• Journal of Information Processing Systems
• /
• 제7권4호
• /
• pp.717-732
• /
• 2011

Classification in biomedical applications is an important task that predicts or classifies an outcome based on a given set of input variables such as diagnostic tests or the symptoms of a patient. Traditionally the classification algorithms would have to digest a stationary set of historical data in order to train up a decision-tree model and the learned model could then be used for testing new samples. However, a new breed of classification called stream-based classification can handle continuous data streams, which are ever evolving, unbound, and unstructured, for instance--biosignal live feeds. These emerging algorithms can potentially be used for real-time classification over biosignal data streams like EEG and ECG, etc. This paper presents a pioneer effort that studies the feasibility of classification algorithms for analyzing biosignals in the forms of infinite data streams. First, a performance comparison is made between traditional and stream-based classification. The results show that accuracy declines intermittently for traditional classification due to the requirement of model re-learning as new data arrives. Second, we show by a simulation that biosignal data streams can be processed with a satisfactory level of performance in terms of accuracy, memory requirement, and speed, by using a collection of stream-mining algorithms called Optimized Very Fast Decision Trees. The algorithms can effectively serve as a corner-stone technology for real-time classification in future biomedical applications.

• 대한의용생체공학회:의공학회지
• /
• 제29권6호
• /
• pp.466-476
• /
• 2008

The more people use ambulatory electrocardiogram(ECG) for arrhythmia detection, the more researchers report the automatic classification algorithms. Most of the previous studies don't consider the un-balanced data distribution. Even in patients, there are much more normal beats than abnormal beats among the data from 24 hours. To solve this problem, the hierarchical classification using 21 features was adopted for arrhythmia abnormal beat detection. The features include R-R intervals and data to describe the morphology of the wave. To validate the algorithm, 44 non-pacemaker recordings from physionet were used. The hierarchical classification model with 2 stages on domain knowledge was constructed. Using our suggested method, we could improve the performance in abnormal beat classification from the conventional multi-class classification method. In conclusion, the domain knowledge based hierarchical classification is useful to the ECG beat classification with unbalanced data distribution.

• 대한의용생체공학회:의공학회지
• /
• 제39권2호
• /
• pp.63-68
• /
• 2018

In modern society, speech recognition technology is emerging as an important technology for identification in electronic commerce, forensics, law enforcement, and other systems. In this study, we aim to develop an age classification algorithm for extracting only MFCC(Mel Frequency Cepstral Coefficient) expressing the characteristics of speech in Korean and applying it to deep learning technology. The algorithm for extracting the 13th order MFCC from Korean data and constructing a data set, and using the artificial intelligence algorithm, deep artificial neural network, to classify males in their 20s, 30s, and 50s, and females in their 20s, 40s, and 50s. finally, our model confirmed the classification accuracy of 78.6% and 71.9% for males and females, respectively.

• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.575-588
• /
• 2012

Exploiting unlabeled text data with a relatively small labeled corpus has been an active and challenging research topic in text mining, due to the recent growth of the amount of biomedical literature. Biomedical named-entity recognition is an essential prerequisite task before effective text mining of biomedical literature can begin. This paper proposes an Active Co-Training (ACT) algorithm for biomedical named-entity recognition. ACT is a semi-supervised learning method in which two classifiers based on two different feature sets iteratively learn from informative examples that have been queried from the unlabeled data. We design a new classification problem to measure the informativeness of an example in unlabeled data. In this classification problem, the examples are classified based on a joint view of a feature set to be informative/non-informative to both classifiers. To form the training data for the classification problem, we adopt a query-by-committee method. Therefore, in the ACT, both classifiers are considered to be one committee, which is used on the labeled data to give the informativeness label to each example. The ACT method outperforms the traditional co-training algorithm in terms of f-measure as well as the number of training iterations performed to build a good classification model. The proposed method tends to efficiently exploit a large amount of unlabeled data by selecting a small number of examples having not only useful information but also a comprehensive pattern.

• 대한의용생체공학회:의공학회지
• /
• 제43권5호
• /
• pp.299-307
• /
• 2022

In this paper, we propose a pre-processing method that converts to Spider Chart image data for classification of gripping movement using EMG (electromyography) sensors and Convolution Neural Networks (CNN) deep learning. First, raw data for six hand gestures are extracted from five test subjects using an 8-channel armband and converted into Spider Chart data of octagonal shapes, which are divided into several sliding windows and are learned. In classifying six hand gestures, the classification performance is compared with the proposed pre-processing method and the existing methods. Deep learning was performed on the dataset by dividing 70% of the total into training, 15% as testing, and 15% as validation. For system performance evaluation, five cross-validations were applied by dividing 80% of the entire dataset by training and 20% by testing. The proposed method generates 97% and 94.54% in cross-validation and general tests, respectively, using the Spider Chart preprocessing, which was better results than the conventional methods.

