generate the medical report based on the proposed medical graph and natural language decoder. It utilizes DenseNet-121 as the image encoder. With DenseNet-121 lack of computational and memory efficiency, this study aims to explore the potential of EfficientNetB0 to EfficientNetB4 as an ASGK image encoder substitute. The framework is trained with IU X-Ray dataset for 30 epochs, with Adam optimizer, a learning rate of 0.01 with 0.8 decay rate, binary cross entropy loss for the medical tags, and cross-entropy loss for the generated medical captions. During the framework training process with each image encoder, the parameter that achieves the highest CIDEr score on the validation set is considered the best image encoder parameter and will be used on the test set. On the test set, EfficientNetB3 as an ASGK image encoder has been shown to increase the CIDEr score to 0.35, a significant increase from the 0.28 CIDEr score obtained by the ASGK using DenseNet-121. This score is only a 1% decrease from the best validation score. It suggests that not only EfficientNetB3 increases the framework's performance, it is also less prone to overfitting. This study has demonstrated that EfficientNetB3 is a potential image encoder substitute for DenseNet-121 in the ASGK framework.

关键词： Automated medical report generation DenseNet-121 EfficientNet Encoder-decoder framework

来源：评论

学校读者我要写书评

暂无评论

Global Patent Landscape of Decision Support System in The Business: An Overview 8

Global Patent Landscape of Decision Support System in The Bu...

引用

8th International Conference on Information Management and Technology, ICIMTech 2023

作者： Irawan, Michelia Champaca Salsabila Purnomo, Agung Sanjaya, Angelie Natalia Meiryani Ubud, Sahnaz Maulana, Fairuz Iqbal Binus Business School Undergraduate Program Bina Nusantara University Entrepreneurship Department Jakarta11480 Indonesia School of Accounting Bina Nusantara University Accounting Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350326093

The study of decision support systems in business and entrepreneurial ecosystems continues to grow and play an essential role. However, few studies have not comprehensively reviewed decision support system studies from the patent perspective. This research attempts to review the global patent landscape and the main trends of patents on decision support systems in business. Research using patent landscapes analysis was intended to clarify data visualization, identification, and analysis. This study uses 6,713 patent documents and 3,492 simple patent families over 35 years from the *** database. The study results reveal increased trends regarding developments to patent activity related to decision support systems in the business. There were business opportunities that business parties could use to the potential for increasing patent filings. The CPC codes that dominate decision support system patents in the business were G (physics). The United States was the most prolific country regarding owners and inventors. © 2023 IEEE.

关键词： Decision support systems

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：