Search

Airline industry is a major global leader in aviation which has made the world an alluring smaller place with an enormous level of mobility and accessibility. It even provides service to almost every other sector, however, it does not receive significant attention, despite its importance. Moreover, its service quality is an aggregate of different interactions between the customers and airline companies. This drove them to implement new business model to conform to the new competitive atmosphere in the industry whose operation is taking place in a completely globalized environment. Thus, the use of chatbots is one of the avenues to meet this end. However, there is a dearth of standardized and validated instrument that best fit to evaluate the use of chatbots in the airline industry based on the combined set of constructs as identified in the conceptual framework. Thus, this study aims to develop and validate an instrument that will evaluate the adoption of chatbots in a service industry, like the airline industry, as well as its non-adoption. Based on the reliability and internal consistency evaluation, only one item was deleted (PIIT construct) since it has the lowest item-test correlation that caused the reliability coefficient to be less than the suggested value of 0.70. All statements in each of the constructs had positive signs, thus, were not reversely worded. Lastly, all the scale reliability coefficient or the overall alpha values are way higher than the suggested value, which means that the internal consistency is either acceptable or highly acceptable.

In agriculture, camouflage, i.e. fruits are occluded due to high color similarity to its environment, is one of the problems of fruit detection and counting for yield estimation. In this paper, we developed a system that automatically detects and counts fruits from images in an unstructured environment with heavy occlusion and high color similarity. We built two datasets by capturing the natural settings of the fruit and fine-tuned various deep convolutional neural networks with region proposal network for a very challenging task of detecting heavily occluded fruits with high color similarity against the background. The evaluation results show an average precision of 0.922 for chili pepper dataset and 0.966 for bell pepper dataset. The result of this network can be integrated into an application for efficient management of agricultural farms, thereby contributing to precision agriculture.

In this work, we present a network architecture with parallel convolutional neural networks (CNN) for removing perspective distortion in images. While other works generate corrected images through the use of generative adversarial networks or encoder-decoder networks, we propose a method wherein three CNNs are trained in parallel, to predict a certain element pair in the 3&times, 3 transformation matrix, M^. The corrected image is produced by transforming the distorted input image using M^&minus, 1. The networks are trained from our generated distorted image dataset using KITTI images. Experimental results show promise in this approach, as our method is capable of correcting perspective distortions on images and outperforms other state-of-the-art methods. Our method also recovers the intended scale and proportion of the image, which is not observed in other works.

This paper describes a system that can distinguish between visually-similar objects, specifically bicycles and motorcycles, successfully from the vantage point of traffic surveillance cameras. The You Only Look Once (YOLO) is used as the main framework in this research due to its speed performance among various machine learning models and methods evaluated. We built a dataset consisting of motorcycle and bicycle images from different CCTV footage for this project. CCTV footage may vary on the angle of view from the object, image resolution, and ambient environment settings. Using this dataset, we trained YOLOv3-based models, and their performances were compared to the vanilla version of YOLOv3 and other pre-trained models. Four (4) models were trained and compared; the best-performing model is shown to be associated with a dataset with properly labeled data (i.e., marking every instance of the object of interest) and having the most number of instances in the training and testing set.Introduction.

Algorithms that perform crowd estimation are dependent on crowd levels. The two approaches to crowd estimation discussed are the model-based and texture-based approaches. The aim of this work is to determine the precision, recall and F-measure of the two algorithms, Histogram of Oriented Gradients (HOG) with Support Vector Machines (SVM) and Region-Specific HOG, for estimating the number of people in high and low crowd levels, respectively, in an indoor area installed with a surveillance camera, while considering the camera’s position and its field of view.

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.

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.

Multiple-image super-resolution (MISR) attempts to recover a high-resolution (HR) image from a set of lowresolution (LR) images. In this paper, we present a mobile MISR tailored to work for a wide range of mobile devices. Our technique aims to address misalignment issues from a previous work and further enhance the quality of HR images produced. The proposed architecture is used to implement a prototype application that is freely available at Google Play Store, titled Eagle-Eye HD Camera. The system is divided into the following modules: Input Module, Edge Detection Module, Image Selection Module, Image Alignment Module, Alignment Selection Module and Image Fusion Module. We assessed the quality of HR images produced by our mobile MISR, through an online survey, as well as compare it with other related SR works. Performance time was also measured. A total of 114 respondents have participated in the survey, where majority of respondents preferred our approach. Our approach is observed to be comparable with other SR works in terms of visual quality and performance time, and guaranteed to work in a mobile environment.

Autonomous robots for smart homes and smart cities mostly require depth perception in order to interact with their environments. However, depth maps are usually captured in a lower resolution as compared to RGB color images due to the inherent limitations of the sensors. Naively increasing its resolution often leads to loss of sharpness and incorrect estimates, especially in the regions with depth discontinuities or depth boundaries. In this paper, we propose a novel Generative Adversarial Network (GAN)-based framework for depth map super-resolution that is able to preserve the smooth areas, as well as the sharp edges at the boundaries of the depth map. Our proposed model is trained on two different modalities, namely color images and depth maps. However, at test time, our model only requires the depth map in order to produce a higher resolution version. We evaluated our model both quantitatively and qualitatively, and our experiments show that our method performs better than existing state-of-the-art models.

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.

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.

In this study, we present Dice's 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.

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).

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 L 2-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.