检索结果-内蒙古大学图书馆

HighTech and Innovation Journal 2025年第1期6卷 67-80页

作者： Latubessy, Anastasya Wardoyo, Retantyo Musdholifah, Aina Kusrohmaniah, Sri Doctoral Program Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Informatics Engineering Faculty of Engineering Universitas Muria Kudus Indonesia Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta55281 Indonesia Department of Psychology Faculty of Psychology Universitas Gadjah Mada Yogyakarta55281 Indonesia

Fine Tuning Attribute Weighted Naïve Bayes (FTAWNB) is a reliable modified Naïve Bayes model. Even though it is able to provide high accuracy on ordinal data, this model is sensitive to outliers. To improve the performance of FTAWNB, this research modified the Partial Instances Reduction (PIR) technique to make the FTAWNB more adaptive to outliers. Nevertheless, in contrast to the original PIR technique, which substitutes missing values for data values deemed outliers, the PIR technique suggested in this study replaces data values deemed outliers using a Naïve Bayes weighting approach. The attribute values from the outlier data are replaced with the highest probability values for the attributes in the actual class. This PIR technique is referred to as modified PIR. The FTAWNB model with modified PIR has been evaluated using the Gaming Disorder dataset. Replacing the four attributes with the least amount of information resulted in accuracy gains of 99.74%, an increase of 1.53% over the FTAWNB model. The experimental result shows that adding the modified PIR technique to the FTAWNB model can handle the outlier in the data, proving it by increasing the performance in terms of accuracy, precision, and recall without pruning the dataset used. © 2025, Ital Publication. All rights reserved.

关键词： Attribute Weighted Classification Fine-Tune Gaming Disorder Instances Reduction Naïve Bayes

来源：评论

学校读者我要写书评

暂无评论

Experiment on UI evaluation using automated test 9th

Experiment on UI evaluation using automated test

引用

9th International Conference on computer science and Computational Intelligence, ICCSCI 2024

作者： Katherina, Kania Saputra, Dany Eka Computer Science Department School of Computer Science Bina Nusantara University Bandung Campus Jakarta11480 Indonesia

Learnability is one important aspect of user interaction that measures how long a user needs to familiarize themselves with the software. The evaluation method using expert analysis or user questionnaire cannot fully capture the learnability aspect of a software. Automated testing can record the user performance data and provide an objective evaluation of learnability. However, embedding recording code to conduct automated test can be expensive. This work proposes a novel method of automatic testing to evaluate the learnability of an existing software. By using Figma and Maze apps, a replica of evaluated software is made and injected with users' performance recording module with much ease. The result of the experiment shows that learnability data can be acquired objectively. In the experiment, the user of evaluated software requires an average learning rate of 3 iterations. While the average completion time is around 2.37 seconds per action for trained respondents and 1.86 seconds for untrained respondents. © 2024 The Authors.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Developing Campus Digital Twin with Integrated 3D Point Clouds and 3D Modeling Techniques 6

Developing Campus Digital Twin with Integrated 3D Point Clou...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Utama, Ryan Nathan Sutjiatmadja, Jonathan Osmond, Fabrian Stefan, Lucas Gunawan, Alexander A.S. Chowanda, Andry Irwansyah, Edy Pramudya, Fabian Surya Game Application & Technology Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9798331539603

Exploring digital twin technology through the creation of 3D digital model offers a powerful tool for enhancing real-time monitoring, predictive analysis, and optimization of complex systems. The purpose of this study is to develop a 3D digital model of our building campus as the first step towards developing a digital twin of the university. In this study, we develop a digital model with integrated 3D point clouds and 3D modeling techniques. By scanning the physical model of the campus, data in the form of point clouds is extracted and unnecessary noise is deleted using Autodesk Recap Pro. These point clouds are used as a benchmark to ensure the 3D models created using Blender are as accurate as possible to the physical model. After successfully creating the digital model, several features/interactions are implemented using Unity to mimic the physical model, thus developing the digital twin. The digital twin of the campus will be used to develop a virtual tour of the campus. We concluded that the 3D digital model of the campus was successfully developed, despite the time-consuming nature of the process. We hope that this study serves as a reference to optimize and enhance digital twin development in the future. © 2024 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Classification of Chili Varieties using Convolutional Neural Network Model 6

