Ai Magazine最新文献

{"title":"Accurate detection of weld seams for laser welding in real-world manufacturing","authors":"Rabia Ali,&nbsp;Muhammad Sarmad,&nbsp;Jawad Tayyub,&nbsp;Alexander Vogel","doi":"10.1002/aaai.12134","DOIUrl":"10.1002/aaai.12134","url":null,"abstract":"<p>Welding is a fabrication process used to join or fuse two mechanical parts. Modern welding machines have automated lasers that follow a predefined weld seam path between the two parts to create a bond. Previous efforts have used simple computer vision edge detectors to automatically detect the weld seam on an image at the junction of two metals to be welded. However, these systems lack reliability and accuracy resulting in manual human verification of the detected edges. This paper presents a neural network architecture that automatically detects the weld seam edge between two metals with high accuracy. We augment this system with a preclassifier that filters out anomalous workpieces (e.g., incorrect placement). Finally, we justify our design choices by evaluating against several existing deep network pipelines as well as proof through real-world use. We also describe in detail the process of deploying the system in a real-world shop floor including evaluation and monitoring. We make public a large well-labeled laser seam dataset to perform deep learning-based edge detection in industrial settings.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 4","pages":"431-441"},"PeriodicalIF":0.9,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12134","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135856069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Expanding impact of mobile health programs: SAHELI for maternal and child care","authors":"Shresth Verma,&nbsp;Gargi Singh,&nbsp;Aditya Mate,&nbsp;Paritosh Verma,&nbsp;Sruthi Gorantla,&nbsp;Neha Madhiwalla,&nbsp;Aparna Hegde,&nbsp;Divy Thakkar,&nbsp;Manish Jain,&nbsp;Milind Tambe,&nbsp;Aparna Taneja","doi":"10.1002/aaai.12126","DOIUrl":"10.1002/aaai.12126","url":null,"abstract":"<p>Underserved communities face critical health challenges due to lack of access to timely and reliable information. Nongovernmental organizations are leveraging the widespread use of cellphones to combat these healthcare challenges and spread preventative awareness. The health workers at these organizations reach out individually to beneficiaries; however, such programs still suffer from declining engagement. We have deployed <span>Saheli</span>, a system to efficiently utilize the limited availability of health workers for improving maternal and child health in India. <span>Saheli</span> uses the Restless Multi-armed Bandit (RMAB) framework to identify beneficiaries for outreach. It is the <i>first deployed application</i> for RMABs in public health, and is already <i>in continuous use</i> by our partner NGO, ARMMAN. We have already reached ∼130K beneficiaries with <span>Saheli</span>, and are on track to serve one million beneficiaries by the end of 2023. This scale and impact has been achieved through multiple innovations in the RMAB model and its development, in preparation of real world data, and in deployment practices; and through careful consideration of responsible AI practices. Specifically, in this paper, we describe our approach to learn from past data to improve the performance of <span>Saheli</span>'s RMAB model, the real-world challenges faced during deployment and adoption of <span>Saheli</span>, and the end-to-end pipeline.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 4","pages":"363-376"},"PeriodicalIF":0.9,"publicationDate":"2023-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12126","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136013330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Energy forecasting with robust, flexible, and explainable machine learning algorithms","authors":"Zhaoyang Zhu,&nbsp;Weiqi Chen,&nbsp;Rui Xia,&nbsp;Tian Zhou,&nbsp;Peisong Niu,&nbsp;Bingqing Peng,&nbsp;Wenwei Wang,&nbsp;Hengbo Liu,&nbsp;Ziqing Ma,&nbsp;Xinyue Gu,&nbsp;Jin Wang,&nbsp;Qiming Chen,&nbsp;Linxiao Yang,&nbsp;Qingsong Wen,&nbsp;Liang Sun","doi":"10.1002/aaai.12130","DOIUrl":"10.1002/aaai.12130","url":null,"abstract":"<p>Energy forecasting is crucial in scheduling and planning future electric load, so as to improve the reliability and safeness of the power grid. Despite recent developments of forecasting algorithms in the machine learning community, there is a lack of general and advanced algorithms specifically considering requirements from the power industry perspective. In this paper, we present eForecaster, a unified AI platform including robust, flexible, and explainable machine learning algorithms for diversified energy forecasting applications. Since October 2021, multiple commercial bus load, system load, and renewable energy forecasting systems built upon eForecaster have been deployed in seven provinces of China. The deployed systems consistently reduce the average Mean Absolute Error (MAE) by 39.8% to 77.0%, with reduced manual work and explainable guidance. In particular, eForecaster also integrates multiple interpretation methods to uncover the working mechanism of the predictive models, which significantly improves forecasts adoption and user satisfaction.