{"title":"Moving Other Way: Exploring Word Mover Distance Extensions","authors":"Ilya Smirnov, Ivan P. Yamshchikov","doi":"10.5220/0011096900003197","DOIUrl":"https://doi.org/10.5220/0011096900003197","url":null,"abstract":": The word mover’s distance (WMD) is a popular semantic similarity metric for two documents. This metric is quite interpretable and reflects the similarity well, but some aspects can be improved. This position paper studies several possible extensions of WMD. We introduce some regularizations of WMD based on a word match and the frequency of words in the corpus as a weighting factor. Besides, we calculate WMD in word vector spaces with non-Euclidean geometry and compare it with the metric in Euclidean space. We validate possible extensions of WMD on six document classification datasets. Some proposed extensions show better results in terms of the k-nearest neighbor classification error than WMD.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134243293","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":"Artificial Neural Networks Jamming on the Beat","authors":"Alexey Tikhonov, Ivan P. Yamshchikov","doi":"10.5220/0010461200370044","DOIUrl":"https://doi.org/10.5220/0010461200370044","url":null,"abstract":"This paper addresses the issue of long-scale correlations that is characteristic for symbolic music and is a challenge for modern generative algorithms. It suggests a very simple workaround for this challenge, namely, generation of a drum pattern that could be further used as a foundation for melody generation. The paper presents a large dataset of drum patterns alongside with corresponding melodies. It explores two possible methods for drum pattern generation. Exploring a latent space of drum patterns one could generate new drum patterns with a given music style. Finally, the paper demonstrates that a simple artificial neural network could be trained to generate melodies corresponding with these drum patters used as inputs. Resulting system could be used for end-to-end generation of symbolic music with song-like structure and higher long-scale correlations between the notes.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121401784","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":"FLOPTICS: A Novel Automated Gating Technique for Flow Cytometry Data","authors":"Wiwat Sriphum, G. Wills, N. Green","doi":"10.5220/0009426300960102","DOIUrl":"https://doi.org/10.5220/0009426300960102","url":null,"abstract":"Gating is a process of cell differentiation of the data obtaining from flow cytometry technique. Flow cytometry (FCM) is a fluorescence concept technique that provide characteristics of individual cells in blood sample. A multidimensional dataset obtained from this method is large and complex so it is difficult to manually analysis and time consuming. Gating is the first step of FCM data analysis and highly subjective. Although many research attempted to reduce this subjectivity, more standard and faster gating technique is still needed. Some existing automated gating technique need many user-defined parameters that can lead to different results for different parameter values. Some techniques have a trouble with time consuming. FLOPTICS is a novel automated gating technique that is a combination of density-based and grid-based clustering algorithms. FLOPTICS has an ability to classify cell on FCM data faster and less user-defined parameter than some of state of art technique such as FlowGrid, FlowPeaks, and FLOCK.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129198472","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}
Ivan P. Yamshchikov, Cyrille Merleau Nono Saha, Igor Samenko, J. Jost
{"title":"It Means More if It Sounds Good: Yet Another Hypotheses Concerning the Evolution of Polysemous Words","authors":"Ivan P. Yamshchikov, Cyrille Merleau Nono Saha, Igor Samenko, J. Jost","doi":"10.5220/0009582801430148","DOIUrl":"https://doi.org/10.5220/0009582801430148","url":null,"abstract":"This position paper looks into the formation of language and shows ties between structural properties of the words in the English language and their polysemy. Using Ollivier-Ricci curvature over a large graph of synonyms to estimate polysemy it shows empirically that the words that arguably are easier to pronounce also tend to have multiple meanings.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117055099","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":"Using the Ornstein-Uhlenbeck Process for Random Exploration","authors":"J. Nauta, Yara Khaluf, P. Simoens","doi":"10.5220/0007724500590066","DOIUrl":"https://doi.org/10.5220/0007724500590066","url":null,"abstract":"In model-based Reinforcement Learning, an agent aims to learn a transition model between attainable states. Since the agent initially has zero knowledge of the transition model, it needs to resort to random exploration in order to learn the model. In this work, we demonstrate how the Ornstein-Uhlenbeck process can be used as a sampling scheme to generate exploratory Brownian motion in the absence of a transition model. Whereas current approaches rely on knowledge of the transition model to generate the steps of Brownian motion, the Ornstein-Uhlenbeck process does not. Additionally, the Ornstein-Uhlenbeck process naturally includes a drift term originating from a potential function. We show that this potential can be controlled by the agent itself, and allows executing non-equilibrium behavior such as ballistic motion or local trapping.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125912366","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":"The Time Operator of Reals","authors":"M. Milovanović, S. Vukmirović","doi":"10.5220/0007747000750084","DOIUrl":"https://doi.org/10.5220/0007747000750084","url":null,"abstract":"The purpose of the paper is to establish the continuum in terms of the complex systems physics. It is based upon the intuitionistic mathematics of Brouwer, implying a processual definition of real numbers that concerns the measurement problem. The Brouwerian continuum is proved to be a categorical skeleton of complex systems whose determining feature is the existence of time operator. Acting on continuous signals, the time operator represents multiresolution hierarchy of the measurement process. The wavelet domain hidden Markov model, that recapitulates statistical properties of the hierarchy, is applicable to a wide range of signals having experimental verification. It indicates a novel method that has already been proved tremendously useful in applied mathematics.