检索结果-内蒙古大学图书馆

2023 International Conference on Artificial Intelligence Robotics, Signal and Image Processing, AIRoSIP 2023

作者： Rahmania, Rissa Heryadi, Yaya Lukas, Lukas Suparta, Wayan Sonata, Ilvico Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Faculty of Engineering Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9798350327472

The existence of fine-grained image classification supporting smart retail provides effectiveness in recognizing products with high similarity. However, the generic classification method performs poorly in identifying products from a subordinate category. This paper aims to identify augmentation techniques to leverage the Vision Transformer (ViT) model to classify the fine-grained grocery product, which involves embedding patches and transformer encoders to extract the main features. First, we develop a fine-grained image dataset with ColorJitter, CutOut, and combining both augmentations. Secondly, we perform experiments and analysis of ViT size, embedded patch size and image size in the patch embedding process. Lastly, the ViT model are evaluated according to the image sizes 224, 384, and 512 in accuracy, loss, and confusion matrix. The highest accuracy was obtained at 0.9922. The ColorJitter and CutOut improved the confusion matrix in ViT-B/16 and ViT-L/16 with an image size of 384 and 512. The results show that both augmentations in the ViT model are able to distinguish fine-grained grocery products. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

UWB Channel Modeling and Simulation with Continuous Frequency Response

引用

China Communications 2022年第11期19卷 88-98页

作者： Kai Mao Qiuming Zhu Xijuan Ye Ruirui Feng Fuqiao Duan Yang Miao Maozhong Song The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space College of Electronic and Information EngineeringNanjing University of Aeronautics and AstronauticsNanjing 211106China The Radio Systems Faculty of Electrical Engineering Computer Science and Mathematics(EEMCS)University of Twentethe Netherlands

Ultra-wideband(UWB)technology is a prospective technology for high-rate transmission and accurate localization in the future communication ***-of-art channel modeling approaches usually divide the UWB channel into several sub-band channels and model them *** considering frequency-dependent channel parameters,a novel analytical UWB channel model with continuous frequency response is *** composite effect of all frequency components within the UWB channel on the channel impulse response(CIR)of delay domain is derived based on the continuous channel transfer function(CTF)of frequency *** this basis,a closed-form simulation model for UWB channels and geometry-based parameter calculation method are developed,which can guarantee the continuity of channel characteristics on the frequency domain and greatly reduce the simulation ***,the proposed method is applied to generate UWB channel with 2 GHz bandwidth at sub-6GHz and millimeter wave(mmWave)bands,*** channel measurements are also carried out to validate the proposed *** simulated CIR and power gain are shown to be in good agreement with the measurement ***,the comparison results of power gain and Doppler power spectral density(DPSD)show that the proposed UWB channel model Received:Apr.23,2022 Revised:Jun.09,2022 Editor:Wei Fan achieves a good balance between the simulation accuracy and efficiency.

关键词： ultra-wideband(UWB)channel continuous frequency response frequency-dependent channel parameters simulation model channel measurement

来源：评论

学校读者我要写书评

暂无评论

Exploring Shifted Domain Problem within MNIST Dataset

Exploring Shifted Domain Problem within MNIST Dataset

引用

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

作者： Hidayaturrahman Heryadi, Yaya Lukas Suparta, Wayan Arifin, Yulyani Bina Nusatara University BINUS Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Faculty of Engineering Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9798350320954

Domain data can be shifted in any direction so it will be shared in different distributions to its original domain. This could be a problem since the model was trained with different distributions. It is found that adversarial domain adaptation using domain adversarial neural networks (DANN) can help to solve this problem on some scale. DANN can minimize the discrepancy between source and target data so the model can work well in both domains. The experiment is done by utilizing MNIST dataset that shifted into some conditions. In a condition when the shifting of distribution is too far, DANN is struggling to maintain the knowledge extracted from source data which leads to underperformance in the source and target domain. In contrast, when the shifting is closer, DANN can easily fit the model so it can perform well in both domains. It proves DANN is one of the good approaches to performing domain adaptation in small discrepancies. © 2023 IEEE.

关键词： Adversarial Domain Adaptation Domain Shifting Problem MNIST Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant neural networks from biological error correction codes

引用

Physical Review E 2024年第5期110卷 054303页

作者： Alexander Zlokapa Andrew K. Tan John M. Martyn Ila R. Fiete Max Tegmark Isaac L. Chuang Center for Theoretical Physics Department of Physics McGovern Institute for Brain Research Department of Brain and Cognitive Sciences Department of Electrical Engineering and Computer Science

It has been an open question in deep learning if fault-tolerant computation is possible: can arbitrarily reliable computation be achieved using only unreliable neurons? In the grid cells of the mammalian cortex, analog error correction codes have been observed to protect states against neural spiking noise, but their role in information processing is unclear. Here, we use these biological error correction codes to develop a universal fault-tolerant neural network that achieves reliable computation if the faultiness of each neuron lies below a sharp threshold; remarkably, we find that noisy biological neurons fall below this threshold. The discovery of a phase transition from faulty to fault-tolerant neural computation suggests a mechanism for reliable computation in the cortex and opens a path towards understanding noisy analog systems relevant to artificial intelligence and neuromorphic computing.

