• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.3 no.2
• /
• pp.30-38
• /
• 1992

In this paper, in order to apply the $\pi$/4 shift QPSK to TCM, we propose the $\pi$/8 shift 8PSK modulation technique and the trellis-coded $\pi$/8 shift 8PSK performing signal set expansion and set partition by phase difference. In addition, the Viterbi decoder with branch metrics of the squared Euclidean distance of the first phase difference as well as the Lth phase difference is introduced in order to improve the bit error rate(BER) performance in differential detection of the trellis-coded $\pi$/8 shift 8 PSK. The proposed Viterbi decoder is conceptually the same as the sliding multiple de- tection by using the branch metric with first and Lth order phase difference. We investigate the performance of the uncoded .pi. /4 shift QPSK and the trellis-coded $\pi$/8 shift 8PSK with or without the Lth phase difference metric in an additive white Gaussian noise (AWGN) and Rayleigh fading channel using the Monte Carlo simulation. The study shows that the $\pi$/4 shift QPSK with the Trellis-code i. e. the trellis-coded $\pi$/8 shift 8PSK is an attractive scheme for power and bandlimited systems and especially, the Viterbi decoder with first and Lth phase difference metrics improves BER performance. Also, the next proposed algorithm can be used in the TC $\pi$/8 shift 8PSK as well as TC MDPSK.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.4
• /
• pp.43-54
• /
• 2007

This paper presents design and verification of a face detection hardware for real time application. Face detection algorithm detects rough face position based on already acquired feature parameter data. The hardware is composed of five main modules: Integral Image Calculator, Feature Coordinate Calculator, Feature Difference Calculator, Cascade Calculator, and Window Detection. It also includes on-chip Integral Image memory and Feature Parameter memory. The face detection hardware was verified by using S3C2440A CPU of Samsung Electronics, Virtex4LX100 FPGA of Xilinx, and a CCD Camera module. Our design uses 3,251 LUTs of Xilinx FPGA and takes about 1.96${\sim}$0.13 sec for face detection depending on sliding-window step size, when synthesized for Virtex4LX100 FPGA. When synthesized on Magnachip 0.25um ASIC library, it uses about 410,000 gates (Combinational area about 345,000 gates, Noncombinational area about 65,000 gates) and takes less than 0.5 sec for face realtime detection. This size and performance shows that it is adequate to use for embedded system applications. It has been fabricated as a real chip as a part of XF1201 chip and proven to work.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.3
• /
• pp.64-69
• /
• 2007

Motion control of the system is a position control of motor. Motion control of an uncertain robot system is considered as one of the most important and fundamental research directions in the robotics. Some distinguished works using linear control, adaptive control, robust control strategies based on computed torque methodology have been reported. However, it is generally recognized within the control community that these strategies suffer from the following problems : the exact robot dynamics are needed and hard to implement, the adaptive control cannot guarantee the performance during the transient period for adaptation under the variation, the robust control algorithms such as the sliding mode control need information on the bounds of the possible uncertainty and disturbance. And it produces a large control input as well. In this dissertation, a motion control for the unmanned intelligent robot system using disturbance observer is studied. This system is affected with an impact vibration disturbance. This paper describes a stable motion control of the system with the consideration of external disturbance. To obtain the stable motion independently against the external disturbance, the disturbance rejection is strongly required. To address the above issue, this paper presents a Disturbance OBserver(DOB) control algorithm. The validity of the suggested DOB robust control scheme is confirmed by several computer simulation results. And the experiments with a motor system is performed to give the validity of applicability in the industrial field. This results make the easier implementation of the controller possible in the field.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.95-108
• /
• 2011

TThis is a study of the personalization method that intelligently adapts the level of clustering considering purchasing index of a customer. In the e-biz era, many companies gather customers' demographic and transactional information such as age, gender, purchasing date and product category. They use this information to predict customer's preferences or purchasing patterns so that they can provide more customized services to their customers. The previous Customer-Segmentation method provides customized services for each customer group. This method clusters a whole customer set into different groups based on their similarity and builds predictive models for the resulting groups. Thus, it can manage the number of predictive models and also provide more data for the customers who do not have enough data to build a good predictive model by using the data of other similar customers. However, this method often fails to provide highly personalized services to each customer, which is especially important to VIP customers. Furthermore, it clusters the customers who already have a considerable amount of data as well as the customers who only have small amount of data, which causes to increase computational cost unnecessarily without significant performance improvement. The other conventional method called 1-to-1 method provides more customized services than the Customer-Segmentation method for each individual customer since the predictive model are built using only the data for the individual customer. This method not only provides highly personalized services but also builds a relatively simple and less costly model that satisfies with each customer. However, the 1-to-1 method has a limitation that it does not produce a good predictive model when a customer has only a few numbers of data. In other words, if a customer has insufficient number of transactional data then the performance rate of this method deteriorate. In order to overcome the limitations of these two conventional methods, we suggested the new method called Intelligent Customer Segmentation method that provides adaptive personalized services according to the customer's purchasing index. The suggested method clusters customers according to their purchasing index, so that the prediction for the less purchasing customers are based on the data in more intensively clustered groups, and for the VIP customers, who already have a considerable amount of data, clustered to a much lesser extent or not clustered at all. The main idea of this method is that applying clustering technique when the number of transactional data of the target customer is less than the predefined criterion data size. In order to find this criterion number, we suggest the algorithm called sliding window correlation analysis in this study. The algorithm purposes to find the transactional data size that the performance of the 1-to-1 method is radically decreased due to the data sparity. After finding this criterion data size, we apply the conventional 1-to-1 method for the customers who have more data than the criterion and apply clustering technique who have less than this amount until they can use at least the predefined criterion amount of data for model building processes. We apply the two conventional methods and the newly suggested method to Neilsen's beverage purchasing data to predict the purchasing amounts of the customers and the purchasing categories. We use two data mining techniques (Support Vector Machine and Linear Regression) and two types of performance measures (MAE and RMSE) in order to predict two dependent variables as aforementioned. The results show that the suggested Intelligent Customer Segmentation method can outperform the conventional 1-to-1 method in many cases and produces the same level of performances compare with the Customer-Segmentation method spending much less computational cost.

• 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.