• Title/Summary/Keyword: Ambient measurement

Search Result 500, Processing Time 0.028 seconds

Estimation of the major sources for organic aerosols at the Anmyeon Island GAW station (안면도에서의 초미세먼지 유기성분 주요 영향원 평가)

  • Han, Sanghee;Lee, Ji Yi;Lee, Jongsik;Heo, Jongbae;Jung, Chang Hoon;Kim, Eun-Sill;Kim, Yong Pyo
    • Particle and aerosol research
    • /
    • v.14 no.4
    • /
    • pp.135-144
    • /
    • 2018
  • Based on a two-year measurement data, major sources for the ambient carbonaceous aerosols at the Anmyeon Global Atmosphere Watch (GAW) station were identified by using the Positive Matrix Factorization (PMF) model. The particulate matter less than or equal to $2.5{\mu}m$ in aerodynamic diameter (PM2.5) aerosols were sampled between June 2015 to May 2017 and carbonaceous species including ~80 organic compounds were analyzed. When the number of factors was 5 or 6, the performance evaluation parameters showed the best results, With 6 factor case, the characteristics of transported factors were clearer. The 6 factors were identified with various analyses including chemical characteristics and air parcel movement analysis. The 6 factors with their relative contributions were (1) anthropogenic Secondary Organic Aerosols (SOA) (10.3%), (2) biogenic sources (24.8%), (3) local biomass burning (26.4%), (4) transported biomass burning (7.3%), (5) combustion related sources (12.0%), and (6) transported sources (19.2%). The air parcel movement analysis result and seasonal variation of the contribution of these factors also supported the identification of these factors. Thus, the Anmyeon Island GAW station has been affected by both regional and local sources for the carbonaceous aerosols.

Comparative Analysis on the Sound Characteristics of Riffles and Pools (여울과 소의 소리특성 비교 분석)

  • Kang, Su-Jin;Kang, Joon-Gu;Kim, Jong-Tae
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.19 no.12
    • /
    • pp.878-886
    • /
    • 2018
  • This study quantified the sounds of riffles and pools in natural rivers and conducted a comparative analysis of the frequency and sound pressure per flow velocity. The surveyed area was Namdaecheon basin in Yangyang-gun, Gangwon-do and the sounds of a total of 23 sites were analyzed. A hydro microphone was used to measure the sound and analyze the data using an acoustic analysis program. The location was also selected at places with minimal ambient noise and the measurement points were the depth of riffles and pools. The results revealed an average difference of 0.515 m/s for flow velocity at 8 riffles and 15 pools. The difference in sound pressure occurred due to the flow velocity. In the case of sound pressure, it was measured at an average of 176.8 dB for riffles and 168.2 dB for pools, demonstrating a difference of approximately 8.6 dB. Furthermore, in the case of maximum sound pressure, riffles showed a constant range between 200 Hz and 250 Hz, while the pools exhibited maximum sound pressure at various frequencies from 200 Hz to 1,000 Hz. This revealed the ecological stream reproduction, development of preferred sound sources for aquatic life, and design of structures.

Generation of calibration standard gases using capillary gas divider: uncertainty measurement and method validation (다중 모세관을 이용한 교정용 표준가스의 제조: 불확도와 유효성 평가)

  • Lee, Sangyun;Hwang, Eun-Jin;Jung, Hye-Ja;Lee, Kwang-Woo;Chun, Ki-Joon
    • Analytical Science and Technology
    • /
    • v.19 no.5
    • /
    • pp.369-375
    • /
    • 2006
  • Calibration gas mixtures were prepared using dynamic volumetric method according to ISO 6145-5 and the uncertainty was evaluated. Ten identical capillaries with 0.25 mm in inner diameter and 50 cm in length were applied in this system. Dilution ratio of parent gas was determined by the number of capillaries that passes parent gas and that passes balance gas through. Capillaries were made of Teflon which had good chemical stability against adsorption of gaseous substances. Mechanical valves were introduced in this system in order to minimize the thermal effect of solenoid valves. Concentration of prepared gases were compared with master grade standard gases in cylinders made by RiGAS Co. and calibration of the instrument were completed using comparison method according to ISO 6143. Experimental results showed that the coefficient of variance of diluted oxygen standard gases showed less then 0.2% in most dilution range, that of diluted hydrogen sulfide standard gases showed less then 1.0%. Therefore, it is proven that the standard gases prepared by this system are appropriate to be used as a calibration standards in ambient monitoring, etc.

