检索结果-内蒙古大学图书馆

HighTech and Innovation Journal 2023年第2期4卷 375-386页

作者： Anni Suharjito Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Lip-reading is a method that focuses on the observation and interpretation of lip movements to understand spoken language. Previous studies have exclusively concentrated on a single variation of residual networks (ResNets). This study primarily aimed to conduct a comparative analysis of several types of ResNets. This study additionally calculates metrics for several word structures included in the GRID dataset, encompassing verbs, colors, prepositions, letters, and numerals. This component has not been previously investigated in other studies. The proposed approach encompasses several stages, namely pre-processing, which involves face detection and mouth location, feature extraction, and classification. The architecture for feature extraction comprises a 3-dimensional convolutional neural network (3D-CNN) integrated with ResNets. The management of temporal sequences during the classification phase is accomplished through the utilization of the bidirectional gated recurrent units (Bi-GRU) model. The experimental results demonstrated a character error rate (CER) of 14.09% and a word error rate (WER) of 28.51%. The combination of 3D-CNN ResNet-34 and Bi-GRU yielded superior outcomes in comparison to ResNet-18 and ResNet-50. The correlation between increased network depth and enhanced performance in lip-reading models was not consistently observed. Nevertheless, the incorporation of additional trained parameters offers certain benefits. Moreover, it has demonstrated superior levels of precision in comparison to human professionals in the task of distinguishing diverse word structures. © Authors retain all copyrights.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Fostering Digital Innovation in Indonesia: The Role of STEM-AI Skills in Overcoming Talent Deficits and Gender Stereotypes 4

Fostering Digital Innovation in Indonesia: The Role of STEM-...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Halim, Erwin Zahra, Amalia Maryani Wulandhari, Lili Ayu Fitrianah, Devi Puspita, Virienia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Communication Department Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

This research explores the optimization of digital talent in advanced industries, particularly in the context of rapid digital transformation. Despite the increasing importance of digital talent for gaining a competitive edge, several challenges persist. In Indonesia, for example, there is a significant shortage of digitally skilled workers, with the World Bank reporting a gap of 9 million skilled individuals over the past 15 years. Additionally, artificial intelligence (AI) is expected to impact 9.5 million jobs, further exacerbating the demand for digital skills. Furthermore, the employability of graduates remains low, largely due to inadequate training, poor language proficiency, and limited cultural sensitivity. Many companies face difficulties in finding qualified individuals, quickly upskilling their workforce, and fostering an innovative organizational culture. This study seeks to evaluate the factors influencing digital talent performance in the context of these challenges. It examines seven key variables: digital readiness, digital technology adoption, relevance of AI, digital skills, individual performance, problem-solving ability, and overall digital talent performance. Hypotheses were tested using Partial Least Squares Structural Equation Modeling (PLS-SEM). Data was collected from 378 participants, primarily students with STEM backgrounds, in the Jabodetabek area of Indonesia in November 2024. The findings reveal that all hypotheses are significant, with results indicating that user satisfaction and the perceived value of digital talent in Indonesia have a notable impact on continued usage intentions in digital roles. © 2024 IEEE.

关键词： digital readiness digital talent performances digital technology individual performance STEM-AI

来源：评论

学校读者我要写书评

暂无评论

Enhancing Efficiency in Yolov8n for Real-Time Detection of Oil Palm Fruits in Plantations Using Mobileone and Cross-Fusion

SSRN

引用

SSRN 2024年

作者： Hugo, Gregory Mushlik, Muhammad Suharjito Computer Science Department BINUS Graduate Program – Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia Industrial Engineering Department BINUS Graduate Program – Master of Industrial Engineering Bina Nusantara University Jakarta11480 Indonesia

Accurate detection of fresh fruit bunches (FFB) ripeness in complex plantation environments is challenging due to occlusion, varying lighting, intricate visual features, and limited computational resources of mobile devices. To address this, a resource-efficient, real-time detection system was developed using an optimized YOLOv8n model. The model integrates MobileOne modules and Cross-Fusion blocks to enhance efficiency without compromising accuracy. Specifically, Conv and C2f modules were replaced with MobileOne modules, reducing parameters by 85% and 81%, respectively. Cross-Fusion improved feature fusion, and its combination with MobileOne (CF-MobileOne) achieved a 51% reduction in parameters while maintaining performance. The dataset comprised images from videos captured in plantations, annotated into five maturity stages: flower, unripe, underripe, ripe, and abnormal, and underwent augmentation with class balancing through manual undersampling. The model outperformed baseline YOLOv8 variants and heavier models like YOLOv9c and Faster R-CNN, achieving an mAP50 of 0.795 and an inference speed of 140.57 FPS. Hyperparameter tuning with a batch size of 64, SGD optimizer, and a learning rate of 0.01 yielded optimal results. Despite challenges in detecting certain classes due to visual similarities and environmental variations, the system effectively enhances productivity and efficiency in precision agriculture for the palm oil industry. © 2024, The Authors. All rights reserved.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Automatic essay scoring for discussion forum in online learning based on semantic and keyword similarities

