• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.1-10
• /
• 2024

Individuals with visual impairments face numerous challenges in their daily lives, with navigating streets and public spaces being particularly daunting. The inability to identify safe crossing locations and assess the feasibility of crossing significantly restricts their mobility and independence. Globally, an estimated 285 million people suffer from visual impairment, with 39 million categorized as blind and 246 million as visually impaired, according to the World Health Organization. In Saudi Arabia alone, there are approximately 159 thousand blind individuals, as per unofficial statistics. The profound impact of visual impairments on daily activities underscores the urgent need for solutions to improve mobility and enhance safety. This study aims to address this pressing issue by leveraging computer vision and deep learning techniques to enhance object detection capabilities. Two models were trained to detect objects: one focused on street crossing obstacles, and the other aimed to search for objects. The first model was trained on a dataset comprising 5283 images of road obstacles and traffic signals, annotated to create a labeled dataset. Subsequently, it was trained using the YOLOv8 and YOLOv5 models, with YOLOv5 achieving a satisfactory accuracy of 84%. The second model was trained on the COCO dataset using YOLOv5, yielding an impressive accuracy of 94%. By improving object detection capabilities through advanced technology, this research seeks to empower individuals with visual impairments, enhancing their mobility, independence, and overall quality of life.

• International Journal of Computer Science & Network Security
• /
• v.24 no.8
• /
• pp.14-20
• /
• 2024

Traffic sign recognition is an essential feature of intelligent transportation systems and Advanced Driver Assistance Systems (ADAS), which are necessary for improving road safety and advancing the development of autonomous cars. This research investigates the incorporation of the YOLOv9 model into traffic sign recognition systems, utilizing its sophisticated functionalities such as Programmable Gradient Information (PGI) and Generalized Efficient Layer Aggregation Network (GELAN) to tackle enduring difficulties in object detection. We employed a publically accessible dataset obtained from Roboflow, which consisted of 3130 images classified into five distinct categories: speed_40, speed_60, stop, green, and red. The dataset was separated into training (68%), validation (21%), and testing (12%) subsets in a methodical manner to ensure a thorough examination. Our comprehensive trials have shown that YOLOv9 obtains a mean Average Precision (mAP@0.5) of 0.959, suggesting exceptional precision and recall for the majority of traffic sign classes. However, there is still potential for improvement specifically in the red traffic sign class. An analysis was conducted on the distribution of instances among different traffic sign categories and the differences in size within the dataset. This analysis aimed to guarantee that the model would perform well in real-world circumstances. The findings validate that YOLOv9 substantially improves the precision and dependability of traffic sign identification, establishing it as a dependable option for implementation in intelligent transportation systems and ADAS. The incorporation of YOLOv9 in real-world traffic sign recognition and classification tasks demonstrates its promise in making roadways safer and more efficient.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.57-64
• /
• 2024

This paper aims to enhance the accuracy of music genre classification for music tracks where genre information is not provided, by utilizing machine learning to classify a large amount of music data. The paper proposes collecting and preprocessing data instead of using the commonly employed GTZAN dataset in previous research for genre classification in music. To create a dataset with superior classification performance compared to the GTZAN dataset, we extract specific segments with the highest energy level of the onset. We utilize 57 features as the main characteristics of the music data used for training, including Mel Frequency Cepstral Coefficients (MFCC). We achieved a training accuracy of 85% and a testing accuracy of 71% using the Support Vector Machine (SVM) model to classify into Classical, Jazz, Country, Disco, Soul, Rock, Metal, and Hiphop genres based on preprocessed data.

• Journal of Periodontal and Implant Science
• /
• v.48 no.2
• /
• pp.114-123
• /
• 2018

Purpose: The aim of the current study was to develop a computer-assisted detection system based on a deep convolutional neural network (CNN) algorithm and to evaluate the potential usefulness and accuracy of this system for the diagnosis and prediction of periodontally compromised teeth (PCT). Methods: Combining pretrained deep CNN architecture and a self-trained network, periapical radiographic images were used to determine the optimal CNN algorithm and weights. The diagnostic and predictive accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic (ROC) curve, area under the ROC curve, confusion matrix, and 95% confidence intervals (CIs) were calculated using our deep CNN algorithm, based on a Keras framework in Python. Results: The periapical radiographic dataset was split into training (n=1,044), validation (n=348), and test (n=348) datasets. With the deep learning algorithm, the diagnostic accuracy for PCT was 81.0% for premolars and 76.7% for molars. Using 64 premolars and 64 molars that were clinically diagnosed as severe PCT, the accuracy of predicting extraction was 82.8% (95% CI, 70.1%-91.2%) for premolars and 73.4% (95% CI, 59.9%-84.0%) for molars. Conclusions: We demonstrated that the deep CNN algorithm was useful for assessing the diagnosis and predictability of PCT. Therefore, with further optimization of the PCT dataset and improvements in the algorithm, a computer-aided detection system can be expected to become an effective and efficient method of diagnosing and predicting PCT.

