• Title, Summary, Keyword: human error

Search Result 1,240, Processing Time 0.057 seconds

A Collaborative Filtering System Combined with Users' Review Mining : Application to the Recommendation of Smartphone Apps (사용자 리뷰 마이닝을 결합한 협업 필터링 시스템: 스마트폰 앱 추천에의 응용)

  • Jeon, ByeoungKug;Ahn, Hyunchul
    • Journal of Intelligence and Information Systems
    • /
    • v.21 no.2
    • /
    • pp.1-18
    • /
    • 2015
  • Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

Technical Efficiency of Medical Resource Supply and Demand (의료자원 공급, 수요의 성과 효율성에 대한 실증분석)

  • Chang, Insu;Ahn, Hyeong Seok;Kim, Brian H.S.
    • Journal of the Korean Regional Science Association
    • /
    • v.34 no.2
    • /
    • pp.3-19
    • /
    • 2018
  • The objective of this study is to observe the efficiency of clinical performance on the supply and demand of medical resources in Korea. For the empirical analysis, we constructed the dataset on age standardized mortality rate, the number of physician, specialist, surgery, medical institution, ratio of general hospitals of 16 provinces in Korea from 2006 to 2013. The panel probability frontier model is employed as an analysis method and considered heteroscedasticity and autocorrelation of the error in panel data. In addition, the demographic and socioeconomic characteristics of the 16 provinces, unemployment rate, elderly population ratio, GRDP per capita, and ratio of hospitals in comparison to the general hospitals are used to find the effect on the technical efficiency of clinical performance on supply and demand of medical resources. The results are as follows. First, for the clinical performance, the supply side of human resources such as doctors and specialists and the demand side factors such as chronic illness clinic per unit population have a significant influence, respectively. Second, the technical efficiency of clinical performance on the supply and demand of medical resources of each input component was 59-70% in terms of clinical efficiency in each region. Third. estimates of technical efficiency of inputs that affect clinical performance showed a slight increase in all regions during the analysis period, but the increase trend decreased slightly. Fourth, the ratio of the elderly population and GRDP per capita have a positive influence on the technical efficiency of clinical performance on the supply and demand of medical resources. The difference of each efficiency by region is due to the regional differences of the input medical resources and the combination of them and the demographic and socioeconomic characteristics of the region. It is understood that the differences in technological efficiency due to the complexity of supply and demand of medical resources, demographic structure and economic difference affecting clinical performance by region are different.

Comparison of Algorithms for Generating Parametric Image of Cerebral Blood Flow Using ${H_2}^{15}O$ PET Positron Emission Tomography (${H_2}^{15}O$ PET을 이용한 뇌혈류 파라메트릭 영상 구성을 위한 알고리즘 비교)

  • Lee, Jae-Sung;Lee, Dong-Soo;Park, Kwang-Suk;Chung, June-Key;Lee, Myung-Chul
    • The Korean Journal of Nuclear Medicine
    • /
    • v.37 no.5
    • /
    • pp.288-300
    • /
    • 2003
  • Purpose: To obtain regional blood flow and tissue-blood partition coefficient with time-activity curves from ${H_2}^{15}O$ PET, fitting of some parameters in the Kety model is conventionally accomplished by nonlinear least squares (NLS) analysis. However, NLS requires considerable compuation time then is impractical for pixel-by-pixel analysis to generate parametric images of these parameters. In this study, we investigated several fast parameter estimation methods for the parametric image generation and compared their statistical reliability and computational efficiency. Materials and Methods: These methods included linear least squres (LLS), linear weighted least squares (LWLS), linear generalized least squares (GLS), linear generalized weighted least squares (GWLS), weighted Integration (WI), and model-based clustering method (CAKS). ${H_2}^{15}O$ dynamic brain PET with Poisson noise component was simulated using numerical Zubal brain phantom. Error and bias in the estimation of rCBF and partition coefficient, and computation time in various noise environments was estimated and compared. In audition, parametric images from ${H_2}^{15}O$ dynamic brain PET data peformed on 16 healthy volunteers under various physiological conditions was compared to examine the utility of these methods for real human data. Results: These fast algorithms produced parametric images with similar image qualify and statistical reliability. When CAKS and LLS methods were used combinedly, computation time was significantly reduced and less than 30 seconds for $128{\times}128{\times}46$ images on Pentium III processor. Conclusion: Parametric images of rCBF and partition coefficient with good statistical properties can be generated with short computation time which is acceptable in clinical situation.

