Search

Recently, facial recognition has been extensively adopted in various fields. Wide applications are associated with a large amount of data transmission so that edge computing is inspired accordingly. In this research task, the major goal of edge computing is to handover a part of the computing work to the terminal equipment; the server only needs to process the results of final return. The IoT configuration proposed includes a perception layer, a transmission layer, and an application layer to fulfil a complete IoT system. In the perception layer, the facial authentication mechanism is adopted. This system is equipped with a highly robust anti‐spoofing function, which can avoid criminal access from photos or electronic screens. Finally, the IoT transmission system is realised as the transmission layer. Combined with such a transmission mechanism, one can distribute user facial features to user's electronic devices instead of storing it in the server. This not only saves storage resources and transmission costs, but also allows users to complete data transmission and face authentication easily.

For the research of wireless power transfer, loosely coupled inductive power transfer (LCIPT) is one of the widely adopted technologies. There are already various researches focusing on development of high-efficiency LCIPT. However, when the transmission and receiver coils are misaligned, the power transfer efficiency will be significantly dropped. This article considers the change of mutual inductance when two induction coils are misaligned. A fuzzy control approach to solve for this problem by adaptively adjusting operational frequency is introduced. Experiments show that it can reduce the power transferring efficiency drop by 11% when two conduction coils are misaligned up to 50 mm. This research also supports adaptive maximum power transfer using tracking mechanism. Before conducting power transmission, the system can choose G2V or V2G according to the vehicle battery capacity via handshaking communication without the need of radio frequency links. In addition, the phase shift pulsewidth modulation technique is proposed for simultaneous data transmission enabling binary quadrature amplitude modulation for digital signal transmission. Fast over current protection is incorporated for power transfer safety when current overload happens. The transmission frequency of this article is controlled to meet the frequency specified by SAE TIR J2954 .

Along with the rapid development of synthetic biology, the technology of biological computers has become increasingly mature in recent years. In this paper, we propose a structure for a biological ...

According to statistics, the majority of accidents are attributed to driver negligence, especially when a driver intends to lane change or to overtake another vehicle, which is most likely to cause accidents. In addition, overtaking is one of the most difficult and complex functions for the development of autonomous driving technologies because of the dynamic and complicated task involved in the control strategy and electronic control systems, such as steering, throttle, and brake control. This paper proposes a safe overtaking maneuver procedure for an autonomous vehicle based on time to lane crossing (TLC) estimation and the model predictive control scheme. As overtaking is one of the most complex maneuvers that require both lane keeping and lane changing, a vision-based lane-detection system is used to estimate TLC to make a timely and accurate decision about whether to overtake or remain within the lane. Next, to maintain the minimal safe distance and to choose the best timing to overtake, the successive linearization-based model predictive control is employed to derive an optimal vehicle controller, such as throttle, brake, and steering angle control. Simultaneously, it can make certain that the longitudinal acceleration and steering velocity are maintained under constraints to maintain driving safety. Finally, the proposed system is validated by real-world experiments performed on a prototype electric golf cart and executed in real-time on the automotive embedded hardware with limited computational power. In addition, communication between the sensors and actuators as well as the vehicle control unit (VCU) are based on the controller area network (CAN) bus to realize vehicle control and data collection. The experiments demonstrate the ability of the proposed overtaking decision and control strategy to handle a variety of driving scenarios, including a lane-following function when a relative yaw angle exists and an overtaking function when the approaching vehicle has a different lateral velocity.

The consumer-level digital camera has become a physiological signal monitoring sensor due to the rapid growth of the remote photoplethysmography (rPPG) technique. However, rPPG suffers from the artifacts caused by video compression, a technique that widely exists in nearly all video-related applications. This limitation greatly narrows the application range of the rPPG. In this paper, a novel physiological signal preserving video compression algorithm called POSSC is proposed such that the existing rPPG signal extraction approaches can be applied directly on the compressed video without modification. The proposed approach consists of three main steps: 1) rPPG feature extraction; 2) sparse subspace clustering; and 3) region of interest (ROI)-based video compression. This paper models the skin/non-skin feature classification problem as sparse subspace clustering. Physiological signals are preserved by allocating more (fewer) bits to the ROI (non-ROI) regions. A self-collected benchmark dataset is established to evaluate the performance of POSSC in terms of body part, ROI size, light source, illumination intensity, and multiple subjects in an image. The results demonstrate that POSCC is effective in preserving physiological signals for facial videos under normal light intensity, insensitive to ROI size, shape, and the number of subjects. This paper also demonstrates the effectiveness of sparse subspace clustering for pulse region detection.