Aerosol Light Absorption and Scattering Coefficient Measurements with a Photoacoustic and Nephelometric Spectrometer (광음향 및 네펠로미터 방식을 이용한 에어로졸 흡수 및 산란계수 측정)

  • Kim, Ji-Hyoung;Kim, Sang-Woo;Heo, Junghwa;Nam, Jihyun;Kim, Man-Hae;Yu, Yung-Suk;Lim, Han-Chul;Lee, Chulkyu;Heo, Bok-Haeng;Yoon, Soon-Chang
    • Atmosphere
    • /
    • v.25 no.1
    • /
    • pp.185-191
    • /
    • 2015
  • Ambient measurements of aerosol light absorption (${\sigma}_a$) and scattering coefficients (${\sigma}_s$) were done at Gosan climate observatory during summer 2008 using a 3-wavelength photoacoustic soot spectrometer (PASS). PASS was deployed photoacoustic method for light absorption and integrated nephelometry for light scattering measurements. The ${\sigma}_a$ and ${\sigma}_s$ from PASS were compared with those from co-located aethalometer and nephelometer measurements. The aethalometer measurements of ${\sigma}_a$ correlated reasonably well with photoacoustic measurements, but the slope of the linear fitting line indicated the PASS measurement values of ${\sigma}_a$ were larger by a factor of 1.53. The nephelometer measurement values of ${\sigma}_s$ correlated very well with PASS measurements of ${\sigma}_s$, with a slope of 1.12 and a small offset. Comparing to the aethalometer measurements, the photoacoustic measurements of ${\sigma}_a$ didn't exhibit a significant (i.e., the ratio between aethalometer and PASS increased) change with increasing relative humidity (RH). The ratio of ${\sigma}_s$ between nephelometer and PASS increased with increasing RH, especially when the RH increased beyond 80%. This apparent increase in ${\sigma}_s$ with RH may be due to the contribution of hygroscopic growth of aerosols.

Detection Characteristics of PSL and TL Methods in Spices Irradiated with Different Radiation Sources (조사선원에 따른 향신료의 PSL과 TL 검지 특성)

  • Kim, Kyu-Heon;Kwak, Ji-Young;Kim, Jung-Ki;Hwang, Cho-Rong;Lee, Jae-Hwang;Park, Yong-Chjun;Kim, Jae-I;Jo, Tae-Yong;Lee, Hwa-Jung;Lee, Sang-Jae;Han, Sang-Bae
    • Journal of Radiation Industry
    • /
    • v.7 no.1
    • /
    • pp.15-21
    • /
    • 2013
  • The detection characteristics of irradiated spices were investigated depending on radiation sources and doses by photostimulated luminescence (PSL) and Thermoluminescence (TL). 6 kinds of spices (turmeric, onion powder, red pepper, basil, parsley, black pepper) were irradiated at 0 to 10 kGy under ambient conditions by both a $^{60}Co$ gamma irradiator and an electron beam (EB) accelerator, respectively. The PSL analysis showed negative results for non-irradiated spices, while irradiated spices gave intermediate and positive value, which presented the limited potential of PSL technique. In TL measurement, TL glow curves on non-irradiated samples appeared at about $300^{\circ}C$ with low intensity. All irradiated samples were easily distinguishable through radiation-specific strong TL glow curves with maximum peak in range of $150{\sim}200^{\circ}C$. TL ratio ($TL_1/TL_2$) obtained by a re-irradiation step could verify the detection result of $TL_1$ glow curves, showing ratios lower than 0.1 in the non-irradiated sample and higher than 0.1 in irradiated ones. Therefore, in PSL measurement, the identification of irradiated spices showed more clear results in electron beam irradiated samples. TL analysis showed obvious difference between non-irradiated and irradiated samples in gamma ray and electron beam irradiated samples.