Classification of Chili Varieties using Convolutional Neural...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Rangkuti, Abdul Haris Wardana, Lie Melinda Putri Quincy, Angelina Pohan, Husni Iskandar Maheswari, Fakhira Shafa Computer Science Department School of Computer Science Bina Nusantara University Bandung Campus Jakarta11480 Indonesia

ISBN: (纸本)9798331539603

The diversity of chili types poses a challenge in accurately identifying chili varieties, hindering the selection of superior varieties by farmers and industry. To address this issue, our research focuses on leveraging machine learning, specifically Convolutional Neural Network (CNN) models, to classify visual images of chili varieties. We collected a dataset comprising 13 classes with a total of 1835 images, representing various species and varieties of chili. The dataset was divided into 70% for training, 20% for validation, and 10% for testing. The training process involved the use of deep learning with several CNN models to evaluate their effectiveness in accurately classifying chili varieties based on visual characteristics. Through refining the model architecture and parameters, our aim is to achieve a classification accuracy above 0.9, demonstrating the potential of CNN in overcoming current challenges in chili variety identification. In the training data experiment, models such as ResNet 50V2, NasNetMobileV2, Densenet169, MobileNetV2, Xception, and InceptionV3 demonstrated accuracy, precision, and recall of more than 92%. Subsequently, during testing data processing, the highest accuracy was achieved by the DenseNet 169 model at 95%, followed by MobileNetV2 at 95.9%, Xception at 94.3%, and InceptionV3 at 91.3%. Overall, our research has successfully classified 13 different varieties of chili peppers. However, further research is warranted to address more diverse image characteristics in other types of images. © 2024 IEEE.

关键词： Pepper

来源：评论

学校读者我要写书评

暂无评论

Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection 38

Towards Learning Group-Equivariant Features for Domain Adapt...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Shin, Sangyun He, Yuhang Vankadari, Madhu Cheng, Ta-Ying Xie, Qian Markham, Andrew Trigoni, Niki Department of Computer Science University of Oxford United Kingdom School of Computer Science University of Leeds United Kingdom

The performance of 3D object detection in large outdoor point clouds deteriorates significantly in an unseen environment due to the inter-domain gap. To address these challenges, most existing methods for domain adaptation harness self-training schemes and attempt to bridge the gap by focusing on a single factor that causes the inter-domain gap, such as objects' sizes, shapes, and foreground density variation. However, the resulting adaptations suggest that there is still a substantial inter-domain gap left to be minimized. We argue that this is due to two limitations: 1) Biased pseudo-label collection from self-training. 2) Multiple factors jointly contributing to how the object is perceived in the unseen target domain. In this work, we propose a grouping-exploration strategy framework, Group Explorer Domain Adaptation (GroupEXP-DA), to addresses those two issues. Specifically, our grouping divides the available label sets into multiple clusters and ensures all of them have equal learning attention with the group-equivariant spatial feature, avoiding dominant types of objects causing imbalance problems. Moreover, grouping learns to divide objects by considering inherent factors in a data-driven manner, without considering each factor separately as existing works. On top of the group-equivariant spatial feature that selectively detects objects similar to the input group, we additionally introduce an explorative group update strategy that reduces the false negative detection in the target domain, further reducing the inter-domain gap. During inference, only the learned group features are necessary for making the group-equivariant spatial feature, placing our method as a simple add-on that can be applicable to most existing detectors. We show how each module contributes to substantially bridging the inter-domain gaps compared to existing works across large urban outdoor datasets such as NuScenes, Waymo, and KITTI. © 2024 Neural information processing systems foundatio

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel Spectral Algorithms for the Partial Credit Model 41

Novel Spectral Algorithms for the Partial Credit Model

引用

41st International Conference on Machine Learning, ICML 2024

作者： Nguyen, Duc Zhang, Anderson Ye Department of Computer & Information Science University of Pennsylvania United States Department of Statistics & Data Science Wharton School University of Pennsylvania United States