关键词： Biological neural networks Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Inference Engine to Predict Uncertain Sugar Content for Sugar Industry 9th

A Hybrid Inference Engine to Predict Uncertain Sugar Content...

引用

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

作者： Asrol, Muhammad Napthaleni Utama, Ditdit Nugeraha Suharjito Harito, Christian Syafrudin, Muhammad Industrial Engineering Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia Department of Artificial Intelligence and Data Science Sejong University Seoul05006 Korea Republic of

The sugar industry is facing challenges in increasing productivity to meet consumer demand. One opportunity for productivity improvement lies in ensuring sugar content. This study proposes a hybrid model to predict sugar content by considering uncertainty factors. A hybrid model combining fuzzy subtractive clustering, and a fuzzy inference system is proposed to predict sugar content. The clustering results using silhouette and fuzzy subtractive clustering successfully identified 6 cluster centres from 2225 datasets collected in a sugar industry in East Java Province. The hybrid inference engine model is designed with fuzzy rules derived from the clustered data. Two inference models are developed: triangular and Gaussian fuzzy numbers. The testing results indicate that the hybrid model with triangular fuzzy numbers shows the smallest error with an R2 value of 0.95. This model is possible to applied in the sugar industry for decision makers in improving productivity with taking attention into uncertain factors influencing sugar content. © 2024 The Authors.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

EEG Microstate Analysis for Diagnosis of Children with ASD 42

EEG Microstate Analysis for Diagnosis of Children with ASD

引用

42nd Chinese Control Conference, CCC 2023

作者： Kong, Xiaoli Li, Jing Ouyang, Gaoxiang School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Beijing Normal University State Key Laboratory of Cognitive Neuroscience and Learning Beijing100875 China

ISBN: (纸本)9789887581543

The analysis of electroencephalogram (EEG) based on machine learning methods has been an effective tool for the diagnosis of children with autism spectrum disorders (ASD). In this paper, we introduce the microstate analysis of EEG to explore whether microstate features can serve as effective biomarkers for ASD diagnosis. After preprocessing raw EEG data, we generate template data by aggregating the EEG data of all the subjects. Afterwards, we segment the template data into five microstate prototypes, and use them to backfit all the preprocessed EEG data to generate a microstate stream. Later, we compute microstate metrics and use various classifiers for the classification. The experimental results show that the features extracted by EEG microstate analysis can distinguish between ASD children and typically developing children more effectively. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

The effect of the cyclic curricular design of modelling-based instruction with virtual labs

引用

International Journal of science Education 2024年第1期46卷 46-72页

作者： Chang, Hsin-Yi Liu, Chen-Chung Wen, Chi-Ting Chang, Ming-Hua Fan Chiang, Shih-Hsun Hwang, Fu-Kwun Program of Learning Sciences and Institute for Research Excellence in Learning Sciences National Taiwan Normal University Taipei Taiwan Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan Department of Computer Science and Information Management Soochow University Taipei Taiwan Department of Physics National Taiwan Normal University Taipei Taiwan

One issue facing teachers who implement model-based instruction within the school system is the tight curricular schedule. The ‘lesson objective tension’ calls for investigations to address instructional issues such as how to organise modelling-based instruction at the curriculum level which is across multiple units. We investigated the effect of the cyclic curricular design spacing out three modelling-based instruction units with virtual labs over three semesters, each involving 73, 181, and 150 junior high school students, respectively. Results indicate that, overall, the approach of modelling with virtual labs better promoted students’ scientific literacy than the traditional instruction did. Specifically, students with low and moderate school science achievements benefitted more as shown in their scientific literacy scores than did the high achievement students. Furthermore, this study found that receiving one unit of modelling-based instruction may not be sufficient to promote students’ scientific literacy, whereas the cyclic approach that suggests students receive two or more units of modelling-based instruction with virtual labs spaced over consecutive semesters had significant effects on promoting students’ scientific literacy. The results provide insights into when and how modelling-based learning with virtual labs can promote scientific literacy at a curricular level. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： lesson objective tension Modelling virtual labs

来源：评论

学校读者我要写书评

暂无评论

A Performance Study of Selected Machine Learning Techniques for Predicting Heart Diseases 2nd

A Performance Study of Selected Machine Learning Techniques ...

