检索结果-内蒙古大学图书馆

International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE)

作者： Aaron Christian Hansel Adrianus Lunardi Pradana Abba Suganda Girsang Ariadi Nugroho Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia

With the large amount of information available on the internet, recommendation tasks have grown to be more crucial than ever. Businesses that store digital media on the internet such as video streaming and music streaming platforms, benefit a lot from recommendation systems. A simple yet powerful recommendation system that can give better recommendation performance is always being sought after. Light Graph Convolution Network (LightGCN) is a simplified version of Graph Convolution Network (GCN) for collaborative filtering in recommendation systems. LightGCN architecture includes only the most essential part of GCN for collaborative filtering that is the neighborhood aggregation, it removes the feature transformation and nonlinear activation because both of them contribute little to no effect to the recommendations. The focus of this research is to optimize LightGCN by tuning the hyperparameters using exhaustive search (grid search). The optimized LightGCN model is able to out-perform LightGCN by more than 140% in music recommendation

关键词： Machine learning algorithms Convolution Collaborative filtering Machine learning Streaming media Media Task analysis

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of COVID-19 Public Activity Restriction (PPKM) Impact using BERT Method

arXiv

引用

arXiv 2022年

作者： Fransiscus Girsang, Abba Suganda Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia

Covid-19 has grown rapidly in all parts of the world and is considered an international disaster because of its wide-reaching impact. The impact of Covid-19 has spread to Indonesia, especially in the slowdown in economic growth. This was influenced by the implementation of Community Activity Restrictions (PPKM) which limited community economic activities. This study analyzes the mapping of public sentiment towards PPKM policies in Indonesia during the pandemic based on Twitter data. Knowing the mapping of public sentiment regarding PPKM is expected to help stakeholders in the policy evaluation process for each region. The method used is BERT with IndoBERT specific model. The results showed the evaluation value of the IndoBERT f-1 score reached 84%, precision 86%, and recall 84%. Meanwhile, f-1 scores 70%, 72% precision, and 70% recall for evaluating the use of SVM. Multinominal Naïve Bayes evaluation shows an f-1 score of 83%, precision of 78%, and recall of 80%. In conclusion, the BERT method with the IndoBERT model is proven to be higher than classical methods such as SVM and Multinominal Naïve Bayes. © 2022, CC BY-NC-ND.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Music Recommendation System for Shared Environments

Music Recommendation System for Shared Environments

引用

International Conference on Systems, Signals and Image Processing, IWSSIP

作者： João G. Bracaioli Vitório Carlos N. Silla Graduate Program in Computer Science (PPGIA) Pontifícia Universidade Católica do Paraná (PUCPR) Curitiba Brazil

The increasing amount of information available nowadays has led to a growth in research on recommendation systems. In the context of music, these systems help individuals filter and discover new music and styles based on their common tastes. However, while most music recommender solutions used by streaming platforms are based on individual characteristics, group recommendations are still underexplored. This paper provides a brief analysis of group recommendation systems and their testing, as well as proposes a real-time music recommendation system for groups that consider shared environment contexts, such as time of day and location, to investigate whether contextual information can improve the selection of songs for a group. The study evaluates different aggregation strategies for individual preferences and uses experiments to test the effectiveness of the proposed system. The results indicate that taking into account contextual information improves user satisfaction and song selection for playlists, making the proposed system promising for music recommendation in shared environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Age and Updating Stability for a Communication Context in VANET

The Age and Updating Stability for a Communication Context i...

引用

Brazilian Symposium on Computing System Engineering (SBESC)

作者： Margarete De Sá Sérgio Gorender Distributed Systems Laboratory (LaSiD) Graduate Program in Mechatronics (PPGM) Computer Science Institute (IC) and Polytechnic School (EP) Federal University of Bahia (UFBA)

ISBN: (数字)9798331509002

ISBN: (纸本)9798331532857

VANETs make it possible to execute specific vehicular applications, in particular those with the aim of turning traffic safe and avoiding congestion. However, it is difficult to maintain communication between vehicles when these vehicles move dynamically at high speeds. Context-aware systems have been studied as a way to monitor context information from sensors, which can be used by systems to adapt to changes in their environment or in application requirements. This concept is used by VANET protocols and applications in different ways. Quality of Context (QoC) metrics are used to qualify the context information considering different characteristics of sensors and of the information, being a base for systems to decide if it is safe and interesting to use specific information. In this paper, we propose QoC metrics related to the stability of the updating process for a vehicular communication context. In addition, we also analyze the Age QoC metric and show how to calculate it for distinct context information. We simulate scenarios to verify the QoC metrics behavior. The results showed that the proposed QoC metrics can properly qualify the vehicular communication context.

