2021 Swedish Artificial Intelligence Society Workshop (SAIS)最新文献

{"title":"Class-Incremental Learning for Semantic Segmentation - A study","authors":"Karl Holmquist, L. Klasén, M. Felsberg","doi":"10.1109/SAIS53221.2021.9483955","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9483955","url":null,"abstract":"One of the main challenges of applying deep learning for robotics is the difficulty of efficiently adapting to new tasks while still maintaining the same performance on previous tasks. The problem of incrementally learning new tasks commonly struggles with catastrophic forgetting in which the previous knowledge is lost.Class-incremental learning for semantic segmentation, addresses this problem in which we want to learn new semantic classes without having access to labeled data for previously learned classes. This is a problem in industry, where few pre-trained models and open datasets matches exactly the requisites. In these cases it is both expensive and labour intensive to collect an entirely new fully-labeled dataset. Instead, collecting a smaller dataset and only labeling the new classes is much more efficient in terms of data collection.In this paper we present the class-incremental learning problem for semantic segmentation, we discuss related work in terms of the more thoroughly studied classification task and experimentally validate the current state-of-the-art for semantic segmentation. This lays the foundation as we discuss some of the problems that still needs to be investigated and improved upon in order to reach a new state-of-the-art for class-incremental semantic segmentation.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124357910","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":"Rock Classification with Machine Learning: a Case Study from the Zinkgruvan Zn-Pb-Ag Deposit, Bergslagen, Sweden","authors":"Filip Simán, N. Jansson, T. Kampmann, F. Liwicki","doi":"10.1109/SAIS53221.2021.9483959","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9483959","url":null,"abstract":"In this paper we assess two traditional machine learning (ML) methods which can be used for automatic rock type classification: (1) the Self-Organising Map (SOM) with k-means clustering, and (2) Classification and Regression Trees (CART). The dataset used for this paper were chemical compositional data of rocks acquired through X-Ray Fluorescence (XRF) analysis. The ground truth of the dataset was generated by human experts in the field of geology. The complexity of the chosen dataset influenced the evaluation performance of the two ML models. We achieve an overall accuracy of 68.02 % and 62.79 % respectively when using SOM with k-means and CART.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124585035","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":"AI Transformation in the Public Sector: Ongoing Research","authors":"Einav Peretz-Andersson, Niklas Lavesson, A. Bifet, Patrick Mikalef","doi":"10.1109/SAIS53221.2021.9483960","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9483960","url":null,"abstract":"Real-world application of data-driven and intelligent systems (AI) is increasing in the private and public sector as well as in society at large. Many organizations transform as a consequence of increased AI implementation. The consequences of such transformations may include new recruitment plans, procurement of additional IT, changes in existing positions and roles, new business models, as well as new policies and regulations. However, it is unclear how this transformation varies across different types of organizations. We study the effects of bottom-up approaches, such as pilot projects and mentoring to specific groups within organizations, and aim to explore how such approaches can complement the top-down approach of strategic AI implementation. Our context is the public sector. Our goal is to acquire an improved understanding of how and when AI transformation occurs in the public sector, which are the consequences, and which strategies are fruitful or detrimental to the organization. We aim to study public sector organizations in Sweden, Norway, New Zealand, Germany, and The Netherlands to learn about potential similarities and differences with regard to AI transformation.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130071058","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":"Machine Learning Computational Fluid Dynamics","authors":"A. Usman, M. Rafiq, Muhammad Saeed, Alissa Nauman, A. Almqvist, M. Liwicki","doi":"10.1109/SAIS53221.2021.9483997","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9483997","url":null,"abstract":"Numerical simulation of fluid flow is a significant research concern during the design process of a machine component that experiences fluid-structure interaction (FSI). State-of-the-art in traditional computational fluid dynamics (CFD) has made CFD reach a relative perfection level during the last couple of decades. However, the accuracy of CFD is highly dependent on mesh size; therefore, the computational cost depends on resolving the minor feature. The computational complexity grows even further when there are multiple physics and scales involved making the approach time-consuming. In contrast, machine learning (ML) has shown a highly encouraging capacity to forecast solutions for partial differential equations. A trained neural network has offered to make accurate approximations instantaneously compared with conventional simulation procedures. This study presents transient fluid flow prediction past a fully immersed body as an integral part of the ML-CFD project. MLCFD is a hybrid approach that involves initialising the CFD simulation domain with a solution forecasted by an ML model to achieve fast convergence in traditional CDF. Initial results are highly encouraging, and the entire time-based series of fluid patterns past the immersed structure is forecasted using a deep learning algorithm. Prepared results show a strong agreement compared with fluid flow simulation performed utilising CFD.