• Title/Summary/Keyword: Label Design

Search Result 153, Processing Time 0.026 seconds

Hyperspectral Image Classification via Joint Sparse representation of Multi-layer Superpixles

  • Sima, Haifeng;Mi, Aizhong;Han, Xue;Du, Shouheng;Wang, Zhiheng;Wang, Jianfang
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.12 no.10
    • /
    • pp.5015-5038
    • /
    • 2018
  • In this paper, a novel spectral-spatial joint sparse representation algorithm for hyperspectral image classification is proposed based on multi-layer superpixels in various scales. Superpixels of various scales can provide complete yet redundant correlated information of the class attribute for test pixels. Therefore, we design a joint sparse model for a test pixel by sampling similar pixels from its corresponding superpixels combinations. Firstly, multi-layer superpixels are extracted on the false color image of the HSI data by principal components analysis model. Secondly, a group of discriminative sampling pixels are exploited as reconstruction matrix of test pixel which can be jointly represented by the structured dictionary and recovered sparse coefficients. Thirdly, the orthogonal matching pursuit strategy is employed for estimating sparse vector for the test pixel. In each iteration, the approximation can be computed from the dictionary and corresponding sparse vector. Finally, the class label of test pixel can be directly determined with minimum reconstruction error between the reconstruction matrix and its approximation. The advantages of this algorithm lie in the development of complete neighborhood and homogeneous pixels to share a common sparsity pattern, and it is able to achieve more flexible joint sparse coding of spectral-spatial information. Experimental results on three real hyperspectral datasets show that the proposed joint sparse model can achieve better performance than a series of excellent sparse classification methods and superpixels-based classification methods.

A Study on Target Ages and Sizes of Korean Women′s Ready-made Clothes (한국 성인여자 기성복 브랜드의 타깃 연령 및 생산사이즈에 관한 실태조사 연구)

  • 조영아
    • The Research Journal of the Costume Culture
    • /
    • v.8 no.4
    • /
    • pp.549-561
    • /
    • 2000
  • The purpose of this study was to survey and analyze the age classification of women customers as a target market and sizes on a label that were actually produced by each brand in Korean national brands ; they were classified into size for bodice and bottom, and compared with the distribution of national data of women's body measurement. They were analyzed and classified by brand groups of 'miss', 'missy', 'Mrs.'and 'madam', The results were ; 1) It was found that recent products for ready-made for women's clothes tend to be designed with target to the measured ages classified by the range of five or ten years. The main practice was that for 'miss'brand group the age range was of five years, and for 'missy'brand group, ten years. And for 'Mrs'and 'madam'brand groups, it was of 15 or 20 years. So that, it is necessary to design their clothes based on their features of body considering the intervals of age. 2) 'Mrs'and 'madam'groups were most remarkable for their distribution into a vast range of sizes for three control dimensions and waist girth size when compared to 'miss'and 'missy'groups. The distribution of brand size had no relation with that of body measurement, and in particular, none was produced for short height size between 145 and 150 ㎝. For tall height size between 175 and 180 ㎝, many brand sizes were distributed while body measurement was few. It means that distribution of brand size was different from real distribution of body measurement was few. It means that distribution of brand size was different from real distribution of body measurement as a result that the larger the bust girth in such cases over 160 ㎝, the larger the size of hip girth. Even as for the height 155 and 160 ㎝ in which body measurement is concentrated, there were many problems because while sizes of 'large'bust girth and 'small'hip girth had a large distribution, their clothes were not produced.

  • PDF

Feature Selection Using Submodular Approach for Financial Big Data

  • Attigeri, Girija;Manohara Pai, M.M.;Pai, Radhika M.
    • Journal of Information Processing Systems
    • /
    • v.15 no.6
    • /
    • pp.1306-1325
    • /
    • 2019
  • As the world is moving towards digitization, data is generated from various sources at a faster rate. It is getting humungous and is termed as big data. The financial sector is one domain which needs to leverage the big data being generated to identify financial risks, fraudulent activities, and so on. The design of predictive models for such financial big data is imperative for maintaining the health of the country's economics. Financial data has many features such as transaction history, repayment data, purchase data, investment data, and so on. The main problem in predictive algorithm is finding the right subset of representative features from which the predictive model can be constructed for a particular task. This paper proposes a correlation-based method using submodular optimization for selecting the optimum number of features and thereby, reducing the dimensions of the data for faster and better prediction. The important proposition is that the optimal feature subset should contain features having high correlation with the class label, but should not correlate with each other in the subset. Experiments are conducted to understand the effect of the various subsets on different classification algorithms for loan data. The IBM Bluemix BigData platform is used for experimentation along with the Spark notebook. The results indicate that the proposed approach achieves considerable accuracy with optimal subsets in significantly less execution time. The algorithm is also compared with the existing feature selection and extraction algorithms.