Although the antilock braking system (ABS) has been commonly used in electric vehicles (EVs), most of the vehicles still use the traditional hydraulic-based disc brake in which the driving and the braking systems are two individual modules. A novel integrated driving and braking control system with an ABS for EVs was developed, and an electric scooter was used as the experimental object. While braking, the motor acts as a generator. The autonomously generated inertial energy was used to generate a reverse magnetic braking torque and realise an antilock braking control with fast response. Compared with the existing regenerative and short-circuit braking methods, the proposed method uses back electromotive force to yield a reverse magnetic braking torque in a sophisticated manner. In the proposed method, a capacitor-aided regenerative braking strategy was used in an antilock braking controller. For the ABS control design, the slip ratio was maintained within an optimal range for obtaining the best tyre–road surface adhesion using a fuzzy slip ratio controller to prevent the wheel from skidding during emergency braking. For real-world verification, the electric scooter was subjected to various on-road tests to examine the performance of the proposed method.

Taiwanese is one of the main languages spoken by Taiwanese. Taiwanese was commonly used language in Taiwan before, but now it is facing the dilemma of declining. Therefore, maintaining traditional culture in the ever-changing trend is a major issue. In this study, we developed the Taiwanese speech recognition system which the Kaldi Toolkit was used to implement. The Taiwanese corpus was collected by Taiwan Taiwanese National Reading Competition and Classmate Recording, and about 11 hours of audio files were collected in total. Because the training data is a small dataset, two data augmentation methods are used to increase the training data, so that the acoustic model can be more robust and more effective training. One method is speed perturbation, which speeds up the original data by 1.1 times and slows it down by 0.9 times. Another method is to use multi-condition training data to simulate the reverberation of the original speech and add background noise. The background noise includes music, speech, and noise. The acoustic model is trained for different hybrid deep neural network architectures which can use the advantages of each neural network by hybrid different neural networks, such as CNN-LSTM-TDNN. In the experimental results, the CER in the domain of language modeling reaches 3.95%, and the CER of the online decoding test is 3.06%. Compared with other research on Taiwanese speech recognition of similar dataset size, the recognition results are better than other studies.

Due to the advantages of non-contact and low-cost, visual heart rate (HR) estimation is attracting more and more scholars to research. Recently, Some studies have shown that deep learning method could be developed for visual HR estimation. In this paper, we proposed an End-to-end deep neural network method for this task. The network is consisted of 2D convolutional (Conv2D) and LSTM (long short-term memory) operations. The Conv2D operation extract spatial feature and LSTM capture temporal information. The input of our model is facial ROI video and output is the predict HR. Experiment demonstrate that the proposed method could estimate HR value precisely.

Remote photoplethysmography (rPPG) has attracted much attention in recent years. This research proposes to apply rPPG to the fitness training scenario, enabling non-contact measurement of the subject's heart rate during training. Currently, most existing approaches suffer from a major weakness, i.e. the subject's body needs to remain stably while conducting measurement, which significantly hinders practical applications of the approach. The main purpose of this paper is to build a training system based on rPPG and fitness machines to provide users with better ergonomic exercise experiences. We have built a spinning bike system that combines a camera and an adaptive controller based on heart rate feedback for tracking the desired exercise intensity. Fuzzy control is introduced in the feedback control loop by considering heart rate and heart rate variability simultaneously for better representation of the physical status. Some preliminary results are briefly presented. This research demonstrates promising performance improvement by combining rPPG heart rate estimation and fitness machine control.

In this paper, an intelligent overtaking system is developed, which includes overtaking possibility strategy (OPS), autonomous overtaking control scheme, and then successfully implemented on an autonomous vehicle. The OPS is based on the image recognition technology for detecting surrounding vehicles and lane lines, and further calculate the time to lane crossing (TLC) as the basis of overtaking or keep within your lane. Thus, this research can implement two functions, such as lane following and overtake. An autonomous overtaking control scheme using the successive linearization based model predictive control is developed to derive the appropriate throttle, brake and steering angle actuators for a car. This control approach can provide stable and safety overtaking maneuvers effectively. Finally, the proposed system has been incorporated into an electrical golf car and tested in a real-road environment, where the communication of the whole sensors, actuators as well as vehicle control unit (VCU) are used the controller area network (CAN) bus to realize control and data collection. Some of the experimental results demonstrate the feasibility of using the overtaking strategies by considering various traffic situations.

