Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665708
Marcelo Nery, R. Santos, W. Santos, Vítor Lourenço, M. Moreno
Knowledge Engineering is key to enable knowledge extraction, representation and reasoning, leading to better business insights and decisions. Current advances in machine learning and new trends in AI are bringing a plethora of algorithms capable of performing advanced pattern recognition and data classification. The ability to link, to organize and to query the outputs of these algorithms as well as the ability to handle huge amounts of data and its multiple sources is crucial to maximize the potential of such advances, specially over large datasets. This paper presents challenges in the context of digital agriculture and our position in moving forward with these capabilities whilst using knowledge engineering techniques.
{"title":"Facing Digital Agriculture Challenges with Knowledge Engineering","authors":"Marcelo Nery, R. Santos, W. Santos, Vítor Lourenço, M. Moreno","doi":"10.1109/AI4I.2018.8665708","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665708","url":null,"abstract":"Knowledge Engineering is key to enable knowledge extraction, representation and reasoning, leading to better business insights and decisions. Current advances in machine learning and new trends in AI are bringing a plethora of algorithms capable of performing advanced pattern recognition and data classification. The ability to link, to organize and to query the outputs of these algorithms as well as the ability to handle huge amounts of data and its multiple sources is crucial to maximize the potential of such advances, specially over large datasets. This paper presents challenges in the context of digital agriculture and our position in moving forward with these capabilities whilst using knowledge engineering techniques.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126059323","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665716
Zhu Zhou, T. Zhang
With the complexity, heterogeneity, and scale of today's networks, service assurance is becoming increasingly complicated. Meanwhile, significant amounts of telemetry data are collected on virtual network functions; it has been proposed that machine learning can be used to predict/forecast key performance indicators by analyzing this data and then taking actions to prevent severe service degradation. In this paper, we demonstrate the process of telemetry data collecting and filtering, feature dimension reduction, and machine learning algorithm selection for detecting packet loss in a NFV based vEPC test system.
{"title":"Applying Machine Learning to Service Assurance in Network Function Virtualization Environment","authors":"Zhu Zhou, T. Zhang","doi":"10.1109/AI4I.2018.8665716","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665716","url":null,"abstract":"With the complexity, heterogeneity, and scale of today's networks, service assurance is becoming increasingly complicated. Meanwhile, significant amounts of telemetry data are collected on virtual network functions; it has been proposed that machine learning can be used to predict/forecast key performance indicators by analyzing this data and then taking actions to prevent severe service degradation. In this paper, we demonstrate the process of telemetry data collecting and filtering, feature dimension reduction, and machine learning algorithm selection for detecting packet loss in a NFV based vEPC test system.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115035770","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665694
Gian Antonio Susto, M. Terzi, Chiara Masiero, S. Pampuri, A. Schirru
On-line and phone banking frauds are responsible for millions of dollars loss every year. In this work, we propose a Machine Learning-based Decision Support System to automatically associate a risk factor to each transaction performed through an on-line/mobile banking system. The proposed approach has a hierarchical architecture: First, an unsupervised Machine Learning module is used to detect abnormal patterns or wrongly labeled transactions; then, a supervised module provides a risk factor for the transactions that were not marked as anomalies in the previous step. Our solution exploits personal and historical information about the user, statistics that describe online traffic generated on the online/mobile banking system, and features extracted from motives of the transactions. The proposed approach deals with dataset unbalancing effectively. Moreover, it has been validated on a large database of transactions and on-line traffic provided by an industrial partner.
{"title":"A Fraud Detection Decision Support System via Human On-Line Behavior Characterization and Machine Learning","authors":"Gian Antonio Susto, M. Terzi, Chiara Masiero, S. Pampuri, A. Schirru","doi":"10.1109/AI4I.2018.8665694","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665694","url":null,"abstract":"On-line and phone banking frauds are responsible for millions of dollars loss every year. In this work, we propose a Machine Learning-based Decision Support System to automatically associate a risk factor to each transaction performed through an on-line/mobile banking system. The proposed approach has a hierarchical architecture: First, an unsupervised Machine Learning module is used to detect abnormal patterns or wrongly labeled transactions; then, a supervised module provides a risk factor for the transactions that were not marked as anomalies in the previous step. Our solution exploits personal and historical information about the user, statistics that describe online traffic generated on the online/mobile banking system, and features extracted from motives of the transactions. The proposed approach deals with dataset unbalancing effectively. Moreover, it has been validated on a large database of transactions and on-line traffic provided by an industrial partner.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122071639","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665709
Ryota Shimizu, Kosuke Asako, Hiroki Ojima, Shohei Morinaga, M. Hamada, T. Kuroda
We propose a novel method of training neural networks for industrial image classification that can reduce the effect of imbalanced data in supervised training. We considered visual quality inspection of industrial products as an image-classification task and attempted to solve this with a convolutional neural network; however, a problem of imbalanced data emerged in supervised training in which the neural network cannot optimize parameters. Since most industrial products are not defective, samples of defective products were fewer than those of the non-defective products; this difference in the number of samples causes an imbalance in training data. A neural network trained with imbalanced data often has varied levels of precision in determining each class depending on the difference in the number of class samples in the training data, which is a significant problem in industrial quality inspection. As a solution to this problem, we propose a balanced mini-batch training method that can virtually balance the class ratio of training samples. In an experiment, the neural network trained with the proposed method achieved higher classification ability than that trained with over-sampled or undersampled data for two types of imbalanced image datasets.