引用

Asian Association of Open Universities Journal 2023年第3期18卷 262-278页

作者： Dhini, Bachriah Fatwa Girsang, Abba Suganda Sufandi, Unggul Utan Kurniawati, Heny Department of Multimedia Teaching Material Production Center Universitas Terbuka Tangerang Selatan Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia Faculty of Sains and Technology Universitas Terbuka Tangerang Selatan Indonesia

Purpose: The authors constructed an automatic essay scoring (AES) model in a discussion forum where the result was compared with scores given by human evaluators. This research proposes essay scoring, which is conducted through two parameters, semantic and keyword similarities, using a SentenceTransformers pre-trained model that can construct the highest vector embedding. Combining these models is used to optimize the model with increasing accuracy. Design/methodology/approach: The development of the model in the study is divided into seven stages: (1) data collection, (2) pre-processing data, (3) selected pre-trained SentenceTransformers model, (4) semantic similarity (sentence pair), (5) keyword similarity, (6) calculate final score and (7) evaluating model. Findings: The multilingual paraphrase-multilingual-MiniLM-L12-v2 and distilbert-base-multilingual-cased-v1 models got the highest scores from comparisons of 11 pre-trained multilingual models of SentenceTransformers with Indonesian data (Dhini and Girsang, 2023). Both multilingual models were adopted in this study. A combination of two parameters is obtained by comparing the response of the keyword extraction responses with the rubric keywords. Based on the experimental results, proposing a combination can increase the evaluation results by 0.2. Originality/value: This study uses discussion forum data from the general biology course in online learning at the open university for the 2020.2 and 2021.2 semesters. Forum discussion ratings are still manual. In this survey, the authors created a model that automatically calculates the value of discussion forums, which are essays based on the lecturer's answers moreover rubrics. © 2023, Bachriah Fatwa Dhini, Abba Suganda Girsang, Unggul Utan Sufandi and Heny Kurniawati.

关键词： Discussion forum Essay scoring Keyword similarity Semantic similarity

来源：评论

学校读者我要写书评

暂无评论

Indonesian Agricultural-crops Classification Using Transfer Learning Model 8

Indonesian Agricultural-crops Classification Using Transfer ...

引用

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

作者： Isnan, Mahmud Hidayat, Alam Ahmad Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Department of Mathematics School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

Classification of Indonesian crops is a critical task in developing farming and getting more understanding of agriculture. However, there is no clear task in classifying types of crops in Indonesia. Transfer learning has been used successfully in a variety of image classification applications. Thus, in this paper, we collected images of Indonesian crops from the internet randomly and proposed a classification by using transfer learning of deep learning with four pre-trained models: EffficientNetB0, ResNet18, VGG19, and AlexNet. In the experiment, augmentation techniques such as random horizontal flip, random vertical flip, and random affine were utilized to prevent the network from overfitting. The result found that EfficientNet-B0 outperformed other models with an accuracy of 82.55. Then, the model struggled to distinguish between crops in the same family. According to the results, although transfer learning can work well to classify images of Indonesian agricultural crops, some improvements are still required to address existing issues. © 2023 The Authors. Published by Elsevier B.V.

关键词： Agriculture Classification Crop Deep Learning Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Count-Data Mixed Models of Topical Tweets: A Case of Indonesia Flood Events 8

Count-Data Mixed Models of Topical Tweets: A Case of Indones...

引用

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

作者： Hidayat, Alam Ahmad Pardamean, Bens Mathematics Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

Examining topic-level variability in modeling Twitter data can potentially yield more comprehensive insights into public perception during critical periods, thereby enhancing natural disaster mitigation and surveillance efforts. In this study, we utilized generalized linear mixed models (GLMMs) to illustrate the variability in tweet counts related to specific topics in Indonesia during the flood events that occurred in February 2021. The glmmTMB library in R was employed for this purpose. The data were assumed to follow two distinct exponential distributions: Poisson and Negative Binomial. To incorporate random effects, random intercepts and random slopes were introduced, allowing them to vary randomly across topics in the initial two models. Additionally, the final model addressed issues related to dispersion and zero-inflation. By evaluating the Akaike Information Criteria scores, we determined that a model based on the Negative Binomial distribution with random zero-inflation intercepts best fit the data. The chosen model formulation and the estimated parameters have the potential to forecast topic-specific trends in Indonesian flood-related Twitter data. © 2023 The Authors. Published by Elsevier B.V.

