• Title/Summary/Keyword: Long-distance training

Search Result 51, Processing Time 0.028 seconds

Changes of Heart Rate During Marathon Running (장거리 (마라톤)선수에서의 전 경기중 심박동수의 변화)

  • Kim, In-Kyo;Lee, Jung-Woo;Hah, Jong-Sik;Ryu, Yun-Hee;Choi, Jung-Ok;Kim, Ki-Ho
    • The Korean Journal of Physiology
    • /
    • v.13 no.1_2
    • /
    • pp.1-12
    • /
    • 1979
  • To evaluate the present status of physical fittness of Korean long distance runners, body fat, pulmonary functions, maximal oxygen intake and oxygen debt were measured in 5 elite marathoners (A group), 6 college student runners (B group) and 3 middle school student runners (C group). After laboratory tests, full course marathon running was performed in 2 elite marathoners during which their heart rates were monitored continuously. The results are summerized as follows: 1) Total body fat in all three groups are in the range of 13-15% of their body weight. 2) In all three groups, average values of various pulmonary functions were within the normal limits, but those of tidal volume were higher and respiratory rate were lower in comparison to normal values. These phenomena may represent respiratory adaptations against training. The average resting oxygen consumptions in A,B and C were $322{\pm}23$, $278{\pm}14$ and $287{\pm}16$m1/min, respectively. 3) In all three groups, resting blood pressures were in the normal range, but the resting heart rate was slightly lower in groups A $(56{\pm}3\;beats/min)$ and B $(64{\pm}2\;beats/min)$ and higher in group C $(82{\pm}9\;beats/min)$ in comparison to normal values. These changes in cardiovascular functions in marathoners may also represent adaptive phenomena. 4) During treadmill running the minute ventilation and oxygen consumption of the runners increased lineally with work load in all three groups. When the oxygen consumption was related to heart rate, it appeared to be a exponential function of the heart rate in all three groups. 5) The average maximal heart rates during maximal work were $196{\pm}3$, $191{\pm}3$ and $196{\pm}5\;beats/min$ for groups A,B and C, respectively. Maximal oxygen intakes were $84.2{\pm}3.3\;ml/min/kg$ in group A, $65.2{\pm}1.1\;ml/min/kg$ in group B and $58.7{\pm}0.4\;ml/min/kg$ in group C. 6) In all three groups, oxygen debts and the rates of recovery of heart rate after treadmill running were lower than those of long ditsance runners reported previously. 7) The 40 km running time in 2 elite marathoners was recorded to be $2^{\circ}42'25'$, and their mean speed was 243 m/min (ranged 218 to 274 m/min). The heart rate appeared to increase lineally with running speed, and the total energy expenditure during 40 km running was approximately 1360.2 Calories. From these it can be speculated that if their heart rates were maintained at 166 beats/min during the full course of marathon running, their records would be arround $2^{\circ}15'$. Based on these results, we may suspect that a successful long distance running is, in part, dependent on the economical utilization of one's aerobic capacity.

  • PDF

Automatic gasometer reading system using selective optical character recognition (관심 문자열 인식 기술을 이용한 가스계량기 자동 검침 시스템)

  • Lee, Kyohyuk;Kim, Taeyeon;Kim, Wooju
    • Journal of Intelligence and Information Systems
    • /
    • v.26 no.2
    • /
    • pp.1-25
    • /
    • 2020
  • In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

A Study on Production Well Placement for a Gas Field using Artificial Neural Network (인공신경망 시뮬레이터를 이용한 가스전 생산정 위치선정 연구)