This paper proposes a novel traction control system (TCS) based on feedback sensing of multi‐state of electric scooters (i.e. vehicle‐road inclination, vehicle yaw rate, vehicle lateral fo...

This paper develops a modular multilevel inverter which integrates driving/braking control schemes in a unit for electric vehicles. The multiple driving components are used to balance surg...

Signal frequency estimation is a fundamental issue in the domain of signal processing. In this paper, we proposed a novel framework, named FreqEnet (Frequency estimation network), for estimating frequency based on deep learning method. The signal frequency estimation refers to as a regression issue and predict it with LTSM module. The framework is exceedingly concise, consisted of only three LSTM and one fully connect layers, and the running time is less than 0.3 ms on CPU (i7-7700, 3.60 GHz). Two periodic signals are generated for training our model. In addition, uniform and Gauss white noise are introduce to original signal for evaluating the robustness and generalization of the framework. In addition, the proposed method performs extremely excellence in processing latent. Even if given only one periodic piece of signal, the method could predicts a precise result. Extensive experiments demonstrate that FreqEnet achieves competitive performance of estimating frequency.

A sensorless driving/braking control system for electric vehicles is explained in the present paper. In the proposed system, a field-oriented control (FOC) was used to integrate driving and braking controls in a unified module for reducing the cost of hardware and simultaneously incorporating functional flexibility. An antilock braking system can swiftly halt a vehicle during emergency braking. An electromagnetic reverse braking scheme that provided retarding torque to a running wheel was developed. The scheme could switch the state of the MOSFETs used in the system by alternating the duty cycle of pulse width modulation to adjust the braking current generated by the back electromotive force (EMF) of the motor. In addition, because the braking energy required for the electromagnetic braking scheme is related only to the back EMF, the vehicle operator can control the braking force and safely stop an electric vehicle at high speeds. The proposed integrated sensorless driving and electromagnetic braking system was verified experimentally.

Implementation of a multifunctional contactless bidirectional charging and discharging system with the aid of giant magnetoresistance (GMR) effect for car parking guidance is proposed. Traditional Hall effect sensors can detect magnetic flux changes. However, if the changes are not significant enough to induce detectable interference voltage, there will be error detection. To remedy, a GMR sensor may detect tiny changes in the magnetic field, which will produce a larger change in resistance; this resistance is less susceptible to external noise influence while generating a relatively stable signal level. As a novel application, our research task combines a GMR sensor, a flexible magnetic stripe constituted by GMRs, a microprocessor and a wireless inductive power/data transfer module to realize a positioning control system for the parking lot's microgrid. Real-world experiments are conducted to verify the proposed approach.

Background Synthesis of a variety of biological circuits for specific functional purposes has made a tremendous progress in recent years. The ultimate goal of combining molecular biology and engineering is to realize a functional biocomputer. To address this challenge, all previous efforts work toward building up the bio-computer as the ultimate goal. To this aim, there should be a key module, named control unit (CU), to direct a serious of logic or arithmetic operations within the processor. Methods This research task develops a bio-CU to work with a bio-ALU, which is realized from the combination of previously developed genetic logic gates to fulfill the kernel function of CPU as those done in the silicon computer. Results A possible framework of the bio-CPU has demonstrated how to connect a bio-CU with a bio-ALU to conduct a fetch-decode-execute cycle of a macro instruction. It presents not only capability of 4-bit full adder but coordination of related modules in biocomputer. Conclusions We have demonstrated computer simulation for applications of the genetic circuits in biocomputer construction. It’s expected to inspire follow-up study to synthesize potential configurations of the future biocomputer.

Subspace clustering methods based on self-expressiveness model have recently attracted much attention. However, there exists a gap between subspace-preserving coefficient and the final clustering result due to the lack of graph connectivity. The problem has not been well tackled in the published literature. This paper significantly improves the graph connectivity by adding an effective projection step to the recently proposed method SSC-OMP. With this projection step, it is possible to establish a theoretical guarantee that the subspace-preserving condition leads directly to the exact clustering result, which bridges the gap. Moreover, the potential advantage of the proposed algorithm over prior methods is its robustness to noise. Experimental results demonstrate that the proposed approach enjoys a high clustering accuracy and a fast processing speed in comparison with state-of-the-art algorithms.

