2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)最新文献_第8页

Identification and Analysis of Ancient Glass Based on Logistic Regression and Machine Learning Model 基于逻辑回归和机器学习模型的古玻璃识别与分析

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212785

Junjie Hu, Shengjie Yu

{"title":"Identification and Analysis of Ancient Glass Based on Logistic Regression and Machine Learning Model","authors":"Junjie Hu, Shengjie Yu","doi":"10.1109/AINIT59027.2023.10212785","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212785","url":null,"abstract":"During the ancient Silk Road period, glass played a significant role in witnessing cultural integration. However, glass was highly susceptible to environmental and weathering effects. This article aims to explore the changes in elements that occur during the weathering process of glass and propose a method to identify and classify glass based on corresponding characteristics. To begin, an in-depth examination and classification of the components of ancient glass artifacts were conducted. Logistic regression models and ensemble learning techniques, specifically classification tree ensemble learning, a machine learning algorithm, were utilized to improve the understanding of the factors influencing glass properties. These methods enabled the training and optimization of two different types of ancient glass. Additionally, sensitivity analysis was carried out, revealing the significant impact of barium content on ancient glass. Finally, examples of the two glass types were analyzed, and the predicted results from the models were compared. This process led to the determination of an optimal classification model that exhibits excellent applicability, accuracy, and simplicity. The research presents innovative ideas for the identification and authentication of cultural relics such as glass.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114207949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simulation research on the fluorescence excitation and acquisition of SWNT strain sensor based on the principle of photoluminescence 基于光致发光原理的SWNT应变传感器荧光激发与采集仿真研究

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212578

J. Zhang, Fuzhong Zheng, Zhonghao Li, Yuting Lu, Shan Wang, Qiang Cao

{"title":"Simulation research on the fluorescence excitation and acquisition of SWNT strain sensor based on the principle of photoluminescence","authors":"J. Zhang, Fuzhong Zheng, Zhonghao Li, Yuting Lu, Shan Wang, Qiang Cao","doi":"10.1109/AINIT59027.2023.10212578","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212578","url":null,"abstract":"The non-contact strain sensor based on the single-walled carbon nanotube (SWCNT) photoluminescence effect has a great potential that attracted extensive research from both domestic and international scholars. In order to research the non-contact strain sensor, the current paper proposed a fluorescence excitation and acquisition system platform for SWCNT strain sensors, and designed the structures of its optical components. The design, installation, and debugging of this system are conducted. Results show that the fluorescence excitation and acquisition system established in this paper is a suitable platform for SWCNT optical full field strain measurement. Based on this system, the fluorescence excitation and acquisition of the SWCNT film are simulated and analyzed by using OpticStudio software. Simulation results show that the fluorescence intensity is in partial positively correlated with the excitation light intensity, and the light spot diameter could be controlled within 0.1mm. The light spot scanning resolution of the SWNT film achieved the expected effect.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114784348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Short-Term Bus Load Forecasting Based on Combined Feature Selection and GRU-Attention Model 基于特征选择和GRU-Attention模型的短期公交负荷预测

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212714

Bo Li, Kuo Xin, Ruifeng Zhao, Jiangang Lu, Kaiyan Pan

引用次数: 0

Grid Transient Simulation Using Attention-Based Data Augmentation Technique with Supercomputing 基于注意力的超级计算数据增强技术的网格瞬态仿真

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212834

Rundong Gan, Xun Li, Wei Wei, H. Su, Zhu Zhan

{"title":"Grid Transient Simulation Using Attention-Based Data Augmentation Technique with Supercomputing","authors":"Rundong Gan, Xun Li, Wei Wei, H. Su, Zhu Zhan","doi":"10.1109/AINIT59027.2023.10212834","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212834","url":null,"abstract":"The stability of power systems, central to the unimpeded flow of daily life and economic activities in our modern world, is a critical aspect requiring precise forecasting. Notwithstanding, predicting such stability becomes an arduous task, especially amidst situations fraught with high complexity. To mitigate this, our study presents an avant-garde approach for transient simulation of power systems, incorporating Transformer-based data augmentation techniques. We proceed to delineate the application of Transformer models for data augmentation in our methodology. The ensuing augmented data is then used for training models to predict both the stability result and stability index of power systems. Comparative analysis between predictions sourced from original and augmented data indicates that the utilisation of Transformer data augmentation significantly boosts the accuracy of our forecasts. Additionally, we undertake an exhaustive examination of the prediction outcomes, enabling the identification of key factors that impact the stability of power systems. This paper, therefore, offers a groundbreaking and highly effective predictive method for power system stability, yielding a significant advancement in our understanding of power system dynamics and offering preemptive measures to counter potential instability.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124058645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fragile fingerprint for protecting the integrity of the Vision Transformer 脆弱的指纹，以保护视觉变压器的完整性