A Study on Job Stress of Dental Technician (치과기공사의 업무스트레스에 대한 연구)

  • Lee, Deok-Su;Kwak, Dong-Ju;Nam, Sang-Yong
    • Journal of Technologic Dentistry
    • /
    • v.24 no.1
    • /
    • pp.51-63
    • /
    • 2002
  • The purpose of this study was to be of use for getting rid of job stress from dental technicians, by examining how much they were stressed out at work place as one of the professional medical personnels. The subjects in this study were 255 selected dental technicians who were working in the region of Taegu. The one-on-one interview was conducted from March 1 to 30, 2001, with structured questionnaire. The questionnaire sued in this study included 19 question items about the general characteristics and 29 items regarding job stress. The job stress was categorized into seven subareas based on earlier studies and considering the job situations of dental technicians: heavy workload, job conflicts, improper treatment, role and job knowledge, human relations, physical environment and personal matters. The job stress extent was measured on five-point Likert scale that is widely used in social science: one point for no stress, two for little stress, three for so-so, four for a little stress, and five for severe stress. Therefore, a higher point means a severer job stress. The reliability of the questionnaire turned out very good with Cronbach a = 0.9272. The findings of this study were as follows: 1. The general characteristics of the dental technicians investigated could be described as below: (1) By gender, 80.4% of the dental technicians were male, and 50.2%, the largest percentage, were in their 20s, followed by those in their 30s, those in their 40s, and those in their 50s in the order named. (2) The most common work place was dental technician shop(92.5%), followed by dental technology room in dental hospital or clinic and in general hospital in the order named. The primary duties were coating materials work(30.6%), followed by sculpture, grinding, partial and full denture and orthodontics in the order named. 2. The most larges (1) The most largest motivation to be a dental technician was its being a professional(33.7%), followed by the advice from others, their own aptitude, and good economic treatment in the order named. 3. Their job stress could be explained as below: (1) Their collective job stress average was 3.96$^{\circ}{\ae}$0.50 on the basis of 5 point, which showed that they were exposed to a fairly severe job stress. (2) By area, they were most stressed out from heavy workload (4.12), and they also were severely stressed from role and job knowledge(4.02) and personal matters(4.00). (3) By situation, they were most stressed when the disagreement of prosthesis that results from a specific error is unconditionally attributed to them(4.43). And they were also stressed a lot when their workload increases due to the rework(4.38), when a dentist asks something difficult for them to resolve(4.20), when heavy workload makes their working hours irregular and it's impossible to lead a personal life or have leisure time(4.16), and when they are o work for an excessively short time(4.16). This fact indicated that most of the dental technicians were exposed to a lot of stress in conjunction with job performance. 4. The main duties they took charge of didn't make any significant difference to their job stress, but yielded a significant difference to the extent of job stress in individual areas and the order of the most stressful one. Those who were engaged in grinding were most stressed from their own matters, whereas heavy workload was most stressful for those who were engaged in the other types of works. 5. As a result of seeing if their personal characteristics yielded any differences to job stress, the personal characteristics that made their job stress vary significantly were working hours, motivation of being a dental technician, job satisfaction and willingness to continue doing dental technology works. There was a tendency that longer working hours led to severer job stress, and those who chose to be a dental technician according to their own aptitude were less stressed than the others who became a dental technician because of economic reason or advices from others. And the people who were satisfied with their job were exposed to less job stress than the others who weren't, and those who had an intention to keep that job as much as possible were less stressed, compared to the others who hadn't.

