2023 IEEE Conference on Artificial Intelligence (CAI)最新文献_第4页

Fuzzy Networks for Explainable Artificial Intelligence 可解释人工智能的模糊网络

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/cai54212.2023.00094

Farzad Arabikhan, A. Gegov, U. Kaymak, Negar Akbari

引用次数: 0

PharmBERT: a Fine-tuned Model for Pharmaceutical Error Prediction PharmBERT:药物误差预测的微调模型

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00151

Gang Hu, Bo Yu, Dustin Doctor

引用次数: 0

Robust Active Simultaneous Localization and Mapping Based on Bayesian Actor-Critic Reinforcement Learning 基于贝叶斯Actor-Critic强化学习的鲁棒主动同步定位与映射

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00035

Bryan Pedraza, Dimah Dera

{"title":"Robust Active Simultaneous Localization and Mapping Based on Bayesian Actor-Critic Reinforcement Learning","authors":"Bryan Pedraza, Dimah Dera","doi":"10.1109/CAI54212.2023.00035","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00035","url":null,"abstract":"Autonomous mobile robots play vital roles in business, industry, manufacturing, e-commerce, and healthcare. Autonomous navigation and obstacle avoidance involve localizing a robot to actively explore and map an unknown environment autonomously without prior knowledge. Simultaneous localization and mapping (SLAM) present a severe challenge. This paper proposes a novel approach for robust navigation and robot action mapping based on Bayesian Actor-Critic (A2C) reinforcement learning. The principle of Actor-Critic combines policy-based and value-based learning by splitting the model into two: the policy model (Actor) computes the action based on the state, and the value model (Critic) tracks whether the agent is ahead or behind during the game. That feedback guides the training process, where both models participate in a game and optimize their output as time passes. We develop a Bayesian A2C model that generates robot actions and quantifies uncertainty on the actions toward robust exploration and collision-free navigation. We adopt the Bayesian inference and optimize the variational posterior distribution over the unknown model parameters using the evidence lower bound (ELBO) objective. The first-order Taylor series approximates the mean and covariance of the variational distribution passed through non-linear functions in the A2C model. The propagated covariance estimates the robot's action uncertainty at the output of the Actor-network. Experiments demonstrate the superior robustness of the proposed Bayesian A2C model exploring heavily noisy environments compared to deterministic homologs. The proposed framework can be applied to other fields of research (underwater robots, biomedical devices/robots, micro-robots, drones, etc.) where robustness and uncertainty quantification are critical.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114730436","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

Meta-ERM: Metaheuristic Optimization Platform for Energy Resource Management in the Smart Grid 智能电网能源管理的元启发式优化平台

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00034

José Almeida, Rafael Barbarroxa, F. Lezama, J. Soares, L. Gomes, F. Oliveira, Z. Vale

引用次数: 0

A Time Series Clinical Data-driven Preprocessing Approach to Early Sepsis Diagnosis 时间序列临床数据驱动的预处理方法在脓毒症早期诊断中的应用

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00070

SadikAref SadikAref, Lachin Fernando, Sindhu Ghanta

{"title":"A Time Series Clinical Data-driven Preprocessing Approach to Early Sepsis Diagnosis","authors":"SadikAref SadikAref, Lachin Fernando, Sindhu Ghanta","doi":"10.1109/CAI54212.2023.00070","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00070","url":null,"abstract":"Sepsis, leading to an estimated 11 million deaths per year, is often left undiagnosed due to its heterogeneity and lack of a single diagnostic test [3]. Every hour of delay in sepsis treatment increases the mortality rate by 4-8%, making early diagnosis and medical intervention critical to saving lives [1].Although several machine learning models have been developed using clinical data, their performance has been unsatisfactory, with low sensitivity scores leading to high mortality. To overcome this, a unique segmentation method is applied to a large time series clinical dataset of 40,336 patients, including 2,932 sepsis and 37,404 nonsepsis cases, comprising 41 variables of laboratory values, vital signs, and demographic data. Multiple experiments are conducted using different machine learning algorithms such as K-Nearest Neighbors, Random Forest, Multi-Layer Perceptron, and Gradient Boosting. The findings reveal that the XGB algorithm with a six-hour early prediction outperforms other models with a recall value of 0.98 and AUROC of 0.98 in predicting sepsis onset. Additionally, the use of data from 12 hours before onset results in a performance recall of 0.86 and AUROC of 0.95. These results demonstrate the potential of utilizing machine learning algorithms for early sepsis detection and highlight the importance of time series data segmentation and feature engineering for improved model performance.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123642603","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