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 4","pages":"377-393"},"PeriodicalIF":0.9,"publicationDate":"2023-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12130","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136212318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decision making in open agent systems","authors":"Adam Eck,&nbsp;Leen-Kiat Soh,&nbsp;Prashant Doshi","doi":"10.1002/aaai.12131","DOIUrl":"10.1002/aaai.12131","url":null,"abstract":"<p>In many real-world applications of AI, the set of actors and tasks are not constant, but instead change over time. Robots tasked with suppressing wildfires eventually run out of limited suppressant resources and need to temporarily disengage from the collaborative work in order to recharge, or they might become damaged and leave the environment permanently. In a large business organization, objectives and goals change with the market, requiring workers to adapt to perform different sets of tasks across time. We call these multiagent systems (MAS) <b>open agent systems</b> (OASYS), and the <i>openness</i> of the sets of agents and tasks necessitates new capabilities and modeling for decision making compared to planning and learning in <i>closed</i> environments. In this article, we discuss three notions of openness: agent openness, task openness, and type openness. We also review the past and current research on addressing the novel challenges brought about by openness in OASYS. We share lessons learned from these efforts and suggest directions for promising future work in this area. We also encourage the community to engage and participate in this area of MAS research to address critical real-world problems in the application of AI to enhance our daily lives.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 4","pages":"508-523"},"PeriodicalIF":0.9,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12131","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135146704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introduction to the special issue on Innovative Applications of Artificial Intelligence (IAAI 2023)","authors":"Karen Zita Haigh,&nbsp;Alexander Wong,&nbsp;YuHao Chen","doi":"10.1002/aaai.12132","DOIUrl":"10.1002/aaai.12132","url":null,"abstract":"&lt;p&gt;&lt;i&gt;This special issue of AI Magazine covers select applications from the IAAI conference held in 2023 in Washington, DC. The articles address a broad range of very challenging issues and contain great lessons for AI researchers and application developers&lt;/i&gt;.&lt;/p&gt;&lt;p&gt;The goal of the Innovative Applications of Artificial Intelligence (IAAI) conference is to highlight new, innovative systems and application areas of AI technology and to point out the often-overlooked difficulties involved in deploying complex technology to end users. Those of us who have ventured out of the realm of pure research and tried to build applications to be used by our fellow humans realize that it takes a lot more than just brilliant algorithms to make an application survive in the real world. Each application that succeeds is worth celebrating, and the teams behind them are due wholehearted congratulations.&lt;/p&gt;&lt;p&gt;It is in this spirit that we bring you this special issue covering select applications from the IAAI conference held in February 2023 in Washington, DC. The articles address a broad range of challenging issues and contain lessons for fellow AI researchers and application developers.&lt;/p&gt;&lt;p&gt;IAAI acceptance criteria are different from most academic conferences in that the end-user application &lt;i&gt;must&lt;/i&gt; come first and foremost. A paper written for the annual AAAI or IJCAI conferences is unlikely to be accepted for IAAI because these papers focus on the innovation in the algorithm. IAAI focuses on how to get algorithms to the end user. A paper that describes a small change in a learning model to achieve 1% improvement in accuracy over related work is not appropriate for IAAI. Meanwhile, IAAI would be very interested in a similar paper saying that the current model is not deployable (e.g., due to size or training data), but a small change in the model that loses 1% accuracy allows it to be deployable.&lt;/p&gt;&lt;p&gt;The articles in this issue cover humanitarian needs, manufacturing, and forecasting. A common theme is that all deployed applications work directly with end users to design a system that meets end-user needs. Many of the papers have co-authors from the end user community, which strengthens the paper significantly. The papers focus on end-user concerns, both in terms of solving the true end-user problem and in terms of generating explainable results.&lt;/p&gt;&lt;p&gt;The first article by Rahul Nair from IBM with Bo Madsen and Alexander Kjærum from the Danish Refugee Council presents a system that forecasts the dynamics of refugee displacements. The system, &lt;i&gt;Foresight&lt;/i&gt;, supports long-term forecasts aimed at humanitarian response planning. The explainable system provides evidence and context supporting the forecast and allows analysts to explore “what if” scenarios. Challenges to fielding this system include human-centered design, acceptance in the user community, and technical maturity, notably the lack of high-quality data. Foresight now covers 25 countries and 89% of","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 4","pages":"352-353"},"PeriodicalIF":0.9,"publicationDate":"2023-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12132","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134943961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An explainable forecasting system for humanitarian needs assessment","authors":"Rahul Nair,&nbsp;Bo Madsen,&nbsp;Alexander Kjærum","doi":"10.1002/aaai.12133","DOIUrl":"10.1002/aaai.12133","url":null,"abstract":"<p>We present a machine learning system for forecasting forced displacement populations deployed at the Danish Refugee Council (DRC). The system, named Foresight, supports long-term forecasts aimed at humanitarian response planning. It is explainable, providing evidence and context supporting the forecast. Additionally, it supports scenarios, whereby analysts are able to generate forecasts under alternative conditions. The system has been in deployment since early 2020 and powers several downstream business functions within DRC. It is central to our annual Global Displacement Report, which informs our response planning. We describe the system, key outcomes, lessons learnt, along with technical limitations and challenges in deploying machine learning systems in the humanitarian sector.