LSTM-based Deep Learning for Time Series Forecasting: The Case of Corporate Credit Score Prediction (시계열 예측을 위한 LSTM 기반 딥러닝: 기업 신용평점 예측 사례)

  • Lee, Hyun-Sang;Oh, Sehwan
    • The Journal of Information Systems
    • /
    • v.29 no.1
    • /
    • pp.241-265
    • /
    • 2020
  • Purpose Various machine learning techniques are used to implement for predicting corporate credit. However, previous research doesn't utilize time series input features and has a limited prediction timing. Furthermore, in the case of corporate bond credit rating forecast, corporate sample is limited because only large companies are selected for corporate bond credit rating. To address limitations of prior research, this study attempts to implement a predictive model with more sample companies, which can adjust the forecasting point at the present time by using the credit score information and corporate information in time series. Design/methodology/approach To implement this forecasting model, this study uses the sample of 2,191 companies with KIS credit scores for 18 years from 2000 to 2017. For improving the performance of the predictive model, various financial and non-financial features are applied as input variables in a time series through a sliding window technique. In addition, this research also tests various machine learning techniques that were traditionally used to increase the validity of analysis results, and the deep learning technique that is being actively researched of late. Findings RNN-based stateful LSTM model shows good performance in credit rating prediction. By extending the forecasting time point, we find how the performance of the predictive model changes over time and evaluate the feature groups in the short and long terms. In comparison with other studies, the results of 5 classification prediction through label reclassification show good performance relatively. In addition, about 90% accuracy is found in the bad credit forecasts.

An Active Co-Training Algorithm for Biomedical Named-Entity Recognition

  • Munkhdalai, Tsendsuren;Li, Meijing;Yun, Unil;Namsrai, Oyun-Erdene;Ryu, Keun Ho
    • Journal of Information Processing Systems
    • /
    • v.8 no.4
    • /
    • 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.

A Design of ITMS(Intelligent Transport Monitoring System) for Optimization of Freight Transport (화물 수송의 최적화를 위한 ITMS(Intelligent Transport Monitoring System) 설계)

  • Jeong, EunHee;Lee, ByungKwan;Jung, INa
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.17 no.12
    • /
    • pp.2853-2858
    • /
    • 2013
  • This paper proposes the ITMS(Intelligent Transport Monitoring System) which manages the route and state of freight by using the Meteorological Office, the Transportation Management Center, GPS and Sensors, etc. The ITMS consists of the CIMS(Container Inner Monitoring System) transmitting the inner temperature and humidity of a container, the TMM(Transport Management Module) computing an estimated time of arrival with Freight Vehicle location information and transmits the result to the CIMS, the FMM(Freight Management Module) checking and managing the freight freshness by using the temperature and humidity of the collected containers, and the SMM(Stevedoring Management Module) selecting the container loading and unloading places with the information transmitted from the CIMS, the TMM, and the FMM and attaching the freight formation to containers using an RFID label. The ITMS not only checks the freight condition at intervals but also acquires and manages the freight information with RFID labels rapidly and accurately.

Endovascular Treatment of Congenital Portosystemic Shunt: A Single-Center Prospective Study

  • Ponce-Dorrego, Maria-Dolores;Hernandez-Cabrero, Teresa;Garzon-Moll, Gonzalo
    • Pediatric Gastroenterology, Hepatology & Nutrition
    • /
    • v.25 no.2
    • /
    • pp.147-162
    • /
    • 2022
  • Purpose: To design a prospective study on endovascular closure of congenital portosystemic shunts. The primary endpoint was to assess the safety of endovascular closure. The secondary endpoint was to evaluate the clinical, analytical and imaging outcomes of treatment. Methods: Fifteen patients (age range: 2 days to 21 years; 10 male) were referred to our center due to congenital portosystemic shunts. The following data were collected prior to treatment: age, sex, medical history, clinical and analytical data, urine trimethylaminuria, abdominal-US, and body-CT. The following data were collected at the time of intervention: anatomical and hemodynamic characteristics of the shunts, device used, and closure success. The following data were collected at various post-intervention time points: during hospital stay (to confirm shunt closure and detect complications) and at one year after (for clinical, analytical, and imaging purposes). Results: The treatment was successful in 12 participants, migration of the device was observed in two, while acute splanchnic thrombosis was observed in one. Off-label devices were used in attempting to close the side-to-side shunts, and success was achieved using Amplatzer™ Ductus-Occluder and Amplatzer™ Muscular-Vascular-Septal-Defect-Occluder. The main changes were: increased prothrombin activity (p=0.043); decreased AST, ALT, GGT, and bilirubin (p=0.007, p=0.056, p=0.036, p=0.013); thrombocytopenia resolution (p=0.131); expansion of portal veins (p=0.005); normalization of Doppler portal flow (100%); regression of liver nodules (p=0.001); ammonia normalization (p=0.003); and disappearance of trimethylaminuria (p=0.285). Conclusion: Endovascular closure is effective. Our results support the indication of endovascular closure for side-to-side shunts and for cases of congenital absence of portal vein.

