• Industrial Engineering and Management Systems
• /
• v.16 no.1
• /
• pp.64-79
• /
• 2017

Identifying disease genes from human genome is a critical task in biomedical research. Important biological features to distinguish the disease genes from the non-disease genes have been mainly selected based on traditional feature selection approaches. However, the traditional feature selection approaches unnecessarily consider many unimportant biological features. As a result, although some of the existing classification techniques have been applied to disease gene identification, the prediction performance was not satisfactory. A small set of the most important biological features can enhance the accuracy of disease gene identification, as well as provide potentially useful knowledge for biologists or clinicians, who can further investigate the selected biological features as well as the potential disease genes. In this paper, we propose a new stepwise random forests (SRF) approach for biological feature selection and disease gene identification. The SRF approach consists of two stages. In the first stage, only important biological features are iteratively selected in a forward selection manner based on one-dimensional random forest regression, where the updated residual vector is considered as the current response vector. We can then determine a small set of important biological features. In the second stage, random forests classification with regard to the selected biological features is applied to identify disease genes. Our extensive experiments show that the proposed SRF approach outperforms the existing feature selection and classification techniques in terms of biological feature selection and disease gene identification.

• The Journal of Internal Korean Medicine
• /
• v.36 no.2
• /
• pp.122-152
• /
• 2015

Objectives: This study was designed to develop a standard tool for pattern identification of gastroesophageal reflux disease (GERD) patients. Methods: Korean and Chinese literature was selected that mentioned pattern identification of GERD. We gathered the pattern identification and their symptoms and a Chinese medical doctor proficient in Korean translated the Chinese characters into Korean. A Korean linguist then confirmed the translation results to develop a draft of the standard tool for pattern identification of gastroesophageal reflux disease (PIGERD). The final PIGERD was developed after assessment by an expert committee composed of professors from the Korean Medicine University, using the following items: inclusion of the pattern identification and its symptoms, importance of items, and validity of translation. Results: Six pattern identifications and 94 symptoms were selected from 45 references and translated into Korean. Four pattern identifications [pattern/syndrome of liver qi invading the stomach (肝胃不和), spleen-stomach weakness (脾胃虛弱), spleen-stomach dampness-heat (脾胃濕熱), and stomach yin deficiency (胃陰不足)] and 49 symptoms were then selected through the Delphi method by the expert committee. The final standard PIGERD tool was completed after the assessment of translation validity and reflection of individual opinions by the expert committee. This tool consists of 40 items including tongue and pulse diagnosis. The weighted value was also computed from assessment of the importance of items. Conclusions: We developed a standard tool for pattern identification of gastroesophageal reflux disease (PIGERD) to clarify the pattern identification of patients with gastroesophageal reflux disease for standardized diagnosis.

• Journal of Multimedia Information System
• /
• v.4 no.4
• /
• pp.233-238
• /
• 2017

Automatic identification of disease in plants from their leaves is one of the most challenging task to researchers. Diseases among plants degrade their performance and results into a huge reduction of agricultural products. Therefore, early and accurate diagnosis of such disease is of the utmost importance. The advancement in deep Convolutional Neural Network (CNN) has change the way of processing images as compared to traditional image processing techniques. Deep learning architectures are composed of multiple processing layers that learn the representations of data with multiple levels of abstraction. Therefore, proved highly effective in comparison to many state-of-the-art works. In this paper, we present a plant disease identification methodology from their leaves using deep CNNs. For this, we have adopted GoogLeNet that is considered a powerful architecture of deep learning to identify the disease types. Transfer learning has been used to fine tune the pre-trained model. An accuracy of 85.04% has been recorded in the identification of four disease class in Apple plant leaves. Finally, a comparison with other models has been performed to show the effectiveness of the approach.

• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1115-1126
• /
• 2021

Plant disease is one of the most irritating problems for agriculture growers. Thus, timely detection of plant diseases is of high importance to practical value, and corresponding measures can be taken at the early stage of plant diseases. Therefore, numerous researchers have made unremitting efforts in plant disease identification. However, this problem was not solved effectively until the development of artificial intelligence and big data technologies, especially the wide application of deep learning models in different fields. Since the symptoms of plant diseases mainly appear visually on leaves, computer vision and machine learning technologies are effective and rapid methods for identifying various kinds of plant diseases. As one of the fruits with the highest nutritional value, apple production directly affects the quality of life, and it is important to prevent disease intrusion in advance for yield and taste. In this study, an improved deep residual network is proposed for apple leaf disease identification in a novel way, a global residual connection is added to the original residual network, and the local residual connection architecture is optimized. Including that 1,977 apple leaf disease images with three categories that are collected in this study, experimental results show that the proposed method has achieved 98.74% top-1 accuracy on the test set, outperforming the existing state-of-the-art models in apple leaf disease identification tasks, and proving the effectiveness of the proposed method.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.149-158
• /
• 2024

Traditional manual identification of crop leaf diseases is challenging. Owing to the limitations in manpower and resources, it is challenging to explore crop diseases on a large scale. The emergence of artificial intelligence technologies, particularly the extensive application of deep learning technologies, is expected to overcome these challenges and greatly improve the accuracy and efficiency of crop disease identification. Crop leaf disease identification models have been designed and trained using large-scale training data, enabling them to predict different categories of diseases from unlabeled crop leaves. However, these models, which possess strong feature representation capabilities, require substantial training data, and there is often a shortage of such datasets in practical farming scenarios. To address this issue and improve the feature learning abilities of models, this study proposes a deep transfer learning adaptation strategy. The novel proposed method aims to transfer the weights and parameters from pre-trained models in similar large-scale training datasets, such as ImageNet. ImageNet pre-trained weights are adopted and fine-tuned with the features of crop leaf diseases to improve prediction ability. In this study, we collected 16,060 crop leaf disease images, spanning 12 categories, for training. The experimental results demonstrate that an impressive accuracy of 98% is achieved using the proposed method on the transferred ResNet-50 model, thereby confirming the effectiveness of our transfer learning approach.

• 대한상한금궤의학회지
• /
• v.10 no.1
• /
• pp.143-152
• /
• 2018

Objective : A Patient complaining of dizziness was diagnosed and treated with the Shanghanlun disease pattern identification diagnostic system and was analyzed to report cases Methods : Based on the Shanghanlun disease pattern identification diagnostic system, we analyzed a case treated with the Baekho-tang and counseling. Results : Baekho-tang showed a rapid improvement in the patient. During the period of 20 days, dizziness were greatly improved. Conclusions : The Baekho-tang, which is not well known yet, can show rapid effect and can be diagnosed frequently through the Shanghanlun disease pattern identification diagnostic system.

• 대한상한금궤의학회지
• /
• v.9 no.1
• /
• pp.85-99
• /
• 2017

Objective : The objective of this study is to define the conceptional meaning of Shanghanlun provision while applying Shanghanlun disease pattern identification diagnostic system. Methods : 2 clinical cases, whose patients were treated by Injinho-tang, which was selected according to Shanghanlun provisions dualized with Je-Gang(提綱) and Jo-Moon(條文), were analyzed. Results : According to the results of analysis of 2 cases, the patients' diseases were improved when the treatment was applied according to Shanghanlun disease pattern identification diagnostic system and the interpretation of Shanghanlun provisions according to the etymology of Chinese character. Conclusions : These results suggests that Shanghanlun provisions be applied according to etymological interpretation of Chinese character in Shanghanlun disease pattern identification diagnostic system.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.24 no.1
• /
• pp.15-21
• /
• 2010

