• 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.

• Journal of Aquaculture
• /
• v.2 no.2
• /
• pp.53-90
• /
• 1989

Feeding proper level of ration matchable with the appetite of fish will enhance production and also prevent waste of food and its consequence, side effects such as pollution of culture medium. To pursue this goal, elaborate studies on dissolved oxygen concentrations- as the major force in inducing appetite and the growth outcome are necessary. The growth of common carp of 67, 200, 400, 600, and 800 gram size groups was studied at oxygen concentrations ranging from 2.0 to 6 mg/$\iota$ in relation to rations from 1 to as many percent of the initial body weight as could be consumed under constant temperature of $25^{\circ}C$. The results from the experiments are summarized as followings; 1. Appetite: The smaller fish exhibited higher degree of appetite than the bigger ones at the same oxygen concentrations. The bigger the fish the less tolerant it was to the lower oxygen thersholds, and the degree of tolerence decreased as ration level increased. 2. Growth : Growth rate (percent per day) increased - unless consumption was suppressed by low oxygen levels- as the ration was increased to maximum. In case of 67 g fish, it reached the highest point of $5.05\%$ / day at $7\%$ ration under 5.0 mg/$\iota$ of oxygen. In case of 200 g fish, the maximum growth rate of $3.75\%$/day appeared at the maximum ration of $6\%$ under 5.5 mg/$\iota$ of oxygen. In 400 g fish, the highest growth of $3.37\%$/day occurred at the maximum ration of $5\%$ and 6.0 mg/$\iota$ of oxygen. In 600 g fish, the highest growth rate of $2.82\%$ /day was at the maximum ration of $4\%$ under 5.5 mg/$\iota$ oxygen. In case of 800g fish, the highest growth rate of $1.95\%$/day was at maximum tested ration of $3\%$ under 5.0 mg/$\iota$ oxygen. 3. Food Conversion Efficiency: Food conversion efficiency ($\%$ dry feed converted into the fish tissue) first increased as the ration was increased, reached maximum at certain food level, then started decreasing with further increase in the ration. The maximum conversion efficiency stood at higher feeding rate for the smaller fish than the larger ones. In case of 67 g fish, the maximum food conversion efficiency was at $4\%$ ration within 3.0-4.0 mg/$\iota$ oxygen. In 200g fish, the maximum efficiency was at $3\%$ ration within 4.0-4.5 mg/$\iota$ oxygen. In 400g fish, the maximum efficiency was at $2\%$ ration within 4.0 - 4.5 mg/$\iota$ oxygen. In 600 and 800g fish, the maximum conversion efficiency shifted to the lowest ration ($1\%$) and lower oxygen ranges. 4. Behaviour: The fish within uncomfortably low oxygen levels exhibited suppressed appetite and movements and were observed to pass feces quicker and in larger quantity than the ones in normal condition; in untolerably low oxygen the fish were lethargic, vomited, and had their normal skin color changed into pale yellow or grey patches. All these processes contributed to reducing food conversion efficiency. On the other hand, the fish within relatively higher oxygen concentrations exhibited higher degree of movement and their food conversion tended to be depressed when compared with sister groups under corresponding size and ration within relatively low oxyen level. 5. Suitability of Oxygen Ranges to Rations: The oxygen level of 2.0- 2.5 mg/$\iota$ was adequate to sustain appetite at $1\%$ ration in all size groups. As the ration was increased higher oxygen was required to sustain the fish appetite and metabolic activity, particularly in larger fish. In 67g fish, the $2\%$ ration was well supported by 2.0-2.5 mg/$\iota$ range; as the ration increased to $5\%$, higher range of 3.0-4.0 mg/$\iota$ brought better appetite and growth; from 5 till $7\%$ (the last tested ration for 67 g fish) oxygen levels over 4.0 mg/$\iota$ could sustain appetite. In 200 g fish, the 2 and $3\%$ rations brought the best growth and conversion rates at 3.5-4.5 mg/$\iota$ oxygen level; from 3 till $6\%$ (the last tested ration at 200 g fish) oxyge groups over 4.5 mg/$\iota$ were matchable with animal's appetite. In 400, 600, and 800 g fish, all the rations above $2\%$ had to be generally supported with oxygen levels above 4.5 mg/$\iota$.

• Korean Journal of Occupational Health Nursing
• /
• v.3
• /
• pp.54-70
• /
• 1993

