27,122 Hits in 9.1 sec

Deep Learning Approaches for Predictive Masquerade Detection

Wisam Elmasry, Akhan Akbulut, Abdul Halim Zaim
2018 Security and Communication Networks  
On the other hand, a CNN model is employed in a dynamic approach. Moreover, twelve well-known evaluation metrics are used to assess model performance in each of the data configurations.  ...  Although considerable work has been focused on masquerade detection for more than a decade, achieving a high level of accuracy and a comparatively low false alarm rate is still a big challenge.  ...  Conflicts of Interest The authors declare that there are no conflicts of interest regarding the publication of this paper.  ... 
doi:10.1155/2018/9327215 fatcat:xokoxyih4bcopdkxxc4wk7xa3i

Reinforcement Learning for Test Case Prioritization [article]

Mojtaba Bagherzadeh, Nafiseh Kahani, Lionel Briand
2021 arXiv   pre-print
We then rely on carefully selected and tailored state-of-the-art RL techniques to automatically and continuously learn a test case prioritization strategy, whose objective is to be as close as possible  ...  , thus paving the way for using RL to prioritize test cases in a CI context.  ...  We also want to express our gratitude to the authors of the two previous studies on reinforcement learning and test prioritization ( [6] , [15] ), for making their data and artifacts available and answering  ... 
arXiv:2011.01834v2 fatcat:qlbgsayzdvb6nhxs3ezgvodxhe

A Large-Scale Pseudoword-Based Evaluation Framework for State-of-the-Art Word Sense Disambiguation

Mohammad Taher Pilehvar, Roberto Navigli
2014 Computational Linguistics  
Consequently, evaluations tend to be performed on a small scale, which does not allow for in-depth analysis of the factors that determine a systems' performance.  ...  The evaluation of several tasks in lexical semantics is often limited by the lack of large amounts of manual annotations, not only for training purposes, but also for testing purposes.  ...  A Large-scale Pseudoword-based Evaluation Framework for WSD the graph tends to have a higher number of incident edges.  ... 
doi:10.1162/coli_a_00202 fatcat:4jyf4y5pu5ddnbnaeu4i2dgfja

Topics and Label Propagation: Best of Both Worlds for Weakly Supervised Text Classification [article]

Sachin Pawar, Nitin Ramrakhiyani, Swapnil Hingmire, Girish K. Palshikar
2017 arXiv   pre-print
We demonstrate the effectiveness of our approach on various datasets and compare with state-of-the-art weakly supervised text classification approaches.  ...  We propose a Label Propagation based algorithm for weakly supervised text classification.  ...  We evaluated LPA-TD on 4 datasets of the 20NG corpora and compared with multiple baselines.  ... 
arXiv:1712.02767v1 fatcat:lmqv4afstffpffqpu67tn2f6pq

Semantic Enrichment for Recommendation of Primary Studies in a Systematic Literature Review

Giuseppe Rizzo, Federico Tomassetti, Antonio Vetrò, Luca Ardito, Marco Torchiano, Maurizio Morisio, Raphaël Troncy
2015 Digital Scholarship in the Humanities  
We trained our system with di↵erent configurations of relevant documents and we tested the goodness of our approach with an empirical assessment.  ...  A Systematic Literature Review (SLR) identifies, evaluates and synthesizes the literature available for a given topic.  ...  Acknowledgments This work was partially supported by the European Union's 7th Framework Programme via the projects LinkedTV (GA 287911).  ... 
doi:10.1093/llc/fqv031 dblp:journals/lalc/RizzoTVATMT17 fatcat:ylq7ddc5dffffizde2ychwury4

Model for Detection of Masquerade Attacks Based on Variable-Length Sequences

Ghazaros Barseghyan, Yuyu Yuan, Manawa Anakpa
2020 IEEE Access  
Although the CNN achieved state-of-theart results for SEA1v49, PU Enriched Full, Greenberg Enriched Full, PU Truncated Full, and Greenberg Truncated Full on multiple evaluation metrics, the TPR results  ...  Two data configurations are used in the literature: truncated and enriched. The truncated data configuration indicates that a dataset contains only command names.  ... 
doi:10.1109/access.2020.3039166 fatcat:dkjsankjinghdj4tdsv72wy52y

Exploiting Context-Aware Event Data for Fault Analysis

Cuong Huy Nguyen, Tran Manh Ha, Quy Tran Vu, Synh Viet Uyen Ha
2016 REV Journal on Electronics and Communications  
Fault analysis in communication networks and distributed systems is a difficult process that heavily depends on system administrator's experience and supporting tools.  ...  The experimental results reveal that the accuracy score of the approach reaches 85% on average. The paper also includes detailed analysis for the results.  ...  Acknowledgements This research activity is funded by Vietnam National University, Ho Chi Minh City (VNU-HCM) under the type-B project of "Augmenting fault detection services on large and complex network  ... 
doi:10.21553/rev-jec.139 fatcat:abdk7cqymjbynm2q2avroov6xm

Novel Semantic-Based Probabilistic Context Aware Approach for Situations Enrichment and Adaptation

Abderrahim Lakehal, Adel Alti, Philippe Roose
2022 Applied Sciences  
Experimental results show that the proposed approach enhances accuracy rate with a high number of situations rules.  ...  A comparison with existing recommendation approaches shows that the proposed approach is more efficient and decreases the execution time.  ...  Data Availability Statement: Data available on request due to restrictions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app12020732 fatcat:7ltj3bog3jdzdfy5swysvapyfa

