Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional ...neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance.
Brain organoids derived from human pluripotent stem cells provide a highly valuable in vitro model to recapitulate human brain development and neurological diseases. However, the current systems for ...brain organoid culture require further improvement for the reliable production of high-quality organoids. Here, we demonstrate two engineering elements to improve human brain organoid culture, (1) a human brain extracellular matrix to provide brain-specific cues and (2) a microfluidic device with periodic flow to improve the survival and reduce the variability of organoids. A three-dimensional culture modified with brain extracellular matrix significantly enhanced neurogenesis in developing brain organoids from human induced pluripotent stem cells. Cortical layer development, volumetric augmentation, and electrophysiological function of human brain organoids were further improved in a reproducible manner by dynamic culture in microfluidic chamber devices. Our engineering concept of reconstituting brain-mimetic microenvironments facilitates the development of a reliable culture platform for brain organoids, enabling effective modeling and drug development for human brain diseases.
As autonomous vehicles (AVs) are advancing to higher levels of autonomy and performance, the associated technologies are becoming increasingly diverse. Lane-keeping systems (LKS), corresponding to a ...key functionality of AVs, considerably enhance driver convenience. With drivers increasingly relying on autonomous driving technologies, the importance of safety features, such as fail-safe mechanisms in the event of sensor failures, has gained prominence. Therefore, this paper proposes a reinforcement learning (RL) control method for lane-keeping, which uses surrounding object information derived through LiDAR sensors instead of camera sensors for LKS. This approach uses surrounding vehicle and object information as observations for the RL framework to maintain the vehicle's current lane. The learning environment is established by integrating simulation tools, such as IPG CarMaker, which incorporates vehicle dynamics, and MATLAB Simulink for data analysis and RL model creation. To further validate the applicability of the LiDAR sensor data in real-world settings, Gaussian noise is introduced in the virtual simulation environment to mimic sensor noise in actual operational conditions.
Exosuits have been broadly researched owing to their benefits from soft and deformable nature. However, compared to exoskeletons, the exosuits have disadvantages in that the deformation of suit and ...human tissue can cause dissipation, leading to low force transfer efficiency. In this study, we explore the force capability and human-suit stiffness depending on the anchor point positions of the exosuit, introducing a better understanding of exosuit design. We found the relationships between the anchor point position and the force capability, and the anchor point position and the human-suit stiffness by conducting human subject experiments. When the distance between the anchor point of the waist belt and the anchor point of the thigh brace increased, the force capability increased, whereas the human-suit stiffness decreased. Also, statistical analyses are implemented to verify significant differences according to the anchor point position with a 5% significance level. Moreover, we discuss why the capability of force transmission and the human-suit stiffness differ depending on the anchor point positions. The force capability differed with anchor point positions because of the change in the effective cable stroke. Additionally, the force capability changes nonlinearly owing to the body curve as the condition level of the anchor points changes. The human-suit stiffness is affected by the interference of the body when the assistive force is transmitted through the cable. Characteristics of the force capability and human-suit stiffness model can be used to optimize the performance of existing exosuit or to serve a valuable guide of design a new exosuit when the exosuit needs to maximize the force capability or stiffness.
Sensor fusion frameworks for indoor localization are developed with the specific goal of reducing positioning errors. Although many conventional localization frameworks without fusion have been ...improved to reduce positioning error, sensor fusion frameworks generally provide a further improvement in positioning accuracy. In this paper, we propose a sensor fusion framework for indoor localization using the smartphone inertial measurement unit (IMU) sensor data and Wi-Fi received signal strength indication (RSSI) measurements. The proposed sensor fusion framework uses location fingerprinting and trilateration for Wi-Fi positioning. Additionally, a pedestrian dead reckoning (PDR) algorithm is used for position estimation in indoor scenarios. The proposed framework achieves a maximum of 1.17 m localization error for the rectangular motion of a pedestrian and a maximum of 0.44 m localization error for linear motion.
ZnO is of great interest for large-area optoelectronic devices, e.g., flat panel displays, light-emitting diodes, transparent semiconductors, and transparent conductive oxides (TCOs) etc., owing to ...its good optical properties. In the present study, quaternary ZnO thin films are deposited on a soda lime glass substrate using Mg and group III elements, such as Al, Ga, and In, to enhance the optical and electrical properties. The structural, optical, and electrical properties of quaternary ZnO TCO materials are investigated for improved thin film solar cell performance. All of the films show a uniform microstructure without any void and crack and have a transmittance over 75% in the visible region. They possess comparable band gap differences. Especially, as for the optical properties, a Mg and Ga co-doped ZnO, MgGaZnO (MGZO) thin film shows a high optical band gap of 3.87 eV with a transmittance of about 90% in the visible region. In addition, the MGZO thin film shows improved electrical properties with the lowest resistivity of 3.97 × 10−4 Ωcm, higher carrier concentration of 1.11 × 1021cm−3, high mobility of 14.07 cm2V−1s−1 and lower sheet resistance of 7.39Ω/sq. Moreover, a wide band gap of 3.87 eV is obtained for MGZO thin films, and the performance of a Cu2ZnSn(S, Se)4 (CZTSSe) photovoltaic device fabricated with a MGZO TCO layer is improved owing to higher band gap and outstanding electronic properties. The improved short circuit current results in a device with a MGZO thin film with a power conversion efficiency of 8.79%.