Previously standardization study for identifying 5 types of pattern identification of stroke patients has been performed and the Korean standard of pattern identification (II) was developed. In the present study we investigated the interactions between total indices designated by the Korean standard of pattern identification(KSPI II) and indices for PI of Cold-Heat and Deficiency-Excess. Indicators for Cold-Heat and Deficiency-Excess are isolated from 58 indices through the survey of oriental medicine doctors and their relationship with KSPI-II indices was analyzed by corresponding analysis method using data of 1581 stroke patients. Means and standard deviations indicated that 2 Cold indices, 14 Heat indices, 12 Deficiency indices, and 5 Excess indices were included for Cold-Heat and Deficiency-Excess pattern identification. The results of corresponding analysis shows the relationship of 57 indices and 4 types of pattern identification (excluding 1 index and 1 pattern among 58 indices and 5 patterns) using the cross-tabulation which was obtained from the clinical data. Most of Cold and Heat index were divided to dimension 1(inertia 51.9%) obtained from the result of corresponding analysis. Deficiency and Excess index were partially associated with dimension 2(inertia 31.7%). These data suggest that pattern identification of Cold-Heat plays an role in the standardization of pattern identification in stroke, although further studies are required by various trials such as analysis of surveys and clinical data.

• The Journal of the Society of Stroke on Korean Medicine
• /
• v.13 no.1
• /
• pp.24-32
• /
• 2012

Object : The purpose of this study is to observe the correlation between change in pattern identification symptoms and scandinavian stroke scale in ischemic stroke patient who had receive traditional Korean medical treatment and conservative treatment. Methods : 43 subjects were recruited from patients with ischemic stroke within 30 days of onset. We chose the subjects who had at least one follow up session and had checked the score between last follow up session and first session in pattern identification and scandinavian stroke scale. We also assessed the correlation between pattern identification and scandinavian stroke scale. Results : There were significant negative correlation between pattern identification and scandinavian stroke scale in Fire-heat pattern and positive correlation in Dampness-phlegm pattern. Conclusions : This study provides evidence that collaborative treatment maybe effective in improving neurologic symptoms in ischemic stroke patients diagnosed as Fire-heat pattern. Further studies with larger scale and longer observation period, more neurologicscales scales, control group would be required.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.24 no.5
• /
• pp.727-736
• /
• 2010

This study is about researching mechanistic pattern identification of disease for DongEuiBoGam NaeGyungPyen by analysing with pattern identification of modern Traditional Korean medical patholgy as more logical, systematic and standardized theory. Disease pattern mechanisms of uterine, urine and excrements parts of DongEuiBoGam NaeGyun gPyen in NaeGyungPyen of DongEuiBoGam are these. Menstrual irregularities in DongEuiBoGam can be classified flui d-humor depletion, blood deficiency, qi deficiency, qi stagnation, qi stagnation complicated by heat, blood stasis, blood deficiency complicated by heat, syndrome of heat entering blood chamber, syndrome of cold entering blood chamber. The disease pattern of abdominal pain after menstruation in DongEuiBoGam is blood deficiency complicated by heat, and a dysmenorrhea represents blood stasis with heat, fluid-humor deficiency. Advanced menstruation represent dual heat of the qi and blood, delayed menstruation is blood deficiency. The disease pattern of inhibited urination in DongEuiBoGam can be classified deficiency heat pattern of kidney yin deficiency(yin deficiency with effulgent fire), kidney qi deficiency, yin deficiency with yang hyperactivity, fluid-humor depletion, spleen-stomach dual deficiency, and excess he at pattern of bladder excess heat. The disease pattern of urinary incontinence in DongEuiBoGam can be classified deficiency pattern of kidney-bladder qi deficiency, consumptive disease, lung qi deficiency, kidney yin deficiency(yin deficiency with effulgent fire), kidney yang deficiency and excess pattern of lower energizer blood amassment, bladder excess heat. And most of them are deficiency from deficiency-excess Pattern Identification. The disease pattern of diarrhea in DongEuiBoGam can be classified deficiency pattern of qi deficiency, qi fall, spleen yang deficiency, kidney yang deficiency and so on and excess pattern of wind-cold-summerheat-dampness-fire, phlegm-fluid retention, dietary irregularities, qi movement stagnation. And most of them are deficiency from deficiency-excess Pattern Identification. Like these, this study identify pattern of disease in DongEuiBoGam by mechanism of disease theory.