{"title":"A Practical Approach to Spam Mitigation","authors":"Dobrin Tashev","doi":"10.1145/3134302.3134311","DOIUrl":"https://doi.org/10.1145/3134302.3134311","url":null,"abstract":"The paper describes the spam problem within a small company and a practical approach applied to mitigate it. The proposed solution is based on a practical approach to spam mitigation, as a combination of free online RBL services and a small PHP system for local black list management. The results of the pilot test period are conclusive about the positive effect of the suggested approach. The paper also offers ideas for further improvement.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"187 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134162834","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":"Outlier Detection via Deep Learning Architecture","authors":"Irina Kakanakova, S. Stoyanov","doi":"10.1145/3134302.3134337","DOIUrl":"https://doi.org/10.1145/3134302.3134337","url":null,"abstract":"An important issue in processing data from sensors is outlier detection. Plenty of methods for solving this task exist - applying rules, Support Vector Machines, Naive Bayes. They are not computationally intensive and give good results where border between outliers and inliers is linear. However, when the border's shape is highly non-linear, more sophisticated methods should be applied, with the requirement of not being computationally intensive. Deep learning architecture is applied to solve this problem and results are compared with the ones obtained by applying shallow architectures.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134623110","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 Comparison of Record and Play Honeypot Designs","authors":"Jarko Papalitsas, Sampsa Rauti, V. Leppänen","doi":"10.1145/3134302.3134307","DOIUrl":"https://doi.org/10.1145/3134302.3134307","url":null,"abstract":"Record and play -honeypots mimic normal TCP traffic and fool the adversary with fake data while simultaneously keeping the setting realistic. ln this paper, we propose several designs for such honeypots. Two important aspects of honeypot design are considered. First, we compare named entity recognition systems in order to recognize the entities in the messages the honeypot modifies. Second, we consider methods to fake these entities consistently. Pros and cons of each approach -- varying from the better accuracy of the fake responses to the possibility of causing side effects on the real services -- are discussed.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125122997","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":"Gamification in Education: A Passing Trend or a Genuine Potential?","authors":"D. Dicheva","doi":"10.1145/3134302.3134305","DOIUrl":"https://doi.org/10.1145/3134302.3134305","url":null,"abstract":"Traditional schooling is perceived by many students as ineffective and boring. Although teachers continuously seek novel instructional approaches, it is largely agreed that today's schools face major problems around student motivation and engagement. The use of educational games as learning tools is a promising approach. Games have remarkable motivational power. They utilize a number of mechanisms to encourage people to engage with them, often without any reward, just for the joy of playing and the possibility to win. However, creating a highly engaging, full-blown educational game is difficult, time consuming and costly and typically targets only a single set of learning objectives as chosen by the game designer. Yet, the effective classroom adoption of games requires an appropriate pedagogical integration and sometimes a certain technical infrastructure. Can we then, instead of using full-scale games, incorporate game thinking and game design elements in the learning environment as an alternative, less costly and more flexible approach to improving learners' engagement and motivation? Gamification -- the use of game design elements in non-game contexts -- has already seen a successful adoption in many areas including business, marketing, politics, health, fitness and travel. It seems surprising that the education is not in the list of \"success stories\" yet. Is this just a matter of late reaction or a wait for more persuasive evidence? Can gamification be used in an educational context as well and if so, which are the factors promising success? The talk will explore these questions giving specific attention to the motivational factors that impact learning and behaviour change and will present an overview of the current state of the art and the challenges in using gamification in education.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126101237","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 Approach for Mammography Image Segmentation","authors":"M. Stoeva, V. Bozhikova","doi":"10.1145/3134302.3134316","DOIUrl":"https://doi.org/10.1145/3134302.3134316","url":null,"abstract":"This paper addresses the problem of segmenting tomographic images for the purpose of diagnosing breast cancer. In case of glandular and dense breasts cancers may be missed, due to the effect of overlapping tissues. The goal of this study is to develop, test, and validate an approach and algorithm for segmentation of breast masses from tomosynthesis images. The approach developed uses processing by elements for improving contrast of images using a specific function for extracting a preparation from the image. The image-preparation is segmented by a threshold criterion for uniformity and morphological operations. The threshold is determined based on the entropy of the image histogram. Developed algorithm is applied to real images with highly deteriorated contrast and shows stable results. An important characteristic of the approach is the ability of the result of segmentation to cover completely the sought find.