Smart manufacturing based on cyber-physical manufacturing systems (CPMS) has become the development trend and been widely recognized all over the world. Throughout the development trend of CPMS, one of the key issues is industrial Internet-of-Things (IIoT) with the characteristics of automation, smart connected, real-time monitoring, and collaborative control. Along with the permeation and applications of advanced technologies in manufacturing, massive amounts of data have been generated in the manufacturing process. However, the current 3th generation mobile network (3G), 4G and other communication technologies cannot meet the demands of CPMS for high data rate, high reliability, high coverage, low latency, etc., which hinders the development and implementation of CPMS. As a future advanced wireless transmission technology, 5G has a significant potential to promote IIoT and CPMS. Based on the architecture and characteristics of 5G wireless communication technology, this paper proposes the architecture of 5G-based IIoT, and describes the implementation methods of different advanced manufacturing scenarios and manufacturing technologies under the circumstances of three typical application modes of 5G, respectively, i.e., enhance mobile broadband (eMBB), massive machine type communication (mMTC), ultra-reliable and low latency communication (URLLC). Besides, the characteristics, key technologies and challenges of the 5G based IIoT are also analyzed.

Sobriety test, which commonly uses a breathalyser for estimating blood alcohol content (BAC) from a breath sample, is commonly used to detect drunk driving. The detection often gives rise to sanitary concern and violation of human right. This research proposes a new method that employs non-invasive measurement of photoplethysmography (PPG) signal for detecting BAC of the test subject under the sobriety test. The PPG signal is measured via an LED transmitter and a receiver that illuminates finger and measures the changes in lighting. Since a PPG signal contains information of systolic and diastolic blood pressure, it is possible to be used for the purpose of detecting BAC. The authors have developed a practical alcohol sobriety test system to analyse the status of alcohol intake of the subject. Extensive tests have been conducted to examine feasibility of the proposed system with an identification rate up to 85%.

In recent years, brushless DC motors (BLDCMs) have replaced brushed DC motors in the design of electric scooters (ESs). This study proposes a new antilock braking system (ABS) based on a slip ratio estimator for ES utilising the braking force generated by the BLDCM when electrical energy is released to the virtual load, yielding an effect analogous to the ABS control in gas-powered vehicles. Compared with mechanical ABS, the proposed design possesses the advantage of rapid torque responses because no mechanical parts needed. Current control design is used to adjust the braking torque, and the sliding-mode control strategy is adopted to regulate the slip ratio to attain the optimal road adhesion during emergency braking. A variety of experiments are conducted for functional and performance verification.

The digital revolution of noncontact physiological signal monitoring in clinical and home health care is underway, and deep learning techniques are incredibly popular. Camera-based physiological signal monitoring for adults has made considerable progress in recent years. However, most of existing methods and datasets are developed for adult subjects, and until now, there has been no neonatal public database that is collected for developing deep learning method. Thus, in this paper, we introduce a large-scale newborn baby database, named NBHR (newborn baby heart rate estimation database), to fill the abovementioned knowledge gap. A total of 9.6 h of clinical videos (1130 videos totaling 921 GB) and reference vital signs are recorded from 257 infants at 0–6 days old. The facial videos and corresponding synchronized physiological signals, including photoplethysmograph information, heart rate, and oxygen saturation level, are recorded in our database. This large-scale database could be used to develop deep learning methods to estimate heart rate or oxygen saturation levels. Furthermore, a multitask deep learning method, called NBHRnet, is proposed to estimate heart rate based on the NBHR database, and the model is succinct that it can be deployed on a computer without GPUs. The experimental results indicate that NBHRnet yields competitive performance in predicting infant heart rate, with a mean absolute error of 3.97 bpm and a mean absolute percentage error of 3.28%; additionally, it can estimate heart rate almost instantaneously (2 s/60 frames). Our datasets are freely publicly available by request.

In electronic systems, dynamic random access memory (DRAM) is one of the core modules in the modern silicon computer. As for a bio-computer, one would need a mechanism for storage of bio-information named 'data', which, in binary logic, has two levels, logical high and logical low, or in the normalised form, '1' and '0'. This study proposes a possible genetic DRAM based on the modified electronic configuration, which uses the biological reaction to fulfil an equivalent RC circuit constituting a memory cell. The authors implement fundamental functions of the genetic DRAM by incorporating a genetic toggle switch for data hold. The results of simulation verify that the basic function can be used on a bio-storage module for the future bio-computer.