The Partial Credit Model (PCM) of Andrich (1978) and Masters (1982) is a fundamental model within the psychometric literature with wide-ranging modern applications. It models the integer-valued response that a subject gives to an item where there is a natural notion of monotonic progress between consecutive response values, such as partial scores on a test and customer ratings of a product. In this paper, we introduce a novel, time-efficient and accurate statistical spectral algorithm for inference under the PCM model. We complement our algorithmic contribution with in-depth non-asymptotic statistical analysis, the first of its kind in the literature. We show that the spectral algorithm enjoys the optimal error guarantee under three different metrics, all under reasonable sampling assumptions. We leverage the efficiency of the spectral algorithm to propose a novel EM-based algorithm for learning mixtures of PCMs. We perform comprehensive experiments on synthetic and real-life datasets covering education testing, recommendation systems, and financial investment applications. We show that the proposed spectral algorithm is competitive with previously introduced algorithms in terms of accuracy while being orders of magnitude faster. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Advanced Encryption Algorithm for Enhancing data Security in Cloud Computing

引用

Recent Advances in Electrical and Electronic Engineering 2025年第5期18卷 623-636页

作者： Anandh, R. Swaminathan, A. Jadhav, Swati Dhondiram Valarmathi, P. Gopinath, N. Tiwari, Kanchan S. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Computer Science and Business Systems Panimalar Engineering College Poonamallee Chennai India Department of Computer Engineering Keystone School of Engineering Maharashtra Pune India Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Department of Electronics and Telecommunication Modern Education Society’s Wadia College of Engineering Pune India

Aim: Cloud computing (CC) is a revolutionary new archetype in which users pool their computing resources to provide greater efficiency for everyone. data become increasingly vulnerable to diverse security threats from attackers when millions of users circulate the same network for data transmission. Protecting these reports has shifted to the vanguard of priorities. The existing data security approach prioritizes protecting data at rest in cloud storage but gives less thought to protecting data in transit. During transmission, the data are vulnerable to intrusion attempts. Methods: The third-party auditor is provided access to data during the transfer phase, which is also the current pattern. As the attacker can now pose as a trusted third party, it makes the data more susceptible to unauthorized access. However, growing concerns regarding data privacy and security have made outsourcing sensitive information to faraway data centers difficult. As a result, new security concerns in the cloud necessitate an improved version of the tried-and-true advanced encryption standard (AES) algorithm. Key aspects presented in this study include a secure and private framework for owner data. It improves upon the 128 AES technique by adding a second round of encryption using a different key, allowing for a throughput of 1000 blocks per second. However, the standard method uses a single round key and only 800 blocks per second. The suggested approach reduces energy consumption, improves load distribution, and optimizes network trust and resource management. Results: The proposed architecture allows for the use of AES with cipher lengths of 16, 32, 64, and 128 bytes. The effectiveness of the algorithm in terms of attaining target quality metrics is illustrated graphically via simulation results. This strategy reduces power consumption by 13.23%, network utilization by 12.43%, and delay by 16.53%, according to the outcomes. Conclusion: As a result, the recommended architecture enhance

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

A Mixed-Methods Study of Wait Time Perception and Discrepancy in Technology-Mediated Mobility Systems

引用

Proceedings of the ACM on Human-computer Interaction 2025年第2期9卷 1-28页

作者： Wang, Guang Singh, Vivek K Zhang, Desheng Department of Computer Science Florida State University TallahasseeFL United States School of Communication and Information Rutgers University New BrunswickNJ United States Department of Computer Science Rutgers University New BrunswickNJ United States