Particulate Matter 10 from Asian Dust Storms Induces the Expression of Reactive Oxygen Species, NF-κ, TGF-β and Fibronectin in WI-26 VA4 Epithelial Cells (황사의 PM10이 WI-26 VA4 Cells에서 Reactive Oxygen Species, NFκB, TGF-β, Fibronectin의 발현에 미치는 영향)

  • Park, Kyeong Seon;Kim, Yu Jin;Yoon, Jin Young;Kyung, Sun Young;An, Chang Hyeok;Lee, Sang Pyo;Park, Jeong Woong;Jeong, Sung Hwan
    • Tuberculosis and Respiratory Diseases
    • /
    • v.65 no.6
    • /
    • pp.504-511
    • /
    • 2008
  • Background: Particulate matter may be toxic to human tissue. Ambient air particulate matter ${\leq}10{\mu}m$ in aerodynamic size ($PM_{10}$), which changes under different environmental conditions, is a complex mixture of organic and inorganic compounds. The Asian dust event caused by meteorological phenomena can also spread unique particulate matter in affected areas. We evaluated production of ROS, $TGF-{\beta}$, fibronectin, and $NF{\kappa}B$ by exposing normal epithelial cells to Asian dust particulate matter. Methods: Bronchial epithelial cells were exposed to 0, 50, ${\leq}100{\mu}g/ml$ of a suspension of $PM_{10}$ for 24 h. ROS were detected by measurement of DCF release from DCF-DA by FACScan. $TGF-{\beta}$, fibronectin, and $NF{\kappa}B$ were detected by western blotting. Results: $PM_{10}$ exposure increased the expression of $TGF-{\beta}$, fibronectin, and $NF{\kappa}B$. ROS production and $TGF-{\beta}$ levels were significantly higher with 50 or ${\leq}100{\mu}g/ml$ $PM_{10}$. Fibronectin and $NF{\kappa}B$ production were significantly higher after ${\leq}100{\mu}g/ml$ of $PM_{10}$. Conclusion: $PM_{10}$ from Asian dust particles might have fibrotic potential in bronchial epithelial cells via ROS induction after $PM_{10}$ exposure.

An Experimental Study on Establishing Criteria of Gripping Work in Construction Site (건설 현장 악력 작업안전 기준 설정에 관한 실험적 연구)

  • 손기상;이인홍;최만진;안병준
    • Journal of the Korean Society of Safety
    • /
    • v.10 no.3
    • /
    • pp.81-95
    • /
    • 1995
  • Now, safety assurance in construction sites should be accomplished by its own organization rather than control of the code or government. It is believed that the safety assurance can be considerably improved by a lecture or an education using the existing theories or literatures up to now, but it is thought that fundamental safety assurance we not able to be accomplished without developing safety devices '||'&'||' equipment or taking fundamental measures, based on the result analyzed from workers behaviors. There are various behaviors of the workers showed in construction site, but only tests for hammerusing works such as form, re-bar, stone workers directly related to the grip strength are mainly performed, investigated and measured here for the study. The above works are similar to power grip, 7th picture on seven items which are categorized for hand grip types(Ammermin 1956 ; Jones ; Kobrick 1958). Measurements of grip strength are commonly taken in anthropometric surveys. They are easy to administer but unfortunately it is rather dubious whether they yield any data that are of interest to the engineer. Very fewer controls of tools are grasped and squeesed studies showed very little overall correlation between grip strength and other measures of bodily strength (Laubach, Kromer, and Thordsen 1972), but hammer-using work which is practically progressed in construction site are mainly influenced with grip strength. According to the investigation on work measurement, it is shown that 77% of form worker are using hammer to be related to grip strength. In this study, it is particularly noticed that wearing safety gloves in construction site is required for workers safety but 20% difference between grip strength with safety gloves and without ones are commonly neglected in the site(Fig. 1). Nevertheless, safety operation with consideration of the above 20% difference is not considered in the construction site. Factors of age, kinds of work, working time, with or without safety gloves are in vestigated '||'&'||' collected at the sites for this study. Test, not at each working hour but at 14 : 00 when the almost all of the workers think the most tired, resulting from the questionaires, also when it is shown on the research report has been performed and compared for main kinds of works : form '||'&'||' re-bar work. Tests were performed with both left SE rightand of the workers simultaneously in construction site using Rand Dynamometer(Model 78010, Lafayette Instrument Co., Indiana, U.S.A) by reading grip strength on the gauge while they are pulling, and then by interviewing on their ages, works, experiences and etc., directly. The above tests have been performed for the dates of 15th march-26th May '95 with consideration of site condition. And even if various factors of ambient temperature on the testing date, working condition, individual worker's habit and worker's condition of the previous ate are concerned with the study. Those are considered as constants in this study. Samples are formwork 53, rebar 62, electrician 5, plumber 4, welding 1 from D construction Co., Ltd, ; formwork 12, re-bar 5, electrician 2, from S construction Co., Ltd, , formwork 78, re-bar 18, plumber 31, electrician 13, labor 48, plumber 31, plasterer 15, concrete placer 6, water proof worker 3, maisony 5 from B construction Co., Ltd. As In the previously mentioned, main aspect to be investigated in this study will be from '||'&'||' re-bar work because grip strength will be directly applied to these two kinds of works ; form '||'&'||' re-bar work, eventhough there are total 405 samples taken. It is thought that a frequency of accident occurrence will be mainly two work postures "looking up '||'&'||' looking down" to be mainly sorted, but this factor is not clarified in this study because It will be needed a lot of work more. Tests has been done at possible large scale of horizontally work-extended sites within one hour in order to prevent or decrease errors '||'&'||' discrepancies from time lag of the test. Additionally, the statistical package computer program SPSS PC+has been used for the study.

