Y. Shirota, Mima Fujimaki, Emi Tsujiura, Michiya Morita, J. Machuca
{"title":"A SHAP Value-Based Approach to Stock Price Evaluation of Manufacturing Companies","authors":"Y. Shirota, Mima Fujimaki, Emi Tsujiura, Michiya Morita, J. Machuca","doi":"10.1109/AI4I51902.2021.00026","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00026","url":null,"abstract":"In this study, we propose the usage of Shapley values as explanatory variables’ values to represent operational competence measures and try to relate such operational competencies to stock price evaluation. For this analysis, we used the data of Japanese manufacturing companies of three industries, automobiles, electronics and precision machinery equipment. Based on the analysis results, we advocate this type of approach can be expected to provide more reliable information because such operational measures are considered to signal the status of management quality competence.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122260452","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}
Maurizio De Micco, Diego Gragnaniello, F. Zonfrilli, M. Villone, G. Poggi, L. Verdoliva, V. Guida
{"title":"Deep learning-based non-intrusive detection of instabilities in formulated liquids","authors":"Maurizio De Micco, Diego Gragnaniello, F. Zonfrilli, M. Villone, G. Poggi, L. Verdoliva, V. Guida","doi":"10.1109/AI4I51902.2021.00020","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00020","url":null,"abstract":"Stability is a key property of formulated liquids for industrial applications. Before their commercialization, a solid assessment of stability under various operative conditions must be carried out. Traditionally, this is performed by expert researchers that observe the liquid over time and point out the possible occurrence of instabilities. However, this is a costly and time-consuming process. Here, we investigate the potential of deep learning approaches for automatic image-based assessment of formulated liquid stability. Leveraging a recently developed dataset, comprising thousands of images of formulated liquids stored in transparent jars, we implement and test several state-of-the-art Convolutional Neural Networks (CNNs) with different loss functions and augmentation strategies. Experiments prove the effectiveness of this non-invasive approach opening the way to further applications.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132551854","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}
{"title":"Modeling and generating marketplace activities with PROV-DM","authors":"B. V. Batlajery","doi":"10.1109/AI4I51902.2021.00031","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00031","url":null,"abstract":"A movement to support sustainability in fashion has emerged as a result of the damaging environment. We address this problem by providing sustainability-related information of the fashion product as transparent as possible, for individuals to perform better judgemental decision about the product. We propose the use of the PROV family in the modelling processes of users in purchasing a product and generating provenance activities of such behaviour. Ultimately, this will generate the lineage of a product and how it is treated.In this paper, we discuss the use of PROV family in modeling and generating the provenance records of purchasing activities. We demonstrate our work by presenting a real use case of an online fashion marketplace situated in Exeter, UK. The marketplace is set to allow its users exchanging (through buying and selling activities) their personal fashion products, with a goal to reduce the overall products waste. Hence, our contributions are an introduction of sustainable use case with provenance and investigation of the potential provenance related issues through modeling and generating the dynamic processes in the online marketplace.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129504006","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}
{"title":"Explainable Artificial Intelligence for Predictive Maintenance Applications using a Local Surrogate Model","authors":"Andrea Torcianti, S. Matzka","doi":"10.1109/AI4I51902.2021.00029","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00029","url":null,"abstract":"This paper provides an explanatory interface using Local Interpretable Model-agnostic Explanations (LIME) for a predictive maintenance dataset. The explanations are evaluated and the explanatory quality of the model is compared to two previous explainable models for the same dataset.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133607211","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}
Louis B. Rosenberg, G. Willcox, Martti Palosuo, G. Mani
{"title":"Forecasting of Volatile Assets using Artificial Swarm Intelligence","authors":"Louis B. Rosenberg, G. Willcox, Martti Palosuo, G. Mani","doi":"10.1109/AI4I51902.2021.00015","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00015","url":null,"abstract":"Swarm Intelligence (SI) is a natural process that has been shown to amplify decision-making accuracy in many social species, from schools of fish to swarms of bees. Artificial Swarm Intelligence (ASI) is a technology that enables similar benefits in networked human groups. The present research tests whether ASI enables human groups to reach more accurate financial forecasts. Specifically, a group of MBA candidates at Cambridge University was tasked with forecasting the three-day price change of 12 highly volatile assets, a majority of which were cult (or meme) stocks. Over a period of 9 weeks, human forecasters who averaged +0.96% ROI as individuals amplified their ROI to +2.3% when predicting together in artificial swarms (p=0.128). Further, a $$5,000$ bankroll was managed by investing in the top three buy recommendations produced each week by ASI, which yielded a 2.0% ROI over the course of the 9-week study. This suggests that swarm-based forecasting has the potential to boost the performance of financial traders in real-world settings.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133568554","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}