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131139773","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":"Is the Visitor Reading or Navigating?","authors":"Peter Krátky, Tomás Repiský, D. Chudá","doi":"10.1145/3134302.3134330","DOIUrl":"https://doi.org/10.1145/3134302.3134330","url":null,"abstract":"When a user browses a webpage, he or she generates a lot of data while moving with mouse or touchpad. The movement data hides useful information about the activity of the user. Knowing this might be useful for the perfect timing of hints online. In this paper, we propose our method for detection of browsing activity, specifically reading content and navigating. We describe our experiment in simulated news portal to acquire the dataset and we present the detection method results.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"7 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114123889","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":"Proceedings of the 18th International Conference on Computer Systems and Technologies","authors":"B. Rachev, A. Smrikarov","doi":"10.1145/3134302","DOIUrl":"https://doi.org/10.1145/3134302","url":null,"abstract":"CompSysTech'17 is the Eighteenth Bulgarian International Computer Science and Technologies Conference, organized by the Association for Computing Machinery, N.Y. USA, via its Bulgarian Chapter - acmbul in association with the Bulgarian Academ-ic Society of Computer Systems and Information Technologies and the Bulgarian Union of Automation&Informatics (UAI). This Conference is the 30th acmbul event during the last 27 years and it is the first Bulgarian Conference in Computing.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123589196","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":"Text Classification Based on Enriched Vector Space Model","authors":"T. Georgieva-Trifonova","doi":"10.1145/3134302.3134343","DOIUrl":"https://doi.org/10.1145/3134302.3134343","url":null,"abstract":"As one of the challenges to text classification can be indicated applying a model with the following characteristics: acceptable computational complexity of the model construction; dimension reduction of the vector space without significant decreasing of the classification performance. The present research aims to find a possible solution to mentioned problems. This paper proposes a model obtained by enrichment of the vector space model with the association relationships between words extracted from their co-occurrence in the text documents. For this purpose, the lift measure of association rules between word pairs is calculated. Experiments are conducted on Reuters-21578 dataset by using SVM classifier. The results confirm that applying the model improves the binominal and polynomial classification performance in comparison to the vector space model with respect to the F-measure even after word filtering, leading to a significant dimension reduction.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131726421","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":"Evaluating Coherence of Essays using Sentence-similarity Networks","authors":"K. Zupanc, M. Savić, Z. Bosnić, M. Ivanović","doi":"10.1145/3134302.3134322","DOIUrl":"https://doi.org/10.1145/3134302.3134322","url":null,"abstract":"The main weakness of automated essay evaluation systems is their predominant focus on vocabulary and text syntax, while consideration of text semantics is often neglected. In this work, we propose several new attributes for measuring coherence and consistency of essays that are based on a network representation of essays. In this representation, nodes represent sentences and links reflect similarity between them. We evaluated the proposed attributes on a benchmark dataset showing that their integration into a state-of-the-art system for essay evaluation indicates a potential for improvement of predictive performance.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130172751","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":"Smart Multifunctional Digital Content Ecosystem Using Emotion Analysis of Voice","authors":"A. Iliev, P. Stanchev","doi":"10.1145/3134302.3134342","DOIUrl":"https://doi.org/10.1145/3134302.3134342","url":null,"abstract":"In an attempt to establish an improved service-oriented architecture (SOA) for interoperable and customizable access of digital cultural resources an automatic deterministic technique can potentially lead to the improvement of searching, recommending and personalizing of content. Such technique can be developed in many ways using different means for data search and analysis. This paper focuses on the use of voice and emotion recognition in speech as a main vehicle for delivering an alternative way to develop novel solutions for integrating the loosely connected components that exchange information based on a common data model. The parameters used to construct the feature vectors for analysis carried pitch, temporal and duration information. They were compared to the glottal symmetry extracted from the speech source using inverse filtering. A comparison to their first derivatives was also a subject of investigation in this paper. The speech source was a 100-minute long theatrical play containing four male speakers and was recorder at 8kHz with 16-bit sample resolution. Four emotional states were targeted namely: happy, angry, fear, and neutral. Classification was performed using k-Nearest Neighbor method. Training and testing experiments were performed in three scenarios: 60/40, 70/30 and 80/20 minutes respectively. A close comparison of each feature and its rate of change show that the time-domain features perform better while using lesser computational strain than their first derivative counterparts. Furthermore, a correct recognition rate was achieved of up 95% using the chosen features.","PeriodicalId":131196,"journal":{"name":"Proceedings of the 18th International Conference on Computer Systems and Technologies","volume":"344 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116485471","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}