  • PDF

Thermal Environments of Children's Parks during Heat Wave Period (폭염 시 어린이공원의 온열환경)

  • Ryu, Nam-Hyong;Lee, Chun-Seok
    • Journal of the Korean Institute of Landscape Architecture
    • /
    • v.44 no.6
    • /
    • pp.84-97
    • /
    • 2016
  • This study was to investigate the user's thermal environments of the children's parks according to pavements and sunscreen types during periods of heat waves. The measurements were conducted at the sand pits, rubber chip pavement, shelters, and green shade ground of the two children's parks located in Jinju, Korea(Chilam: $N\;35^{\circ}11^{\prime}1.4{^{\prime}^{\prim}}$, $E\;128^{\circ}5^{\prime}31.7{^{\prime}^{\prime}}$, elevation 38m, Gaho: $N\;35^{\circ}09^{\prime}56.8{^{\prime}^{\prime}}$, $E\;128^{\circ}6^{\prime}41.1{^{\prime}^{\prime}}$, elevation 24m) over three days during 11-13, August, 2016. The highest ambient air temperatures at the Jinju Meteorological Office during the three measurement days were $35.9{\sim}36.8^{\circ}C$, which corresponded with the extremely hot weather. A series of experiments measured air temperature, relative humidity, wind velocity, black globe temperature, and long-wave and short-wave radiation of the six directions 0.6 m above ground level. The wet bulb globe temperature(WBGT) and the universal thermal climatic index(UTCI) were used to evaluate thermal stress. Surface temperature images of the play equipment were also taken using infrared thermography. Surface temperatures of the play equipment and grounds were used to evaluate burn risk through contact with playground materials. The results showed the following. The maximum air temperatures averaged over 1-hour period for three days were $36.6{\sim}39.4^{\circ}C$. The sun shades reduced those temperatures by up to $2.8^{\circ}C$(green shade) and $1.0^{\circ}C/2.3^{\circ}C$(shelters). The minimum relative humidity values averaged over 1-hour period for three days were 44~50%. The sun shades increased those humidity values by up to 6%(green shade) and 4%/6%(shelters). The risk of heat related illness at the measurement sites of the children's parks were extreme and high in the daytime hours. The maximum WBGT values averaged over a 30-minute period for three days were $31.2{\sim}33.6^{\circ}C$. The sun shades reduced those WBGT values by up to $2.4^{\circ}C$(green shade) and $0.5^{\circ}C/2.1^{\circ}C$(shelters) compared to sandpits, but would not block the risk of heat related illness in the daytime hours. The category of heat stress at the measurement sites of the children's parks were extreme and very strong in the daytime hours. The maximum UTCI values averaged over a 30-minute period for three days were $39.9{\sim}48.1^{\circ}C$. The sun shades reduced those UTCI values by up to $7.8^{\circ}C$(green shade) and $4.1^{\circ}C/8.2^{\circ}C$(shelters) compared to sandpits, but could not lower heat stress category from extreme and very strong to strong and moderate in the daytime hours. According to the burn threshold criteria when skin was in contact with playground materials, the maximum surface temperature of the stainless steels($70.8^{\circ}C$) surpassed three seconds $60^{\circ}C$ threshold for uncoated steel, that of the rubber chip($76.5^{\circ}C$) surpassed five seconds $74^{\circ}C$ threshold for the plastic, that of the plastic slide($68.5^{\circ}C$) and seats($71.0^{\circ}C$) surpassed the one min $60^{\circ}C$ threshold for plastic, respectively. The surface temperatures of shaded play equipment were lower approximately $20^{\circ}C$ than those of play equipment exposed to the sun. Therefore, sun shades can block the risk of burns in daytime hours. Because of the extreme and high risk of heat related illness and extreme and high heat stress at the children's parks during periods of heat waves, parents and administrators must protect children from the use of playgrounds. The risk of burn when contact with play equipments and grounds at the children's parks during periods of heat waves, was very high. The sun shades are essential to block the risk of burn from play equipments and grounds at the children's parks during heat waves.

