• Journal of the Korea Society of Computer and Information
• /
• v.22 no.11
• /
• pp.97-104
• /
• 2017

Location prediction has been successfully utilized to provide high quality of location-based services to customers in many applications. In its usual form, the conventional type of location prediction is to predict future locations based on user's past movement history. However, as location prediction needs are expanded into much complicated cases, it becomes necessary quite frequently to make inference on the locations that target user visited in the past. Typical cases include the identification of locations that infectious disease carriers may have visited before, and crime suspects may have dropped by on a certain day at a specific time-band. Therefore, primary goal of this study is to predict locations that users visited in the past. Information used for this purpose include user's demographic information and movement histories. Data mining classifiers such as Bayesian network, neural network, support vector machine, decision tree were adopted to analyze 6868 contextual dataset and compare classifiers' performance. Results show that general Bayesian network is the most robust classifier.

• The Plant Pathology Journal
• /
• v.26 no.2
• /
• pp.198-202
• /
• 2010

A study was conducted to find out the relationship of physico-chemical properties (viz. organic carbon(OC), pH, electrical conductivity, nitrogen, phosphorus and potassium content) of ginger growing soil with incidence percentage of rhizome rot and wilt disease complex of ginger. Organic carbon content and pH of the ginger soil contributed significantly (93%) in the prediction of ginger rhizome rot and wilt disease complex incidence with negative correlation. Soil having weak acidic reaction with OC percent greater than 2.25 was observed to have the lower average incidence of the disease.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.96-105
• /
• 2024

We propose a method to automatically predict Alzheimer's disease from speech data using the ChatGPT large language model. Alzheimer's disease patients often exhibit distinctive characteristics when describing images, such as difficulties in recalling words, grammar errors, repetitive language, and incoherent narratives. For prediction, we initially employ a speech recognition system to transcribe participants' speech into text. We then gather opinions by inputting the transcribed text into ChatGPT as well as a prompt designed to solicit fluency evaluations. Subsequently, we extract embeddings from the speech, text, and opinions by the pretrained models. Finally, we use a classifier consisting of transformer blocks and linear layers to identify participants with this type of dementia. Experiments are conducted using the extensively used ADReSSo dataset. The results yield a maximum accuracy of 87.3% when speech, text, and opinions are used in conjunction. This finding suggests the potential of leveraging evaluation feedback from language models to address challenges in Alzheimer's disease recognition.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.8
• /
• pp.335-343
• /
• 2019

Healthy living is an essential element of human happiness. Quality eating provides the basis for life, and the health of livestock, which provides meat and dairy products, has a direct impact on human health. In the case of calves, diarrhea is the cause of all diseases.In this paper, we use a sensor to measure calf 's biometric data to diagnose calf diarrhea. The collected biometric data is subjected to a preprocessing process for use as meaningful information. We measure calf birth history and calf biometrics. The ontology is constructed by inputting environmental information of housing and biochemistry, immunity, and measurement information of human body for disease management. We will build a knowledge base for predicting calf diarrhea by predicting calf diarrhea through logical reasoning. Predict diarrhea with the knowledge base on the name of the disease, cause, timing and symptoms of livestock diseases. These knowledge bases can be expressed as domain ontologies for parent ontology and prediction, and as a result, treatment and prevention methods can be suggested.

• Journal of the Korean Society of Radiology
• /
• v.7 no.3
• /
• pp.191-198
• /
• 2013

We verified reason of pain by rotator cuff disease using shoulder sonography and found a correlation between shoulder pain and stress. To find out the accuracy of sonographic prediction of rotator cuff disease among the patients with shoulder pain we surveyed 184 patients in S hospital in Seoul Korea between January to October 2012. These patients were previously diagnosed with the torn rotator cuff, adhesive capsulitis and impingement syndrom with shoulder pain. In most times, the rotator cuff disease was diagnosed among the physical workers who use shoulder excessively and also in the women in their 50~60 years of age(144 patients, 78.3%). There were significant correlation between rotator cuff disease and the stress of pain, between sonographic prediction and pain(p<.05). There were significance between shoulder pain and stress in daily life according to result for survey of BEPSI-K(p<.05).

