Computer Science
Loading...
ISSN 1508-2806
e-ISSN: 2300-7036
Issue Date
2022
Volume
Vol. 23
Number
No. 1
Description
Reviewed by: Bartosz Minch, Janusz Bobulski, Aleksander Byrski, Jiri Mazurek, Shalaka Deore, Aybeyan Selimi, Daniela Milosevic, Adam Sędziwy
Journal Volume
Computer Science
Vol. 23 (2022)
Projects
Pages
Articles
Robust content-based image retrieval using ICCV, GLCM, and DWT-MSLBP descriptors
(Wydawnictwa AGH, 2022) Chavda, Sagar; Goyani, Mahesh
Content-based image retrieval (CBIR) retrieves visually similar images from a dataset based on a specified query. A CBIR system measures the similarities between a query and the image contents in a dataset and ranks the dataset images. This work presents a novel framework for retrieving similar images based on color and texture features. We have computed color features with an improved color coherence vector (ICCV) and texture features with a gray-level co-occurrence matrix (GLCM) along with DWT-MSLBP (which is derived from applying a modified multi-scale local binary pattern [MS-LBP] over a discrete wavelet transform [DWT], resulting in powerful textural features). The optimal features are computed with the help of principal component analysis (PCA) and linear discriminant analysis (LDA). The proposed work uses a variancebased approach for choosing the number of principal components/eigenvectors in PCA. PCA with a 99.99% variance preserves healthy features, and LDA selects robust ones from the set of features. The proposed method was tested on four benchmark datasets with Euclidean and city-block distances. The proposed method outshines all of the identified state-of-the-art literature methods.
Immersive feedback in fencing training using mixed reality
(Wydawnictwa AGH, 2022) Malawski, Filip
During sports training, providing athletes with real-time feedback that is based on the automatic analysis of motion is both useful and challenging. In this work, a novel system that is based on mixed reality is proposed and verified. The system allows for immersive and real-time visual feedback in fencing training. Novel methods have been introduced for 3D blade tracking from a single RGB camera, creating weapon-action models by recording the actions of a coach and evaluating the trainee’s performance against these models. Augmented reality glasses with see-through displays are employed, and a method for coordinate mapping between the virtual and real environments is proposed, this will allow for the provision of real-time visual cues and feedback by overlaying virtual trajectories on the real-world view. The system has been verified experimentally in fencing bladework training (with the supervision of a fencing coach). The results indicate that the proposed system allows novice fencers to perform their exercises more precisely.
Improving modified policy iteration for probabilistic model checking
(Wydawnictwa AGH, 2022) Mohagheghi, Mohammadsadegh; Karimpour, Jaber; Isazadeh, Ayaz
Along with their modified versions, value iteration and policy iteration are well-known algorithms for the probabilistic model checking of Markov decision processes. One challenge with these methods is that they are time-consuming in most cases. Several techniques have been proposed to improve the performance of iterative methods for probabilistic model checking, however, the running times of these techniques depend on the graphical structure of the utilized model. In some cases, their performance can be worse than the performance of standard methods. In this paper, we propose two new heuristics for accelerating the modified policy iteration method. We first define a criterion for the usefulness of the computations of each iteration of this method. The first contribution of our work is to develop and use a criterion to reduce the number of iterations in modified policy iteration. As the second contribution, we propose a new approach for identifying useless updates in each iteration. This method reduces the running time of the computations by avoiding the useless updates of states. The proposed heuristics have been implemented in the PRISM model checker and applied on several standard case studies. We compare the running time of our heuristics with the running times of previous standard and improved methods. Our experimental results show that our techniques yields a significant speed-up.
Named-entity recognition for Hindi language using context pattern-based maximum entropy
(Wydawnictwa AGH, 2022) Jain, Arti; Yadav, Divakar; Arora, Anuja; Tayal, Devendra K.
This paper describes a named-entity-recognition (NER) system for the Hindi language that uses two methodologies: an existing baseline maximum entropy-based named-entity (BL-MENE) model, and the proposed context pattern-based MENE (CP-MENE) framework. BL-MENE utilizes several baseline features for the NER task but suffers from inaccurate named-entity (NE) boundary detection, misclassification errors, and the partial recognition of NEs due to certain missing essentials. However, the CP-MENE-based NER task incorporates extensive features and patterns that are set to overcome these problems. In fact, CP-MENE’s features include right-boundary, left-boundary, part-of-speech, synonym, gazetteer and relative pronoun features. CP-MENE formulates a kind of recursive relationship for extracting highly ranked NE patterns that are generated through regular expressions via Python@ code. Since the web content of the Hindi language is arising nowadays (especially in health care applications), this work is conducted on the Hindi health data (HHD) corpus (which is readily available from the Kaggle dataset). Our experiments were conducted on four NE categories, namely, Person (PER), Disease (DIS), Consumable (CNS), and Symptom (SMP).
Ensemble machine learning methods to predict the balancing of ayurvedic constituents in the human body
(Wydawnictwa AGH, 2022) Rajasekar Vani; Krishnamoorthi Sathya; Saračević Muzafer; Pepic Dzenis; Zajmovic Mahir; Zogic Haris
In this paper, we demonstrate the result of certain machine-learning methods like support vector machine (SVM), naive Bayes (NB), decision tree (DT), k-nearest neighbor (KNN), artificial neural network (ANN), and AdaBoost algorithms for various performance characteristics to predict human body constituencies. Ayurveda-dosha studies have been used for a long time, but the quantitative reliability measurement of these diagnostic methods still lags. The careful and appropriate analysis leads to an effective treatment to predict human body constituencies. From an observation of the results, it is shown that the AdaBoost algorithm with hyperparameter tuning provides enhanced accuracy and recall (0.97), precision and F-score (0.96), and lower RSME values (0.64). The experimental results reveal that the improved model (which is based on ensemble-learning methods) significantly outperforms traditional methods. According to the findings, advancements in the proposed algorithms could give machine learning a promising future.