The Influence of Store Environment on Service Brand Personality and Repurchase Intention (점포의 물리적 환경이 서비스 브랜드 개성과 재구매의도에 미치는 영향)

  • Kim, Hyoung-Gil;Kim, Jung-Hee;Kim, Youn-Jeong
    • Journal of Global Scholars of Marketing Science
    • /
    • v.17 no.4
    • /
    • pp.141-173
    • /
    • 2007
  • The study examines how the environmental factors of store influence service brand personality and repurchase intention in the service environment. The service industry has been experiencing the intensified competition with the industry's continuous growth and the influence from rapid technological advancement. Under the circumstances, it has become ever more important for the brand competitiveness to be distinctively recognized against competition. A brand needs to be distinguished and differentiated from competing companies because they are all engaged in the similar environment of the service industry. The differentiation of brand achievement has become increasingly important to highlight certain brand functions to include emotional, self-expressive, and symbolic functions since the importance of such functions has been further emphasized in promoting consumption activities. That is the recent role of brand personality that has been emphasized in the service industry. In other words, customers now freely and actively express their personalities or egos in consumption activities, taking an important role in construction of a brand asset. Hence, the study suggests that it is necessary to disperse the recognition and acknowledgement that the maintenance of the existing customers contributes more to boost repurchase intention when it is compared to the efforts to create new customers, particularly in the service industry. Meanwhile, the store itself can offer a unique environment that may influence the consumer's purchase decision. Consumers interact with store environments in the process of,virtually, all household purchase they make (Sarel 1981). Thus, store environments may encourage customers to purchase. The roles that store environments play are to provide informational cues to customers about the store and goods and communicate messages to stimulate consumers' emotions. The store environments differentiate the store from competing stores and build a unique service brand personality. However, the existing studies related to brand in the service industry mostly concentrated on the relationship between the quality of service and customer satisfaction, and they are mostly generalized while the connective studies focused on brand personality. Such approaches show limitations and are insufficient to investigate on the relationship between store environment and brand personality in the service industry. Accordingly, the study intends to identify the level of contribution to the establishment of brand personality made by the store's physical environments that influence on the specific brand characteristics depending on the type of service. The study also intends to identify what kind of relationships with brand personality exists with brand personality while being influenced by store environments. In addition, the study intends to make meaningful suggestions to better direct marketing efforts by identifying whether a brand personality makes a positive influence to induce an intention for repurchase. For this study, the service industry is classified into four categories based on to the characteristics of service: experimental-emotional service, emotional -credible service, credible-functional service, and functional-experimental service. The type of business with the most frequent customer contact is determined for each service type and the enterprise with the highest brand value in each service sector based on the report made by the Korea Management Association. They are designated as the representative of each category. The selected representatives are a fast-food store (experimental-emotional service), a cinema house (emotional-credible service), a bank (credible-functional service), and discount store (functional-experimental service). The survey was conducted for the four selected brands to represent each service category among consumers who are experienced users of the designated stores in Seoul Metropolitan City and Gyeonggi province via written questionnaires in order to verify the suggested assumptions in the study. In particular, the survey adopted 15 scales, which represent each characteristic factor, among the 42 unique characteristics developed by Jennifer Aaker(1997) to assess the brand personality of each service brand. SPSS for Windows Release 12.0 and LISREL were used in the analysis of data verification. The methodology of the structural equation model was used for the study and the pivotal findings are as follows. 1) The environmental factors ware classified as design factors, ambient factors, and social factors. Therefore, the validity of measurement scale of Baker et al. (1994) was proved. 