Feature matching and instance reweighting with transfer learning for human activity recognition using smartphone

Human activity recognition using smartphone has been attracting great interest. Since collecting large amount of labeled data is expensive and time-consuming for conventional machine learning techniques, transfer learning techniques have been proposed for activity recognition. However, existing transfer learning techniques typically rely on feature matching based on global domain shift and lack considering the intra-class knowledge transfer. In this paper, a novel transfer learning technique is proposed for cross-domain activity recognition, which can properly integrate feature matching and instance reweighting across the source and target domain in principled dimensionality reduction. The experiments using three real datasets demonstrate that the proposed scheme can achieve much higher precision (92%), recall (91%), and F1-score (92%), in comparison with the existing schemes.

     

Effect of stents coated with a combination of sirolimus and alpha-lipoic acid in a porcine coronary restenosis model

The aim of this study was to evaluate antiproliferative sirolimus- and antioxidative alpha-lipoic acid (ALA)-eluting stents using biodegradable polymer [poly-l-lactic acid (PLA)] in a porcine coronary overstretch restenosis model. Forty coronary arteries of 20 pigs were randomized into four groups in which the coronary arteries had a bare metal stent (BMS, n = 10), ALA-eluting stent with PLA (AES, n = 10), sirolimus-eluting stent with PLA (SES, n = 10), or sirolimus- and ALA-eluting stent with PLA (SAS, n = 10). A histopathological analysis was performed 28 days after the stenting. The ALA and sirolimus released slowly over 30 days. There were no significant differences between groups in the injury or inflammation score; however, there were significant differences in the percent area of stenosis (56.2 ± 11.78 % in BMS vs. 51.5 ± 12.20 % in AES vs. 34.7 ± 7.23 % in SES vs. 28.7 ± 7.30 % in SAS, P < 0.0001) and fibrin score [1.0 (range 1.0–1.0) in BMS vs. 1.0 (range 1.0–1.0) in AES vs. 2.0 (range 2.0–2.0) in SES vs. 2.0 (range 2.0–2.0) in SAS, P < 0.0001] between the four groups. The percent area of stenosis based on micro-computed tomography corresponded with the restenosis rates based on histopathological stenosis in different proportions in the four groups (54.8 ± 7.88 % in BMS vs. 50.4 ± 14.87 % in AES vs. 34.5 ± 7.22 % in SES vs. 28.9 ± 7.22 % in SAS, P < 0.05). SAS showed a better neointimal inhibitory effect than BMS, AES, and SES at 1 month after stenting in a porcine coronary restenosis model. Therefore, SAS with PLA can be a useful drug combination for coronary stent coating to suppress neointimal hyperplasia.     

Localization algorithm using a virtual label for a mobile robot in indoor and outdoor environments

Scanning laser range sensors provide range data consisting of a set of point measurements. The laser sensor URG-04LX has a distance range of approximately 0.02–4 m and a scanning angle range of 240°. Usually, such an image range is acquired from one viewpoint by “moving” the laser beam using rotating mirrors/prisms. The orientation of the laser beam can easily be measured and converted into the coordinates of the image. This article conducts localization using virtual labels with data about distances in the environment obtained from 2D distance laser sensors. This method puts virtual labels on special features and points which are along the mobile robot’s path. The current location is calculated by combining the virtual label and the range image of the laser range finder.     

A Data‐driven Segmentation for the Shoulder Complex

The human shoulder complex is perhaps the most complicated joint in the human body being comprised of a set of three bones, muscles, tendons, and ligaments. Despite this anatomical complexity, computer graphics models for motion capture most often represent this joint as a simple ball and socket. In this paper, we present a method to determine a shoulder skeletal model that, when combined with standard skinning algorithms, generates a more visually pleasing animation that is a closer approximation to the actual skin deformations of the human body. We use a data‐driven approach and collect ground truth skin deformation data with an optical motion capture system with a large number of markers (200 markers on the shoulder complex alone). We cluster these markers during movement sequences and discover that adding one extra joint around the shoulder improves the resulting animation qualitatively and quantitatively yielding a marker set of approximately 70 markers for the complete skeleton. We demonstrate the effectiveness of our skeletal model by comparing it with ground truth data as well as with recorded video. We show its practicality by integrating it with the conventional rendering/animation pipeline.     

Two versions of architectures for dynamic implied addressing mode

The complexity of today’s embedded applications increases with various requirements such as execution time, code size or power consumption. To satisfy these requirements for performance, efficient instruction set design is one of the important issues because an instruction customized for specific applications can make better performance than multiple instructions in aspect of fast execution time, decrease of code size, and low power consumption. Limited encoding space, however, does not allow adding application specific and complex instructions freely to the instruction set architecture. To resolve this problem, conventional architectures increases free space for encoding by trimming excessive bits required beyond the fixed word length. This approach however shows severe weakness in terms of the complexity of compiler, code size and execution time. In this paper, we propose a new instruction encoding scheme based on the dynamic implied addressing mode (DIAM) to resolve limited encoding space and side-effect by trimming. We report our two versions of architectures to support our DIAM-based approach. In the first version, we use a special on-chip memory to store extra encoding information. In the second version, we replace the memory by a small on-chip buffer along with a special instruction. We also suggest a code generation algorithm to fully utilize DIAM. In our experiment, the architecture augmented with DIAM shows about 8% code size reduction and 18% speed up on average, as compared to the basic architecture without DIAM.     

On the generation of test patterns for multiple faults

This article presents a new method to generate test patterns for multiple stuck-at faults in combinational circuits. We assume the presence of all multiple faults of all multiplicities and we do not resort to their explicit enumeration: the target fault is a single component of possibly several multiple faults. New line and gate models are introduced to handle multiple fault effect propagation through the circuits. The method tries to generate test conditions that propagate the effect of the target fault to primary outputs. When these conditions are fulfilled, the input vector is a test for the target fault and it is guaranteed that all multiple faults of all multiplicities containing the target fault as component are also detected. The method uses similar techniques to those in FAN and SOCRATES algorithms to guide the search part of the algorithm, and includes several new heuristics to enhance the performance and fault detection capability. Experiments performed on the ISCAS'85 benchmark circuits show that test sets for multiple faults can be generated with high fault coverage and a reasonable increase in cost over test generation for single stuck-at faults.     

Tracking of moving interfaces in sedimentation processes using electrical impedance tomography

Sedimentation monitoring is widely used to control and optimize industrial processes. In this paper we propose a novel computational method for sedimentation monitoring using electrical impedance tomography (EIT). EIT measurements consist of electric current and voltage measurements that are made on the surface of the sedimentation tank and therefore they do not interfere with the sedimentation process. The proposed computational method is based on shape estimation and state estimation formulation of the EIT problem. The sedimentation is parameterized by the locations of the phase interfaces and conductivities of the phase layers. Three different evolution models for the state parameters are considered and the state estimates are computed using the extended Kalman filter algorithm. The performance of the method and the models are evaluated using simulated data from a six electrode EIT measurement configuration. From the results a promising performance of the method can be seen.