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130987677","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":"Identifying cheating behaviour with machine learning","authors":"Elina Kock, Yamma Sarwari, Nancy Russo, Magnus Johnsson","doi":"10.1109/SAIS53221.2021.9484044","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9484044","url":null,"abstract":"We have investigated machine learning based cheating behaviour detection in physical activity-based smart-phone games. Sensor data were acquired from the accelerometer/gyroscope of an iPhone 7 during activities such as jumping, squatting, stomping, and their cheating counterparts. Selected attributes providing the most information gain were used together with a sequential model yielding promising results in detecting fake activities. Even better results were achieved by employing a random forest classifier. The results suggest that machine learning is a strong candidate for detecting cheating behaviours in physical activity-based smartphone games.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114791244","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":"Welcome Message from the Chairs","authors":"","doi":"10.1109/sais53221.2021.9483951","DOIUrl":"https://doi.org/10.1109/sais53221.2021.9483951","url":null,"abstract":": The talk will be why, what and how of 6G and present some potential solutions that address these challenges. These challenges relate to future wireless, ubiquitous coverage and Core network that underpin concept of Future Network of Networks. Prof. Ari Pouttu has scientific and engineering experience as a researcher, project manager and research manager in various domains of ICT development. The projects under his command have resulted in waveforms and system designs for military radio communication, radar systems, embedded device networks, future wireless radio communications including cellular systems, cognitive networks and navigation applications. He has published more than 70 conference or journal papers in the field of wireless communications and he holds two patents. He is the principal investigator of 5G test network (5GTN) experimental research, and vice-director of the national 6G Flagship Programme as well as 6GESS programme targeting 6G solutions including wireless solutions for business verticals such as energy, industry, health and automotive. Abstract: The architectures of mobile networks have seen an unprecedented techno-economic transformation, fusing the telecommunications world within the cloud world, adding the spices of Software Engineering to the overall system design, and ultimately yielding the concept of Telco Cloud. This has brought significant benefits in terms of reducing expenditure and operational costs, flexibility in deployment, and faster time to market. The key enablers are network function virtualization, software-defined networking, and edge/cloud computing. Artificial intelligence is also kicking in this arena. When all these technologies are well integrated, the creation and life-cycle management of fully programmable, flexible, service-tailored, and automated end-to-end network slices/services become possible. This will support diverse 5G and beyond 5G services, spanning from tactile IoT to pervasive robotics and immersive services. In this talk 6G Flagship introduces an unprecedented and disruptive vision for 6G that shifts the perception of future mobile networks from the old-fashioned concept of “network of networks” towards a new vision of “service of services.” The talk then introduces the functional model of the envisioned system architecture, along with its components. It then provides a high-level description of the logical architecture.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132551112","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":"Towards motivation-driven intelligent interfaces: formal argumentation meets activity theory","authors":"Esteban Guerrero, H. Lindgren","doi":"10.1109/SAIS53221.2021.9484008","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9484008","url":null,"abstract":"Theories about human activity and motivation point out that motives are driving forces behind human activities and development of healthy and unhealthy habits. Activity theory is one of these that has been applied to develop activity-centered user interfaces. Activity theory differentiates between sense-making and stimuli-oriented types of motives that have a strong influence on our daily behavior. Two main challenges are explored in this paper: 1) the personalisation of graphical user interfaces to mediate representations of motivation-based activities to support behaviour change processes; and 2) the proactiveness of such visual representations.As methods, we use activity theory as a framework for defining the motivations’ dynamics, and formal argumentation theory as the underlying mechanism for interactive reasoning and decision-making in the process of generating the user interface.Our contributions are two-folded: 1) a dynamic graphical user interface where the background responds to behaviors linked to sense-making motives, and the foreground to stimuli motivation; and 2) a non-monotonic reasoning mechanism endowing the user interface with proactiveness (not only react to the user interactions but trigger and direct attention to potential conflicts), and a motive-based behavior conflict resolution process. Future work includes user studies to explore how triggering of focus may create increased awareness in an individual of conflicting motives in daily activities and how this may support changes of unhealthy habits.