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 4","pages":"354-362"},"PeriodicalIF":0.9,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12133","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135483553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of deep metric learning in the verification process of wheel design similarity: Hyundai motor company case","authors":"Kyung Pyo Kang,&nbsp;Ga Hyeon Jung,&nbsp;Jung Hoon Eom,&nbsp;Soon Beom Kwon,&nbsp;Jae Hong Park","doi":"10.1002/aaai.12127","DOIUrl":"10.1002/aaai.12127","url":null,"abstract":"<p>The global automobile market experiences quick changes in design preferences. In response to the demand shifts, manufacturers now try to apply new technologies to bring a novel design to market faster. In this paper, we introduce a novel AI application that performs a similarity verification task of wheel designs that aims to solve the real-world problem. Through the deep metric learning approach, we empirically prove that the cross-entropy loss does similar tasks as the pairwise losses do in the embedding space. On Jan 2022, we successfully transitioned the verification system to the wheel design process of Hyundai Motor Company's design team and shortened the verification time by 90% to a maximum of 10 min. With a few clicks, the designers at Hyundai Motor could take advantage of our verification system.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 4","pages":"406-417"},"PeriodicalIF":0.9,"publicationDate":"2023-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12127","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135483410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novelty detection for election fraud: A case study with agent-based simulation data","authors":"Khurram Yamin,&nbsp;Nima Jadali,&nbsp;Yao Xie,&nbsp;Dima Nazzal","doi":"10.1002/aaai.12112","DOIUrl":"https://doi.org/10.1002/aaai.12112","url":null,"abstract":"<p>In this paper, we propose a robust election simulation model and independently developed election anomaly detection algorithm that demonstrates the simulation's utility. The simulation generates artificial elections with similar properties and trends as elections from the real world, while giving users control and knowledge over all the important components of the elections. We generate a clean election results dataset without fraud as well as datasets with varying degrees of fraud. We then measure how well the algorithm is able to successfully detect the level of fraud present. The algorithm determines how similar actual election results are as compared to the predicted results from polling and a regression model of other regions that have similar demographics. We use k-means to partition electoral regions into clusters such that demographic homogeneity is maximized among clusters. We then use a novelty detection algorithm implemented as a one-class support vector machine where the clean data is provided in the form of polling predictions and regression predictions. The regression predictions are built from the actual data in such a way that the data supervises itself. We show both the effectiveness of the simulation technique and the machine learning model in its success in identifying fraudulent regions.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 3","pages":"255-262"},"PeriodicalIF":0.9,"publicationDate":"2023-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12112","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50125753","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards machines that understand people","authors":"Andrew Howes,&nbsp;Jussi P. P. Jokinen,&nbsp;Antti Oulasvirta","doi":"10.1002/aaai.12116","DOIUrl":"https://doi.org/10.1002/aaai.12116","url":null,"abstract":"<p>The ability to estimate the state of a human partner is an insufficient basis on which to build cooperative agents. Also needed is an ability to predict how people adapt their behavior in response to an agent's actions. We propose a new approach based on computational rationality, which models humans based on the idea that predictions can be derived by calculating policies that are approximately optimal given human-like bounds. Computational rationality brings together reinforcement learning and cognitive modeling in pursuit of this goal, facilitating machine understanding of humans.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 3","pages":"312-327"},"PeriodicalIF":0.9,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12116","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50129136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Visual crowd analysis: Open research problems","authors":"Muhammad Asif Khan,&nbsp;Hamid Menouar,&nbsp;Ridha Hamila","doi":"10.1002/aaai.12117","DOIUrl":"https://doi.org/10.1002/aaai.12117","url":null,"abstract":"<p>Over the last decade, there has been a remarkable surge in interest in automated crowd monitoring within the computer vision community. Modern deep-learning approaches have made it possible to develop fully automated vision-based crowd-monitoring applications. However, despite the magnitude of the issue at hand, the significant technological advancements, and the consistent interest of the research community, there are still numerous challenges that need to be overcome. In this article, we delve into six major areas of visual crowd analysis, emphasizing the key developments in each of these areas. We outline the crucial unresolved issues that must be tackled in future works, in order to ensure that the field of automated crowd monitoring continues to progress and thrive. Several surveys related to this topic have been conducted in the past. Nonetheless, this article thoroughly examines and presents a more intuitive categorization of works, while also depicting the latest breakthroughs within the field, incorporating more recent studies carried out within the last few years in a concise manner. By carefully choosing prominent works with significant contributions in terms of novelty or performance gains, this paper presents a more comprehensive exposition of advancements in the current state-of-the-art.</p>","PeriodicalId":7854,"journal":{"name":"Ai Magazine","volume":"44 3","pages":"296-311"},"PeriodicalIF":0.9,"publicationDate":"2023-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/aaai.12117","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"50121071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}