Implementation of Git's Commit Message Complex Classification Model for Software Maintenance

  • Choi, Ji-Hoon;Kim, Joon-Yong;Park, Seong-Hyun
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.11
    • /
    • pp.131-138
    • /
    • 2022
  • Git's commit message is closely related to the project life cycle, and by this characteristic, it can greatly contribute to cost reduction and improvement of work efficiency by identifying risk factors and project status of project operation activities. Among these related fields, there are many studies that classify commit messages as types of software maintenance, and the maximum accuracy among the studies is 87%. In this paper, the purpose of using a solution using the commit classification model is to design and implement a complex classification model that combines several models to increase the accuracy of the previously published models and increase the reliability of the model. In this paper, a dataset was constructed by extracting automated labeling and source changes and trained using the DistillBERT model. As a result of verification, reliability was secured by obtaining an F1 score of 95%, which is 8% higher than the maximum of 87% reported in previous studies. Using the results of this study, it is expected that the reliability of the model will be increased and it will be possible to apply it to solutions such as software and project management.

Image Clustering Using Machine Learning : Study of InceptionV3 with K-means Methods. (머신 러닝을 사용한 이미지 클러스터링: K-means 방법을 사용한 InceptionV3 연구)

  • Nindam, Somsauwt;Lee, Hyo Jong
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2021.11a
    • /
    • pp.681-684
    • /
    • 2021
  • In this paper, we study image clustering without labeling using machine learning techniques. We proposed an unsupervised machine learning technique to design an image clustering model that automatically categorizes images into groups. Our experiment focused on inception convolutional neural networks (inception V3) with k-mean methods to cluster images. For this, we collect the public datasets containing Food-K5, Flowers, Handwritten Digit, Cats-dogs, and our dataset Rice Germination, and the owner dataset Palm print. Our experiment can expand into three-part; First, format all the images to un-label and move to whole datasets. Second, load dataset into the inception V3 extraction image features and transferred to the k-mean cluster group hold on six classes. Lastly, evaluate modeling accuracy using the confusion matrix base on precision, recall, F1 to analyze. In this our methods, we can get the results as 1) Handwritten Digit (precision = 1.000, recall = 1.000, F1 = 1.00), 2) Food-K5 (precision = 0.975, recall = 0.945, F1 = 0.96), 3) Palm print (precision = 1.000, recall = 0.999, F1 = 1.00), 4) Cats-dogs (precision = 0.997, recall = 0.475, F1 = 0.64), 5) Flowers (precision = 0.610, recall = 0.982, F1 = 0.75), and our dataset 6) Rice Germination (precision = 0.997, recall = 0.943, F1 = 0.97). Our experiment showed that modeling could get an accuracy rate of 0.8908; the outcomes state that the proposed model is strongest enough to differentiate the different images and classify them into clusters.

Proposal for User-Product Attributes to Enhance Chatbot-Based Personalized Fashion Recommendation Service (챗봇 기반의 개인화 패션 추천 서비스 향상을 위한 사용자-제품 속성 제안)

  • Hyosun An;Sunghoon Kim;Yerim Choi
    • Journal of Fashion Business
    • /
    • v.27 no.3
    • /
    • pp.50-62
    • /
    • 2023
  • The e-commerce fashion market has experienced a remarkable growth, leading to an overwhelming availability of shared information and numerous choices for users. In light of this, chatbots have emerged as a promising technological solution to enhance personalized services in this context. This study aimed to develop user-product attributes for a chatbot-based personalized fashion recommendation service using big data text mining techniques. To accomplish this, over one million consumer reviews from Coupang, an e-commerce platform, were collected and analyzed using frequency analyses to identify the upper-level attributes of users and products. Attribute terms were then assigned to each user-product attribute, including user body shape (body proportion, BMI), user needs (functional, expressive, aesthetic), user TPO (time, place, occasion), product design elements (fit, color, material, detail), product size (label, measurement), and product care (laundry, maintenance). The classification of user-product attributes was found to be applicable to the knowledge graph of the Conversational Path Reasoning model. A testing environment was established to evaluate the usefulness of attributes based on real e-commerce users and purchased product information. This study is significant in proposing a new research methodology in the field of Fashion Informatics for constructing the knowledge base of a chatbot based on text mining analysis. The proposed research methodology is expected to enhance fashion technology and improve personalized fashion recommendation service and user experience with a chatbot in the e-commerce market.