The main goal of this paper is to develop a deep-learning-based instance segmentation of lane detection for time to lane crossing (TLC) estimation. As is well known, the TLC strategy can build lane departure warning systems (LDWs) with enhanced predictive capabilities which play the role of security early warning in order to prevent dangerous driving situations. LDWs quite relies on the accurate detection of the road markings. Instance segmentation is a task to detect specific objects in an image and create a mask around the object. We use an evolved fully convolutional networks (FCNs) based instance segmentation to yield the high-quality segmentation maps with finer details. It is an effective approach to providing us the high accurate lane detection for LDWs. Time to lane crossing (TLC) is a kind of lane departure indicator in LDWs. For TLC computation, both straight and curved vehicle paths are considered. Thus, the road curvature is an important variable in computations. In this paper, a lane mark fitting algorithm based on inverse perspective mapping (IPM) and sliding window technologies are proposed to compute the road curvature. TLC is duration available for the driver before any lane boundary crossing. The experimental results demonstrate that the proposed deep learning-based instance segmentation can significantly detect the lane. The experiment results illustrate that the proposed TLC estimation strategy can significantly enhance the lane marks recognition accuracy and then provide drivers with timely warnings to avoid unintentional lane departure.

Estimation of the visual pulse rate (also called heart rate) refers to extraction of the pulse rate from a facial video. With the studies on extracting photoplethysmography (PPG) signals from a facial video, the non-contacted measurement method has aroused great interest among researchers over the past few years. In this study, a novel one-stage spatio-temporal framework, namely PRnet, is proposed to estimate the pulse rate from a stationary facial video. First, visual pulse rate estimation is defined as a regression task based on deep neural networks, in which a video is mapped to a pulse rate value. Then, 3D convolutional neural networks (Conv3D) and Long short-term memory (LSTM) modules are used to extract spatial and latent temporal information that is hidden in a video. Subsequently, one fully connected layer is applied in the last layer of PRnet to estimate the pulse rate directly. Based on the exquisite framework design, our proposed method realizes competitive performance, especially in terms of processing latency, since it does not rely on power spectral density (PSD) and traditional Fast Fourier Transform (FFT) algorithms. Using our method, only 60 frames of video (2 s) are required for the robust prediction of the pulse rate, whereas 6–30 s of video are typically required for other methods. Finally, a novel visual pulse rate estimation database, which includes pulse rate range at various times of day, is collected to evaluate the proposed framework. The results of extensive experiments demonstrate that PRnet performs competitively while compared with state-of-the-art methods.

Most electric vehicles use regenerative brakes, since this kind of braking system design recycles electromotive force to increase electric power endurance during braking. This research proposes a sensor-free, integrated driving and braking control system that uses a space-vector-pulse-width module to synthesize stator current by purpose. It calculates the rotor position angle of the motor by detecting variation in the stator current and completes a closed-loop control. When the motor receives a brake command, the controller changes the inverter-switching sequence to generate reverse torque and a magnetic field to complete the driving or braking function using field-oriented control (FOC). This provides a smoother and more accurate motor control than sinusoidal commands with Hall feedback. Compared to the regenerative brake and rheostatic brake, the proposed braking system has a powerful braking torque and shorter reaction time. Comparisons of reaction times for a modified four-wheel electric vehicle equipped with a permanent magnet synchronous motor under neutral-sliding-status, FOC based braking, and short-circuit braking were conducted.

Genetic networks play an important role in systems biology as they explain the interactions between genes and proteins. However, the genetic networks are described by dynamical systems with nonlinear uncertainties and usually affected by stochastic internal fluctuations, and stochastic external disturbances. The design addressed in this paper is concerned with robust state estimator of stochastic genetic networks in the presence of nonlinear uncertainties. The objective is to estimate the true concentrations of mRNAs and proteins of the noisy nonlinear genetic networks. Based on the notion of Lyapunov functions, we improve the design condition for the robust estimator to ensure that the estimation error satisfies H∞ performance criterion. The sufficient condition is derived in terms of parameter-dependent linear matrix inequalities, which are convex constraints, and can be efficiently solved via the sum-of-squares technique. We provide two numerical examples of real genetic networks to illustrate the effectiveness of the proposed method.

The heart rate of subjects is extracted from video data during exercises and is treated as a negative feedback parameter for the control of fitness devices. The probability distribution in RGB space of the parameters of the skin reflection model is analyzed based on the experimental data taken under a wide range of environmental settings. A novel pulse extraction algorithm is proposed based on this distribution, which sets aside distribution centers as the model parameters for preliminary pulse separation and adopts cascade least mean square adaptive filters to compensate for modeling errors. A Gaussian distribution-based heart rate estimation algorithm is employed for heart rate stabilization. In addition, the concept of heart rate negative feedback control is introduced, e.g., the treadmill speed and incline can be adjusted interactively based on the subject's heart rate. The heart rate measurement accuracy and the control scheme have been evaluated by a self-collected benchmark dataset and a prototype system. The heart rate measurement accuracy is increased over the state-of-the-art algorithms by more than 10% on average. The heart rate negative feedback control improves human–machine interaction performance compared with a traditional control scheme that uses the predefined program regardless of the subjects’ physical state. The proposed technique pioneers new possibilities for the usage of fitness devices.