  • Han, Dong-Kwon;Kang, Il-Oh;Kwon, Sun-Il
    • Journal of the Korean Institute of Gas
    • /
    • v.17 no.2
    • /
    • pp.59-69
    • /
    • 2013
  • This study presents development of the ANN simulator for well placement of infill drilling in gas fields. The input data of the ANN simulator includes the production time, well location, all inter well distances, boundary inter well distance, infill well position, productivity potential, functional links, reservoir pressure. The output data includes the bottomhole pressure in addition to the production rate. Thus, it is possible to calculate the productivity and bottomhole pressure during production period simultaneously, and it is expected that this model could replace conventional simulators. Training for the 20 well placement scenarios was conducted. As a result, it was found that accuracy of ANN simulator was high as the coefficient of correlation for production rate was 0.99 and the bottomhole pressure 0.98 respectively. From the resultes, the validity of the ANN simulator has been verified. The term, which could produce Maximum Daily Quantity (MDQ) at the gas field and the productivity according to the well location was analyzed. As a result, the MDQ could be maintained for a short time in scenario C-1, which has the three infill wells nearby aquifer boundary, and a long time in scenario A-1. In conclusion, it was found that scenario A maintained the MDQ up to 21% more than those of scenarios B and C which include parameters that might affect the productivity. Thus, the production rate can be maximized by selecting the location of production wells in comprehensive consideration of parameters that may affect the productivity. Also, because the developed ANN simulator could calculate both production rate and bottomhole pressure, respectively, it could be used as the forward simulator in a various inverse model.

Automated Vehicle Research by Recognizing Maneuvering Modes using LSTM Model (LSTM 모델 기반 주행 모드 인식을 통한 자율 주행에 관한 연구)

  • Kim, Eunhui;Oh, Alice
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.16 no.4
    • /
    • pp.153-163
    • /
    • 2017
  • This research is based on the previous research that personally preferred safe distance, rotating angle and speed are differentiated. Thus, we use machine learning model for recognizing maneuvering modes trained per personal or per similar driving pattern groups, and we evaluate automatic driving according to maneuvering modes. By utilizing driving knowledge, we subdivided 8 kinds of longitudinal modes and 4 kinds of lateral modes, and by combining the longitudinal and lateral modes, we build 21 kinds of maneuvering modes. we train the labeled data set per time stamp through RNN, LSTM and Bi-LSTM models by the trips of drivers, which are supervised deep learning models, and evaluate the maneuvering modes of automatic driving for the test data set. The evaluation dataset is aggregated of living trips of 3,000 populations by VTTI in USA for 3 years and we use 1500 trips of 22 people and training, validation and test dataset ratio is 80%, 10% and 10%, respectively. For recognizing longitudinal 8 kinds of maneuvering modes, RNN achieves better accuracy compared to LSTM, Bi-LSTM. However, Bi-LSTM improves the accuracy in recognizing 21 kinds of longitudinal and lateral maneuvering modes in comparison with RNN and LSTM as 1.54% and 0.47%, respectively.

Oral hygiene management of patients with dental implants using electronic media (Smartphone) (전자매체(스마트폰)를 이용한 치과임플란트환자의 구강위생 관리)

  • Yang, Hyun Woo;Kim, Jin;Choi, Hanmaeum;Fang, Yiqin;Kim, So Young;Lee, Chunui
    • Journal of Korean Academy of Dental Administration
    • /
    • v.7 no.1
    • /
    • pp.39-43
    • /
    • 2019
  • Smartphone usage has become so common that it has reached 2 billion people in the last year. As a result of this, hospitals have started making use of smartphones at various medical sites and research services for patients. This study aimed to establish support for developing a long distance program for patients with implants who have difficulty visiting clinics or with busy modern lives, by using smartphones for oral hygiene management instruction. The data were collected for 12 weeks, from July 24 to October 21, 2015, for patients who agreed to participate in the study. Although the subjects found the process of transferring photos via smartphone to be cumbersome (75%), the satisfaction level of the oral hygiene management program was excellent for all participating patients, and they all wanted to continue with further management using this process. The results from the phone satisfaction survey showed that oral hygiene self-management after oral hygiene control training by smartphones was mostly equal to previous habits (87.5%) or had partially increased but had not decreased. The need for data on more varied age groups and the issues of protecting the security of personal information on smartphones require further study. However, our study confirmed the efficacy of using electronic media (smartphones) for oral hygiene management in patients with a dental implant due to their improvement of oral hygiene performance as evidenced by less bleeding from probing on post-program visit.