{"title":"Balanced Mini-Batch Training for Imbalanced Image Data Classification with Neural Network","authors":"Ryota Shimizu, Kosuke Asako, Hiroki Ojima, Shohei Morinaga, M. Hamada, T. Kuroda","doi":"10.1109/AI4I.2018.8665709","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665709","url":null,"abstract":"We propose a novel method of training neural networks for industrial image classification that can reduce the effect of imbalanced data in supervised training. We considered visual quality inspection of industrial products as an image-classification task and attempted to solve this with a convolutional neural network; however, a problem of imbalanced data emerged in supervised training in which the neural network cannot optimize parameters. Since most industrial products are not defective, samples of defective products were fewer than those of the non-defective products; this difference in the number of samples causes an imbalance in training data. A neural network trained with imbalanced data often has varied levels of precision in determining each class depending on the difference in the number of class samples in the training data, which is a significant problem in industrial quality inspection. As a solution to this problem, we propose a balanced mini-batch training method that can virtually balance the class ratio of training samples. In an experiment, the neural network trained with the proposed method achieved higher classification ability than that trained with over-sampled or undersampled data for two types of imbalanced image datasets.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129939177","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665702
A. Chakraborty
Image recognition is a major area of application of machine learning - evolving at a rapid pace with a number of programming platforms available to developers. While each platform has its own uniqueness, the methodology of image recognition consists of a sequence of image processing tasks, development of a classifier algorithm, training and testing followed by deployment. This tutorial will delve into the programming aspects of image processing including thresholding, contouring and template matching. In order to provide practical hands on programming this tutorial will closely look at three real life applications of image pattern recognition namely ALPR using Tesseract OCR and will touch upon using CNN for character detection. The tutorial will explain the algorithm, implementation of pseudocode through Python using two major platforms: OpenCV and Tensorflow.
{"title":"Image Processing and Image Pattern Recognition a Programming Tutorial","authors":"A. Chakraborty","doi":"10.1109/AI4I.2018.8665702","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665702","url":null,"abstract":"Image recognition is a major area of application of machine learning - evolving at a rapid pace with a number of programming platforms available to developers. While each platform has its own uniqueness, the methodology of image recognition consists of a sequence of image processing tasks, development of a classifier algorithm, training and testing followed by deployment. This tutorial will delve into the programming aspects of image processing including thresholding, contouring and template matching. In order to provide practical hands on programming this tutorial will closely look at three real life applications of image pattern recognition namely ALPR using Tesseract OCR and will touch upon using CNN for character detection. The tutorial will explain the algorithm, implementation of pseudocode through Python using two major platforms: OpenCV and Tensorflow.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"38 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124267978","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665683
Debojyoti Dutta, Amit Kumar Saha, Johnu George, Xinyuan Huang, Ramdoot Pydipaty, Purushotham Kamath, L. Tucker
Even though AI/ML is of strategic importance for many companies, it is not easy to come up with an AI life cycle in a multi-cloud world that is being increasingly embraced. In this paper, we present our position on an AI strategy that is future proof and does not force vendor lock in.
{"title":"Towards #consistentAI Position Paper","authors":"Debojyoti Dutta, Amit Kumar Saha, Johnu George, Xinyuan Huang, Ramdoot Pydipaty, Purushotham Kamath, L. Tucker","doi":"10.1109/AI4I.2018.8665683","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665683","url":null,"abstract":"Even though AI/ML is of strategic importance for many companies, it is not easy to come up with an AI life cycle in a multi-cloud world that is being increasingly embraced. In this paper, we present our position on an AI strategy that is future proof and does not force vendor lock in.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128950927","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}
Pub Date : 2018-09-01DOI: 10.1109/ai4i.2018.8665703
{"title":"Ai4i 2018 Organizing Committee","authors":"","doi":"10.1109/ai4i.2018.8665703","DOIUrl":"https://doi.org/10.1109/ai4i.2018.8665703","url":null,"abstract":"","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129095084","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665711
Nikhil Nigam, S. Lall, P. Hovareshti, Kristopher L. Ezra, L. Mockus, D. Tolani, Shawn Sloan
Research in multi-agent systems has mostly focused on heuristic/semi-heuristic methods for control, which lack in robustness and generalizability. Control theoretic techniques guarantee stability (and often optimality), but the results are limited in scope. Hence, there is a need to design intelligent control techniques as a function of sub-system dynamics, network structure and control/decision processes. We are developing S4C - a control theoretic framework for analysis and design of interacting robotic systems. We use “sufficient statistics” to generalize the separation principle - enabling decoupled optimal control and estimation. These techniques are applied to a missile guidance problem, demonstrating robustness to sensor/process noise. An agent-based simulation architecture has also been developed and used for studies. In addition, we use a verification and validation approach based on Gaussian process regression to test for cases where modeling assumptions are relaxed.
