• Journal of Information Processing Systems
• /
• 제12권3호
• /
• pp.436-454
• /
• 2016

This research presents the battery discharge rate models for the energy consumption of mobile phone batteries based on machine learning by taking into account three usage patterns of the phone: the standby state, video playing, and web browsing. We present the experimental design methodology for collecting data, preprocessing, model construction, and parameter selections. The data is collected based on the HTC One X hardware platform. We considered various setting factors, such as Bluetooth, brightness, 3G, GPS, Wi-Fi, and Sync. The battery levels for each possible state vector were measured, and then we constructed the battery prediction model using different regression functions based on the collected data. The accuracy of the constructed models using the multi-layer perceptron (MLP) and the support vector machine (SVM) were compared using varying kernel functions. Various parameters for MLP and SVM were considered. The measurement of prediction efficiency was done by the mean absolute error (MAE) and the root mean squared error (RMSE). The experiments showed that the MLP with linear regression performs well overall, while the SVM with the polynomial kernel function based on the linear regression gives a low MAE and RMSE. As a result, we were able to demonstrate how to apply the derived model to predict the remaining battery charge.

• 한국식품과학회지
• /
• 제49권6호
• /
• pp.699-709
• /
• 2017

본 연구의 목적은 반응표면분석법(RSM)을 이용하여 뽕잎과 오디 최적 혼합비율을 첨가한 기능성 녹두죽을 개발하는데 있다. 뽕잎과 오디의 최적 혼합비율을 산출하기 위해서 독립변수로 뽕잎분말(X1)과 오디분말(X2)을 설정하였고, 종속변수로는 pH(Y1), 당도(Y2), 점도(Y3), L(Y4), a(Y5), b(Y6), 색(Y7), 향(Y8), 맛(Y9), 전반적인 기호도(Y10), 총 폴리페놀 함량(Y11) 및 DPPH 라디칼 소거능($IC_{50}$)(Y12)으로 설정하였다. RSM을 이용하여 산출된 뽕잎과 오디의 최적 혼합비율은 뽕잎분말 3.88 g, 오디분말 6 g이었다. 뽕잎과 오디 최적 혼합비율을 첨가한 기능성죽의 총 폴리페놀 함량은 330.99 mg TAE/100 g이였고, DPPH 라디칼 소거능($IC_{50}$)은 650.10 g/mL으로 나타났다. 뽕잎과 오디 최적 혼합비율을 첨가한 기능성죽의 pH는 6.53이었으며, 당도는 $8.93^{\circ}Bx$로 나타났다. 뽕잎과 오디 최적 혼합비율을 첨가한 기능성죽의 색도에서 명도 값은 34.41, 적색도 값은 1.36, 황색도 값은 4.47이였고, 점성은 3584 cP로 나타났다. 뽕잎과 오디 최적 혼합비율을 첨가한 기능성죽의 관능평가에서 색은 5.20, 향은 5.85, 맛은 6.00이고, 전반적인 기호도는 6.22로 관능평가 점수가 우수하게 나타났다. 결론적으로 본 연구를 통해 개발된 뽕잎과 오디 최적혼합비율이 첨가된 기능성 녹두죽은 산화방지 활성 뿐만 아니라 죽이 갖추어야 할 품질특성도 우수하여 바쁜 현대인의 식사대용으로 활용가치가 높다고 본다.

• Advances in Computational Design
• /
• 제7권2호
• /
• pp.113-128
• /
• 2022

Water consumption is strongly affected by numerous factors, such as population, climatic, geographic, and socio-economic factors. Therefore, the implementation of a reliable predictive model of water consumption pattern is challenging task. This study investigates the performance of predictive models based on multi-layer perceptron (MLP), multiple linear regression (MLR), and support vector regression (SVR). To understand the significant factors affecting water consumption, the stepwise regression (SW) procedure is used in MLR to obtain suitable variables. Then, this study also implements three predictive models based on these significant variables (e.g., SWMLR, SWMLP, and SWSVR). Annual data of water consumption in Thailand during 2006 - 2015 were compiled and categorized by provinces and distributors. By comparing the predictive performance of models with all variables, the results demonstrate that the MLP models outperformed the MLR and SVR models. As compared to the models with selected variables, the predictive capability of SWMLP was superior to SWMLR and SWSVR. Therefore, the SWMLP still provided satisfactory results with the minimum number of explanatory variables which in turn reduced the computation time and other resources required while performing the predictive task. It can be concluded that the MLP exhibited the best result and can be utilized as a reliable water demand predictive model for both of all variables and selected variables cases. These findings support important implications and serve as a feasible water consumption predictive model and can be used for water resources management to produce sufficient tap water to meet the demand in each province of Thailand.

