Traditional process models like Petri nets effectively describe the control flow of processes but fail to capture stochastic information such as choice likelihoods. To address this, Stochastic Labeled Petri Nets (SPNs...
详细信息
ISBN:
(纸本)9798350365030
Traditional process models like Petri nets effectively describe the control flow of processes but fail to capture stochastic information such as choice likelihoods. To address this, Stochastic Labeled Petri Nets (SPNs) have recently gained attention, extending Petri nets with transition weights that allow to associate executions with probabilities. the language of an SPN thereby becomes a probability distribution over traces (i.e., sequences of activities). To assess an SPN's quality, Earth Mover's Stochastic Conformance (EMSC) emerged as a natural metric that measures the similarity of the SPN's trace distribution to the observed real-world distribution. In this paper, we propose a locally optimal approach for fine-tuning (or finding) transitions weights to maximize an SPN's EMSC. Leveraging the relationship between EMSC and the Wasserstein distance, which recently gained attention as a loss function in machinelearning, we compute subgradients for EMSC to optimize transition weights via subgradient descent. Besides, we propose a straightforward solution to handle models that allow for infinitely many traces. Our optimization approach is broadly applicable for EMSC that is, for EMSC using arbitrary trace-to-trace distances-unlike existing works that either to not explicitly consider EMSC or only special variants. We demonstrate the applicability of our approach on several real-life event logs and discovery algorithms, comparing it to state-of-the-art stochastic process discovery methods and a recent full automated simulation approach.
the proceedings contain 39 papers. the special focus in this conference is on communication and computational technologies. the topics include: Conceptual Framework for Risk Mitigation and Monitoring in Software Organ...
ISBN:
(纸本)9789819774227
the proceedings contain 39 papers. the special focus in this conference is on communication and computational technologies. the topics include: Conceptual Framework for Risk Mitigation and Monitoring in Software Organizations Based on Artificial Immune System;a Multilevel Home Fire Detection and Alert System Using Internet of things (IoT);smart Baby Warmer with Integrated Weight Sensing;a Robust Multi-head Self-attention-Based Framework for Melanoma Detection;Domain Knowledge Based Multi-CNN Approach for Dynamic and Personalized Video Summarization;Efficient Information Retrieval: AWS Textract in Action;text Summarization Techniques for Kannada Language;Parkinson’s Detection From Gait Time Series Classification Using LSTM Tuned by Modified RSA Algorithm;human Action recognition Using Depth Motion Images and Deep learning;maximizing Portfolio Returns in Stock Market Using Deep Reinforcement Techniques;Detecting AI Generated Content: A Study of Methods and Applications;A Systemic Review of machinelearning Approaches for Malicious URL Detection;digital Image Forgery Detection Based on Convolutional Neural Networks;Banana Freshness Classification: A Deep learning Approach with VGG16;greenHarvest: data-Driven Crop Yield Prediction and Eco-Friendly Fertilizer Guidance for Sustainable Agriculture;real-Time Deep learning Based Image Compression Techniques: Review;fog-Cloud Enabled Human Falls Prediction System Using a Hybrid Feature Selection Approach;a 4-Input 8-Bit Comparator with Enhanced Binary Subtraction;multivalued Dependency in Neutrosophic database System;traffic Sign recognition Framework Using Zero-Shot learning;machinelearning Techniques to Categorize the Sentiment Analysis of Amazon Customer Reviews;alzheimer’s Disease Diagnosis Using machinelearning and Deep learning Techniques;sentinel Eyes Violence Detection System;Detection of Alzheimer’s Disease from Brain MRI Images Using Convolutional Neural Network.
A In December 2019, the SARS-CoV-2-caused coronavirus infection (COVID-19) spread to all countries, infecting thousands of people and killing several of them. COVID-19 often results in a mild sickness, while it may so...
详细信息
Facial Expression recognition (FER) systems classify emotions by using geometrical approaches or machinelearning (ML) algorithms such as Convolutional Neural Networks (CNNs). Due to their complexity, these FER system...
详细信息
Artificial Intelligence (AI)-based emotion recognition using various kinds of data has attracted vast attention in recent years. Impressive results have been achieved, but only recently the influence of the training d...
详细信息
ISBN:
(数字)9781665490627
ISBN:
(纸本)9781665490627
Artificial Intelligence (AI)-based emotion recognition using various kinds of data has attracted vast attention in recent years. Impressive results have been achieved, but only recently the influence of the training data with its potential biases and variations in annotation quality are discussed. Still, the majority of the research literature focuses on improving machinelearning techniques and model performance using single data sets. Literature on the impact of training data remains scarce. therefore, in this paper we investigate the influence of the training data on the accuracy of recognizing emotional states in facial expressions by a comparative evaluation, using multiple established facial image databases. Results reveal inconsistencies in the data annotations as well as ambiguities in the emotional states expressed. thus, they allow to critically discuss data quality of the training data, contributing to a more in-depth understanding of previous emotion recognition approaches, and improving the design of more transparent AI solutions.
Basketball has been a popular domain for researchers to collect and analyse vast amount of data. Withthe data of players, teams, games, and seasons, researchers can gain useful insights into players and matches. Nowa...
详细信息
the proceedings contain 11 papers. the special focus in this conference is on Emerging Technologies for Developing Countries. the topics include: Comprehensive Review of Smart Parking Occupancy Prediction Models in Na...
ISBN:
(纸本)9783031639982
the proceedings contain 11 papers. the special focus in this conference is on Emerging Technologies for Developing Countries. the topics include: Comprehensive Review of Smart Parking Occupancy Prediction Models in Nairobi City: Strengths, Weaknesses, and Research Gaps;Integration of IK, Satellite Imagery data, Weather data and Time Series Models in Season Behaviour Predictions. Case of Swayimane, KZN, South Africa;preface;state-of-the-Art Review on Recent Trends in Automatic Speech recognition;predicting Malaria Outbreak Using Indigenous Knowledge and Fuzzy Cognitive Maps: A Case Study of Vhembe District in South Africa;A Systematic Review on the Use of AI-Powered Cloud Computing for Healthcare Resilience;Towards a Smart Healthcare System for Non-Communicable Diseases (NCDs) Management: A Bibliometric Analysis;a machinelearning Approach to Mental Disorder Prediction: Handling the Missing data Challenge;adopting Blockchain for Enhancing data Security and Privacy in Service-Based Digital Platforms: A Case Study of a Distributed Application (Dapp) Global Mission Services.
the proceedings contain 40 papers. the topics discussed include: data science approach for climate change in Saudi Arabia: trend analysis;visualization approach to forecasting retail business;text mining to analyze ma...
ISBN:
(纸本)9781665477239
the proceedings contain 40 papers. the topics discussed include: data science approach for climate change in Saudi Arabia: trend analysis;visualization approach to forecasting retail business;text mining to analyze mammogram screening results for breast cancer patients in Saudi Arabia;implementation of an effective framework in merging cybersecurity and software engineering;alarm rationalization for cybersecurity monitoring;a comparative assessment of accomplishment of sustainable development goals in tropical region;properties and future of the skew Kalman filters;web scraping for data analytics: a beautiful soup implementation;and a machinelearning approach to identifying facial masks in real time.
this paper presents a thorough evaluation of machinelearning algorithms for assessing the risk of having diabetes withthe help of the Pima Indian Diabetes dataset. In view of the global diabetes epidemic, timely and...
详细信息
this paper explores the integration of keyword extraction techniques into audio and video recognition systems designed for mobile office environments. As the prevalence of mobile devices reshapes traditional workspace...
详细信息
暂无评论