Remote photoplethysmography (rPPG) has recently attracted much attention due to its non-contact measurement convenience and great potential in health care and computer vision applications. However, almost all the existing rPPG methods are based on uncompressed video data, which greatly limits its application to the scenarios that require long-distance video transmission. This paper proposes a novel framework as a first attempt to address the rPPG pulse extraction in presence of video compression artifacts. Based on the analysis of the impact of various compression methods on rPPG measurements, the problem is cast as single-channel signal separation. The framework consists of three major steps to extract the pulse waveform and heart rate by exploiting frequency structure of the rPPG signal. A benchmark dataset which contains stationary and motion videos has been built. The results show that the proposed algorithm significantly improves the SNR and heart rate precision of state-of-the-art rPPG algorithms on stationary videos and has a positive effect on motion videos at low bitrates.

Nowadays, technology of data transmission is growing fast and has been well applied to different fields depending on practical demands. In which, internet-of-things (IoT)-related applications are the most popular mechanism with respective application scenarios. This study integrates ECG-based biometric authentication to create a sophisticated application for extreme demand of access security to the IOT system. This mechanism not only increases the users' convenience, but greatly protects privacy of the users.

There are two novel techniques in the research of wireless power transfer (WPT), i.e. bidirectional WPT and bidirectional data transmission. The bidirectional WPT allows vehicles to be charged and provide charge to other accepting objects; the bidirectional data transmission allows the WPT system charging without any additional communication device. Both of them are sensitive to the induction coil alignment. Due to the misalignment between the transmission coil and the receiver coil, the output power will result in a drop. The misalignment problem affects the power transmission efficiency significantly. This paper combines bidirectional wireless power transfer with bidirectional data transmission, and constructs a complete bidirectional charging system through a fuzzy control strategy to resolve the issue.

Currently, electric vehicle technology is becoming more and more mature. Although the anti-lock braking system (ABS) has been commonly applied, most electric vehicles (EVs) still use traditional hydraulic-based disc braking, which has the drawbacks that vehicle wheels are is easy to skid in the rainy day, and easy to be abraded during emergency brake. As a novel method of braking, regenerative braking has the advantages of compact structure, sensitive response, reliability and controllable braking distance. In this research task, a regenerative driving and braking control system for EVs with satisfactory braking performance is proposed. When braking, a motor is converted into a generator-the acquired energy can be used to generate reverse magnetic braking torque with fast response. On this basis, an anti-lock braking controller is realize. A PID controller is also designed to drive the motor and a fuzzy slip ratio controller is designed and used to obtain the optimal slip ratio. Finally, real-world experiments are conducted to verify the proposed method.

We propose a novel single face image super-resolution method, which is named Face Conditional Generative Adversarial Network (FCGAN), based on boundary equilibrium generative adversarial networks. Without taking any prior facial information, our approach combines the pixel-wise L1 loss and GAN loss to optimize our super-resolution model and to generate a high-quality face image from a low-resolution one robustly (with upscaling factor 4 × ). Additionally, Compared with existing peer researches, both training and testing phases of FCGAN are end-to-end pipeline without pre/post-processing. To enhance the convergence speed and strengthen feature propagation, the Generator and Discriminator networks are designed with a skip-connection architecture, and both using an auto-encoder structure. Quantitative experiments demonstrate that our model achieves competitive performance compared with the state-of-the-art models based on both visual quality and quantitative criterions. We believe this high-quality face image generated method can impact many applications in face identification and intelligent monitor.

The potential of genetic clock lies in its role to triggering logic reaction for sequential biological circuits. In general, biochemical reaction of the biological system is extremely slow. However, a square wave generator used as a genetic clock the transient response should be fast enough to catch the reaction change between two logic levels. Therefore, the requirement for instantaneous changes in logic status is not likely to exist in biological systems. This paper presents a method of synthesizing a genetic clock generator based on the combination of a toggle switch with two biological logic gates. A dual repressor is used to connect the two fundamental biologic circuits. Analysis of the characteristic responses of this genetic clock with its relation to the key parameters is provided.