{"title":"Sufficient Statistics for Optimal Decentralized Control in System of Systems","authors":"Nikhil Nigam, S. Lall, P. Hovareshti, Kristopher L. Ezra, L. Mockus, D. Tolani, Shawn Sloan","doi":"10.1109/AI4I.2018.8665711","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665711","url":null,"abstract":"Research in multi-agent systems has mostly focused on heuristic/semi-heuristic methods for control, which lack in robustness and generalizability. Control theoretic techniques guarantee stability (and often optimality), but the results are limited in scope. Hence, there is a need to design intelligent control techniques as a function of sub-system dynamics, network structure and control/decision processes. We are developing S4C - a control theoretic framework for analysis and design of interacting robotic systems. We use “sufficient statistics” to generalize the separation principle - enabling decoupled optimal control and estimation. These techniques are applied to a missile guidance problem, demonstrating robustness to sensor/process noise. An agent-based simulation architecture has also been developed and used for studies. In addition, we use a verification and validation approach based on Gaussian process regression to test for cases where modeling assumptions are relaxed.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121356691","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665691
M. Moreno, R. Santos, Reinaldo Silva, W. Santos, Renato Cerqueira
Seismic data interpretation process is a time consuming and knowledge intensive process. Recently, research community proposed machine learning techniques to extract information from seismic images, aiming at assisting this interpretation process. Although useful, these techniques solve just part of the seismic interpretation problem. They focus on identifying specific features (e.g. salt diapirs, reservoir facies, mini-basins) but they fail in identifying and analyzing the spatial correlation among them. In this work we propose the use of hyper knowledge specifications to address this issue. The main contribution of this work is not only to present hyper knowledge templates to this problem, but also the discussions about how to map hyperknowledge as a knowledge graph as well as creating a reasoning engine that exploits the knowledge graph representation.
{"title":"Assisting Seismic Image Interpretations with Hyperknowledge","authors":"M. Moreno, R. Santos, Reinaldo Silva, W. Santos, Renato Cerqueira","doi":"10.1109/AI4I.2018.8665691","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665691","url":null,"abstract":"Seismic data interpretation process is a time consuming and knowledge intensive process. Recently, research community proposed machine learning techniques to extract information from seismic images, aiming at assisting this interpretation process. Although useful, these techniques solve just part of the seismic interpretation problem. They focus on identifying specific features (e.g. salt diapirs, reservoir facies, mini-basins) but they fail in identifying and analyzing the spatial correlation among them. In this work we propose the use of hyper knowledge specifications to address this issue. The main contribution of this work is not only to present hyper knowledge templates to this problem, but also the discussions about how to map hyperknowledge as a knowledge graph as well as creating a reasoning engine that exploits the knowledge graph representation.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114536752","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}
Pub Date : 2018-09-01DOI: 10.1109/AI4I.2018.8665693
Xiaofeng Yue, Guangzhi Qu, Bo Liu, Anyi Liu
Sound source detection and localization have a lot of practical uses in many industrial settings. Most of sound source direction detection algorithms in literature are designed to identify the angle of sound source in a 2D space. In this work, we propose to use convolutional neural networks to detect the sound source direction in a 3D space. This algorithm is based on the generalized cross correlation method with phase transform (GCC-PHAT) [1] to derive time delay of arrival (TDOA). By using a convolutional neural network model, this algorithm can be applied and deployed. In addition, by modifying GCC-PHAT formula, this approach also works of multiple sound sources detection. Simulation experimental results on single sound source and multiple sound sources detection show the proposed system could work in most situations.
{"title":"Detection Sound Source Direction in 3D Space Using Convolutional Neural Networks","authors":"Xiaofeng Yue, Guangzhi Qu, Bo Liu, Anyi Liu","doi":"10.1109/AI4I.2018.8665693","DOIUrl":"https://doi.org/10.1109/AI4I.2018.8665693","url":null,"abstract":"Sound source detection and localization have a lot of practical uses in many industrial settings. Most of sound source direction detection algorithms in literature are designed to identify the angle of sound source in a 2D space. In this work, we propose to use convolutional neural networks to detect the sound source direction in a 3D space. This algorithm is based on the generalized cross correlation method with phase transform (GCC-PHAT) [1] to derive time delay of arrival (TDOA). By using a convolutional neural network model, this algorithm can be applied and deployed. In addition, by modifying GCC-PHAT formula, this approach also works of multiple sound sources detection. Simulation experimental results on single sound source and multiple sound sources detection show the proposed system could work in most situations.","PeriodicalId":133657,"journal":{"name":"2018 First International Conference on Artificial Intelligence for Industries (AI4I)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124909567","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：