• Archives of Pharmacal Research
• /
• 제27권9호
• /
• pp.906-911
• /
• 2004

In order to evaluate estrogenic compounds in natural products, an in vitro detection system was established. For this system, the human breast cancer cell line MCF7 was stably trans-fected using an estrogen responsive chloramphenicol acetyltransferase (CAT) reporter plas-mid yielding MCF7/pDsCAT-ERE119-Ad2MLP cells. To test the estrogenic responsiveness of this in vitro assay system, MCF7/pDsCAT-ERE119-Ad2MLP cells were treated with various concentrations of 17f3-estradiol. Treatments of 10$^{-8}$ to 10$^{-12}$ M 17$\beta$-estradiol revealed significant concentration dependent estrogenic activities compared with ethanol. We used in vitro assay system to detect estrogenic effects in Puerariae radix and Ginseng radix Rubra extracts. Treat-ment of 500 and 50 $\mu\textrm{g}$/ml of Puerariae radix extracts increased the transcriptional activity approximately 4- and 1.5-fold, respectively, compared with the ethanol treatment. Treatment of 500, 50, and 5 $\mu\textrm{g}$/ml of Ginseng radix Rubra extracts increased the transcriptional activity approximately 3.2-,2.7, and 1.4-fold, respectively, compared with the ethanol treatment. These observations suggest that Puerariae radix and Ginseng radix Rubra extracts have effective estrogenic actions and that they could be developed as estrogenic supplements.

• Geomechanics and Engineering
• /
• 제31권3호
• /
• pp.291-304
• /
• 2022

Maximum shear modulus (G_max or G₀) is an important soil property useful for many engineering applications, such as the analysis of soil-structure interactions, soil stability, liquefaction evaluation, ground deformation and performance of seismic design. In the current study, bender element (BE) tests are used to evaluate the effect of the void ratio, effective confining pressure, grading characteristics (D₅₀, C_u and C_c), anisotropic consolidation and initial fabric anisotropy produced during specimen preparation on the G_max of sand-gravel mixtures. Based on the tests results, an empirical equation is proposed to predict G_max in granular soils, evaluated by the experimental data. The artificial neural network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) models were also applied. Coefficient of determination (R²) and Root Mean Square Error (RMSE) between predicted and measured values of G_max were calculated for the empirical equation, ANN and ANFIS. The results indicate that all methods accuracy is high; however, ANFIS achieves the highest accuracy amongst the presented methods.

• The Korean Journal of Physiology and Pharmacology
• /
• 제8권6호
• /
• pp.319-327
• /
• 2004

This study was aimed at evaluating the effect of defibrotide on the development of the surgically induced reflux esophagitis, on gastric secretion, lipid peroxidation, polymorphonuclear leukocytes (PMNs) accumulation, polymorphonuclear leukocytes adherence, superoxide anion and hydrogen peroxide production in PMNs, scavenge of hydroxyl radical and hydrogen peroxide, cytokine (interleukin-1 ${\beta}$, tumor necrosis $factor-{\alpha}$) production in blood, and intracelluar calcium mobilization in PMNs. Defibrotide did not inhibit the gastric secretion and not change the gastric pH. Treatment of esophagitis rats with defibrotide inhibited lipid peroxidation, and myeloperoxidase (MPO) in the esophagus in comparison with untreated rats. Defibrotide significantly decreased the PMN adherence to superior mesenteric artery endothelium in a dose-dependent manner, Superoxide anion and hydrogen peroxide production in $1{\mu}M$ formylmethionylleucylphenylalanine (fMLP)- or $0.1{\mu}g/ml$ N-phorbol 12-myristate 13-acetate (PMA)-activated PMNs was inhibited by defibrotide in a dose-dependent fashion. Defibrotide effectively scavenged the hydrogen peroxide but did not scavenge the hydroxyl radical. Treatment of esophagitis rats with defibrotide inhibited interleukin-1 ${\beta}$ production in the blood in comparison with untreated rats, but tumor necrosis $factor-{\alpha}$ production was not affected by defibrotide. The fMLP-induced elevation of intracellular calcium in PMNs was inhibited by defibrotide. The results of this study suggest that defibrotide may have partly beneficial protective effects against reflux esophagitis by the inhibition lipid peroxidation, PMNs accumulation, PMNs adherence to endothelium, reactive oxygen species production in PMNs, inflammatory cytokine production(i.e. interleukin-1 ${\beta}$), and intracellular calcium mobilization in PMNs in rats.