HomePlug AV (HPAV) is a standard developed by HomePlug Powerline Alliance (HPA) for power line communication. In HomePlug AV, it uses a technology named Carrier Sense Multiple Access with Collision Avoidance (CSMA/CA) to reduce collision happened in network. However, when network nodes increase, the contention window number may not be wide enough. It will cause collision probability to increase. In this paper, we introduce a new idea of adaptive contention window which will produce suitable contention window under actual network environment. Our method only requires the information of CSMA/CA parameters. It means that one doesn’t need to correct the original CSMA/CA procedure but substitutes old parameters by the new ones. Simulation experiments conducted in the network simulator NS3 show that compared with HomePlug AV, our method promotes throughput significantly when the node number increases.

This paper gives an idea of realization of an integrated driving-braking control unit for electric bikes based on the proportional-integral-derivative (PID) control. We apply field oriented control (FOC) for the driving unit and braking section design, two ways are jointed together for adjustment of the braking torque of a customized brushless DC hub motor (BLDCHM). The major one is to proceed the idea from software design, using a program to alternate the duty cycle of pulse width modulated commands for braking torque adjustment according to the road condition. The design has been practically realized for an electric bike with a BLDCHM. All results have been extensively verified via a variety of real-world experiments.

It's a major drawback of the battery charging in traditional electric vehicles is that it relies on the use of a plug-in device for battery charging. This research proposes a wireless power and bidirectional data transmission scheme, data related to battery status, vehicle identification number, or emergency messages can be mutually transmitted between two isolated units via an LC tank. The primary unit employs an inverter to yield alternating current and power flow to the load via mutual inductance. The secondary unit transfers data by adjusting current of load, and the primary unit receives data based on the zero-voltage switching (ZVS) method. The primary unit transfers command by trimming the current's curve and the secondary unit receives command and make decoding using the period of carrier wave. The design scheme is useful to handle the situation of emergency by sending back the message to the primary unit to make an emergent halt.

Increasing applications of fundamental biological gates have been successfully built during this decade. Proceeding to the current development, this study presents a genetic arithmetic and logical unit (ALU) design based on a series of genetic logic gates. The system level's architecture consists of three parts: temp register, ALU and accumulator register. Using the concept of the ALU on the digital computer, the authors present the fundamental function of the genetic ALU via full adder register and also build the bio-storage devices to store data generated from the genetic ALU. The system in this study shows the capability of computing and storage on the biocomputer.

An electrocardiogram (ECG) records changes in the electric potential of cardiac cells using a noninvasive method. Previous studies have shown that each person's cardiac signal possesses unique characteristics. Thus, researchers have attempted to use ECG signals for personal identification. However, most studies verify results using ECG signals taken from databases which are obtained from subjects under the condition of rest. Therefore, the extraction and analysis of a subject's ECG typically occurs in the resting state. This study presents experiments that involve recording ECG information after the heart rate of the subjects was increased through exercise. This study adopts the root mean square value, nonlinear Lyapunov exponent, and correlation dimension to analyse ECG data, and uses a support vector machine (SVM) to classify and identify the best combination and the most appropriate kernel function of a SVM. Results show that the successful recognition rate exceeds 80% when using the nonlinear SVM with a polynomial kernel function. This study confirms the existence of unique ECG features in each person. Even in the condition of exercise, chaotic theory can be used to extract specific biological characteristics, confirming the feasibility of using ECG signals for biometric verification.

Sophisticated technologies realized from applying the idea of biometric identification are increasingly applied in the entrance security management system, private document protection, and security access control. Common biometric identification involves voice, attitude, keystroke, signature, iris, face, palm or finger prints, etc. Still, there are novel identification technologies based on the individual's biometric features under development [1-4].

This invention proposes a novel light emitting diode (LED) lighting (dimmable) control scheme to transmit digital data through a magnetic field generated by a flyback driver that utilizes digitized data to adjust the brightness of LEDs for potential applications. This design would eliminate the cost of establishing wireless transmission hardware by simply relying on the magnetic field for communication to meet the management of the lighting control system. The method used a frequency-shift keying (FSK) technique on the secondary side of the system to send digitized data to the primary side. The primary side of the system interpreted the control commands by detecting the frequency change, and the corresponding lighting control was decoded. The inner communication connected the primary and secondary sides to the transformer through wirelessly transmitted data, which eliminated the requirements of optical coupling and peripheral circuits. For extended applications, the designed system can be combined with sensors at home for lighting management with the benefits of energy saving and potential emergency warnings.

