Search

Objectives: To try another non-invasive method to evaluate the relationship between Magnetic Resonance (MR) elastic value and pathological grade of Hepatocellular Carcinoma (HCC) using Magnetic Resonance Elastography (MRE). Methods: Forty-seven HCC patients underwent MR Imaging (MRI), elastography in the upper abdomen. The elastic value of the lesion area was measured, and that of the normal liver tissue was measured adjacent to the lesion area at the same level. The Mann-Whitney U test was used to compare the difference in elasticity between the lesion area and normal area, and the difference between the low and middle-high differentiation groups. The Receiver Operating Characteristic Curve (ROC) of the lesion area and normal area in the complete case group and different differentiation groups were used to determine the diagnostic cut-off value to distinguish the lesion area from the normal area in each group. Results: (1) There was a significant difference in elasticity between the normal area and HCC area (p

Terrain problems have caused floods to occur frequently, which will cause flooding, landslides, destroying facilities and casualties in Taiwan. With the growth of machine performance and the gradual completion of training data, object recognition approaches based on convolutional neural network (CNN) have performed well in various disaster monitoring systems. However, in the actual domain, as time goes by, changes in the background, viewpoint, and environment caused by weather and time conditions will cause the model to be inaccurate for the outdoor CCTVs. In this paper, we proposed an automatic incremental training approach combined with deep convolutional generative adversarial network (DCGAN) to greatly reduce the time and labor cost of model retraining. The experimental results show that the proposed approach can effectively reduce labeling effort and achieve the recall closing to the model with manually labeled and training by human.

Traditionally, doctors have used stethoscopes for chest auscultation to diagnose respiratory and heart diseases. Auscultation can be used to initially diagnose the status of the patient, but this depends on the doctor's experience and waste time. Recently, electronic auscultation is proposed to diagnose the condition more carefully by sampling and processing sound signals. This paper designs a simple self-made stethoscope to digitize medical sound data. The sounds are then analyzed to give preliminary diagnosis to track health condition. The wave of monitored sounds and analyzed results can be displayed on mobile phones, so that patients can know health status immediately. In addition, an e-health home gateway and cloud-based AI system are also proposed for home-care patients to monitor health condition of chronic patients anytime at home or long-care center.

In this paper, we propose a differentially fed ultrawideband (UWB) quasi-self-complementary (QSC) antenna with a 5.5-GHz notch band. By designing the first five modes of the complementary antenna in the passband, the desired UWB response is achieved. To suppress the common-mode (CM) signals, instead of directly connecting to the complementary antenna, the differential feedline is deployed symmetrically across the input slotline so that weak coupling can be established when in CM operation. A 5.5-GHz notch band for preventing undesired WLAN signals is implemented by tapping λ/4 open stubs near the bisection plane. The differentially fed UWB complementary antenna have good differential-mode (DM) performance, high CM rejection, as well as low DM-to-CM conversion. The measured results show that the 10-dB DM passband is from 2.75 to 11.01 GHz, except the notch band; the CM reflection coefficient is greater than −2.62 dB and the DM-to-CM conversion is lower than −24.7 dB in the 2–12 GHz frequency range.

With the explosive growth of new energy vehicles, 4~5years later, there will be a lot of decommissioned battery problems around the world. In order to promote the cascade utilization of power battery, the system of recycle and utilization of power battery is established to reduce the frequency of safety accidents of inferior battery products in the market, and to improve the control and reliability of power battery system and improve the power battery industry chain. Therefore, contra posing “battery PSD big data system judgment and detection” technology, and because of the interface signal, we will compile the soft code, and then independently set up the back-end data analysis, and develop the App program intelligent platform, With the signal and platform supporting each other, It can solve the problem of intelligent power balance, and discuss the demand integration of users or enterprises. Related information can be transmitted among battery module management units through communication protocols such as CAN,SPI or UART, and further information can be transferred to the upper layer of the battery management system control core (Battery Control Unit, BCU), According to this information, BCU can realize the control strategy of battery management, warning and safety protection.

Most photographer robots can only capture frontal-like faces, posing limitations on broader applications, especially when it is needed to capture non-frontal faces. We built a photographer robot with a multiview face detector embedded so that it can capture faces with a large range of poses. The core part of the multiview face detector is a state-of-the-art facial landmark model which can track facial features and contours and is robust to illumination variation and partial occlusion. Our photographer robot is built on the low-cost Turtlebot platform, which solves the issues of SLAM and auto-navigation. To reveal its application scope, it has been tested in various scenarios, including single and multiple persons, faces of different poses and under various lighting conditions.

Based on Lax-Friedrichs scheme, we developed a new fast sweeping method of calculating the direct traveltime field for both quasi-Pand quasi-S-wave in general anisotropic media. The ray vector and the polarization can be obtained from the slowness vector at any given points in the model and the seismic ray path can be traced following the opposite direction of ray vectors. We illustrate the efficiency and accuracy of this new algorithm using 2-D and 3-D numerical examples.

A UWB impulse radio (IR) timed-array radar using time-shifted direct-sampling architecture is presented. The transmitter array can generate and send a variety of 10GS/s pulses towards targets. The receiver array samples the reflected signal in RF domain directly by time interleaved sampling with equivalent sampling rate of 20 GS/s. The radar system can determine time of arrival (TOA) and direction of arrival (DOA) through time-shifted sampling edges which are generated by on-chip digital-to-time converters (DTC). The proposed architecture has range and azimuth resolution of 0.75 cm and 3 degree respectively. This prototype is implemented in a 0.18µm CMOS technology.

With the development of steganalysis, steganalysis- proof ability of steganography is becoming more and more important. The evaluation for steganalysis-proof ability of steganographic algorithms can provide theoretical foundation and promote the development of steganalysis-proof ability of steganographic algorithms. This paper proposes an evaluation scheme for steganalysis-proof ability of steganographic algorithms. According to the intensity of steganalysis, this scheme classifies the steganalysis-proof ability of steganographic algorithms into three grades from weakness to strongness. The proof schemes to the three grades are given in this paper, which thus can be used to evidently prove the grade of steganalysis-proof ability of any steganographic algorithms. The evaluation scheme has a better performance of evaluating the steganalysis-proof ability of a steganographic algorithm, and can provide a quantitative evaluation criterion for steganalysis-proof ability of steganographic algorithms.

Secret messages can be embedded in a webpage by switching the uppercase-lowercase states of letters in tags. In this paper, a novel steganalytic approach called Tag-Mismatch analysis for detection of hidden information embedded in tags is presented. In order to guarantee reasonable false positive and false negative, the approach is firstly trained on a set of 4,100 webpages to determine the decision threshold. It is shown that the length of embedded secret messages can be estimated with relatively high precision and the resulting detection algorithm is simple and fast. The experimental results show that the detection rate is larger than 85%, as the embedded rate is larger than 0.3%.