European Experience in Implementing Innovative Educational Technologies in the Field of Culture and the Arts: Current Problems and Vectors of Development

  • Kdyrova, I.O.;Grynyshyna, M.O.;Yur, M.V.;Osadcha, O.A.;Varyvonchyk, A.
    • International Journal of Computer Science & Network Security
    • /
    • v.22 no.5
    • /
    • pp.39-48
    • /
    • 2022
  • The main purpose of the work is to analyze modern innovative educational practices in the field of culture and art and their effectiveness in the context of the spread of digitalization trends. The study used general scientific theoretical methods of analysis, synthesis, analogy, comparative, induction, deduction, reductionism, and a number of others, allowing you to fully understand the pattern of modern modernization processes in a long historical development and demonstrate how the rejection of the negativity of progress allows talented artists to realize their own potential. The study established the advantages and disadvantages of involving innovative technologies in the educational process on the example of European experience and outlined possible ways of implementing digitalization processes in Ukrainian institutions of higher education, formulated the main difficulties encountered by teachers and students in the use of technological innovation in the pandemic. The rapid development of digital technologies has had a great impact on the sphere of culture and art, both visual, scenic, and musical in all processes: creation, reproduction, perception, learning, etc. In the field of art education, there is a synthesis of creative practices with digital technologies. In terms of music education, these processes at the present stage are provided with digital tools of specially developed software (music programs for composition and typing of musical text, recording, and correction of sound, for quality listening to the whole work or its fragments) for training programs used in institutional education and non-institutional learning as a means of independent mastering of the theory and practice of music-making, as well as other programs and technical tools without which contemporary art cannot be imagined. In modern stage education, the involvement of video technologies, means of remote communication, allowing realtime adjustment of the educational process, is actualized. In the sphere of fine arts, there is a transformation of communicative forms of interaction between the teacher and students, which in the conditions of the pandemic are of two-way communication with the help of information and communication technologies. At this stage, there is an intensification of transformation processes in the educational industry in the areas of culture and art.

A Deep Learning Based Approach to Recognizing Accompanying Status of Smartphone Users Using Multimodal Data (스마트폰 다종 데이터를 활용한 딥러닝 기반의 사용자 동행 상태 인식)

  • Kim, Kilho;Choi, Sangwoo;Chae, Moon-jung;Park, Heewoong;Lee, Jaehong;Park, Jonghun
    • Journal of Intelligence and Information Systems
    • /
    • v.25 no.1
    • /
    • pp.163-177
    • /
    • 2019
  • As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

A study on the improvement of distribution system by overseas agricultural investment (해외농업투자에 따른 유통체계 개선방안에 관한 연구)