引用

2nd International Conference on Security and Information Technologies with AI, Internet Computing and Big-data Applications, SITAIBA 2023

作者： Olorunfemi, Blessing Oluwatobi Ogunde, Adewale Opeoluwa Adeniyi, Abidemi Emmanuel Awotunde, Joseph Bamidele Imoize, Agbotiname Lucky Li, Chun-Ta Faculty of Natural Sciences Department of Computer Science Redeemer’s University Osun Nigeria Department of Computer Science Bowen University Iwo Nigeria Faculty of Information and Communication Sciences Department of Computer Science University of Ilorin Ilorin240003 Nigeria Faculty of Engineering Department of Electrical and Electronics Engineering University of Lagos Lagos Akoka100213 Nigeria Bachelor’s Program of Artificial Intelligence and Information Security Fu Jen Catholic University New Taipei City24206 Taiwan

ISBN: (纸本)9789819777853

Heart Disease remains a leading cause of mortality worldwide. It alarmingly rises at a quick rate, making early heart disease prediction crucial for effective prevention and timely intervention. Heart disease diagnosis is a difficult process that requires technical skills and accuracy to complete. With improvements in technology, computing has lent its voice to simplify the diagnosis of various health problems. Machine learning uses past or existing history to predict future results. Various machine learning techniques have been developed over the years and used in predicting heart diseases with various levels of performance. Identifying the best-suited machine learning technique to use for prediction purposes can be a challenging task. This research work analyses the performance of seven (7) machine learning techniques, comprising AdaBoost Algorithm, KNN, Logistic Regression, Naïve Bayes Classifier, Random Forest, SVM, and XGBoost. The heart disease dataset was downloaded from the UCI repository and analysed using Python programming language in the Jupyter Notebook environment. A comparative analysis of the seven (7) techniques was performed based on Accuracy, Precision, and Recall. From the results obtained, KNN, Random Forest, and XGBoost showed superior performance over the others with an accuracy of 100%, AdaBoost Algorithm followed with an accuracy of 92.2%, SVM followed with an accuracy of 91.71%, Naïve Bayes Classifier followed with an accuracy of 88.29% while Logistic Regression has the least accuracy of 86.34%. KNN, RF, and XGBoost outperformed AdaBoost, SVN, and LR. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach to IoT- Based Water Quality Monitoring 5

Machine Learning Approach to IoT- Based Water Quality Monito...

引用

5th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2023

作者： Chang, Chin-Chih Wei, Chi-Hung Lin, Min-Tien Hwang, Sz-Chwun John Chung Hua University Department of Computer Science and Information Engineering Hsinchu Taiwan Chung Hua University Program in Engineering Science Hsinchu City Taiwan Chung Hua University Department of Landscape Architecture Hsinchu Taiwan

ISBN: (纸本)9798350320978

Water resources are inevitable for human survival but untreated wastewater harms the environment. Thus, ongoing monitoring of water quality is necessary to identify pollution sources and prevent further damage. For such monitoring, an IoT water quality monitoring system was developed using Arduino technology to collect and transmit data to MQTT Brokers and store it in a database. The data is presented on a monitoring webpage. Three machine learning methods (Random Forest, ANN, and LightGBM) were used for backend analysis and prediction. LightGBM was found to have the highest prediction accuracy for NH3, pH, ORP, and temperature. The research contributes to reducing the need for frequent and costly data collection by using an IoT system for real-time monitoring and employing machine learning predictions to compensate for missing data. This approach provides a more efficient and effective method for analyzing and predicting water quality. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Data Mining and Bioinformatics Approaches to Elucidate Bacterial Communities in the Extreme Environment

Data Mining and Bioinformatics Approaches to Elucidate Bacte...

引用

2023 International Conference on Informatics, Multimedia, Cyber and Information Systems, ICIMCIS 2023

作者： Trinugroho, Joko Pebrianto Hidayat, Alam Ahmad Nirwantono, Rudi Asadi, Faisal Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Bioinformatics and Data Science Research Center Mathematics Department Jakarta11480 Indonesia Bina Nusantara University Faculty of Engineering Bioinformatics and Data Science Research Center Biotechnology Department Jakarta11480 Indonesia Bina Nusantara University School of Computer Science Bioinformatics and Data Science Research Center Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350307306

Bacteria are microscopic organisms that can be found in many environments. They are abundant and have many roles in our life. Studying bacteria is essential so that we can identify the bacteria that are needed for many industrial applications. However, the main problem is that majority of the bacteria are unculturable, hampering the exploration of bacteria from different environments. Metagenomics approach which employs Next Generation Sequencing technology could help study bacteria by utilizing 16S rRNA marker gene. This study aims to demonstrate data mining and bioinformatics approaches to analyze 16S rRNA sequencing data. The raw sequencing data of 16S rRNA was collected from biological database. Then, the data were trimmed, denoised, and clustered to generate Amplicon Sequence Variants (ASVs). Diversity (alpha and beta) and taxonomic analyses were then conducted to elucidate the bacterial diversity and taxonomic profile of ASVs. The results of this work showed that Shannon and PD indices in China's hot spring were higher than Singapore and the USA. Furthermore, a significant difference was observed in the PD index. The unweighted UniFrac distance also showed there was a significant difference of the bacterial communities between the three locations. In addition, the taxonomic investigation unveiled prevalent bacterial groups in the ecosystem, namely Proteobacteria, Chloroflexi, Cyanobacteria, and Crenarchaeota. The research outcomes have the potential to serve as a foundational resource for subsequent bacterial metagenomic research, particularly the hot spring environment. © 2023 IEEE.

关键词： Bacteria

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：