• ETRI Journal
• /
• v.45 no.6
• /
• pp.1079-1089
• /
• 2023

Stroke is one of the leading causes of long-term disability worldwide, placing huge burdens on individuals and society. Further, automatic human activity recognition is a challenging task that is vital to the future of healthcare and physical therapy. Using a baseline long short-term memory recurrent neural network, this study provides a novel dataset of stretching, upward stretching, flinging motions, hand-to-mouth movements, swiping gestures, and pouring motions for improved model training and testing of stroke-affected patients. A MATLAB application is used to output textual and audible prediction results. A wearable sensor with a triaxial accelerometer is used to collect preprocessed real-time data. The model is trained with features extracted from the actual patient to recognize new actions, and the recognition accuracy provided by multiple datasets is compared based on the same baseline model. When training and testing using the new dataset, the baseline model shows recognition accuracy that is 11% higher than the Activity Daily Living dataset, 22% higher than the Activity Recognition Single Chest-Mounted Accelerometer dataset, and 10% higher than another real-world dataset.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.89-94
• /
• 2024

Indian subcontinent is a birthplace of multilingual people where documents such as job application form, passport, number plate identification, and so forth is composed of text contents written in different languages/scripts. These scripts may be in the form of different indic numerals in a single document page. Due to this reason, building a generic recognizer that is capable of recognizing handwritten indic digits written by diverse writers is needed. Also, a lot of work has been done for various non-Indic numerals particularly, in case of Roman, but, in case of Indic digits, the research is limited. Moreover, most of the research focuses with only on MNIST datasets or with only single datasets, either because of time restraints or because the model is tailored to a specific task. In this work, a hybrid model is proposed to recognize all available indic handwritten digit images using the existing benchmark datasets. The proposed method bridges the automatically learnt features of Capsule Network with hand crafted Bag of Feature (BoF) extraction method. Along the way, we analyze (1) the successes (2) explore whether this method will perform well on more difficult conditions i.e. noise, color, affine transformations, intra-class variation, natural scenes. Experimental results show that the hybrid method gives better accuracy in comparison with Capsule Network.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.5
• /
• pp.217-220
• /
• 2024

Predicting earthquake occurrences accurately is challenging, and preparing all buildings with seismic design for such random events is a difficult task. Analyzing building features to predict potential damage and reinforcing vulnerabilities based on this analysis can minimize damages even in buildings without seismic design. Therefore, research analyzing the efficiency of building damage prediction models is essential. In this paper, we compare the accuracy of earthquake damage prediction models using machine learning classification algorithms, including Random Forest, Extreme Gradient Boosting, LightGBM, and CatBoost, utilizing data from buildings damaged during the 2015 Nepal earthquake.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• Korean Journal of Agricultural Science
• /
• v.49 no.4
• /
• pp.837-845
• /
• 2022

In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2564-2588
• /
• 2024

Due to COVID19 pandemic, most of educational institutions and schools changed the traditional way of teaching to online teaching and learning using well-known Learning Management Systems (LMS) such as Moodle, Canvas, Blackboard, etc. Accordingly, LMS started to generate a large data related to students' characteristics and achievements and other course-related information. This makes it difficult to teachers to monitor students' behaviour and performance. Therefore, a need to support teachers with a tool alerting student who might be in risk based on their recorded activities and achievements in adopted LMS in the school. This paper focuses on the benefits of using recorded data in LMS platforms, specifically Moodle, to predict students' performance by analysing their behavioural data and engagement activities using data mining techniques. As part of the overall process, this study encountered the task of extracting and selecting relevant data features for predicting performance, along with designing the framework and choosing appropriate machine learning techniques. The collected data underwent pre-processing operations to remove random partitions, empty values, duplicates, and code the data. Different machine learning techniques, including k-NN, TREE, Ensembled Tree, SVM, and MLPNNs were applied to the processed data. The results showed that the MLPNNs technique outperformed other classification techniques, achieving a classification accuracy of 93%, while SVM and k-NN achieved 90% and 87% respectively. This indicates the possibility for future research to investigate incorporating other neural network methods for categorizing students using data from LMS.

