检索结果-内蒙古大学图书馆

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Mohammad Faisal Riftiarrasyid Ford Lumban Gaol Haryono Soeparno Yulyani Arifin Computer Science Department Binus Graduate Program – Computer Science Bina Nunsantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

Although drones have become increasingly advanced and sophisticated, they still face challenges such as limited computing power and high-power consumption. Optimizing their features is a key strategy to address these limitations. One critical feature that can be further improved is the algorithm for specialized tasks like obstacle detection. Recent studies have primarily relied on earlier versions of YOLO for this purpose. However, with the release of the latest YOLO versions, YOLOv10 and YOLOv11, there is an opportunity to assess their suitability for drone applications. In this study, we trained YOLOv10-nano and YOLOv11-nano using a drone-specific dataset and compared their performance with similar studies. The results indicate that YOLOv11-nano outperforms YOLOv10-nano in bounding-box prediction, achieving a higher mAP of 0.957 with a 0.22 difference, as well as faster inference times with a 74.1 ms improvement, resulting in a frame rate gain of 0.0421 FPS. However, when compared to earlier studies, YOLOv11-nano demonstrates superior precision but lags in real-time processing speed. These findings highlight the trade-off between accuracy and inference time, highlighting the suitability of YOLOv11-nano for applications in drone development where accuracy takes precedence over processing speed.

关键词： YOLO Training Seminars Accuracy Cameras Prediction algorithms Real-time systems Intelligent systems Information technology Drones

来源：评论

学校读者我要写书评

暂无评论

ApiPot: A Novelty API Honeypot for Exhaustive Attack Feature Detection in HTTP Protocol

ApiPot: A Novelty API Honeypot for Exhaustive Attack Feature...

引用

International Conference on Future Internet of Things and Cloud (FiCloud)

作者： Kalpin Erlangga Silaen Benfano Soewito Maria Susan Anggreainy Aditya Kurniawan Computer Science Department BINUS Graduate Program - Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331527198

ISBN: (纸本)9798331527204

This paper introduces a novel honeypot called Apipot, specifically designed to emulate API services over the HTTP protocol, with the main purpose of capturing the feature set of each HTTP request more than what is typically recorded in standard web server logs. Web server limitations in logging HTTP requests to API-based applications from visitors mean that critical data required for comprehensive threat analysis and attacker profiling is lost. Apipot overcomes this problem by simulating API services and capturing all the features of HTTP requests. We expected that capturing more features in HTTP requests would enable deeper insight into attacker methods, thereby significantly improving sophisticated cyber attack detection and the ability to more accurately profile attackers, thereby contributing to identifying attackers behind cyber attacks. Our experiment result shows that Apipot can capture 119 unique HTTP headers and 491 unique queries, along with IP source, body, URL, host, and other HTTP request features, from 196,206 requests toward Apipot in 61 days. This result proves that Apipot can capture more features from an HTTP request compared to a web server. As far as we know, Apipot is the first honeypot that mimics an API to capture HTTP request features.

关键词： Uniform resource locators Feature detection Feature extraction HTTP Web servers Vectors IP networks Cyberattack Standards Monitoring

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

Evaluating Vision Transformers Efficiency in Image Captioning

Evaluating Vision Transformers Efficiency in Image Captionin...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Bintang Kevin Hizkia Samosir Sani Muhamad Isa Computer Science Department Binus Graduate Program – Master of Computer Science Binus University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

This study investigates the performance of Vision Transformer (ViT) variants—the Shifted Window Transformers (SWIN), Distillation with No Labels (DINO), and Data-efficient Image Transformers (DeIT)—in image captioning tasks using the Flickr8K dataset. While ViT architectures have shown promise in image classification, their effectiveness for image captioning, particularly with smaller datasets, remains unclear. The models' performance was evaluated using BLEU metrics, while training efficiency was analyzed through Pareto front analysis of computational time and accuracy. Among the tested variants, SWIN Transformers demonstrated superior performance (BLEU-1: 64.4, BLEU-2: 33.9, BLEU-3: 17.1, BLEU-4: 8.4), followed by DINO (BLEU-1: 63.1, BLEU-2: 32.7, BLEU-3: 16.4, BLEU-4: 7.5), while DeIT showed the weakest performance (BLEU-1: 61.6, BLEU-2: 31.1, BLEU-3: 14.7, BLEU-4: 6.5). SWIN Transformers achieved the shortest training time at 3 minutes 31 seconds per epoch, making it the most efficient model among ViT variants based on Pareto front analysis. While ViT variants achieved competitive BLEU-1 scores comparable to previous top models, they struggled with generating coherent, longer sentences, as evidenced by suboptimal BLEU-4 scores. These findings provide empirical evidence of how the lack of inductive bias in transformer architectures affects their ability to capture complex scene relationships, despite their strong feature detection capabilities, contributing to the understanding of transformer models' limitations in vision-language tasks, especially with limited data.

