• Journal of Internet Computing and Services
• /
• v.16 no.1
• /
• pp.67-74
• /
• 2015

In recent years, frequent itemset mining for considering the importance of each item has been intensively studied as one of important issues in the data mining field. According to strategies utilizing the item importance, itemset mining approaches for discovering itemsets based on the item importance are classified as follows: weighted frequent itemset mining, frequent itemset mining using transactional weights, and utility itemset mining. In this paper, we perform empirical analysis with respect to frequent itemset mining algorithms based on transactional weights. The mining algorithms compute transactional weights by utilizing the weight for each item in large databases. In addition, these algorithms discover weighted frequent itemsets on the basis of the item frequency and weight of each transaction. Consequently, we can see the importance of a certain transaction through the database analysis because the weight for the transaction has higher value if it contains many items with high values. We not only analyze the advantages and disadvantages but also compare the performance of the most famous algorithms in the frequent itemset mining field based on the transactional weights. As a representative of the frequent itemset mining using transactional weights, WIS introduces the concept and strategies of transactional weights. In addition, there are various other state-of-the-art algorithms, WIT-FWIs, WIT-FWIs-MODIFY, and WIT-FWIs-DIFF, for extracting itemsets with the weight information. To efficiently conduct processes for mining weighted frequent itemsets, three algorithms use the special Lattice-like data structure, called WIT-tree. The algorithms do not need to an additional database scanning operation after the construction of WIT-tree is finished since each node of WIT-tree has item information such as item and transaction IDs. In particular, the traditional algorithms conduct a number of database scanning operations to mine weighted itemsets, whereas the algorithms based on WIT-tree solve the overhead problem that can occur in the mining processes by reading databases only one time. Additionally, the algorithms use the technique for generating each new itemset of length N+1 on the basis of two different itemsets of length N. To discover new weighted itemsets, WIT-FWIs performs the itemset combination processes by using the information of transactions that contain all the itemsets. WIT-FWIs-MODIFY has a unique feature decreasing operations for calculating the frequency of the new itemset. WIT-FWIs-DIFF utilizes a technique using the difference of two itemsets. To compare and analyze the performance of the algorithms in various environments, we use real datasets of two types (i.e., dense and sparse) in terms of the runtime and maximum memory usage. Moreover, a scalability test is conducted to evaluate the stability for each algorithm when the size of a database is changed. As a result, WIT-FWIs and WIT-FWIs-MODIFY show the best performance in the dense dataset, and in sparse dataset, WIT-FWI-DIFF has mining efficiency better than the other algorithms. Compared to the algorithms using WIT-tree, WIS based on the Apriori technique has the worst efficiency because it requires a large number of computations more than the others on average.

• 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.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.2
• /
• pp.110-114
• /
• 2012

Purpose : PET/CT is widely used for early checking up of cancer and following up of pre and post operation. Image reconstruction method is advanced with mechanical function. We want to evaluate image quality of each reconstruction program based on time of flight (TOF). Materials and Methods : After acquiring phantom images during 2 minutes with Gemini TF (Philips, USA), Biograph mCT (Siemens, USA) and Discovery 690 (GE, USA), we reconstructed image applied to Astonish TF (Philips, USA), ultraHD PET (Siemens, USA), Sharp IR (GE, USA) and not applied. inside of Flangeless Esser PET phantom (Data Spectrum corp., USA) was filled with $^{18}F$-FDG 1.11 kBq/ml (30 Ci/ml) and 4 hot inserts (8. 12. 16. 25 mm) were filled with 8.88 kBq/ml (240 ${\mu}Ci/ml$) the ratio of background activity and hot inserts activity was 1 : 8. Inside of triple line phantom (Data Spectrum corp., USA) was filled with $^{18}F$-FDG 37 MBq/ml (1 mCi). Three of lines were filled with 0.37 MBq (100 ${\mu}Ci$). Contrast ratio and background variability were acquired from reconstruction image used Flangeless Esser PET phantom and resolution was acquired from reconstruction image used triple line phantom. Results : The contrast ratio of image which was not applied to Astonish TF was 8.69, 12.28, 19.31, 25.80% in phantom lid of which size was 8, 12, 16, 25 mm and it which was applied to Astonish TF was 6.24, 13.24, 19.55, 27.60%. It which was not applied to ultraHD PET was 4.94, 12.68, 22.09, 30.14%, it which was applied to ultraHD PET was 4.76, 13.23, 23.72, 31.65%. It which was not applied to SharpIR was 13.18, 17.44, 28.76, 34.67%, it which was applied to SharpIR was 13.15, 18.32, 30.33, 35.73%. The background variability of image which was not applied to Astonish TF was 5.51, 5.42, 7.13, 6.28%. it which was applied to Astonish TF was 7.81, 7.94, 6.40 6.28%. It which was not applied to ultraHD PET was 6.46, 6.63, 5.33, 5.21%, it which was applied to ultraHD PET was 6.08, 6.08, 4.45, 4.58%. It which was not applied to SharpIR was 5.93, 4.82, 4.45, 5.09%, it which was applied to SharpIR was 4.80, 3.92, 3.63, 4.50%. The resolution of phantom line of which location was upper, center, right, which was not applied to Astonish TF was 10.77, 11.54, 9.34 mm it which was applied to Astonish TF was 9.54, 8.90, 8.88 mm. It which was not applied to ultraHD PET was 7.84, 6.95, 8.32 mm, it which was applied to ultraHD PET was 7.51, 6.66, 8.27 mm. It which was not applied to SharpIR was 9.35, 8.69, 8.99, it which was applied to SharpIR was 9.88, 9.18, 9.00 mm. Conclusion : Image quality was advanced generally while reconstruction program which is based on time of flight was used. Futhermore difference of result compared each manufacture reconstruction program showed up, however this is caused by specification of instrument of each manufacture and difference of reconstruction algorithm. Therefore we need further examination to find out appropriate reconstruction condition while using reconstruction program used for advance of image quality.