  • PDF

A study of Brachytherapy for Intraocular Tumor (안구내 악성종양에 대한 저준위 방사선요법에 관한 연구)

  • Ji, Gwang-Su;Yu, Dae-Heon;Lee, Seong-Gu;Kim, Jae-Hyu;Ji, Yeong-Hun
    • The Journal of Korean Society for Radiation Therapy
    • /
    • v.8 no.1
    • /
    • pp.19-27
    • /
    • 1996
  • I. Project Title A Study of Brachytherapy for intraocular tumor II. Objective and Importance of the project The eye enucleation or external-beam radiation therapy that has been commonly used for the treatment of intraocular tumor have demerits of visual loss and in deficiency of effective tumor dose. Recently, brachytherapy using the plaques containing radioisotope-now treatment method that decrease the demerits of the above mentioned treatment methods and increase the treatment effect-is introduced and performed in the countries, Our purpose of this research is to design suitable shape of plaque for the ophthalmic brachytherapy, and to measure absorbed doses of Ir-192 ophthalmic plaque and thereby calculate the exact radiation dose of tumor and it's adjacent normal tissue. III. Scope and Contents of the project In order to brachytherapy for intraocular tumor, 1. to determine the eye model and selected suitable radioisotope 2. to design the suitable shape of plaque 3. to measure transmission factor and dose distribution for custom made plaques 4. to compare with the these data and results of computer dose calculation models IV. Results and Proposal for Applications The result were as followed. 1. Eye model was determined as a 25mm diameter sphere, Ir-192 was considered the most appropriate as radioisotope for brachytherapy, because of the size, half, energy and availability. 2. Considering the biological response with human tissue and protection of exposed dose, we made the plaques with gold, of which size were 15mm, 17mm and 20mm in diameter, and 1.5mm in thickness. 3. Transmission factor of plaques are all 0.71 with TLD and film dosimetry at the surface of plaques and 0.45, 0.49 at 1.5mm distance of surface, respectively. 4. As compared the measured data for the plaque with Ir-192 seeds to results of computer dose calculation model by Gary Luxton et al. and CAP-PLAN (Radiation Treatment Planning System), absorbed doses are within ${\pm}10\%$ and distance deviations are within 0.4mm Maximum error is $-11.3\%$ and 0.8mm, respectively. As a result of it, we can treat the intraocular tumor more effectively by using custom made gold plaque and Ir-192 seeds.

  • PDF

Changes in the inward current and membrane conductance after fertilization in the mouse eggs (수정에 의한 Mouse egg의 세포막전류 변화)

  • Hong, Seong-geun;Park, Choon-ok;Han, Jae-hee;Kim, Ik-hyun;Ha, Dae-sik;Kwun, Jong-kuk
    • Korean Journal of Veterinary Research
    • /
    • v.32 no.2
    • /
    • pp.157-164
    • /
    • 1992
  • Changes in the both inward current and conductance of membrane by the fertilization were observed using the one microelectrode voltage clamp(or switch clamp) technique. Unfertilized eggs and both 1- and 2-cell stage eggs after fertilization were donated from the superovulated mouse (ICR, more than 6 weeks old) treated with PMSG(pregnant mare serum gonadotropin, Sigma) and HCG(human chorionic gonadotropin, Sigma) and naturally mated ones, respectively in this experiment. Membrane potential was held at -90mV and the voltage step was applied from -80mV to 50mV with interval of 10mV or 20mV for 300ms. since both of amplitudes and time courses in the membrane currents were various according to the states of cells and clamping condition, results were presented by their $averages{\pm}SEM$(standard mean error)and ratios or percentages. Inward currents began to appear in response to the step depolarization from -60mV and reached its maximum at -50mV. However, since the potential was not clamped evenly during the voltage step, current-voltage(I-V) relationship might be positively shifted 10 or 20mV. From the steady-state currents plotted in the I-V curve, outward rectification was markedly observed. Peak inward currents$(i_{in})$ at -50mV were $-0.62{\pm}0.23nA$(n=4),$-0.52{\pm}0.25nA$(n=5) and $-0.37{\pm}0.25nA$(n=6), in the 1-cell stage, 2-cell stage fertilized eggs and in the unfertilized eggs, respectively. Pure inward current (difference between steady-state and peak, $i_{in. pure}$) were $-1.01{\pm}0.23nA$, $-0.69{\pm}0.43nA$ and $-0.68{\pm}0.29nA$, respectively in the 1-cell stage fertilized eggs, unfertilized eggs and 2-cell stage fertilized eggs. These results suggested that the outward current in fertilized eggs of 2-cell stage was more increased than those in the unfertilized eggs. Pure inward currents in the all stages of eggs showed a similar fashion in the I-V relationship from -50mV to 50mV and reversal potential at 50mV. Time constant of inactivation$({\tau})$ in the inward current was decreased as the membrane potential was depolarized in the unfertilized and 2-cell stage eggs but in the 1-cell stage eggs t was not likely to be affected significantly. Slope conductances were 14.2nS, 8.9n5 and 7.7nS in the 1-cell, 2-cell stage fertilized eggs and the unfertilized eggs, respectively. Membranes between two cells within a zona pellucida seem to be electrical-connected in the 2-cell stage eggs from the observation made in the analysis for the electronic spread and decay to the current stimuli. Both of inward current and membrane conductance were increased after fertilization in the mouse eggs. Inward current seems to be carried by the same ion or through the same channels up to the 2-cell stage and ion that carried inward current was thought to play important function after fertilization in the mouse eggs.