关键词： Measurement Roads Vehicular ad hoc networks Sensor phenomena and characterization Turning Systems engineering and theory Stability analysis Sensor systems Reliability Monitoring

来源：评论

学校读者我要写书评

暂无评论

Identification of Diseases in Greenhouse Tomato Cultivation: A New Dataset and Baseline Results

Identification of Diseases in Greenhouse Tomato Cultivation:...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Grasielli B. Zimmermann Marcelo E. Pellenz Alceu De Souza Britto Yandre M. G. da Costa Graduate Program in Computer Science (PPGIa) Pontifical Catholic University of Parana (PUCPR) Curitiba PR Brazil State University of Maringá (UEM) Maringá Brazil

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Plant diseases are one of the factors that compro-mise food production goals. Tomatoes are one of the world's most consumed vegetables and are widely affected by various diseases. Tomato cultivation in greenhouses enables continuous production. In this context, this research focuses on identifying diseases in greenhouse tomato cultivation scenarios. For this study, new datasets were created with two image sizes: the Tomato Leaf Image Dataset (TLID) with image sizes of 256 x 256 pixels and 15,256 images, and the Patch Tomato Leaf Image Dataset (PTLID) with patch sizes of 32 x 32 pixels and 227,218 images. Both datasets comprise seven classes, including four types of diseases, two combinations of diseases on the same leaf, and the healthy leaf. Machine Learning techniques have been widely used to identify plant diseases. This work presents two machine learning methods tested with both datasets. In the proposed models, three convolutional neural networks were combined: a customized CNN, VGG19, and Resnet50, along with two voting classification methods using Hard and Soft de-cisions. The evaluation conducted on the datasets demonstrated that using patches significantly improves results, achieving an accuracy of 90.48%. This technique enables the identification of the disease stage.

关键词： Plant diseases Image segmentation Accuracy Databases Noise Greenhouses Machine learning Network architecture Convolutional neural networks Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

AV Navigation in 3D Urban Environments with Curriculum-based Deep Reinforcement Learning

AV Navigation in 3D Urban Environments with Curriculum-based...

引用

2023 International Conference on Unmanned Aircraft Systems, ICUAS 2023

作者： Braathen De Carvalho, Kevin De Oliveira, Iure Rosa L. Brandao, Alexandre S. Universidade Federal de Viçosa Nucleus of Specialization in Robotics Department of Electrical Engineering Graduate Program in Computer Science MG Viçosa36570-900 Brazil Federal University of Viçosa Department of Electrical Engineering MG Viçosa Brazil

ISBN: (纸本)9798350310375

Unmanned Aerial Vehicles (UAVs) are widely used in various applications, from inspection and surveillance to transportation and delivery. Navigating UAVs in complex 3D environments is a challenging task that requires robust and efficient decision-making algorithms. This paper presents a novel approach to UAV navigation in 3D environments using a Curriculum-based Deep Reinforcement Learning (DRL) approach. The proposed method utilizes a deep neural network to model the UAV's decision-making process and to learn a mapping from the state space to the action space. The learning process is guided by a reinforcement signal that reflects the performance of the UAV in terms of reaching its target while avoiding obstacles and with energy efficiency. Simulation results show that the proposed method has a positive trade off when compared to the baseline algorithm. The proposed method was able to perform well in environments with a state space size of 22 millions, allowing the usage in big environments or in maps with high resolution. The results demonstrate the potential of DRL for enabling UAVs to operate effectively in complex environments. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Utilizing Semi-supervised Method in Predicting BRCA1 Pathogenicity Variants

引用

Procedia computer science 2023年 227卷 36-45页

作者： Alam Ahmad Hidayat Joko Pebrianto Trinugroho Rudi Nirwantono Digdo Sudigyo Bens Pardamean Department of Mathematics School of Computer Science Bina Nusantara University Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia 11480

Quantifying the effect of mutations in the BRCA1 gene is useful for understanding their clinical consequences on breast cancer. Machine learning models can be applied to predict the landscape of protein variant effects that might not be always accessible by experiments. In this work, we propose a simple semi-supervised learning method using a Gaussian mixture model to predict ∼90% of the unlabeled missense variants of the BRCA1 gene collected from the ClinVar database. High-quality embeddings are used as a feature of the protein sequences, extracted using the latest pre-trained transformer-based language protein model. A statistical test show that the protein embeddings are effective and robust for predicting pathogenicity. Further, the lower representations of the features are then fed into the semi-supervised model. The prediction performance of the model only for the labeled testing data achieves an AUC score and an accuracy of 79.27% and 71.58%, respectively. Using our defined pathogenic probability score, we find that ∼94% of variants in our unlabeled dataset are well-separated into either benign or pathogenic classes according to that scoring. Our scores obtain a moderate Spearman rank correlation with the results of established unsupervised variant effect models. Finally, our approach can potentially be developed for more accurate and biologically reliable predictions of the variant effects.