关键词： Training Measurement Analytical models Feature detection Computational modeling computer architecture Transformers Data models Computational efficiency Image classification

来源：评论

学校读者我要写书评

暂无评论

Ensemble-Stacking Machine Learning Model for Multi-Class Skin Diseases Identification 5

Ensemble-Stacking Machine Learning Model for Multi-Class Ski...

引用

5th International Conference on Biomedical Engineering, IBIOMED 2024

作者： Tandelon, Dennis Christiono, David Lawrence Andryani, Nur Afny Catur Gondokaryono, Srie P. Rahardja, July I. Danarti, Retno School of Computer Science Bina Nusantara University Computer Science Department Jakarta Indonesia Bina Nusantara University BINUS Graduate Program Doctor of Computer Science Department Jakarta Indonesia Indonesian Society of Dermatology & Venereology Padjadjaran University Faculty of Medicine Indonesia Dermatovenereology Department Indonesia Indonesian Society of Dermatology & Venereology Gadjah Mada University Faculty of Medicine Indonesia Dermatovenereology Department Indonesia

ISBN: (纸本)9798350389265

Algorithm development on skin diseases identification with high cardinality classification is still very challenging. In addition, the high similarity appearance among diseases makes the computer vision approach meet high difficulties on providing clear distinct feature representation. In general, some literature shows that the performance of single machine learning or single deep learning techniques can be further improved when merged by ensemble mechanism. This approach has been applied on binary skin's cancer diseases diagnosis prediction and successfully improve the prediction ability. This paper elaborates the potential of ensemble machine learning approaches using stacking techniques on conducting feature extraction and classification model for identifying more general skin diseases based on dermoscopy images and mobile phone images. The proposed model combines three different CNN architectures, ResNet50, Xception, and VGG16 to extract features from the image then stacked as input for the model trained using five different algorithms, which are logistic regression, support vector machines, multi-layer perceptron, k-nearest neighbors, random forests and the combination of these algorithm in stacking classifier as the base estimators and final estimator. The simulation results present the proposed ensemble - stacking model succeeds to improve the identification ability in all utilized datasets. In addition, the proposed ensemble - stacking models show better recall which indicates good sensitivity on handling false negative. It is beneficial for medical application. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of LSTM and Transformer for Time Series Data Forecasting

Comparison of LSTM and Transformer for Time Series Data Fore...

引用

International Conference on Informatics and Computational sciences (ICICoS)

作者： Ilvico Sonata Yaya Heryadi Computer Science Department Binus Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350375886

ISBN: (纸本)9798350375893

Time series data is data that is collected periodically and has certain time intervals. Time series data is widely available in the fields of finance, meteorology, signal processing, health, and economics. Weather data, stock prices, and sales data are examples of time series data. Time series data analysis can be used to predict future conditions based on patterns and values from previous data through a forecasting process. These forecasting results are useful for identifying trends and data patterns for decision making. The rapid development of deep learning models can now be used as a method for forecasting time series data. Deep learning models that are suitable for forecasting include sequence-to-sequence models such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Transformer. LSTM and Transformer are sequence-to-sequence models that are widely used for forecasting time series data. Research to compare the accuracy of the two models is still very limited. This article will discuss the use of the LSTM and Transformer models for the time series data forecasting process using Hewlett Packard stock price data from 1962 to 2022. The accuracy results show that the LSTM model outperforms the Transformer model in forecasting Hewlett Packard stock prices.

关键词： Accuracy Recurrent neural networks Biological system modeling Time series analysis Predictive models Transformers Data models

来源：评论

学校读者我要写书评

暂无评论

News Classification Based On News Headline Using SVC Classifier 16

News Classification Based On News Headline Using SVC Classif...