2) The service brand personalities were subdivided as sincerity, excitement, competence, sophistication, and ruggedness, which makes the use of the brand personality scales by Jennifer Aaker(1997) appropriate in the service industry as well. 3) One-way ANOVA analysis on the scales of store environment and service brand personality showed that there exist statistically significant differences in each service category. For example, the social factors were highest in discount stores, while the ambient factors and design factors were highest in fast-food stores. The discount stores were highest in the sincerity and excitement, while the highest point for banks was in the competence and ruggedness, and the highest point for fast-food stores was in the sophistication, The consumers will make a different respond to the physical environment of stores and service brand personality that are inherent to the corresponding service interface. Hence, the customers will make a different decision-making when dealing with different service categories. In this aspect, the relationships of variables in the proposed hypothesis appear to work in a different way depending on the exposed service category. 4) The store environment factors influenced on service brand personalities differently by category of service. The factors of store's physical environment are transferred to a brand and were verified to strengthen service brand personalities. In particular, the level of influence on the service brand personality by physical environment differs depending on service category or dimension, which indicates that there is a need to apply a different style of management to a different service category or dimension. It signifies that there needs to be a brand strategy established in order to positively influence the relationship with consumers by utilizing an appropriate brand personality factor depending on different characteristics by service category or dimension. 5) The service brand personalities influenced on the repurchase intention. Especially, the largest influence was made in the sophistication dimension of service brand personality scale; the unique and characteristically appropriate arrangement of physical environment will make customers stay in the service environment for a long time and will lead to give a positive influence on the repurchase intention. 6) The store environment factors influenced on the repurchase intention. Particularly, the largest influence was made on the social factors of store environment. The most intriguing finding is that the service factor among all other environment factors gives the biggest influence to the repurchase intention in most of all service types except fast-food stores. Such result indicates that the customers pay attention to how much the employees try to provide a quality service when they make an evaluation on the service brand. At the same time, it also indicates that the personal factor is directly transmitted to the construction of brand personality. The employees' attitude and behavior are the determinants to establish a service brand personality in the process of enhancing service interface. Hence, there should be a reinforced search for a method to efficiently manage the service staff who has a direct contact with customers in order to make an affirmative improvement of the customers' brand evaluation at the service interface. The findings suggest several managerial implications. 1) Results from the empirical study indicated that store environment factors have a strong positive impact on a service brand personality. To increase customers' repurchase intention of a service brand, the management is required to effectively manage store environment factors and create a friendly brand personality based on the corresponding service environment. 2) Mangers and researchers must understand and recognize that the store environment elements are important marketing tools, and that brand personality influences on consumers' repurchase intention. Based on such result of the study, a service brand could be utilized as an efficient measure to achieve a differentiation by enforcing the elements that are most influential among all other store environments for each service category. Therefore, brand personality established involving various store environments will further reinforce the relationship with customers through the elevated brand identification of which utilization to induce repurchase decision can be used as an entry barrier. 3) The study identified the store environment as a component of service brand personality for the store's effective communication with consumers. For this, all communication channels should be maintained with consistency and an integrated marketing communication should be executed to efficiently approach to a larger number of customers. Mangers and researchers must find strategies for aligning decisions about store environment elements with the retailers' marketing and store personality objectives. All ambient, design, and social factors need to be orchestrated so that consumers can take an appropriate store personality. In this study, the induced results from the previous studies were extended to the service industry so as to identify the customers' decision making process that leads to repurchase intention and a result similar to those of the previous studies. The findings suggested several theoretical and managerial implications. However, the situation that only one service brand served as the subject of analysis for each service category, and the situation that correlations among store environment elements were not identified, as well as the problem of representation in selection of samples should be considered and supplemented in the future when further studies are conducted. In addition, various antecedents and consequences of brand personality must be looked at in the aspect of the service environment for further research.