  • PDF

Automatic Interpretation of Epileptogenic Zones in F-18-FDG Brain PET using Artificial Neural Network (인공신경회로망을 이용한 F-18-FDG 뇌 PET의 간질원인병소 자동해석)

  • 이재성;김석기;이명철;박광석;이동수
    • Journal of Biomedical Engineering Research
    • /
    • v.19 no.5
    • /
    • pp.455-468
    • /
    • 1998
  • For the objective interpretation of cerebral metabolic patterns in epilepsy patients, we developed computer-aided classifier using artificial neural network. We studied interictal brain FDG PET scans of 257 epilepsy patients who were diagnosed as normal(n=64), L TLE (n=112), or R TLE (n=81) by visual interpretation. Automatically segmented volume of interest (VOI) was used to reliably extract the features representing patterns of cerebral metabolism. All images were spatially normalized to MNI standard PET template and smoothed with 16mm FWHM Gaussian kernel using SPM96. Mean count in cerebral region was normalized. The VOls for 34 cerebral regions were previously defined on the standard template and 17 different counts of mirrored regions to hemispheric midline were extracted from spatially normalized images. A three-layer feed-forward error back-propagation neural network classifier with 7 input nodes and 3 output nodes was used. The network was trained to interpret metabolic patterns and produce identical diagnoses with those of expert viewers. The performance of the neural network was optimized by testing with 5~40 nodes in hidden layer. Randomly selected 40 images from each group were used to train the network and the remainders were used to test the learned network. The optimized neural network gave a maximum agreement rate of 80.3% with expert viewers. It used 20 hidden nodes and was trained for 1508 epochs. Also, neural network gave agreement rates of 75~80% with 10 or 30 nodes in hidden layer. We conclude that artificial neural network performed as well as human experts and could be potentially useful as clinical decision support tool for the localization of epileptogenic zones.

  • PDF

Three-dimensional Model Generation for Active Shape Model Algorithm (능동모양모델 알고리듬을 위한 삼차원 모델생성 기법)

  • Lim, Seong-Jae;Jeong, Yong-Yeon;Ho, Yo-Sung
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.43 no.6
    • /
    • pp.28-35
    • /
    • 2006
  • Statistical models of shape variability based on active shape models (ASMs) have been successfully utilized to perform segmentation and recognition tasks in two-dimensional (2D) images. Three-dimensional (3D) model-based approaches are more promising than 2D approaches since they can bring in more realistic shape constraints for recognizing and delineating the object boundary. For 3D model-based approaches, however, building the 3D shape model from a training set of segmented instances of an object is a major challenge and currently it remains an open problem in building the 3D shape model, one essential step is to generate a point distribution model (PDM). Corresponding landmarks must be selected in all1 training shapes for generating PDM, and manual determination of landmark correspondences is very time-consuming, tedious, and error-prone. In this paper, we propose a novel automatic method for generating 3D statistical shape models. Given a set of training 3D shapes, we generate a 3D model by 1) building the mean shape fro]n the distance transform of the training shapes, 2) utilizing a tetrahedron method for automatically selecting landmarks on the mean shape, and 3) subsequently propagating these landmarks to each training shape via a distance labeling method. In this paper, we investigate the accuracy and compactness of the 3D model for the human liver built from 50 segmented individual CT data sets. The proposed method is very general without such assumptions and can be applied to other data sets.