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130668661","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":"An Empirical Research on the Investment Strategy of Stock Market based on Deep Reinforcement Learning model","authors":"Yuming Li, Pin Ni, Victor Chang","doi":"10.5220/0007722000520058","DOIUrl":"https://doi.org/10.5220/0007722000520058","url":null,"abstract":"The stock market plays a major role in the entire financial market. How to obtain effective trading signals in the stock market is a topic that stock market has long been discussing. This paper first reviews the Deep Reinforcement Learning theory and model, validates the validity of the model through empirical data, and compares the benefits of the three classical Deep Reinforcement Learning models. From the perspective of the automated stock market investment transaction decision-making mechanism, Deep Reinforcement Learning model has made a useful reference for the construction of investor automation investment model, the construction of stock market investment strategy, the application of artificial intelligence in the field of financial investment and the improvement of investor strategy yield.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114572919","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":"A Generalized Notion of Time for Modeling Temporal Networks","authors":"Konstantin Kueffner, Mark Strembeck","doi":"10.5220/0007764000930100","DOIUrl":"https://doi.org/10.5220/0007764000930100","url":null,"abstract":"Most approaches for modeling and analyzing temporal networks do not explicitly discuss the underlying notion \u0000of time. In this paper, we therefore introduce a generalized notion of time for temporal networks. Our \u0000approach also allows for considering non-deterministic time and incomplete data, two issues that are often \u0000found when analyzing data-sets extracted from online social networks, for example. In order to demonstrate \u0000the consequences of our generalized notion of time, we also discuss the implications for the computation of \u0000(shortest) temporal paths in temporal networks.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117133715","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}
A. Alenezi, Hany F. Atlam, Reem Alsagri, M. Alassafi, G. Wills
{"title":"IoT Forensics: A State-of-the-Art Review, Challenges and Future Directions","authors":"A. Alenezi, Hany F. Atlam, Reem Alsagri, M. Alassafi, G. Wills","doi":"10.5220/0007905401060115","DOIUrl":"https://doi.org/10.5220/0007905401060115","url":null,"abstract":"The IoT is capable of communicating and connecting billions of things at the same time. The concept offers numerous benefits for consumers that alters how users interact with the technology. With this said, however, such monumental growth within IoT development also gives rise to a number of legal and technical challenges in the field of IoT forensics. Indeed, there exist many issues that must be overcome if effective IoT investigations are to be carried out. This paper presents a review of the IoT concept, digital forensics and the state-of-the-art on IoT forensics. Furthermore, an exploration of the possible solutions proposed in recent research and IoT forensics challenges that are identified in the current research literature are examined. Picks apart the challenges facing IoT forensics which have been established in recent literature. Overall, this paper draws attention to the obvious problems – open problems which require further efforts to be addressed properly.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115194918","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}
Aida Omerovic, Hanne Vefsnmo, Gencer Erdogan, O. Gjerde, E. Gramme, S. Simonsen
{"title":"A Feasibility Study of a Method for Identification and Modelling of Cybersecurity Risks in the Context of Smart Power Grids","authors":"Aida Omerovic, Hanne Vefsnmo, Gencer Erdogan, O. Gjerde, E. Gramme, S. Simonsen","doi":"10.5220/0007697800390051","DOIUrl":"https://doi.org/10.5220/0007697800390051","url":null,"abstract":"Power grids are undergoing a digital transformation are therefore becoming increasingly complex. As a result of this they are also becoming vulnerable in new ways. With this development come also numerous risks. Cybersecurity is therefore becoming crucial for ensuring resilience of this infrastructure which is critical to safety of humans and societies. Risk analysis of cybersecurity in the context of smart power grids is, however, particularly demanding due to its interdisciplinary nature, including domains such as digital security, the energy domain, power networks, the numerous control systems involved, and the human in the loop. This poses special requirements to cybersecurity risk identification within smart power grids, which challenge the existing state-of-the-art. This paper proposes a customized four-step approach to identification and modelling of cybersecurity risks in the context of smart power grids. The aim is that the risk model can be presented to decision makers in a suitable interface, thereby serving as a useful support for planning, design and operation of smart power grids. The approach applied in this study is based on parts of the \"CORAS\" method for model-based risk analysis. The paper also reports on results and experiences from applying the approach in a realistic industrial case with a distribution system operator (DSO) responsible for hosting a pilot installation of the self-healing functionality within a power distribution grid. The evaluation indicates that the approach can be applied in a realistic setting to identify cybersecurity risks. The experiences from the case study moreover show that the presented approach is, to a large degree, well suited for its intended purpose, but it also points to areas in need for improvement and further evaluation.","PeriodicalId":414016,"journal":{"name":"International Conference on Complex Information Systems","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122843163","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}