  • Sun, Il-Suck;Lee, Dong-Ok
    • Journal of Distribution Science
    • /
    • v.8 no.3
    • /
    • pp.17-26
    • /
    • 2010
  • Recently concerns have been raised due to the unbalanced supply of crops: the price of crops has been unstable and at one point the price went up so high that the word Agflation(agriculture+ inflation) was coined. Korea, in particular, is a small-sized country and needs to secure the stable supply of crops by investing in the produce importation at a national level. Investment in foreign produce importation is becoming more important as a measure for sufficient supply of crops, limited supply of domestic crops, weakened farming conditions worldwide, as well as recent changes in the use of crops due to the development of bio-fuels, influence of carbon emission on crops, the price increase in crops, and influx of foreign hot money. However, there are many problems with investing in foreign produce importation: lack of support from the government; lack of farming information and technology; difficulty in securing the capital; no immediate pay-off from the investment and insufficient management. Although foreign produce is originally more price-competitive than domestic produce, it loses its competiveness in the process of importation (due to high tariffs) and poor distribution system, which makes it difficult to sell in Korea. Therefore, investment in foreign produce importation is being questioned for feasibility; to make it possible, foreign produce must maintain the price-competitiveness. Especially, harvest of agricultural products depends on natural and geographical conditions of each country and those products have indigenous properties, so distribution system according to import and export of agricultural products should be treated more carefully than that of other industries. Distribution costs are differentiated into each item and include cost of sorting and wrapping, cost of wrapping materials, cost of domestic transport, cost of international transport and cost of clearing customs for import and export. So transporting and storing agricultural products generates considerable costs compared with other products. Also, due to upgrade of dietary life, needs for stability, taste and visible quality toward food including agricultural products are being raised and wrong way of storage causes decomposition of food and loss of freshness, making the storage more difficult than that in room temperature, so storage and transport in distribution of agricultural products needs specialty. In addition, because lack of specialty in distribution and circulation such as storage and wrapping does not solve limit factors in distance, the distribution and circulation has been limited to a form of import and export within short-distant region. Therefore, need for distribution out-sourcing which can satisfy specialty in managing distribution and circulation and it is needed to establish more effective distribution system. However, existing distribution system of agricultural products is exposed to various problems including problems in distribution channel, making distribution and strategy for distribution and those problems are as follows. First, in case of investment in overseas agricultural industry, stable supply of the products is difficult because areas of production are dispersed widely and influenced by outer factors due to including overseas distribution channels. Also, at the aspect of quality, standardization of products is difficult, distribution system is quite complicated and unreasonable due to long distribution channels according to international trade and financial and institutional support is not enough. Especially, there are quite a lot of ineffective factors including multi level distribution process, dramatic gap between production cost and customer's cost, lack of physical distribution facilities and difficulties in storage and transport due to lack of wrapping containers. Besides, because import and export of agricultural products has been manages under the company's own distribution according to transaction contract between manufacturers and exporting company, efficiency is low due to excessive investment in fixed costs and lack of specialty in dealing with agricultural products causes fall of value of products, showing the limit to lose price-competitiveness. Especially, because lack of specialty in distribution and circulation such as storage and wrapping does not solve limit factors in distance, the distribution and circulation has been limited to a form of import and export within short-distant region. Therefore, need for distribution out-sourcing which can satisfy specialty in managing distribution and circulation and it is needed to establish more effective distribution system. Second, among tangible and intangible services which promote the efficiency of the whole distribution, a function building distribution environment which includes distribution information, system for standard and inspection, distribution finance, system for diversification of risks, education and training, distribution administration and tax system is wanted. In general, such a function building distribution environment is difficult to be changed and supplement innovatively because its effect compared with investment does not appear immediately despite of its necessity. Especially, in case of distribution of agricultural products, as a function of collecting and distributing is performed individually through various channels, the importance of distribution information and standardization is getting more focus due to the problem of repetition of work and lack of specialty. Also, efficient management of distribution is quite difficult due to lack of professionals in distribution, so support to professional education is needed. Third, though effort to keep self-sufficiency ratio of staple food, rice is regarded as important at the government level, level of dependency on overseas of others crops is high. Therefore, plan for stable securing food resources aside from staple food is also necessary. Especially, governmental organizations of agricultural products distribution in Korea are production-centered and have unreasonable structure whose function at the aspect of distribution and consumption is quite insufficient. And development of new distribution channels which can deal with changes in distribution environment and they do not achieve actual results of strategy for distribution due to non-positive strategy for price distribution. That is, it implies the possibility that base for supply will become vulnerable because it does not mediate appropriate interests on total distribution channels such as manufacturers, wholesale dealers and vendors by emphasizing consumer protection excessively in the distribution of agricultural products. Therefore, this study examined fundamental concept and actual situation for our investment to overseas agriculture, drew necessities, considerations, problems, etc. of overseas agricultural investment and suggested improvements at the level of distribution for price competitiveness of agricultural products cultivated in overseas under five aspects; government's indirect support, distribution's modernization and distribution information function's strengthening, government's political support for distribution facility, transportation route, load and unloading works' improvement, price competitiveness' securing, professional manpower's cultivation by education and training, etc. Here are some suggestions for foreign produce importation. First, the government should conduct a survey on the current distribution channels and analyze the situation to establish a measure for long-term development plans. By providing each agricultural area with a guideline for planning appropriate production of crops, the government can help farmers be ready for importation, and prevent them from producing same crops all at the same time. Government can sign an MOU with the foreign government and promote the importation so that the development of agricultural resources can be stable and steady. Second, the government can establish a strategy for an effective distribution system by providing farmers and agriculture-related workers with the distribution information such as price, production, demand, market structure and location, feature of each crop, and etc. In order for such distribution system to become feasible, the government needs to reconstruct the current distribution system, designate a public organization for providing distribution information and set the criteria for level of produce quality, trade units, and package units. Third, the government should provide financial support and a policy to seek an efficient distribution channel for foreign produce to be delivered fresh: the government should expand distribution facilities (for selecting, packaging, storing, and processing) and transportation vehicles while modernizing old facilities. There should be another policy to improve the efficiency of unloading, and to lower the cost of distribution. Fourth, it is necessary to enact a new law covering exceptional cases for importing produce in order to maintain the price competitiveness; currently the high tariffs is keeping the imported produce from being distributed domestically. However, the new adjustment should be made carefully within the WTO regulations since it can create a problem from giving preferential tariffs. The government can also simplify the distribution channels in order to reduce the cost in the distribution process. Fifth, the government should educate distributors to raise the efficiency and to modernize the distribution system. It is necessary to develop human resources by educating people regarding the foreign agricultural environment, the produce quality, management skills, and by introducing some successful cases in advanced countries.