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123397713","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":"Static Palm Sign Gesture Recognition with Leap Motion and Genetic Algorithm","authors":"S. Rakesh, György Kovács, Hamam Mokayed, Rajkumar Saini, U. Pal","doi":"10.1109/SAIS53221.2021.9508468","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9508468","url":null,"abstract":"Sign gesture recognition is the field that models sign gestures in order to facilitate communication with hearing and speech impaired people. Sign gestures are recorded with devices like a video camera or a depth camera. Palm gestures are also recorded with the Leap motion sensor. In this paper, we address palm sign gesture recognition using the Leap motion sensor. We extract geometric features from Leap motion recordings. Next, we encode the Genetic Algorithm (GA) for feature selection. Genetically selected features are fed to different classifiers for gesture recognition. Here we have used Support Vector Machine (SVM), Random Forest (RF), and Naive Bayes (NB) classifiers to have their comparative results. The gesture recognition accuracy of 74.00% is recorded with RF classifier on the Leap motion sign gesture dataset.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"5 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114039570","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":"Predicting Signed Distance Functions for Visual Instance Segmentation","authors":"Emil Brissman, Joakim Johnander, M. Felsberg","doi":"10.1109/SAIS53221.2021.9484039","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9484039","url":null,"abstract":"Visual instance segmentation is a challenging problem and becomes even more difficult if objects of interest varies unconstrained in shape. Some objects are well described by a rectangle, however, this is hardly always the case. Consider for instance long, slender objects such as ropes. Anchor-based approaches classify predefined bounding boxes as either negative or positive and thus provide a limited set of shapes that can be handled. Defining anchor-boxes that fit well to all possible shapes leads to an infeasible number of prior boxes. We explore a different approach and propose to train a neural network to compute distance maps along different directions. The network is trained at each pixel to predict the distance to the closest object contour in a given direction. By pooling the distance maps we obtain an approximation to the signed distance function (SDF). The SDF may then be thresholded in order to obtain a foreground-background segmentation. We compare this segmentation to foreground segmentations obtained from the state-of-the-art instance segmentation method YOLACT. On the COCO dataset, our segmentation yields a higher performance in terms of foreground intersection over union (IoU). However, while the distance maps contain information on the individual instances, it is not straightforward to map them to the full instance segmentation. We still believe that this idea is a promising research direction for instance segmentation, as it better captures the different shapes found in the real world.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124577718","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":"Hit Detection in Sports Pistol Shooting","authors":"Elinore Stenhager, Niklas Lavesson","doi":"10.1109/SAIS53221.2021.9483984","DOIUrl":"https://doi.org/10.1109/SAIS53221.2021.9483984","url":null,"abstract":"Score calculation and performance analysis of shooting targets is an important aspect in the development of sports shooting ability. An image-based automatic scoring algorithm would provide automation of this procedure and digital visualization of the result. Existing solutions are able to detect hits with high precision. However, these methods are either too expensive or adapted to unrealistic use cases where high quality paper targets are photographed in very favorable environments. Usually, precision pistol shooting is performed outdoors and bullet holes are covered with stickers between shooting rounds. The targets are reused until they are destroyed. This paper introduces the first generation of an image-based method for automatic hit detection adapted to realistic shooting conditions. It relies solely on available image processing techniques. The proposed algorithm detects hits with 40 percent detection rate in low-quality targets, reaching 88 percent detection rate in targets of higher quality.","PeriodicalId":334078,"journal":{"name":"2021 Swedish Artificial Intelligence Society Workshop (SAIS)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115762868","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}