Skeleton Driven Action Recognition Using an Image-Based Spatial-Temporal Representation and Convolution Neural Network

Vinícius Silva, Filomena Soares, Celina P. Leão, João Sena Esteves, Gianni Vercelli
2021 Sensors  
Information that can be used to enrich this interaction and, consequently, adapt the system behavior is the recognition of different actions of the user by using RGB cameras or/and depth sensors.  ...  92.4% ± 0.0% on the test data.  ...  Acknowledgments: The authors thank the teachers and students at the Elementary School of Gualtar (EB1/JI Gualtar) in Braga for their participation in the study.  ... 
doi:10.3390/s21134342 pmid:34201991 fatcat:5dxwrvgh7vddvkbxvcnu2sgjky

VeeAlign: Multifaceted Context Representation using Dual Attention for Ontology Alignment [article]

Vivek Iyer, Arvind Agarwal, Harshit Kumar
2021 arXiv   pre-print
We evaluate our model on four different datasets from different domains and languages, and establish its superiority through these results as well as detailed ablation studies.  ...  In this work, we propose VeeAlign, a Deep Learning based model that uses a novel dual-attention mechanism to compute the contextualized representation of a concept which, in turn, is used to discover alignments  ...  As part of the future work, we propose to implement a syntactic and semantic evaluation with a easily configurable rules and AI models to reduce the manual effort.  ... 
arXiv:2102.04081v3 fatcat:h6rq2vrjsbekfkbofymjasrufq

geneCommittee: a web-based tool for extensively testing the discriminatory power of biologically relevant gene sets in microarray data classification

Miguel Reboiro-Jato, Joel P Arrais, José Oliveira, Florentino Fdez-Riverola
2014 BMC Bioinformatics  
Provided with a straightforward and intuitive interface, geneCommittee is able to render valuable information for diagnostic analyses and clinical management decisions based on systematically evaluating  ...  Results: geneCommittee is a web-based interactive tool for routinely evaluating the discriminative classification power of custom hypothesis in the form of biologically relevant gene sets.  ...  Table 1 1 Structure of the train and test datasets available in geneCommittee straightforward configuration: (i) electing the 300 best genes according to the Chi-square test, (ii) selecting those sets  ... 
doi:10.1186/1471-2105-15-31 pmid:24475928 pmcid:PMC3909759 fatcat:5avybdr4ozblnnhjvy7ssicwga

Benchmarking Knowledge Graphs on the Web [article]

Michael Röder and Mohamed Ahmed Sherif and Muhammad Saleem and Felix Conrads and Axel-Cyrille Ngonga Ngomo
2020 arXiv   pre-print
The growing interest in making use of Knowledge Graphs for developing explainable artificial intelligence, there is an increasing need for a comparable and repeatable comparison of the performance of Knowledge  ...  History in computer science has shown that a main driver to scientific advances, and in fact a core element of the scientific method as a whole, is the provision of benchmarks to make progress measurable  ...  Synthetic datasets are useful to test the scalability of systems based on datasets of varying sizes.  ... 
arXiv:2002.06039v1 fatcat:tc25o6rplbekndjng4cqh2oxoe

Semantic Detection of Targeted Attacks Using DOC2VEC Embedding

Mariam S. El-Rahmany, Ensaf Hussein Mohamed, Mohamed H. Haggag
2021 Journal of Communications Software and Systems  
Based on Sentence Embedding and machine learning approaches, this paper introduces a model for semantic detection of targeted attacks.  ...  The suggested model was tested using a dialogue dataset taken from phone calls, which was manually categorized into four categories.  ...  The proposed model evaluated on two datasets: Dataset 1 is a dataset proposed in [6] that contains 148 text messages, and Dataset 2 is a publicly available dataset on the UCI ML repository (spam dataset  ... 
doi:10.24138/jcomss-2021-0113 fatcat:ozfnk4mgwzgjlhqtaffcsvc2k4


Dimitris Kontokostas, Patrick Westphal, Sören Auer, Sebastian Hellmann, Jens Lehmann, Roland Cornelissen
2014 Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion  
Databugger ensures a basic level of quality by accompanying vocabularies, ontologies and knowledge bases with a number of test cases.  ...  The test queries can be instantiated automatically based on a vocabulary or manually based on the data semantics.  ...  Additionally we provided an evaluation overview on five different datasets and a library of 32,293 unique test cases for 297 common vocabularies.  ... 
doi:10.1145/2567948.2577017 dblp:conf/www/KontokostasWAHLC14 fatcat:kkjpf3tgr5g3helk5gkng2siba

Deep Depth Estimation from Visual-Inertial SLAM [article]

Kourosh Sartipi, Tien Do, Tong Ke, Khiem Vuong, Stergios I. Roumeliotis
2020 arXiv   pre-print
Finally, we show that our method outperforms other state-of-the-art approaches both on training (ScanNet and NYUv2) and testing (collected with Azure Kinect) datasets.  ...  This results in a significant performance gain for the surface normal estimate, and thus the dense depth estimates.  ...  Comparison on ScanNet Datasets We train and evaluate different configurations of our approach on the ScanNet indoor datasets and compare our performance with NeuralRGBD [9] .  ... 
arXiv:2008.00092v2 fatcat:dqzlsio4trgijnpzyxlbdt2t6y
« Previous Showing results 1 — 15 out of 27,122 results