Joel Ilao

Dice's coefficient on trigram profiles as metric for language similarity

In this study, we present Dices coefficient on trigram profiles as metric for language similarity. As testbed, we focused on eight Philippine languages. No known language similarity value for these languages exists. Documents containing transcribed audio recordings, news articles, religious and literary texts were taken from an online corpus and used as training data. Character trigram profiles were then generated using an n-gram generator and language similarity was computed. The results were matched against those reported in the literature and against the language family tree. To evaluate the metric, it was applied to five languages with known similarity values. The results were then compared with an existing lexical similarity metric. The average difference is 27%. Analyses of the results reveal that phonetic spelling play an important role in language similarity. As future work, the metric can be used on phonetic transcriptions.

Multiple-image super-resolution on mobile devices: an image warping approach

This paper discusses a super-resolution (SR) system implemented on a mobile device. We utilized an Android device’s camera to take successive shots and applied a classical multiple-image super-resolution (SR) technique that utilized a set of low-resolution (LR) images. Images taken from the mobile device are subjected to our proposed filtering scheme wherein images that have noticeable presence of blur are discarded to avoid outliers from affecting the produced high-resolution (HR) image. The remaining subset of images are subjected to non-local means denoising, then feature-matched against the first reference LR image. Successive images are then aligned with respect to the first image via affine and perspective warping transformations. The LR images are then upsampled using bicubic interpolation. An L2-norm minimization approach, which is essentially taking the pixel-wise mean of the aligned images, is performed to produce the final HR image.Our study shows that our proposed method performs better than the bicubic interpolation, which makes its implementation in a mobile device quite feasible. We have also proven in our experiments that there are substantial differences from images captured using burst mode that can be utilized by an SR algorithm to create an HR image.

SMO-based System for identifying common lung conditions using histogram

A radiograph is a visualization aid that physicians use in identifying lung abnormalities. Although digitized X-ray images are available, diagnosis by a medical expert through pattern recognition is done manually. Thus, this paper presents a system that utilizes machine learning for pattern recognition and classification of three lung conditions, namely Normal, Pleural Effusion and Pneumothorax cases. Using two histogram equalization techniques, the designed system achieves an accuracy rate of 76.19% and 78.10% by using Sequential Minimal Optimization (SMO).

Measuring language similarity using trigrams: Limitations of language identification

Computational approaches in language identification often result in highnumber of false positivesand low recall rates, especially if the languages involved come from the same subfamily. In this paper, we aim to determine the cause of this problemby measuring language similarity through trigrams. Religious and literary texts were used as training data. Our experiments involving language identification show that the number of common trigrams for a given language pair is inversely proportional to precision and recall rates, whereas the average word length is directly proportional to the number of true positives. Future directions include improving language modeling and providing an approach to increase precision and recall.

Philippine component of the network-based ASEAN language translation public service

Communication between different nations is essential. Languages which are foreign to another impose difficulty in understanding. For this problem to be resolved, options are limited to learning the language, having a dictionary as a guide, or making use of a translator. This paper discusses the development of ASEANMT-Phil, a phrase-based statistical machine translator, to be utilized as a tool beneficial for assisting ASEAN countries. The data used for training and testing came from Wikipedia articles comprising of 124,979 and 1,000 sentence pairs, respectively. ASEANMT-Phil was experimented on different settings producing the BLEU score of 32.71 for Filipino-English and 31.15 for English-Filipino. Future Directions for the translator includes the following: improvement of data through changing or adding the domain or size; implementing an additional approach; and utilizing a larger dictionary to the approach.

Maturity Analysis and Monitoring System for Sugarcane Crops

The sugarcane stalk and foliage colors are strong indicators of maturity. While outdoor conditions affect the lighting of the captured sugarcane image, external factors like shadows and over exposure can easily be neglected in the Hue Saturation Value (HSV) color space. Through a series of experimentations in the HSV color space, the proponents found out that there is a significant shifting of Hue and Saturation values as sugarcane crops mature. The Hue and Saturation frequencies of both matured and not-matured sugarcanes were used as data for the maturity detection comparison module which utilizes RandomForest algorithm with 90.16% accuracy.

Single Player Tracking in Multiple Sports Videos

Performance analysis for basketball development programs are based on the athletes’ movement patterns, playing position on an area, and ball acquisition. The objective of the system is to automate the performance analysis by providing raw statistical data based on the player’s behaviors produced through tracking the player inside the basketball court. Using visual features described by SURF, unoccluded players are localized using a tracking by detection approach with an observed accuracy of 40%. Player positions are also adjusted to compensate for distortions, which improves player localization by 0.11%, on average.

iXray: A Machine Learning-Based Digital Radiograph Pattern Recognition System for Lung Pathology Detection

A radiograph is a visualization aid that physicians use in identifying lung abnormalities. Although digitized x-ray images are available, diagnosis by a medical expert through pattern recognition is done manually. Thus, this paper presents a system that utilizes machine learning for pattern recognition and classification of six lung conditions. Classified into two categories, namely histogram-based (normal, pleural effusion, and pneumothorax) and statistics-based (cardiomegaly, hyperaeration, and possible lung nodules). Using preprocessing and feature extraction techniques, the designed system achieves an accuracy rate of 92.59% for the histogram-based lung conditions using Sequential Minimal Optimization (SMO) and 67.22% for the statistics-based lung conditions using logic operations.

Vsion: Vehicle Occlusion Handling for Traffic Monitoring

Recently, the pervasiveness of street cameras for security and traffic monitoring opens new challenges to the computer vision technology to provide reliable monitoring schemes. These monitoring schemes require the basic processes of detecting and tracking objects, such as vehicles. However, object detection performance often suffers under occlusion. This work proposes a vehicle occlusion handling improvement of an existing traffic video monitoring system, which was later integrated. Two scenarios were considered in occlusion: indistinct and distinct - wherein the occluded vehicles have similar and dissimilar colors, respectively. K-means clustering using the HSV color space was used for distinct occlusion while sliding window algorithm was used for indistinct occlusion. The proposed method also applies deep convolutional neural networks to further improve vehicle recognition and classification. The CNN model obtained a 97.21% training accuracy and a 98.27% testing accuracy. Moreover, it minimizes the effect of occlusion to vehicle detection and classification. It also identifies common vehicle types (bus, truck, van, sedan, SUV, jeepney, and motorcycle) rather than classifying these as small, medium and large vehicles, which were the previous categories. Despite the implementation and results, it is recommended to improve the occlusion handling issue. The disadvantage of the sliding window algorithm is that it requires a lot of memory and is time-consuming. In case of deploying this research for more substantial purposes and intentions, it is ideal to enhance the CNN model by training it with more varied images of vehicles and to implement the system real-time. The results of this work can serve as a contribution for future works that are significant to traffic monitoring and air quality surveillance.

Alternative feature extraction from digitized images of dye solutions as a model for algal bloom remote sensing

Digital images of methyl violet dye and methyl orange solutions were obtained under controlled contributions to simulate images of algal blooms. From those images, feature extraction based from both Red-Green-Blue (RGB) and Hue-Saturation-Value (HSV) color space were used. The independent variable C, which is the concentration value of the dye solution, is mapped independently with the R-channel, G-channel and B-channel as well as the H-channel, S-channel and V-channel. Linear regression and non-linear regression techniques were used to determine the best fit equation while Akaike Information Criterion (AIC) were used to compare which among the equations provide the best fit.