•Comparative study of quaternary transparent conducting oxide with Mg and different group III element (Al, Ga, In) was conducted.•Mg and group III elements co-doped ZnO were deposited on SLG by RF magnetron sputtering system.•The MGZO thin films showed resistivity of 3.97 × 10−4 Ωcm and optical band gap energy of 3.87 eV.•CZTSSe thin films solar cells with MGZO TCO layer showed higher efficiency of 8.79%.
Recent advances in physical reservoir computing, which is a type of temporal kernel, have made it possible to perform complicated timing-related tasks using a linear classifier. However, the fixed ...reservoir dynamics in previous studies have limited application fields. In this study, temporal kernel computing was implemented with a physical kernel that consisted of a W/HfO
/TiN memristor, a capacitor, and a resistor, in which the kernel dynamics could be arbitrarily controlled by changing the circuit parameters. After the capability of the temporal kernel to identify the static MNIST data was proven, the system was adopted to recognize the sequential data, ultrasound (malignancy of lesions) and electrocardiogram (arrhythmia), that had a significantly different time constant (10
vs. 1 s). The suggested system feasibly performed the tasks by simply varying the capacitance and resistance. These functionalities demonstrate the high adaptability of the present temporal kernel compared to the previous ones.
This paper introduces experiment-based modeling and optimization of a reduced-scale Electromagnetic launcher (EML) using the Design of experiments (DOE) technique. Response surface models describing ...the velocity and kinetic energy of the launched projectile were developed using the Box–Behnken method with design variable transforms, and an Analysis of variance (ANOVA) was conducted to refine the models by removing statistically insignificant terms. A bi-objective optimization problem with the maximum velocity and maximum kinetic energy as objects was considered, and a Pareto front was obtained using the generated response surfaces as the solution of the problem. Verification tests on the optimal design points were conducted to demonstrate the validity of the developed models.
Oxygen-vacancy-ordered brownmillerite oxides offer a reversible topotactic phase transition by significantly varying the oxygen stoichiometry of the material without losing its lattice framework. ...This phase transition leads to substantial changes in the physical and chemical properties of brownmillerite oxides, including electrical and ion conductivity, magnetic state, and oxygen diffusivity. In this study, the variations in the resistive switching mode of the epitaxial brownmillerite SrFeO2.5 thin film in the device were studied by systematically controlling the oxygen concentration, which could be varied by changing the compliance current during the first electroforming step. Depending on the compliance current, the SrFeO2.5 devices exhibited either low-power bipolar resistive switching or complementary resistive switching behaviors. A physical model based on the internal redistribution of oxygen ions between the interfaces with the top and the bottom electrodes was developed to explain the complementary resistive switching behavior. This model was experimentally validated using impedance spectroscopy. Finally, the gradual conductance variation in the brownmillerite SrFeO2.5 thin films was exploited to realize synaptic learning.
A metal-free organic dye (JH-1) and an unsymmetrical squaraine dye (SQ2) were used for co-sensitization of a flexible TiO2 electrode in order to obtain a broad spectral response in the visible light ...regions. Because of enhanced light absorption, the performance of the flexible plastic dye-sensitized solar cells (DSSCs) was enhanced. The dye concentration of co-sensitized TiO2 film was higher than that of individual dye-sensitized TiO2 film, leading to improved photovoltaic performance with the panchromatic light harvesting of JH-1 and SQ2 (350–720 nm). Optimum molar ratio of individual dye, dye concentration and adsorption kinetics onto the TiO2 photoelectrode, and ideal thickness of HS-TiO2 layer have been investigated. A flexible DSSC co-sensitized with the molar ratio of 60:40 (JH-1:SQ2) and TiO2 film thickness of 6 μm yielded a high photocurrent density of 12.32 mA cm−2, an open circuit voltage of 0.754 V, a fill factor of 0.68, and a power conversion efficiency of 6.31% under 1 sun illumination (100 mW cm−2). Interestingly, the co-sensitizers did not compete with each other for the absorption. Both the open circuit photovoltage and the photocurrent density were unexpectedly increased with co-sensitization which means that enhancement in photocurrents can be achieved without sacrificing the open circuit photovoltage for the co-sensitized solar cells, once the electron recombination and dye aggregation are retarded by the co-sensitization.
Display omitted
•An organic dye (JH-1) and a squaraine dye (SQ2) were used for co-sensitization of a flexible TiO2 electrode.•Because of enhanced light absorption, the performance of the flexible DSSCs was enhanced.•A DSSC with a molar ratio of 60:40 (JH-1:SQ2) yielded a power conversion efficiency of 6.31%.•Both VOC and JSC were unexpectedly increased with co-sensitization.