关键词： embeddings mutation effect language model protein sequence semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Glyphforge - Automatic Visual Encoding Using Overlapped Visual Variables

Glyphforge - Automatic Visual Encoding Using Overlapped Visu...

引用

International Conference on Information Visualisation (IV)

作者： Diego Hortêncio dos Santos Tiago Davi Oliveira de Araújo Bianchi Serique Meiguins Computer Science Graduate Program Federal University of Pará Pará Belém Brazil IEETA - ESAN University of Aveiro Oliveira de Azeméis Portugal

ISBN: (数字)9798350380163

ISBN: (纸本)9798350380170

This study presents Glyphforge, an automated visual encoding method that makes use of visual variables that partially overlap. The heuristics utilized to optimize the efficiency of the partial overlap factor were derived from studies centered around visual perception assessments. By combining preprocessing and feature selection techniques, this approach aims to identify and retain a maximum of five key features from a given dataset. A visualization technique utilizing layered multidimensional data glyphs was implemented for the purpose of the visual encoding. This tool considers some use cases for the end users, like manipulation of columns and layers, and inverting the dimensions for the glyph layers.

关键词： Visualization Diversity reception Data visualization Feature extraction Encoding Visual perception

来源：评论

学校读者我要写书评

暂无评论

An Investigation of Different Positive and Negative Training Policies for the Task of Hierarchical Music Genre Classification

An Investigation of Different Positive and Negative Training...

引用

International Conference on Systems, Signals and Image Processing, IWSSIP

作者： Cinthya Oestreich Silva Renato Tateiwa Suguiy Carlos N. Silla Graduate Program in Computer Science (PPGIA) Pontifícia Universidade Católica do Paraná (PUCPR) Curitiba Brazil

Within the growth of the music stream companies, the need to classify correctly the musics in their catalogs by genres becomes a really important task. With that, they can suggest songs suitable to the music taste of the user, offering a better user experience. Also, because of the size of their catalogs, this task ought to be done automatically. One way to handle the music genre classification problem is to employ a hierarchical classification approach. In this approach, there is a parent-child relation between the genres, characterizing a hierarchical classification problem. This kind of problem can be tackled by using different approaches, in this paper we investigated the use of the Local Classifier per node approach and different positive and negative training policies. The main contribution of this work is to investigate the impact of different positive and negative training samples policies to train the different classifiers with different versions of the Free Music Archive Database. The computational results show that extracting features from just a part of the music produce similar results from analysing the entire music. In addition, the Random Forest was the best classifier and the less inclusive policy produced the highest scores.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resilient Software Defined Satellite Networks: Combining Clustering Techniques with Efficient Routing Protocols

Resilient Software Defined Satellite Networks: Combining Clu...

引用

International Conference on Software Defined Systems (SDS)

作者： Juliano Antonio da Silva Paulo Mendes Edison Pignaton de Freitas Graduate Program in Computer Science Federal University of Rio Grande do Sul Porto Alegre Brazil Central Research and Technology Airbus Munich Germany

ISBN: (数字)9798331518325

ISBN: (纸本)9798331518332

Low Earth Orbit satellite constellations are highly mobile and thus have time-varying network topologies. Such time-varying networks face various challenges due to intermittently available links and devices. Consequently, many routing algorithms that work well on the terrestrial Internet may not be suitable for Low Earth Orbit (LEO) constellations. This paper provides an analysis of the impact that different types of routing algorithms may have on the performance of LEO constellations. The provided study analyses not only link-state routing algorithms, as used in well-known routing protocols for LEO constellations such as Contact Graph Routing (CGR), which follows a Software Defined Networking (SDN) approach, but also distance-vector algorithms, as well as the potential combination of link-state and distance-vector algorithms when network clusters are used in a LEO constellation.

关键词： Satellites Heuristic algorithms Software algorithms Clustering algorithms Low earth orbit satellites Routing Software Routing protocols Vectors Software defined networking

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：