• Information Systems Review
• /
• v.17 no.2
• /
• pp.133-156
• /
• 2015

A recent interesting user experience in social curation websites is that they often encounter unanticipated, valuable information through accidental, incidental, or serendipitous discoveries. Prior research suggests that serendipity can help solve a problem, generate a creative idea, and invent a new product because it allows for an intellectual leap to arrive at a novel insight that is suddenly instrumental to a task. Despite the significant roles, the notion of serendipity is relatively unexplored especially in the context where people actually experience it, such as social curation websites. In this study, we theoretically identified the key technological features of social curation websites, which support three major curation activities respectively: browsing, collection, and interaction. We then examined their impacts on the occurrence of serendipitous discoveries in the process of information seeking. Our results using data collected from real users reveal that the technological features all affected user experience of serendipity and the interaction feature has stronger impacts than the other two. Moreover, it was also found that user experience of serendipity significantly affected website usage behavior such as intention to return and intention to contribute to the website.

• Journal of the Korean Society for Library and Information Science
• /
• v.52 no.3
• /
• pp.289-334
• /
• 2018

Even though information in many languages other than English is quickly increasing, English is still playing the role of the lingua franca and being accounted for the largest proportion on the web. Therefore, it is necessary to investigate the key features and differences between "information searching behavior using mother tongue as a search language" and "information searching behavior using English as a search language" of users who are non-mother tongue speakers of English to acquire more diverse and abundant information. This study conducted the experiment on the web searching which is applied in concurrent think-aloud method to examine the information searching behavior and the cognitive process in Korean search and English search through the twenty-four undergraduate students at a private university in South Korea. Based on the qualitative data, this study applied the frequency analysis to web search pattern under search language. As a result, it is active, aggressive and independent information searching behavior in Korean search, while information searching behavior in English search is passive, submissive and dependent. In Korean search, the main features are the query formulation by extract and combine the terms from various sources such as users, tasks and system, the search range adjustment in diverse level, the smooth filtering of the item selection in search engine results pages, the exploration and comparison of many items and the browsing of the overall contents of web pages. Whereas, in English search, the main features are the query formulation by the terms principally extracted from task, the search range adjustment in limitative level, the item selection by rely on the relevance between the items such as categories or links, the repetitive exploring on same item, the browsing of partial contents of web pages and the frequent use of language support tools like dictionaries or translators.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.379-386
• /
• 2004

Video segmentation is a fundamental task in video indexing and it includes two kinds of shot change detections such as the abrupt transition and the gradual transition. The abrupt shot boundaries are detected by computing the image-based distance between adjacent frames and comparing this distance with a pre-determined threshold value. However, the gradual shot boundaries are difficult to detect with this approach. To overcome this difficulty, we propose the method that detects gradual transition in the MPEG compressed video using the HMM (Hidden Markov Model). We take two different HMMs such as a discrete HMM and a continuous HMM with a Gaussian mixture model. As image features for HMM's observations, we use two distinct features such as the difference of histogram of DC images between two adjacent frames and the difference of each individual macroblock's deviations at the corresponding macroblock's between two adjacent frames, where deviation means an arithmetic difference of each macroblock's DC value from the mean of DC values in the given frame. Furthermore, we obtain the DC sequences of P and B frame by the first order approximation for a fast and effective computation. Experiment results show that we obtain the best detection and classification performance of gradual transitions when a continuous HMM with one Gaussian model is taken and two image features are used together.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.3
• /
• pp.187-194
• /
• 2012

Prostate cancer is one of the most frequent cancers in men and is a major cause of mortality in the most of countries. In many diagnostic and treatment procedures for prostate disease, transrectal ultrasound(TRUS) images are being used because the cost is low. But, accurate detection of prostate boundaries is a challenging and difficult task due to weak prostate boundaries, speckle noises and the short range of gray levels. This paper proposes a method for automatic prostate segmentation in TRUS images using its average shape model and invariant features. This approach consists of 4 steps. First, it detects the probe position and the two straight lines connected to the probe using edge distribution. Next, it acquires 3 prostate patches which are in the middle of average model. The patches will be used to compare the features of prostate and nonprostate. Next, it compares and classifies which blocks are similar to 3 representative patches. Last, the boundaries from prior classification and the rough boundaries from first step are used to determine the segmentation. A number of experiments are conducted to validate this method and results showed that this new approach extracted the prostate boundary with less than 7.78% relative to boundary provided manually by experts.