• Journal of Internet Computing and Services
• /
• v.21 no.5
• /
• pp.49-56
• /
• 2020

Detecting shadows in images and restoring or removing them was a very challenging task in computer vision. Traditional researches used color information, edges, and thresholds to detect shadows, but there were errors such as not considering the penumbra area of shadow or even detecting a black area that is not a shadow. Deep learning has been successful in various fields of computer vision, and research on applying deep learning has started in the field of shadow detection and removal. However, it was very difficult and time-consuming to collect data for network learning, and there were many limited conditions for shooting. In particular, it was more difficult to obtain shadow data from buildings and satellite images, which hindered the progress of the research. In this paper, we propose a method for generating shadow data from buildings and satellites using Unity3D. In the virtual Unity space, 3D objects existing in the real world were placed, and shadows were generated using lights effects to shoot. Through this, it is possible to get all three types of images (shadow-free, shadow image, shadow mask) necessary for shadow detection and removal when training deep learning networks. The method proposed in this paper contributes to helping the progress of the research by providing big data in the field of building or satellite shadow detection and removal research, which is difficult for learning deep learning networks due to the absence of data. And this can be a suboptimal method. We believe that we have contributed in that we can apply virtual data to test deep learning networks before applying real data.

• Safety and Health at Work
• /
• v.11 no.2
• /
• pp.165-172
• /
• 2020

Background: To gain a better understanding of nonfatal injuries in Alaska, underutilized data sources such as workers' compensation claims must be analyzed. The purpose of the current study was to utilize workers' compensation claims data to estimate the risk of nonfatal, work-related injuries among occupations in Alaska, characterize injury patterns, and prioritize future research. Methods: A dataset with information on all submitted claims during 2014-2015 was provided for analysis. Claims were manually reviewed and coded. For inclusion in this study, claims had to represent incidents that resulted in a nonfatal acute traumatic injury, occurred in Alaska during 2014-2015, and were approved for compensation. Results: Construction workers had the highest number of injuries (2,220), but a rate lower than the overall rate (34 per 1,000 construction workers, compared to 40 per 1,000 workers overall). Fire fighters had the highest rate of injuries on the job, with 162 injuries per 1,000 workers, followed by law enforcement officers with 121 injuries per 1,000 workers. The most common types of injuries across all occupations were sprains/strains/tears, contusions, and lacerations. Conclusion: The successful use of Alaska workers' compensation data demonstrates that the information provided in the claims dataset is meaningful for epidemiologic research. The predominance of sprains, strains, and tears among all occupations in Alaska indicates that ergonomic interventions to prevent overexertion are needed. These findings will be used to promote and guide future injury prevention research and interventions.

• Ocean and Polar Research
• /
• v.29 no.4
• /
• pp.379-389
• /
• 2007

This paper presents an attempt to determine natural background levels of heavy metals which could be used for assessing heavy metal contamination. For this study, a large archive dataset of heavy metal concentration (Cu, Cr, Ni, Pb, Zn) for more than 900 surface sediment samples from various Korean coastal environments was newly compiled. These data were normalized for aluminum (grain-size normalizer) concentration to isolate natural factors from anthropogenic ones. The normalization was based on the hypothesis that heavy metal concentrations vary consistently with the concentration of aluminum, unless these metals are of anthropogenic origin. So, the samples (outliers) suspected of receivingany anthropogenic input were removed from regression to ascertain the "background" relationship between the metals and aluminum. Identification of these outliers was tested using a model of predicted limits at 95%. The process of testing for normality (Kolmogorov-Smirnov Test) and selection of outliers was iterated until a normal distribution was achieved. On the basis of the linear regression analysis of the large archive (please check) dataset, background levels, which are applicable to heavy metal assessment of Korean coastal sediments, were successfully developed for Cu, Cr, Ni, Zn. As an example, we tested the applicability of this baseline level for metal pollution assessment of Masan Bay sediments.