  • PDF

Feasibility of Deep Learning Algorithms for Binary Classification Problems (이진 분류문제에서의 딥러닝 알고리즘의 활용 가능성 평가)

  • Kim, Kitae;Lee, Bomi;Kim, Jong Woo
    • Journal of Intelligence and Information Systems
    • /
    • v.23 no.1
    • /
    • pp.95-108
    • /
    • 2017
  • Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

Visual acuity of Fish -II. Relationship between light intensity line width at visual limit of filefish (어류의 시각에 관한 연구 - II . 쥐치의 시인한계에서의 밝기와 선의 굵기와의 관계)

  • An, Yeong-Il;Yang, Yong-Rim
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.33 no.4
    • /
    • pp.352-359
    • /
    • 1997
  • The visual acuity of filefish Stephanolepis cirrhifer was studied through a series of experiments by observing their responses to target plates. The fish were trained to respond to the target plates made of white acrylic resin with a vertical black line 5cm long in the center. The width of the black line ranged from 0.2mm to 8.0 mm. The line width was diminished unto the fish could no longer distinguish the line at a distance of 100 cm from the target plate. This was repeated under light intensities of 400, 20, 5, 3 and 1 lx at the water surface. Fish were rewarded with bait in front of the target plate if the fish went to the target date (i.e., success).The results show that the training effect of 1lensh had a success rate of over 80% and that the reach times to the target plates were 4~5 seconds over 210 experimental tunes. The success rate was high using the thick line with strong apparent contrast, but was low at the 1 lx. The visible critical width of line became thick with decreasing light intensity, 0.24mm at 400 lx, followed by 0.30mm at 20 lx, 0.40mm at 5 lx, 0.46 mm at 3 lx and 2.87mm at 1 lx. The apparent contrast for visible critical width of line increased with decreasing light intensity, 0.01 at 400 and 20 lx, 0.02 at 5 lx, 0.03 at 3 lx and 0.09 at 1 lx. The line acuity of filefish was best 1.21 at the 400 lx, followed by 0.97 at 20 lx, 0.73 at 5 lx, 0.63 at 3 lx and sharply decreased to 0.10 at 1 lx. The visible ranges for 1mm and 6mm in width of line were about 4.2 m and 25.0 m at the 400 lx light intensity and decreased m 1/14 times and 1/12 times of the 400 lx at 1 lx, respectively.

  • PDF