According as the automation of clerical work(OA ; Office Automation) develops, the use of VDT(Visual or Video Display Terminal) is increasing suddenly. But, in proportion to the spread of office automation(OA tendency), the self-conciousness syptom attendant upon the work is appearing also (Kim, Jung Tae, Lee, Young Ook, 1990). The apparatuses of office enable the clerical workers to be convenient and perform mass businesses. But, they are increasing the opportunity to be exposed to VDT syndrom, techno stress, computer terminal disease, pain by muscle strain(RSI), bradycausia of noise nature, and electromagnetic waves, etc. which are referred to as the new type of occupational diseases to the workers. It is the real situation that the workers to use VDT is complaining of the physical inconvenience sense in the recent newspaper and literature, it is the point of time that the sydrome to come from VDT use and computer terminal disease, etc. must be classified into the occupational disease(Lee, Kwang Young 1990, Lee, Kyoo Hak 1990, Lee, Won Ho 1991, Lee, Si Young 1991, Lee, Joon 1991, Choi, Young Tae 1991, Heo, Seung Ho 1989). In addition, it is the real situation that the scientifitic study result about the scope that electromagnetic waves has influence on the human body has not been suggested yet, and criticism on the stable exposure permission standard about electromagnetic waves to be emitted from VDT and on the problem in the health about electromagnetic waves is continuing. (IEEE Spectrum, 1990). In addition according to the experience of nursery business of industry field, it is the real situation that the patients who consult complaining of physical and mental inconvenience sence, among the users of apparatus of office automation, are reaching 10% of the patients coming to doctor's room. Therefore, it is necessary to confirm the self-consciousness symptom that the clerical workers complain of multilaterally with the actual state examination about the use of the apparatuses of offices automaton. Thus, this study was tried as th basic data for the cosultation and education for the maintenance and furtherance of the health of workers as the nurse of industry field, by confirming the contents of self-consciousness symptom attendant upon the use of the apparatus for office outomation making the financial institution in which the spparatus for office automation in most frequently used as the subject, and by examining whether there is the difference according to the subject of study, the data were collected, by using the questionnaire method, making 200 workers who consented to the study participation as the subject, among the persons who have spent over 3 months since they used the apparatuses for office automation and didn't receive the treatment in hospital due to the clerical disease for recent 3 years. The period of data collection was from Oct. 9, 1991 to Oct. 12. As for the measurement instrument about the complaint if self-consciousness symptom attendant upon the use of apparatuses fo office automation, the question item on the complaint symptom of health problem attendant upon the treatment of VDT that Kim(1991) developed and on CMI health problem and the question items on the fatigue degree due to industry were used by previous examination to 25 persons. Collected data were analyzed with the statistical method such as percentage, arithmetic mean, Person correlation coeffient, Kai square verfication, t-test, ANOVA, etc. by using SPSS/PC+ program, and the result is as follows : 1. The self-consciousness symptom that the clerical workers complained of most frequetly appeared high in 'My eyes are tired'(99.4%), 'I feel fatigue and weariness'(99.4%), 'I feel that my head is heavy5(90.0%), 'eyesight fell'(88.8%), 'I have a stiff neck'(88.8%), 'I fell pain in the shoulder'(85.0%), 'I feel cold and painful in the eyes'(76.9%), 'I feel the dry sense of eyeball'(76.2%), 'My nerves are edgy, and I an fretful, (75.6%), 'I feel pain in the waist'(73.2%) and 'I fell pain in the back'(72.8%). It emerged that the subject use the apparatuses for office automation complained of self-consciousness symptoms related to visual symptoms and musculoskeletal symptoms. 2. As for the general feature of examination subjects, the result to see the distribution by classifying into sex, age, school career, use career of apparatuses for office automation, skillfulness degree of the use of apparatus for office automation, use hours of the apparatuses for office automation per 1 day, type of business of the apparatus for office automation, rest hours during the use of apparatus for office automation, satifaction degree of business of office automation, and work circumstance, etc. emerged as follows : As for the sex of subjects, the distribution showed that men were 58.8% and women were 41.3%, Age was average 26.9. As the distribution of school career, the distribution showed that4below the graduation of high school' was 58.8%, 'graduation from junior college-university' was 35.0%, and 'over graduate school' was 6.3%. In the question to ask the existence or non-existence of experience of health consultation in connection with the work of office automation, the response that I had the consultation exprience and I feel the necessity emergerd as 90.1% And, the case that the subject who didn't wear the glasses or lens before using the OA apparatus wear glasses or lens after using OA apparatus emerged as 28.3% of whole. As for the existence or non-existence of use career of OA apparatus, the case under 3 years was highest as 52. 7%. As for the skillfulnness degree about the use of apparatus for office automation, most of them are skillful with the fact that 'common' was 44.4%, 'skill' was 42.5%, and 'unskillful' was 13.1% As for the use average hours of the apparatus for office automation per 1 day, the distribution showed that the case under 3-6 hours was 33.1%, the case under 6-9 hours was 28.1%, the case under 3 hours was 30.6%, and the case over 9 hours was 8.1% Main OA business and the use hours for 1 day showed in the order of keeping and retrieval, business of information transmission(162min), business of information transmission(79.3 min), business of document framing(55.5 min), and business of duplication and printing(25.4min). as for the rest during the use of apparatus for affice automation, that I take rest occasion demands the major portion, but that I take after completing the work emerged as 33.8%. Though the subiness gets to be convenient by the use of the apparatus for of office automation, respondents who showed the dissatisfaction about the present OA business emergd high as 78.1%. The work circumstances of each office was good with the fact that the temperature of office was 21.8, noise was average 42.7db, and the illumination was average 364.4 lx, in the light of ANSi/HFS 100 Standard. 3. Sight syptom, musculoskeletal symptom, skin and other symptoms showed the significant difference according to the extent of skillfulness of the apparatus for office automation. All the symptoms exept skin symptom showed the difference according to the use hours of the apparatus for office automation. All the question items exept the sytoms of digestive organs and the rest hours during the apparatus for office automation showed the signicant difference. The question item which showed the signicant difference from the satisfaction degree of present OA business showed the significant difference from all the question item classified into 6 groups. But, age and school career didn't significant difference from the complaint of any self-consciousness symptoms.