A Case Study on Forecasting Inbound Calls of Motor Insurance Company Using Interactive Data Mining Technique (대화식 데이터 마이닝 기법을 활용한 자동차 보험사의 인입 콜량 예측 사례)

  • Baek, Woong;Kim, Nam-Gyu
    • Journal of Intelligence and Information Systems
    • /
    • v.16 no.3
    • /
    • pp.99-120
    • /
    • 2010
  • Due to the wide spread of customers' frequent access of non face-to-face services, there have been many attempts to improve customer satisfaction using huge amounts of data accumulated throughnon face-to-face channels. Usually, a call center is regarded to be one of the most representative non-faced channels. Therefore, it is important that a call center has enough agents to offer high level customer satisfaction. However, managing too many agents would increase the operational costs of a call center by increasing labor costs. Therefore, predicting and calculating the appropriate size of human resources of a call center is one of the most critical success factors of call center management. For this reason, most call centers are currently establishing a department of WFM(Work Force Management) to estimate the appropriate number of agents and to direct much effort to predict the volume of inbound calls. In real world applications, inbound call prediction is usually performed based on the intuition and experience of a domain expert. In other words, a domain expert usually predicts the volume of calls by calculating the average call of some periods and adjusting the average according tohis/her subjective estimation. However, this kind of approach has radical limitations in that the result of prediction might be strongly affected by the expert's personal experience and competence. It is often the case that a domain expert may predict inbound calls quite differently from anotherif the two experts have mutually different opinions on selecting influential variables and priorities among the variables. Moreover, it is almost impossible to logically clarify the process of expert's subjective prediction. Currently, to overcome the limitations of subjective call prediction, most call centers are adopting a WFMS(Workforce Management System) package in which expert's best practices are systemized. With WFMS, a user can predict the volume of calls by calculating the average call of each day of the week, excluding some eventful days. However, WFMS costs too much capital during the early stage of system establishment. Moreover, it is hard to reflect new information ontothe system when some factors affecting the amount of calls have been changed. In this paper, we attempt to devise a new model for predicting inbound calls that is not only based on theoretical background but also easily applicable to real world applications. Our model was mainly developed by the interactive decision tree technique, one of the most popular techniques in data mining. Therefore, we expect that our model can predict inbound calls automatically based on historical data, and it can utilize expert's domain knowledge during the process of tree construction. To analyze the accuracy of our model, we performed intensive experiments on a real case of one of the largest car insurance companies in Korea. In the case study, the prediction accuracy of the devised two models and traditional WFMS are analyzed with respect to the various error rates allowable. The experiments reveal that our data mining-based two models outperform WFMS in terms of predicting the amount of accident calls and fault calls in most experimental situations examined.

A Study on eDesign Platform for Effective Communication and Information sharing - with an emphasis on process and template (효과적인 커뮤니케이션과 정보공유를 위한 e디자인 플랫폼 구축에 관한 연구 - 프로세스와 템플릿을 중심으로)

  • 윤주현
    • Archives of design research
    • /
    • v.17 no.2
    • /
    • pp.425-436
    • /
    • 2004
  • A new design field called eDesign appears as if eBiz is an online related business in which an industrialized design creates the individual value added facing a digital revolution. The field of eDesign requires a special design process and management methodology regardless of the fact that human sensitivity will be satisfied through a dehumanized computer technique. However, it is the reality of eDesign that has been dependent upon a simple process or project management tool of general design. In this study, we develop an eDesign platform based on an eDesign process and template mainly focused on eBusiness in order to overcome the wrong situation. The template is a kind of document that has a standardization form. We aim to establish a general process through various case projects, store information using a necessary template, and use for the way of visual communication. We propose a standard of eDesign platform that can be widely applied to the field of design, medium and small enterprises focused on IT businesses or design-team through this project performed as an educational-industrial study. It makes it possible to get a detailed process methodology, which can be applied to many small design related companies that don't have their own process yet, and will be a scale for comparing their own process in which the company has a process of opened standard eDesign with it. In addition, it makes possible a systematic control of the own projects within and outside the firm, accumulating information for the firm through the database, and easy communication. Furthermore, it can be applied to check the process of the project as a checklist, and then it will reduce trial and error repeated for every project that has been done.

  • PDF