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212509

Xin Wang, S. Ni, Jie Wang, Yifan Shang, Linji Zhang

{"title":"Fragile fingerprint for protecting the integrity of the Vision Transformer","authors":"Xin Wang, S. Ni, Jie Wang, Yifan Shang, Linji Zhang","doi":"10.1109/AINIT59027.2023.10212509","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212509","url":null,"abstract":"Nowadays, with the rapidly development of deep learning, deep learning models have been widely deployed in various fields and generated significant commercial interest. Some technology companies upload their trained models to cloud servers and serve them to the end-users. Many works have shown that the convolutional neural networks are vulnerable to some model modification attacks, which raise concerns about integrity authentication of the convolutional neural models. Additionally, Transformers based on attention mechanism are now commonly used in computer vision applications, and the need to verify the integrity of ViTs arises if the ViT model is deployed in the safety critical systems. In this paper, we propose a fragile fingerprint method for verifying the integrity of the ViTs, which is based on the targeted adversarial examples. Compared with the existing works, the proposed fingerprint method does not modify the ViTs. We generate some fragile fingerprints, which are classified as the targeted label. In the verification stage, if the fingerprints are successfully classified as targeted label with 100% success rate, we can claim that the ViTs is not modified. Otherwise, when the fingerprint verification success rate is lower than 100%, we can claim that the integrity of ViTs is compromised. Experimental results demonstrate that the fingerprints can effectively verify the integrity of the ViTs when the ViTs is modified by model attacks, even though only a small number of weights of ViTs are changed.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117003004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improved Algorithm Based on Confidence Propagation Decoding Algorithm 基于置信传播译码算法的改进算法

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212630

Xiuyang Li, Yanfeng Tang, Cheng Zhang, Xiuzhuo Wang

{"title":"Improved Algorithm Based on Confidence Propagation Decoding Algorithm","authors":"Xiuyang Li, Yanfeng Tang, Cheng Zhang, Xiuzhuo Wang","doi":"10.1109/AINIT59027.2023.10212630","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212630","url":null,"abstract":"Low-density parity-check codes(LDPC) have the advantages of high performance, flexibility, parallelized processing and iterative decoding, which make them one of the widely used error correction code schemes in communication and storage systems. In order to improve the decoding convergence speed of low-density parity-check codes, the idea of layered decoding is added to the log-likelihood ratio confidence propagation decoding algorithm, and an improved algorithm based on layered decoding strategy is proposed, which solves the problem of low decoding rate caused by vertical iteration after the completion of horizontal iteration by using the log-likelihood ratio confidence propagation decoding algorithm in each layer, at the same time. The results show that the average decoding rate of the algorithm is improved by about 25.5% compared with that before the improvement without losing or almost losing the error correction performance, and the performance of the improved layered decoding algorithm with log-likelihood ratio confidence propagation decoding is optimal when the signal-to-noise ratio is greater than 4, and the decoding performance is improved.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125001948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Autonomous Following Algorithm for UAV Based on Multi-Scale KCF and KF 基于多尺度KCF和KF的无人机自主跟随算法

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212671

Dandan Luo, Peinan Shao, Hong-xun Xu, Lin Wang

引用次数: 0

PSO Optimization-Based Series-Level Fuzzy PID Underwater Robot Fixed Depth Control 基于粒子群优化的串级模糊PID水下机器人定深控制

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212666

Guwen Ren, Shaojie Xin

引用次数: 0

A Novel U-Shaped Hybrid Network for Single Image Dehazing 用于单幅图像去雾的新型u形混合网络

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212555

Zixin Zhang, Xin Li

{"title":"A Novel U-Shaped Hybrid Network for Single Image Dehazing","authors":"Zixin Zhang, Xin Li","doi":"10.1109/AINIT59027.2023.10212555","DOIUrl":"https://doi.org/10.1109/AINIT59027.2023.10212555","url":null,"abstract":"Image dehazing is a challenging problem due to its ill-posed parameter estimation. Despite the significant success of Convolutional Neural Network (CNNs), the inherent locality of CNNs remains a bottleneck for dehazing performance. Though Transformers mitigate the shortcomings of CNNs and have demonstrated promising performance in high-level vision task, the inherent computational complexity makes them infeasible for low-level vision task. In this work, an efficient U-shaped Convolution and Transformer hybrid network, called UCPformer, is proposed. Specifically, Channel Enhanced Transformer (CET) and Efficient Pixel Enhanced Transformer (EPET) is designed in this paper for efficient encoding and decoding of hazy image features. The CET inherits the local representation capability of CNN and general architecture of Transformer, extracting local information efficiently and treating different channels unequally. The EPET inherits the global context modeling capability of Transformer, treating different pixels unequally with linear complexity. Experiments demonstrate the proposed UCPformer achieve superior performance against other dehazing methods.","PeriodicalId":276778,"journal":{"name":"2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130285970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Short-Time Traffic Flow Prediction Based on a Combined Model of EMD and LSTM 基于EMD和LSTM组合模型的短时交通流预测

2023 4th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) Pub Date : 2023-06-16 DOI: 10.1109/AINIT59027.2023.10212744

Qihan Zhao, Lidu Lou, Bo Ouyang

引用次数: 0