引用

16th International Conference on Telecommunication Systems Services and Applications, TSSA 2022

作者： Leonard, Goldius Sisnadi, Fukriandy Wardhana, Nicholas Vigo Aziz Al-Ghofari, Muhammad Abdul Girsang, Abba Suganda School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Binus Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665455947

News gives new insight and information from all over the world. News has many categories, such as politic, economy, science, and other common news categories. Every news will have their own category based on its content. The classification of news is usually done manually by inputting the category during the news posting. Some of the categories may be inputted incorrectly. The news classifier can be the solution for problem, but the news classifications out there are usually based on the news content. The classifier will receive the word vector inputs that are taken from the news content and try to classify it into one of certain categories. Unfortunately, news contents can be longer and harder to be processed rather than processing the news headline. The news headline is shorter and packs a decent information for the classifier to find out what category it is. Besides the news headline usage, the classifier also needs to be chosen correctly. In this paper, the SVC model will be tested using the news headline data to classify the news and compare with several other models, such as Linear Regression, Multinomial Naive Bayes, Decision Tree, and Random Forest. The common variables to be compared are the accuracy, recall, and precision to evaluate the SVC model. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Deep neural networks and weighted word embeddings for sentiment analysis of drug product reviews 7

Deep neural networks and weighted word embeddings for sentim...

引用

7th International Conference on computer science and Computational Intelligence, CSCI 2022

作者： Suhartono, Derwin Purwandari, Kartika Jeremy, Nicholaus Hendrik Philip, Samuel Arisaputra, Panji Parmonangan, Ivan Halim Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

One of the major tasks of natural language processing is sentiment analysis. The web is a source of unstructured and rich informa-tion with thousands of opinions and reviews. Individuals, businesses, and governments can all benefit from recognizing sentiment. As part of this study, we propose a deep learning-based approach for sentiment analysis on drug product review data obtained from the UCI machine learning repository. As an alternative to deep learning models, this architecture integrates glove word embedding with convolutional neural networks (CNN). Word2vec and GloVe word embedding schemes have been evaluated empirically for their predictive performance in CNN architectures. Based on a comparison of the deep learning architecture with RoBERTa, itcan be seen that BERT architecture outperforms both of them in training and validation. However, CNN models using Glove word embedding provided superior results in testing. © 2022 Elsevier B.V.. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Web Application based Ridesharing Your Transportation in Jakarta 2

Web Application based Ridesharing Your Transportation in Jak...

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Kusuma, Giovanni Randy Handana, Afan Rizqi Warnars, Harco Leslie Hendric Spits School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Binus Graduate Program - Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665400527

The city of Jakarta is getting more and more congested and crowded by the number and types of vehicles. Lack of public awareness to use public transportation causes this congestion to worsen, especially during rush hours in the morning before going to work or school and in the afternoon when returning home. This is also caused by the lack of the government of the capital city of Jakarta in providing cheap, safe, and comfortable public transportation. It is not surprising that the Indonesian government has plans to move the capital city of the Indonesian government from Jakarta on the island of Java to East Kalimantan on the island of Kalimantan. Therefore, seeing this severe traffic jam, it is essential to propose an application that can reduce congestion so that drivers who bring their vehicles can share with people around them to travel to work as a routine activity during weekdays. The model of this vehicle sharing application was designed using use case diagrams, and the database design was designed using class diagrams. In addition, security issues are also significant considering that people meet in this vehicle sharing application, and some bad people may take advantage of it. Therefore user registration and moderation are essential. It is hoped that this vehicle sharing application will reduce congestion in the capital city of Jakarta and become an example in other cities. © 2022 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Enhanced Personality Prediction: Fusing Structural and BERT-Based Lexical Features on Augmented Twitter Data 7

Enhanced Personality Prediction: Fusing Structural and BERT-...

引用

7th International Conference on Information Management and Technology, ICIMTech 2022

作者： Roslynlia Suhartono, Derwin BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (数字)9781665450904

ISBN: (纸本)9781665450904

Conventionally, assessing people's personality done by psychology experts requires more time and effort. Hence automatic personality prediction is starting to get noticed by researchers. Nowadays, many people engage themselves in social media platforms, one of which is Twitter. This platform stores actions done in this media which reflect one's personality. This research focuses on improving the performance of personality prediction models based on machine learning algorithms, by augmenting the dataset using Easy Data Augmentation to overcome imbalance dataset, thereafter combining n-grams with POS-tag weighted by TF-IDF. Results show that this method outperforms other machine learning approaches and decreases bias, with a maximum of 72.62% of the best average accuracy and 72.72% best average Fl score using Support Vector Machine classifier. The second-best model is obtained by XGBoost and, lastly, Naive Bayes classifier. Overall, this study shows that data augmentation with the addition of POS-tag feature is evident in improving the performance of personality prediction models. However, larger data is needed. © 2022 IEEE.

关键词： Learning algorithms

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：