A Model of Computational Creativity based on Engram Cell Theory 基于印迹细胞理论的计算创造力模型

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00121

Qinhan Li, Bin Li

{"title":"A Model of Computational Creativity based on Engram Cell Theory","authors":"Qinhan Li, Bin Li","doi":"10.1109/CAI54212.2023.00121","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00121","url":null,"abstract":"Artificial Intelligence technology has made remarkable progress in machine learning, but it is still in its infancy in creative thinking or computational creativity. In 2018, Yang and Li proposed that the physiological basis for the formation of memories and concepts in the human brain is engram cells (interneuron), and creative thinking is the process of forming new engram cells to connect previously seemingly unrelated concepts. During this process, association and prediction play a key role. In this study, a computational model based on engram cell theory was coded in Python to mimic the process of creative thinking. The validity of the model was tested by simulating the phenomenon of language generation and summarizing the artificial food-set regularity in the plus maze. The results show that, given 29 initial words and certain grammatical rules, the language generation program generates 25,405 sentences after 130,000 calculations, and these generated sentences can be combined into various short paragraphs. After 50 times of training in the cross maze puzzle solving program, the model can master 100% of the rules of artificial food settings. In conclusion, a computational model of creative thinking based on engram cell theory can creatively and automatically generate sentences and paragraphs, and can learn and summarize laws to solve simple puzzles. We plan to further use this model to address complex real-world problems, such as the study of cancer therapeutic targets","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114974481","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

3D Nuclei Segmentation through Deep Learning 基于深度学习的三维核分割

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00137

Roberto Rojas, Carlos F. Navarro, Gabriel A. Orellana, Carmen Gloria Lemus C., V. Castañeda

引用次数: 0

Deep Spectral Features to Detect Atrial Fibrillation using Single-Lead ECG Signals 利用单导联心电信号检测心房颤动的深频谱特征

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00074

Siddhi Bajracharya, Rodrigue Rizk, K. Santosh

{"title":"Deep Spectral Features to Detect Atrial Fibrillation using Single-Lead ECG Signals","authors":"Siddhi Bajracharya, Rodrigue Rizk, K. Santosh","doi":"10.1109/CAI54212.2023.00074","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00074","url":null,"abstract":"Cardiac arrhythmia is a medical condition characterized by irregular heartbeats. Globally, approximately 15-20% of all deaths each year are attributed to undiagnosed arrhythmias. While electrocardiogram (ECG) is a commonly used diagnostic tool to detect heartbeat irregularities, it requires trained experts. To address this challenge, we developed deep spectral features to detect one of the most prevalent forms of arrhythmia, atrial fibrillation, in single-lead ECG signals. Our method utilizes a 2D spectral ECG representation and compares pre-trained deep neural networks (DNNs): DenseNet121, MobileNetV2, ResNet18, and VGG16 to accurately detect atrial fibrillation. Using a single-lead ECG dataset from the PhysioNet Challenge 2017, consisting of 8,528 ECG recordings ranging from 30 to 60 seconds in duration, we achieved a mean F1-score of over 0.90 in less than 30 epochs (training). This surpasses the best-performing model in the 2017 challenge during validation. Our findings demonstrate the potential for deep spectral ECG features to enhance the accuracy and efficiency of arrhythmia detection, aiming to improve patient outcomes and reduce the burden of undiagnosed arrhythmias.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123998908","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

AI Digital Tool Product Lifecycle Governance Framework through Ethics and Compliance by Design† 人工智能数字工具产品生命周期治理框架通过道德和合规设计†

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00155

Eduardo Ortega, Michelle Tran, Grace Bandeen

{"title":"AI Digital Tool Product Lifecycle Governance Framework through Ethics and Compliance by Design†","authors":"Eduardo Ortega, Michelle Tran, Grace Bandeen","doi":"10.1109/CAI54212.2023.00155","DOIUrl":"https://doi.org/10.1109/CAI54212.2023.00155","url":null,"abstract":"The acceleration of Artificial Intelligence (AI) has brought forward new digital tools that have had a wide impact across society. However, AI digital tools (such as ChatGPT, midjourney, DALL-E 2) have brought forward legal and ethical concerns. — Internationally, public, and private leaders are introducing regulatory frameworks to address data governance for such these AI digital tools (i.e., Global Data Protection Regulation, the European AI Act, Blueprint for an AI Bill of Rights, NIST Risk Management Framework, etc.). We recognize that these AI digital tools are a vital aspect of future technological development, but they require input from various sectors in addressing ethics and compliance design. We survey the current landscape of published AI-specific regulatory frameworks and known engineering design process methods. Using a product lifecycle approach, we also introduce a trans-disciplinary framework to address AI ethics and compliance via design. This product lifecycle approach considers several principles: a Human-Centered Design for Risk Assessment, Functional Safety and Risk Management Standardization, and Continuous Governance throughout Product Lifecycle. Establishing risk management throughout AI product lifecycles can ensure accountability for AI product use cases. In addition, by utilizing previous Functional Safety considerations we can create safety mechanisms throughout the product lifecycle of AI digital tools. Finally, establishing in-field testing for continuous governance will enable the flexibility for new compliance standards and transparency. We establish this governance framework to aid in new compliance strategies for these emerging issues with AI digital tools.","PeriodicalId":129324,"journal":{"name":"2023 IEEE Conference on Artificial Intelligence (CAI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125661808","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

Exploring Large Language Models’ Emotion Detection Abilities: Use Cases From the Middle East 探索大型语言模型的情感检测能力:来自中东的用例

2023 IEEE Conference on Artificial Intelligence (CAI) Pub Date : 2023-06-01 DOI: 10.1109/CAI54212.2023.00110

Radhakrishnan Venkatakrishnan, Mahsa Goodarzi, M. A. Canbaz

引用次数: 0