• Research in Plant Disease
• /
• v.19 no.3
• /
• pp.196-200
• /
• 2013

This study was carried out to investigate yield loss due to soybean leaf spot disease caused by Cercospora sojina Hara and to determine the economic threshold level. The investigations revealed highly significant correlations between disease severity (diseased leaf area) and yield components (pod number per plant, total grain number per plant, total grain weight per plant, percent of ripened grain, weight of hundred seed, and yield). The correlation coefficients between leaf spot severity and each component were -0.90, -0.90, -0.92, -0.99, -0.90 and -0.94, respectively. The yield was inversely proportional to the diseased leaf area increased. The regression equation, yield prediction model, between disease severity (x) and yield (y) was obtained as y = -3.7213x + 354.99 ($R^2$ = 0.9047). Based on the yield prediction model, economic injury level and economic threshold level could be set as 3.3% and 2.6% of diseased leaf area of soybean.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.11-21
• /
• 2020

Cardio-cerebrovascular diseases (CCD) account for 24% of the causes of death to Koreans and its proportion is the highest except cancer. Currently, the risk of the cardiovascular disease for domestic patients is based on the Framingham risk score (FRS), but accuracy tends to decrease because it is a foreign guideline. Also, it can't score the risk of cerebrovascular disease. CCD is hard to predict, because it is difficult to analyze the features of early symptoms for prevention. Therefore, proper prediction method for Koreans is needed. The purpose of this paper is validating IG-MLP (Information Gain - Multilayer Perceptron) evaluation based feature selection method using CCD data with simulation. The proposed method uses the raw data of the 4^th ~ 7^th of The Korea National Health and Nutrition Examination Survey (KNHANES). To select the important feature of CCD, analysis on the attributes using IG-MLP are processed, finally CCD prediction ANN model using optimize feature set is provided. Proposed method can find important features of CCD prediction of Koreans, and ANN model could predict more accurate CCD for Koreans.

• Korean Journal Plant Pathology
• /
• v.14 no.5
• /
• pp.433-439
• /
• 1998

The studies on the ecology of virus disease on Chinese cabbage (Brassica campestris subsp. pekinensis) cultivated in alpine area of Kangwon province during summer season to analyse its influence on damage and develope a prediction model were performed from 1993 to 1997. Virus disease on Chinese cabbage occurring in the alpine area showed various symptom types and among there, necrotic spots and dwarf were mainly detected. The disease was increased from early August and continued mid September in every year. The occurrence of virus disease was the highest in 1994 with 20.5%, and the number of aphid vectors were also the highest during the same period. The number of aphids in the alpine areas showed twice peaks every year. For the analysis of damage by virus infection, the infection and injured ratio of all treatments were more than 90% and 80%, respectively. The most important factor for the occurrence of virus disease on Chinese cabbage was temperature. Factors influencing the development of the viral disease in the alpine area were maximum temperature and number of aphid vectors.

• The Magazine of the IEIE
• /
• v.31 no.1
• /
• pp.58-72
• /
• 2004

Smart sensors and biochip technologies have received a great deal of attention in recent years not only because of the enormous potential markets in the healthcare expenditures but more importantly because of its great impact on the quality of human life in the future. Collaborative research among BT (Bio Technologies), IT (Information Technologies) and NT (Nano Technologies) will bring us a new paradigm of the healthcare services. Examples include disease prediction based on the genetic tests, personal medicines, point-of-care analysis, rapid and sensitive infectious disease diagnostics, environmental monitoring for chemical or biological warfares, intelligent drug delivery systems etc. In this report, recent accomplishment in the research area on biosensors, DNA chips, Protein Chips and Lab-on-a-chips are reviewed.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.30 no.5
• /
• pp.414-421
• /
• 2004

This is a reprospective study on the care of odontogenic infections in admission patients with geriatric diseases. The study was based on a series of 480 patients at Dong San Medical Center, Wonju Christian Hospital and Il San Health Insurance Hospital, From Jan. 1, 2000, to Dec. 31, 2002. The Obtained results were as follows: 1. The systemic malignant tumor was the most frequent cause of the geriatric diseases with odontogenic infectious diseases, and refractory lung disease, systemic heart disease, type II diabetes mellitus, cerebrovascular disease, bone & joint disease, senile psychologic disease were next in order of frequency. 2. Male prediction(57.5%) was existed in the odontogenic infectious patients with geriatric diseases. But, there were female prediction in senile psychologic disease, systemic heart disease and cerebrovascular disease. 3. The most common age group of the odontogenic infectious patient with geriatric disease was the sixty decade(47.9%), followed by the seventy & eighty decade in order. 4. In the contents of chief complaints on the odontogenic infectious patients with geriatric disease, peak incidence was occurred as toothache(52.7%), followed by extraction wish, tooth mobility, oral bleeding, oral ulcer, fracture of restoration, gingival swelling in order. 5. In the diagnosis group of odontogenic infectious diseases, periodontitis, pulpitis & periapical abscess were more common. 6. In the treatment group of odontogenic infectious diseases, the most frequent incidence(34.2%) was showed in primary endodontic treatment (pulp extirpation, occlusal reduction and canal opening drainage) and followed by scaling, incision & drainage, only drugs, pulp capping, restoration in order.