Mobility services are becoming increasingly reliant on new technologies and mobile apps to manage and enable rides. In recent years, we have witnessed a rapid growth of technology-mediated mobility services (e.g., ridesharing and carsharing) with the ubiquity of smartphones. As an important technology-mediated mobility service involving interactions between passengers, drivers, and platforms, ridesharing has attracted great interest from the research community. Even though many existing studies have focused on the ridesharing experience of passengers, few of them have conducted a comprehensive study of passenger wait times in ridesharing systems. Prior research has shown that wait time is highly related to user experience. Understanding wait times in technology-mediated mobility systems and identifying factors that may impact them is of great importance for better user experience and the design of next-generation interactive mobility systems. Hence, in this paper, we adopt a mixed-methods approach to comprehensively examine two wait times in one of the largest technology-mediated mobility systems-DiDi, i.e., (i) the promised wait time shown on its mobile app after entering the origin and destination and (ii) the actual wait time. We first interviewed 102 individuals (including 52 passengers and 50 drivers) to understand people's perceptions of the two wait times in the DiDi ridesharing system. Our findings reveal that wait time discrepancy causes problems and negative emotions for passengers, and there are multiple potential factors that impact the discrepancy. To further verify some of these findings from a quantitative perspective, we performed a data-driven analysis based on large-scale ridesharing log data from over 36.6 million rides. Based on these findings, we share some design implications for ridesharing systems including those on minimizing expectation mismatch, supporting algorithmic transparency & fairness, and contextual factors consideration. © 2025 AC

关键词： algorithmic awareness mixed-methods approach mobility system wait time

来源：评论

学校读者我要写书评

暂无评论

Collectively Simplifying Trajectories in a database: A Query Accuracy Driven Approach 40

Collectively Simplifying Trajectories in a Database: A Query...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Wang, Zheng Long, Cheng Cong, Gao Jensen, Christian S. School of Computer Science and Engineering Nanyang Technological University Singapore Aalborg University Department of Computer Science Denmark

ISBN: (纸本)9798350317152

Increasing and massive volumes of trajectory data are being accumulated that may serve a variety of applications, such as mining popular routes or identifying ridesharing candidates. As storing and querying massive trajectory data is costly, trajectory simplification techniques have been introduced that intuitively aim to reduce the sizes of trajectories, thus reducing storage and speeding up querying, while preserving as much information as possible. Existing techniques rely mainly on hand-crafted error measures when deciding which point to drop when simplifying a trajectory. While the hope may be that such simplification affects the subsequent usability of the data only minimally, the usability of the simplified data remains largely unexplored. Instead of using error measures that indirectly may to some extent yield simplified trajectories with high usability, we adopt a direct approach to simplification and present the first study of query accuracy driven trajectory simplification, where the direct objective is to achieve a simplified trajectory database that preserves the query accuracy of the original database as much as possible. Specifically, we propose a multi-agent reinforcement learning based solution with two agents working cooperatively to collectively simplify trajectories in a database while optimizing query usability. Extensive experiments on four real-world trajectory datasets show that the solution is capable of consistently outperforming baseline solutions over various query types and dynamics. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Unlocking Soundscapes: Harnessing Machine Learning for Sound Classification 9

Unlocking Soundscapes: Harnessing Machine Learning for Sound...

引用

9th International Conference on Information Technology and Digital Applications, ICITDA 2024

作者： Hidayat, Alexis Njoo, Davin Bennett Putrajaya Adrian, Gerald Davin Setyoko, Dimas Elang Wijanarko, Bambang Dwi School of Computer Science Bina Nusantara University Computer Science Department Semarang Campus Jakarta11480 Indonesia

ISBN: (纸本)9798331510732

The concept of Smart Cities has been implemented in several major areas to improve the lives of citizens. One of the technologies used is sound classification, which monitors and identifies levels of urban noise. Convolutional Neural Networks (CNNs) have proven to be an effective method for sound classification because they can recognize complex patterns in audio data. Various architectures of Convolutional Neural Networks, such as ResNet, DenseNet, and others, exist for this purpose. This research aims to identify the CNN architecture that performs best in urban sound classification. The methodology involves training and testing existing CNN architecture and evaluating them based on several parameters, including the number of parameters, memory usage, convergence speed, and training time. Experimental results show that the performance of the ResNet family tends to degrade when the network depth increases. The best performance was achieved by the Resnet-18 architecture, with accuracy, precision, recall and F1-Score values of 91.5%, 92.2%, 91.2%, 91.6%. On the other hand, the use of complex features from various scales causes the DenseNet and GoogleNet architectures to be unableto achieve the best performance. © 2024 IEEE.

关键词： Convolutional neural networks

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：