• 한국융합학회논문지
• /
• 제11권3호
• /
• pp.181-186
• /
• 2020

본 연구는 온라인동영상서비스 OTT(Over-the-Top) 이용자의 몰아보기(Binge-watching) 시청행위에 영향을 미치는 요인을 실증적으로 탐색하였다. 이를 위해 2018년 한국언론진흥재단 미디어연구센터의 'OTT 서비스 이용자 인식조사'에 참여한 OTT 이용 경험자 1,000명의 자료를 수집하여 분석하였다. 종속변수는 OTT 서비스 몰아보기로 설정하였으며, 독립변수는 성별, 연령, OTT 서비스 이용 빈도, OTT 콘텐츠 프로그램 추천 알고리즘 만족도, OTT에서 주로 이용하는 콘텐츠 유형을 포함하였다. OTT 몰아보기 시청행위의 예측 요인은 다층 퍼셉트론(MLP) 인공신경망 알고리즘을 이용하여 분석하였다. 연구결과, 연령, OTT 콘텐츠 프로그램 추천 알고리즘 만족도, OTT 서비스 이용 빈도, OTT에서 주로 이용하는 콘텐츠 유형 중 국내드라마, 국내영화, 해외드라마 등이 OTT 몰아보기 시청행위에 중요도가 높은 요인으로 밝혀졌다.

• Tuberculosis and Respiratory Diseases
• /
• 제53권6호
• /
• pp.595-611
• /
• 2002

Akt/PKB protein kinase B, ALI acute lung injury, ARDS acute respiratory distress syndrome, CREB C-AMP response element binding protein, ERK extracelluar signal-related kinase, fMLP fMet-Leu-Phe, G-CSF granulocyte colony-stimulating factor, IL interleukin, ILK integrin-linked kinase, JNK Jun N-terminal kinase, LPS lipopolysaccharide, MAP mitogen-activated protein, MEK MAP/ERK kinase, MIP-2 macrophage inflammatory protein-2, MMP matrix metalloproteinase, MPO myeloperoxidase, NADPH nicotinamide adenine dinucleotide phosphate, NE neutrophil elastase, NF-kB nuclear factor-kappa B, NOS nitric oxide synthase, p38 MAPK p38 mitogen activated protein kinase, PAF platelet activating factor, PAKs P21-activated kinases, PMN polymorphonuclear leukocytes, PI3-K phosphatidylinositol 3-kinase, PyK proline-rich tyrosine kinase, ROS reactive oxygen species, TNF-${\alpha}$ tumor necrosis factor-a.

• 정보과학회 논문지
• /
• 제42권6호
• /
• pp.723-733
• /
• 2015

여러 종류의 해상도를 가지는 단말들에 대해 인터넷을 통해 멀티미디어 동영상을 제공하는 OTT 서비스가 확산되고 있다. 각 단말들은 3G, LTE, VDSL, ADSL등 네트워크 망을 이용한 통신을 하고 있다. 다양한 해상도의 단말들과 다양한 속도의 네트워크망의 이용자들에 맞춰서 새로운 멀티미디어의 압축방식의 필요성이 높아졌다. 스케일러블 부호화 방식은 시간적/공간적 계위성을 제공하기 위해서 멀티미디어 데이터를 저장할 때 계층적 B 화면 구조를 이용하고 있다. 이를 이용하여 계층적으로 부호화된 멀티미디어 데이터는 OTT 서비스에 최적화 되어있으며, 이를 효율적으로 관리하기 위한 파일 배치 기법과 MLP 인기도 관리 정책, WFF 버퍼 캐시 관리 정책을 제안한다. 본 논문에서는 zipf 분포를 이용한 접근 트레이스를 생성하고, 기존 시스템과 제안한 시스템의 성능을 비교 평가하였다.

• 한국통신학회논문지
• /
• 제29권12C호
• /
• pp.1660-1668
• /
• 2004

본 논문에서는 간단한 구조, 적은 계산량과 안정된 빠른 수렴속도를 가진 RBF (Radial Basis Function) 신경회로망을 이용한 이중 임계값 방식의 음성구간 검출기 알고리즘을 제안하고 시뮬레이션을 통해 유용성을 확인하였다. 음성압축기에 사용되는 CELP (Code-Excited Linear Prediction) 파라미터들을 신경회로망 입력으로 하여 잡음에 강하게 반응하게 하였고, 음성구간 검출기의 성능향상을 위해 음성구간과 침묵구간에서 다른 임계값을 사용하는 이중 임계값 방식을 적용하였다. 실험 결과 이중 임계값을 이용한 RBF 신경망 음성구간 검출기는 G.729 Annex B 음성구간 검출기 보다 우수한 성능을 보였고, 기존의 MLP (Multi Layer Perceptron) 신경회로망을 이용한 음성구간 검출기와 비교하여 음성구간에서는 비슷한 성능을 보였으나 침묵구간에서 25% 정도의 성능향상을 보였다.