关键词： count data disaster surveillance floods mixed models Twitter

来源：评论

学校读者我要写书评

暂无评论

Investigation of player emotion and instinct on racing video game using 6-11 framework (Case study: split second (2010) single player modes)

引用

Procedia computer science 2024年 245卷 87-99页

作者： Galih Dea Pratama Andien Dwi Novika Elshad Ryan Ardiyanto Game Application & Technology Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Master of Computer Science Binus Graduate Program Bina Nusantara University Jakarta 11480 Indonesia

Racing is one of the most prominent genres in the modern video game industry, where the games within the genre enable players to use any vehicle of their choice and win through doing series of action within gameplay. Thus, it made the genre popular over the years, spawning many famous titles such as Split Second back in 2010. Like every other video game title, Split Second also invokes the player emotion and instinct during its gameplay session. To understand the emotion and instinct aspect present in players of the game, we will use 6-11 framework which focuses on the two aspects. As part of the conclusion, Split Second game involves instincts such as Competition, Collecting, and Survival, with emotions including Fear, Pride, Joy, and Excitement, which can be found from its vast single player game modes.

关键词： video games racing video games game analysis 6-11 framework

来源：评论

学校读者我要写书评

暂无评论

Analyzing Company's Share Purchase Value Based on Financial Reports Using Artificial Neural Network (ANN) 9

Analyzing Company's Share Purchase Value Based on Financial ...

引用

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

作者： Shawn, Jeremy Gunawan, Jonathan Hao, Chen Zi Anggreainy, Maria Susan Kurniawan, Afdhal Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350370126

Because financial time series forecasting is sensitive to political, economic, and social factors, it is not a simple task. As a result, those who make investments in currency exchange and financial markets typically search for reliable models that can guarantee they will maximize their profile and minimize their losses. Fortunately, many studies have used a method from Artificial Neural Networks (ANNs) called Backpropagation, could improve the predictive accuracy of the behavior of the financial data over time. This paper aims to forecast stock share prediction from closing value of PT. Bank Central Asia Tbk, and PT. Bank Maybank Indonesia Tbk. The results show that the using Backpropagation gives the closest result. And for the rating of judgement for cast accuracy, it exceeded 10% accuracy, which means high accurate from the prediction. For further checking, comparing the results of research from Victor's results, it almost hits the same accuracy percentage. Which means, these prediction are accurate enough to do time series forecasting. © 2023 IEEE.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Energy Sector Stock Price Prediction Using the CNN, GRU & LSTM Hybrid Algorithm

Energy Sector Stock Price Prediction Using the CNN, GRU & LS...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Sulistio, Bambang Warnars, Harco Leslie Hendric Spits Gaol, Ford Lumban Soewito, Benfano Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia

ISBN: (纸本)9798350320954

Nowadays, many people are starting to care about early investment. One of the most popular investments lately, especially for millennials, is a stock investment. In investing, there are advantages and risks of loss. One way to reduce the risk of loss is by using price predictions before investing in stocks. This paper proposes the use of deep learning in making stock predictions. We conducted research by calculating the performance of six deep-learning algorithms to predict stock closing prices. The application of the CNN-LSTM-GRU hybrid algorithm combination produces the best performance compared to other methods, based on the value: Root Mean Squared Error (RMSE) decreased by 1.100 by 14%, Mean Absolute Error (MAE) was successfully reduced by 0.798 by 13.4%, and R Square increased by 0.957 by 3.9%. In predicting stock prices on the Indonesian Stock Exchange, especially in the energy sector, CNN-LSTM-GRU is more appropriate for investors than using a single algorithm to make decisions in investing in stocks.. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Comparison of K-Nearest Neighbor and Support Vector Regression for Predicting Oil Palm Yield 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications, CITISIA 2022

作者： Pardamean, Bens Suparyanto, Teddy Sinaga, Gokma Sahat Tua Elwirehardja, Gregorius Natanael Firmansyah, Erick Ginting, Candra Mawandha, Hangger Gahara Putra, Dian Pratama Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program—Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia Faculty of Agriculture Institute of Agriculture STIPER Yogyakarta55282 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

With the high demand for oil palm production, implementations of Machine Learning (ML) technologies to provide accurate predictions and recommendations to assist oil palm plantation management tasks have become beneficial, such as in predicting annual oil palm. However, different geographical and meteorological conditions may result in different scales of influence for each variable. In this research, K-Nearest Neighbors (KNN) and Support Vector Regression (SVR) were used in predicting oil palm yield based on data collected in Riau, Indonesia. Pearson’s correlation coefficient was also calculated in selecting the input features for the models, whereas normalization and standardization were used in scaling the data. By setting the minimum absolute correlation threshold to 0.1 and using standardization, both models managed to obtain more than 0.81 R2, with SVR obtaining the overall best performance with 0.8709 R2, 1.372 MAE, and 1.8025 RMSE without hyperparameter fine-tuning. It was also discovered that the oil palm yield in the previous year is the variable with the most influence in estimating oil palm yield in the current year, followed by the number of plants and soil types. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Machine learning

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：