The construction of an artificial biological logic circuit using systematic strategy is recognised as one of the most important topics for the development of synthetic biology. In this study, a real‐structured genetic algorithm (RSGA), which combines general advantages of the traditional real genetic algorithm with those of the structured genetic algorithm, is proposed to deal with the biological logic circuit design problem. A general model with the cis ‐regulatory input function and appropriate promoter activity functions is proposed to synthesise a wide variety of fundamental logic gates such as NOT, Buffer, AND, OR, NAND, NOR and XOR. The results obtained can be extended to synthesise advanced combinational and sequential logic circuits by topologically distinct connections. The resulting optimal design of these logic gates and circuits are established via the RSGA. The in silico computer‐based modelling technology has been verified showing its great advantages in the purpose.

Biochemical networks are not only complex but also extremely large. The dynamic biological model of great complexity resulting in a large number of parameters is a main difficulty for optimization and control processes. In practice, it is highly desirable to further simplify the structure of biological models for the sake of reducing computational cost or simplification for the task of system analysis. This paper considers the S-system model used for describing the response of biochemical networks. By introducing the technique of singular value decomposition (SVD), we are able to identify the major state variables and parameters and eliminate unimportant metabolites and the corresponding signal transduction pathways. The model reduction by multiobjective analysis integrates the criteria of reactive weight, sensitivity, and flux analyses to obtain a reduced model in a systematic way. The resultant model is closed to the original model in performance but with a simpler structure. Representative numerical examples are illustrated to prove feasibility of the proposed method.

Efforts have been made to establish computer models of genetic oscillation. We have developed a real structured genetic algorithm (RSGA) which combines advantages of the traditional real genetic algorithm (RGA) with those of the structured genetic algorithm (SGA) and applies it as an optimization strategy for genetic oscillator design. For the generalized design, our proposed approach fulfils all types of genes by minimizing the order of oscillator while searching for the optimal network parameters. The design approach is shown to be capable of yielding genetic oscillators with a simpler structure while possessing satisfactory oscillating behavior. In silico experiments show effectiveness of the proposed algorithm to genetic oscillator design. In particular, it is shown that the proposed approach performs better than the traditional GAs in the sense that a cheaper structure of genetic oscillators can be obtained.

This A fundamental memory unit in traditional computers is typically constituted by several MOSFETs. For biological systems, it is uneasy to realize such a unit for data memorization. How to synthesize a specific storage unit is a preliminary but an important step toward the success of future bio-computers. This paper proposes a structure of a fundamental memory unit necessary with I/O configuration for data read and write. The simulation study has been conducted for verification.

Power line communication (PLC) has been used to transmit and receive digital data via power line in wide application. However, power lines weren’t built for data transmission originally. In practice, data transmission is commonly subjected to switching noise by the multi-path effect. The objective of this research is to establish a platform for easily tune the controller for motor control system under the PLC environment. We build up a dynamic model to simulate the power line environment for communication and propose a frequency-shift keying (FSK) technique to modulate and demodulate the signal for the purpose of network control in the disturbed feedback control loop. A modified proportional-integralderivative controller (PID controller) on positioning control a DC servo motor is proposed to against noise corruption while achieving tracking performance.

This study proposes a newflight route-planning technique for autonomous navigation of unmanned aerial vehicles (UAVs) based on the combination of evolutionary algorithms with virtual potential fields. By combining a radial forcefieldwith a swirling forcefield, three-dimensional virtual potentialfields are constructed for repelling infeasible UAV flight routes from threatening zones. To ensure feasibility, major flight constraints are considered when searching for the optimal flight route. This study examines both singleand multiple-obstacle cases to determine the efficiency of the proposed flight route planner. The UAV navigation method uses an offline planner in known environments and an online planner for flight route replanning when popup threats emerge. Both planners were tested under various scenarios. The results show that the proposed planner can efficiently enable the safe navigation of UAVs.

Synthetic biology is highly valued in the recent decade. In a previous study, Elowitz and Leibler ( Nature , vol. 403, pp. 335-338, 2000) have constructed a biological oscillator in consisting of three genes, and found out its mathematical expressions. Designing the optimal transcription rates of mRNA and the decay rates of protein concentration to track desired sinusoidal signal and achieve the best oscillation have been becoming a challenge problem since then. Actually, design of an oscillator can be regarded as a tracking design problem from the control engineer's viewpoint. Genetic algorithm (GA) bears the feature of searching the global optimum for the optimization problem. However, subject to the fixed solution structure, the results may not be the cheap ones. In this paper, we introduce the real structure genetic algorithm (RSGA) to solve the design problem of synthetic biological oscillators. The design approach is shown to be capable of yielding genetic oscillators with a cheaper structure.