• Journal of Multimedia Information System
• /
• 제3권3호
• /
• pp.97-102
• /
• 2016

Deep learning enables machines to have perception and can potentially outperform humans in the medical field. It can save a lot of time and reduce human error by detecting certain patterns from medical images without being trained. The main goal of this paper is to build the optimal model for breast mass classification by applying various methods that influence the performance of Convolutional Neural Network (CNN). Google's newly developed software library Tensorflow was used to build CNN and the mammogram dataset used in this study was obtained from 340 breast cancer cases. The best classification performance we achieved was an accuracy of 0.887, sensitivity of 0.903, and specificity of 0.869 for normal tissue versus malignant mass classification with augmented data, more convolutional filters, and ADAM optimizer. A limitation of this method, however, was that it only considered malignant masses which are relatively easier to classify than benign masses. Therefore, further studies are required in order to properly classify any given data for medical uses.

• Genomics & Informatics
• /
• 제9권1호
• /
• pp.19-27
• /
• 2011

Gene Expression Omnibus (GEO) has kept the largest amount of gene-expression microarray data that have grown exponentially. Microarray data in GEO have been generated in many different formats and often lack standardized annotation and documentation. It is hard to know if preprocessing has been applied to a dataset or not and in what way. Standard-based integration of heterogeneous data formats and metadata is necessary for comprehensive data query, analysis and mining. We attempted to integrate the heterogeneous microarray data in GEO based on Minimum Information About a Microarray Experiment (MIAME) standard. We unified the data fields of GEO Data table and mapped the attributes of GEO metadata into MIAME elements. We also discriminated non-preprocessed raw datasets from others and processed ones by using a two-step classification method. Most of the procedures were developed as semi-automated algorithms with some degree of text mining techniques. We localized 2,967 Platforms, 4,867 Series and 103,590 Samples with covering 279 organisms, integrated them into a standard-based relational schema and developed a comprehensive query interface to extract. Our tool, GEOQuest is available at http://www.snubi.org/software/GEOQuest/.

• 대한의용생체공학회:의공학회지
• /
• 제31권1호
• /
• pp.40-49
• /
• 2010

A rule weight -based fuzzy classification model is proposed to analyze the patterns of admission-discharge of patients as a previous research for differential diagnosis of dyspnea. The proposed model is automatically generated from a labeled data set, supervised learning strategy, using three procedure methodology: i) select fuzzy partition regions from spatial distribution of data; ii) generate fuzzy membership functions from the selected partition regions; and iii) extract a set of candidate rules and resolve a conflict problem among the candidate rules. The effectiveness of the proposed fuzzy classification model was demonstrated by comparing the experimental results for the dyspnea patients' data set with 11 features selected from 55 features by clinicians with those obtained using the conventional classification methods, such as standard fuzzy classifier without rule weights, C4.5, QDA, kNN, and SVMs.

• 대한의용생체공학회:의공학회지
• /
• 제33권1호
• /
• pp.15-24
• /
• 2012

Classification of human thought is an emerging research field that may allow us to understand human brain functions and further develop advanced brain-computer interface (BCI) systems. In the present study, we introduce a new approach to classify various mental states from noninvasive electrophysiological recordings of human brain activity. We utilized the full spatial and spectral information contained in the electroencephalography (EEG) signals recorded while a subject is performing a specific mental task. For this, the EEG data were converted into a 2D spatiospectral pattern map, of which each element was filled with 1, 0, and -1 reflecting the degrees of event-related synchronization (ERS) and event-related desynchronization (ERD). We evaluated the similarity between a current (input) 2D pattern map and the template pattern maps (database), by taking the inner-product of pattern matrices. Then, the current 2D pattern map was assigned to a class that demonstrated the highest similarity value. For the verification of our approach, eight participants took part in the present study; their EEG data were recorded while they performed four different cognitive imagery tasks. Consistent ERS/ERD patterns were observed more frequently between trials in the same class than those in different classes, indicating that these spatiospectral pattern maps could be used to classify different mental states. The classification accuracy was evaluated for each participant from both the proposed approach and a conventional mental state classification method based on the inter-hemispheric spectral power asymmetry, using the leave-one-out cross-validation (LOOCV). An average accuracy of 68.13% (${\pm}9.64%$) was attained for the proposed method; whereas an average accuracy of 57% (${\pm}5.68%$) was attained for the conventional method (significance was assessed by the one-tail paired $t$-test, $p$ < 0.01), showing that the proposed simple classification approach might be one of the promising methods in discriminating various mental states.

• 대한의용생체공학회:의공학회지
• /
• 제43권5호
• /
• pp.353-360
• /
• 2022

Laryngeal disease harms quality of life, and laryngoscopy is critical in identifying causative lesions. This study extracts and analyzes using radiomics quantitative features from the lesion in laryngoscopy images and will fit and validate a classifier for finding meaningful features. Searching the region of interest for lesions not classified by the YOLOv5 model, features are extracted with radionics. Selected the extracted features are through a combination of three feature selectors, and three estimator models. Through the selected features, trained and verified two classification models, Random Forest and Gradient Boosting, and found meaningful features. The combination of SFS, LASSO, and RF shows the highest performance with an accuracy of 0.90 and AUROC 0.96. Model using features to select by SFM, or RIDGE was low lower performance than other things. Classification of larynx lesions through radiomics looks effective. But it should use various feature selection methods and minimize data loss as losing color data.