Sotaro Maejima, Keisuke Tsunoda, Midori Kodama, N. Arai, Kazuaki Obana
{"title":"Prediction of Unsteady Indoor-Temperature with Few Pattern Data Learning and Prediction Model Selection Based on Feature Contribution","authors":"Sotaro Maejima, Keisuke Tsunoda, Midori Kodama, N. Arai, Kazuaki Obana","doi":"10.1109/AI4I51902.2021.00025","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00025","url":null,"abstract":"The aim of this paper is to predict indoor-temperature by machine learning under three main constraints: 1) indoor-temperature is unsteady due to people flow, 2) only data with few control patterns of air-conditioning can be used for training, and 3) indoor-temperature is to be accurately and plausibly predicted under unknown air-conditioning control patterns not included in training data. Previous studies tried to predict indoor-temperature in buildings without people but with air-conditioning data for various control patterns. However, these constraints make predictions of indoor-temperature irregular because of unsteady indoor-temperature and inadequate data patterns. To solve the problems, we propose a model selection method based on prediction accuracy and feature contribution. The method can select the prediction model appropriate for the observed instability and can augment data patterns. We demonstrate the effectiveness of our proposal using measured sensor data.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122274129","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}
{"title":"Traffic Sign Detection and Recognition using Deep Learning","authors":"Rudri Mahesh Oza, Angelina Geisen, Taehyung Wang","doi":"10.1109/AI4I51902.2021.00012","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00012","url":null,"abstract":"The Advanced Driver Assistance System includes traffic sign identification and recognition. Traffic signs warn drivers of traffic laws, road conditions, and route directions, assisting them in driving more efficiently and safely. Traffic Sign Recognition is a technique for regulating traffic signals, warning drivers, and commanding or prohibiting specific acts. A quick real-time and reliable automated traffic sign detection and recognition system can assist and relieve the driver, improving driving safety and comfort significantly. For autonomous intelligent driving vehicles or driver assistance systems, automatic identification of traffic signals is also important. This paper aims to use Neural Networks to identify traffic sign patterns. Several image processing methods are used to pre-process the images. Then, to understand traffic sign patterns, Neural Networks stages are performed. To find the best network architecture, the system is trained and validated. The results of the experiments show that traffic sign patterns with complex backgrounds can be classified very accurately.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132681035","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}
Tunç Alkanat, Herman G. J. Groot, M. H. Zwemer, E. Bondarev, P. D. With
{"title":"Towards Scalable Abnormal Behavior Detection in Automated Surveillance","authors":"Tunç Alkanat, Herman G. J. Groot, M. H. Zwemer, E. Bondarev, P. D. With","doi":"10.1109/AI4I51902.2021.00013","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00013","url":null,"abstract":"This study presents a scalable automated video surveillance framework that (1) automatically detects the occurrences of abnormal behavior patterns by both pedestrians and vehicles, and (2) directs the focus of the security personnel to the relevant camera view, thereby providing global situational awareness. Powered by deep learning, our methodology can detect both vision and location-based abnormalities, including the events of vandalism, violence, loitering, scouting, and speeding. The proposed framework requires a low initial investment cost and features both real-time detection of various abnormal behaviors and post-crime analysis in scalable form, by enabling wide-area multi-camera networks with person/object re-identification. By combining multiple functionalities in an efficient framework, the proposed system opens up new possibilities for surveillance.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114895067","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}
{"title":"Design and Implementation of Edge Computing for Detection on Embedded Electromobility","authors":"Ching-Lung Su, W. Lai, Jun-Yun Wu, Pin-Yi Wang","doi":"10.1109/AI4I51902.2021.00027","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00027","url":null,"abstract":"The proposed algorithm architecture of deep learning after darknet dropout are porting on embedded evaluation board with artificial intelligence board of Nvidia Jetson TX2. This article uses the post-training results to implement the actual road testing of edge computing. This design presents accurate identification of vehicles, front signal of traffic light status, road speed limit signs, and vehicle location for safe driving behavior modification system.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123684815","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}
{"title":"Network Compression via Cooperative Architecture Search and Distillation","authors":"Fanghui Xue, J. Xin","doi":"10.1109/AI4I51902.2021.00018","DOIUrl":"https://doi.org/10.1109/AI4I51902.2021.00018","url":null,"abstract":"Neural Architecture Search (NAS) and its variants are competitive in many computer vision tasks lately. In this paper, we develop a Cooperative Architecture Search and Distillation (CASD) method for network compression. Compared with prior art, our method achieves better performance in ResNet164 pruning on CIFAR-10 and CIFAR-100 image classifications, promising to be extended to other tasks.","PeriodicalId":114373,"journal":{"name":"2021 4th International Conference on Artificial Intelligence for Industries (AI4I)","volume":"330 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130093136","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}