• International Journal of Advanced Culture Technology
• /
• v.1 no.2
• /
• pp.1-6
• /
• 2013

In this paper, we evaluate performance of existing similarity measurement metric and propose a novel method using user's preferences information entropy to reduce MAE in memory-based collaborative recommender systems. The proposed method applies a similarity of individual inclination to traditional similarity measurement methods. We experiment on various similarity metrics under different conditions, which include an amount of data and significance weighting from n/10 to n/60, to verify the proposed method. As a result, we confirm the proposed method is robust and efficient from the viewpoint of a sparse data set, applying existing various similarity measurement methods and Significance Weighting.

• 한국데이터정보과학회:학술대회논문집
• /
• 2006.11a
• /
• pp.59-69
• /
• 2006

Pearson's correlation coefficient and Vector similarity are generally applied to The users' similarity weight of user based recommender system. This study is needed to find that the correlation coefficient of similarity weight is effected by the number of pair response and significance probability. From the classified correlation coefficient by the significance probability test on the correlation coefficient and pair of response, the change of MAE is studied by comparing the predicted precision of the two. The results are experimentally related with the change of MAE from the significant correlation coefficient and the number of pair response.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.486-493
• /
• 2023

In this paper, we propose an automatic hand gesture area extraction and recognition technique using FMCW radar-based point cloud and LSTM. The proposed technique has the following originality compared to existing methods. First, unlike methods that use 2D images as input vectors such as existing range-dopplers, point cloud input vectors in the form of time series are intuitive input data that can recognize movement over time that occurs in front of the radar in the form of a coordinate system. Second, because the size of the input vector is small, the deep learning model used for recognition can also be designed lightly. The implementation process of the proposed technique is as follows. Using the distance, speed, and angle information measured by the FMCW radar, a point cloud containing x, y, z coordinate format and Doppler velocity information is utilized. For the gesture area, the hand gesture area is automatically extracted by identifying the start and end points of the gesture using the Doppler point obtained through speed information. The point cloud in the form of a time series corresponding to the viewpoint of the extracted gesture area is ultimately used for learning and recognition of the LSTM deep learning model used in this paper. To evaluate the objective reliability of the proposed technique, an experiment calculating MAE with other deep learning models and an experiment calculating recognition rate with existing techniques were performed and compared. As a result of the experiment, the MAE value of the time series point cloud input vector + LSTM deep learning model was calculated to be 0.262 and the recognition rate was 97.5%. The lower the MAE and the higher the recognition rate, the better the results, proving the efficiency of the technique proposed in this paper.

• Journal of Haehwa Medicine
• /
• v.10 no.1
• /
• pp.483-487
• /
• 2001

Morus alba extract(MAE) was tested for its ability to inhibit alloxan induced lipidperoxidation. Lipid peroxide contents in serum, liver, kidney and heart were measured by the TBA method. ICR mice receiving alloxan at a dose of 6mg/kg intraperitoneally after a 24hrs starvation showed significantly increased lipid peroxide contents as compared to untreated control. Lipid peroxide contents in serum, liver, kidney of alloxan-diabetic mice were decreased by the treatment of MAE at the dose of 50mg/kg, 100mg/kg for 7 days.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.987-994
• /
• 2020

In this paper, we studied the effect of kernel size of CNN layer on performance in acoustic noise attenuators. This system uses a deep learning algorithm using a neural network adaptive prediction filter instead of using the existing adaptive filter. Speech is estimated from a single input speech signal containing noise using a 100-neuron, 16-filter CNN filter and an error back propagation algorithm. This is to use the quasi-periodic property in the voiced sound section of the voice signal. In this study, a simulation program using Tensorflow and Keras libraries was written and a simulation was performed to verify the performance of the noise attenuator for the kernel size. As a result of the simulation, when the kernel size is about 16, the MSE and MAE values are the smallest, and when the size is smaller or larger than 16, the MSE and MAE values increase. It can be seen that in the case of an speech signal, the features can be best captured when the kernel size is about 16.

• Journal of Microbiology and Biotechnology
• /
• v.23 no.5
• /
• pp.668-673
• /
• 2013

A recombinant E. coli co-expressing ALA synthase (hemA), NADP-dependent malic enzyme (maeB), and dicarboxylic acid transporter (dctA) was reported to synthesize porphyrin derivatives including iron-containing heme. To enhance the synthesis of bacterial heme, five genes of the porphyrin biosynthetic pathway [pantothenate kinase (coaA), ALA dehydratase (hemB), 1-hydroxymethylbilane synthase (hemC), uroporphyrinogen III synthase (hemD), and uroporphyrinogen III decarboxylase (hemE)] were amplified in the recombinant E. coli co-expressing hemA-maeB-dctA. Pantothenate kinase expression enabled the recombinant E. coli to accumulate intracellular CoA. Intracellular ALA was the most enhanced by uroporphyrinogen III synthase expression, porphobilinogen was the most enhanced by ALA dehydratase expression, uroporphyrin and coproporphyrin were the most enhanced by 1-hydroxymethylbilane synthase expression. The strain co-expressing coaA, hemA, maeB, and dctA produced heme of $0.49{\mu}mol/g$-DCW, which was twice as much from the strain without coaA expression. Further pathway gene amplifications for the porphyrin derivatives are discussed based on the results.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.26-36
• /
• 2021