  • PDF

Ensemble of Nested Dichotomies for Activity Recognition Using Accelerometer Data on Smartphone (Ensemble of Nested Dichotomies 기법을 이용한 스마트폰 가속도 센서 데이터 기반의 동작 인지)

  • Ha, Eu Tteum;Kim, Jeongmin;Ryu, Kwang Ryel
    • Journal of Intelligence and Information Systems
    • /
    • v.19 no.4
    • /
    • pp.123-132
    • /
    • 2013
  • As the smartphones are equipped with various sensors such as the accelerometer, GPS, gravity sensor, gyros, ambient light sensor, proximity sensor, and so on, there have been many research works on making use of these sensors to create valuable applications. Human activity recognition is one such application that is motivated by various welfare applications such as the support for the elderly, measurement of calorie consumption, analysis of lifestyles, analysis of exercise patterns, and so on. One of the challenges faced when using the smartphone sensors for activity recognition is that the number of sensors used should be minimized to save the battery power. When the number of sensors used are restricted, it is difficult to realize a highly accurate activity recognizer or a classifier because it is hard to distinguish between subtly different activities relying on only limited information. The difficulty gets especially severe when the number of different activity classes to be distinguished is very large. In this paper, we show that a fairly accurate classifier can be built that can distinguish ten different activities by using only a single sensor data, i.e., the smartphone accelerometer data. The approach that we take to dealing with this ten-class problem is to use the ensemble of nested dichotomy (END) method that transforms a multi-class problem into multiple two-class problems. END builds a committee of binary classifiers in a nested fashion using a binary tree. At the root of the binary tree, the set of all the classes are split into two subsets of classes by using a binary classifier. At a child node of the tree, a subset of classes is again split into two smaller subsets by using another binary classifier. Continuing in this way, we can obtain a binary tree where each leaf node contains a single class. This binary tree can be viewed as a nested dichotomy that can make multi-class predictions. Depending on how a set of classes are split into two subsets at each node, the final tree that we obtain can be different. Since there can be some classes that are correlated, a particular tree may perform better than the others. However, we can hardly identify the best tree without deep domain knowledge. The END method copes with this problem by building multiple dichotomy trees randomly during learning, and then combining the predictions made by each tree during classification. The END method is generally known to perform well even when the base learner is unable to model complex decision boundaries As the base classifier at each node of the dichotomy, we have used another ensemble classifier called the random forest. A random forest is built by repeatedly generating a decision tree each time with a different random subset of features using a bootstrap sample. By combining bagging with random feature subset selection, a random forest enjoys the advantage of having more diverse ensemble members than a simple bagging. As an overall result, our ensemble of nested dichotomy can actually be seen as a committee of committees of decision trees that can deal with a multi-class problem with high accuracy. The ten classes of activities that we distinguish in this paper are 'Sitting', 'Standing', 'Walking', 'Running', 'Walking Uphill', 'Walking Downhill', 'Running Uphill', 'Running Downhill', 'Falling', and 'Hobbling'. The features used for classifying these activities include not only the magnitude of acceleration vector at each time point but also the maximum, the minimum, and the standard deviation of vector magnitude within a time window of the last 2 seconds, etc. For experiments to compare the performance of END with those of other methods, the accelerometer data has been collected at every 0.1 second for 2 minutes for each activity from 5 volunteers. Among these 5,900 ($=5{\times}(60{\times}2-2)/0.1$) data collected for each activity (the data for the first 2 seconds are trashed because they do not have time window data), 4,700 have been used for training and the rest for testing. Although 'Walking Uphill' is often confused with some other similar activities, END has been found to classify all of the ten activities with a fairly high accuracy of 98.4%. On the other hand, the accuracies achieved by a decision tree, a k-nearest neighbor, and a one-versus-rest support vector machine have been observed as 97.6%, 96.5%, and 97.6%, respectively.