• Analytical Science and Technology
• /
• v.28 no.4
• /
• pp.270-277
• /
• 2015

Boiling point (BP) is one of the most fundamental physicochemical properties of organic compounds to characterize and identify the thermal characteristics of target compounds. Previously developed QSPR equations, however, still had some limitation for the specific compounds, like high-energy molecules, mainly because of the lack of experimental data and less coverage. A large BP dataset of 5,923 solid organic compounds was finally secured in this study, after dedicated pre-filtration of experimental data from different sources, mostly consisting of compounds not only from common organic molecules but also from some specially used molecules, and those dataset was used to build the new BP prediction model. Various machine learning methods were performed for newly collected data based on meaningful 2D descriptor set. Results of combined check showed acceptable validity and robustness of our models, and consensus approaches of each model were also performed. Applicability domain of BP prediction model was shown based on descriptor of training set.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1562-1582
• /
• 2024

The prediction of pedestrian trajectory is conducive to reducing traffic accidents and protecting pedestrian safety, which is crucial to the task of intelligent driving. The existing methods mainly use the past pedestrian trajectory to predict the future deterministic pedestrian trajectory, ignoring pedestrian intention and trajectory diversity. This paper proposes a multi-modal trajectory prediction model that introduces pedestrian intention. Unlike previous work, our model makes multi-modal goal-conditioned trajectory pedestrian prediction based on the past pedestrian trajectory and pedestrian intention. At the same time, we propose a novel Gate Recurrent Unit (GRU) to process intention information dynamically. Compared with traditional GRU, our GRU adds an intention unit and an intention gate, in which the intention unit is used to dynamically process pedestrian intention, and the intention gate is used to control the intensity of intention information. The experimental results on two first-person traffic datasets (JAAD and PIE) show that our model is superior to the most advanced methods (Improved by 30.4% on MSE_0.5s and 9.8% on MSE_1.5s for the PIE dataset; Improved by 15.8% on MSE_0.5s and 13.5% on MSE_1.5s for the JAAD dataset). Our multi-modal trajectory prediction model combines pedestrian intention that varies at each prediction time step and can more comprehensively consider the diversity of pedestrian trajectories. Our method, validated through experiments, proves to be highly effective in pedestrian trajectory prediction tasks, contributing to improving traffic safety and the reliability of intelligent driving systems.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.137-148
• /
• 2014

Recommender system has become one of the most important technologies in e-commerce in these days. The ultimate reason to shop online, for many consumers, is to reduce the efforts for information search and purchase. Recommender system is a key technology to serve these needs. Many of the past studies about recommender systems have been devoted to developing and improving recommendation algorithms and collaborative filtering (CF) is known to be the most successful one. Despite its success, however, CF has several shortcomings such as cold-start, sparsity, gray sheep problems. In order to be able to generate recommendations, ordinary CF algorithms require evaluations or preference information directly from users. For new users who do not have any evaluations or preference information, therefore, CF cannot come up with recommendations (Cold-star problem). As the numbers of products and customers increase, the scale of the data increases exponentially and most of the data cells are empty. This sparse dataset makes computation for recommendation extremely hard (Sparsity problem). Since CF is based on the assumption that there are groups of users sharing common preferences or tastes, CF becomes inaccurate if there are many users with rare and unique tastes (Gray sheep problem). This study proposes a new algorithm that utilizes Social Network Analysis (SNA) techniques to resolve the gray sheep problem. We utilize 'degree centrality' in SNA to identify users with unique preferences (gray sheep). Degree centrality in SNA refers to the number of direct links to and from a node. In a network of users who are connected through common preferences or tastes, those with unique tastes have fewer links to other users (nodes) and they are isolated from other users. Therefore, gray sheep can be identified by calculating degree centrality of each node. We divide the dataset into two, gray sheep and others, based on the degree centrality of the users. Then, different similarity measures and recommendation methods are applied to these two datasets. More detail algorithm is as follows: Step 1: Convert the initial data which is a two-mode network (user to item) into an one-mode network (user to user). Step 2: Calculate degree centrality of each node and separate those nodes having degree centrality values lower than the pre-set threshold. The threshold value is determined by simulations such that the accuracy of CF for the remaining dataset is maximized. Step 3: Ordinary CF algorithm is applied to the remaining dataset. Step 4: Since the separated dataset consist of users with unique tastes, an ordinary CF algorithm cannot generate recommendations for them. A 'popular item' method is used to generate recommendations for these users. The F measures of the two datasets are weighted by the numbers of nodes and summed to be used as the final performance metric. In order to test performance improvement by this new algorithm, an empirical study was conducted using a publically available dataset - the MovieLens data by GroupLens research team. We used 100,000 evaluations by 943 users on 1,682 movies. The proposed algorithm was compared with an ordinary CF algorithm utilizing 'Best-N-neighbors' and 'Cosine' similarity method. The empirical results show that F measure was improved about 11% on average when the proposed algorithm was used