In this study, a deep learning model for predicting the queue length was developed using the information collected from the image detector. Then, a multiple regression analysis model, a statistical technique, was derived and compared using two indices of mean absolute error(MAE) and root mean square error(RMSE). From the results of multiple regression analysis, time, day of the week, occupancy, and bus traffic were found to be statistically significant variables. Occupancy showed the most strong impact on the queue length among the variables. For the optimal deep learning model, 4 hidden layers and 6 lookback were determined, and MAE and RMSE were 6.34 and 8.99. As a result of evaluating the two models, the MAE of the multiple regression model and the deep learning model were 13.65 and 6.44, respectively, and the RMSE were 19.10 and 9.11, respectively. The deep learning model reduced the MAE by 52.8% and the RMSE by 52.3% compared to the multiple regression model.

• Parasites, Hosts and Diseases
• /
• v.56 no.3
• /
• pp.247-257
• /
• 2018

The aim of this study was to conduct a freshwater snail survey in Mae Lao agricultural basin to assess the diversity with a focus on habitat types and their larval trematode infections. Snails were collected and examined in 14 sites of Mae Lao agricultural basin from August 2016 to October 2017. A total of 1,688 snail individuals were collected and classified into 7 families, 8 genera, and 12 species. Snail diversity and habitat types were higher in rice paddies than irrigation canals and streams. The most abundant species was Bithynia siamensis siamensis, representing 54.6% of the sample. Three species of snails act as first intermediate host were found with cercarial infections. They were Filopaludina sumatrensis polygramma, B. s. siamensis, and Melanoides tuberculata. The cercariae were categorized into 7 types; echinostome, monostome, gymnocephalous, virgulate, parapleurolophocercous, pleurolophocercous and megalurous cercariae. Parapleurolophocercous cercariae constituted the most common type of cercariae recovered, contributing 41.2% of all infections in snails. Echinostome metacercariae infections were found in 6 snail species with 7.6% prevalence. In addition, the metacercaria of avian trematode, Thapariella sp. were found in Filopaludina spp. snails and B. funiculata with a prevalence of 0.5%. This is the first report for Thapariella metacercariae in the snail host, B. funiculata, and also confirmed that viviparid and bithyniid snails act as the second intermediate hosts of this trematode. This work will provide new information on the distribution and intermediate host of trematode in this area.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.249-255
• /
• 2000

HRIV(Hybrid Rule-Interval Variation) method is presented to stabilize a class of nonlinear systems, where SMC(Sliding Mode Control) and ADC (ADaptive Control) schemes are incorporated to overcome the unstable characteristics of a conventional FLC(Fuzzy Logic Control). HRIV method consists of two modes: I-mode (Integral Sliding Mode PLC) and R-mode(RIV method). In I-mode, SMC is used to compensate for MAE(Minimum Approximation Error) caused by the heuristic characteristics of FLC. In R-mode, RIV method reduces interval lengths of rules as states converge to an equilibrium point, which makes the defined Lyapunov function candidate negative semi-definite without considering MAE, and the new uncertain parameters generated in R-mode are compensated by SMC. In RIV method, the overcontraction problem that the states are out of a rule-table can happen by the excessive reduction of rule intervals, which is solved with a dynamic modification of rule-intervals and a transition to I-mode. Especially, HRIV method has advantages to use the analytic upper bound of MAE and to reduce Its effect in the control input, compared with the previous researches. Finally, the proposed method is applied to stabilize a simple nonlinear system and a modified inverted pendulum system in simulation experiments.

• Journal of Internet Computing and Services
• /
• v.8 no.6
• /
• pp.95-102
• /
• 2007

Recommender System based on the Collaborative Filtering has a problem of trust of the prediction accuracy because of its problem of sparsity. If the sparsity of a preference value is large, it causes a problem on a process of a choice of neighbors and also lowers the prediction accuracy. In this article, a change of MAE based on the sparsity is studied, groups are classified by sparsity and then, the significant difference among MAEs of classified groups is analyzed. To improve the accuracy of prediction among groups by the problem of sparsity, We studied the improvement of an accurate prediction for recommending system through reducing sparsity by sorting sparsity items, and replacing the average preference among them that has a lot of respondents with the preference evaluation value.