An 8-tap feed-forward equalizer (FFE) and 10-tap decision feedback equalizer (DFE) were designed for the IEEE 802.3u 100Base-TX specification. The weights of these adaptive filters are updated with a sign–sign least-mean-square (SSLMS) algorithm. To ensure the flexibility of the circuits for various environments channel lengths, the equalizers are designed such that the number of taps can be adjusted to between 1 and 8 for the FFE and 1 and 10 for the DFE. Results indicated that the equalizer can compensate for channel delays of more than 20 dB, and it achieved a bit error rate of 2 × 10−3. Both FFE and DFE not only mitigate signal distortion but also significantly eliminate inter-symbol interference (ISI) in high-speed serializer/deserializer (SerDes) communication systems. The application-specific integrated circuit (ASIC) was designed using Verilog Hardware Description Language (HDL) and implemented with the TSMC 90-nm CMOS 1P9M standard cell process. In simulations, the chip area, delay cycle, and logic gate counts were 845.445 × 845.445 μm2, 12 cycles, and 75 187 gates, respectively. The supplied voltage and frequency of the proposed adaptive DFE were 1.2 V and 250 MHz, respectively.

This study proposes an Internet of Things (IoT)-based smart home system that sends and receives packets through the RS232 protocol and processes them using deep learning. A Field-Programmable Gate Array (FPGA) development board serves as a transceiver, operating a universal serial bus (USB) interface and a Wi-Fi module. The proposed system comprises a built-in wireless transceiver, a set of sensors, a development board running a deep learning algorithm, an MQTT communication protocol, and a terminal device controller. The objective is to implement an IoT -based smart home system with wireless data transmission. Node-RED is used to develop a comprehensive smart home system on the server side for IoT applications, facilitating data access, data processing, and terminal device control. The aim is to achieve automatic regulation and ensure comfortable indoor temperatures. In experiments, the root mean squared error difference between actual and predicted temperatures was approximately 0.4426 °C. After evaluation experiments with the FPGA development board, an application-specific integrated circuit (ASIC) based on the TSMC 0.18-μm CMOS process was used. Simulation results indicate that the chip area is approximately 1.186 × 1.188 mm2, and the dynamic power consumption is approximately 8.1674 mW at a power supply of 1.8 V and operating frequencies of 50 and 5 MHz.

With the development of technology, the automation industry has gradually improved, and the application of the visual-inertial system has become increasingly prosperous. Self-driving cars and autonomous mobile robots often use the visual-inertial system as a state estimator, and their image information can be used in the artificial intelligence part to provide more information about the robot. The combination of a monocular camera and an inertial sensor has the characteristics of light weight and low power. Monocular Visual-Inertial SLAM is a system that relies on monocular cameras and inertial sensors to perform localization and mapping. Monocular Visual-Inertial SLAM restores its vector to scale with the help of known extrinsic parameter information. However, compared with other methods, it is necessary to be careful in estimating the gyroscope bias of the inertial sensor. The bias and noise of the inertial sensor will directly affect the results of pre-integration, as well as the accuracy of the visual-inertial scale recovery. This phenomenon is called scale uncertainty, which results in feature points with uncertain scale or depth, rapidly reducing the accuracy of pose estimation. This paper proposes an architecture of visual-inertial based on Structure-Scale Adaptivity. In this study, the tightly coupled residual between the structure scale and the pose is designed to provide adaptivity according to the feature conditions, providing system structure and scale constraints, and thus suppressing the problem of scale uncertainty. This study is compared with state-of-the-art algorithms and succeeds in scenarios where other algorithms have failed. It also obtains the best accuracy results in the overall test. Finally, we evaluate our proposed method on VCU-RVI and KITTI datasets, demonstrating the proposed algorithm's effectiveness and feasibility for monocular visual-inertial SLAM.

The development of monocular visual simultaneous localization and mapping (VSLAM) has slowly begun in recent years. At present, the sensors used for VSLAM include monocular, binocular, or depth. For visual mapping, two problems will be encountered and the mapping cannot be performed. One is when there are not enough feature points, the camera's pose at the next moment cannot be estimated, such as a wall. The other is the VSLAM of dynamic environment changes may not be recognized as the same object because the feature matching needs to be coded through its surrounding environment, so it is easy to lose track when encountering changes in light. Compared with binocular and depth, monocular vision lacks depth information, but because it is cheap and easy to install, it needs to be used by multiple people. The current research proposes adding other information, including the camera height, the scene of the reference object and depth estimation by learning methods. The study uses the OpenVSLAM architecture to estimate the camera height scale, and proposes the mechanism be based on the change in the average scale of the first five key frames, with the average scale being updated at the same time to correct the current scale. Through this method, the drastic changes in scale are corrected, and the accuracy of trajectory positioning is improved. We also evaluate our proposed method on a real KITTI Dataset and demonstrate the proposed algorithm is effective and feasible for monocular visual SLAM.

Robots are widely used as unmanned vehicles in smart factories. In order to operate the robot in a known environment, the robot must be able to plan the path. The planned path must enable the robot to reach a destination from the starting point and the robot must avoid all obstacles during movement. This study uses a four-parameter logic curve path planning method that uses a closed formula solution and a curve with minimal design parameters to quickly generate an ideal path. The characteristics of the curve are used to derive the S and half-S curves as the solution path. The shortest path is used as the selection reference target to select parameters B and C for the four-parameter logic curve. For the S path, the best solution is chosen. The half -S curve is limited by the elastic end-point heading angle, which gives a unique set of parameter solutions. The generated path does not allow the robot to completely avoid obstacles so a hierarchical half-S curve path planning mechanism is used. A via point is generated at the collision point using the gradient vector for the edge of the obstacle. The planner continues to perform half-S path planning until the path planning ends.

This research project aims to build a LoRa-based Internet of Things (IoT) secure localization system and application based on multi-sensor fusion calculation. The system of this project comprises LoRa hosts, which receive the signals from various nodes, and are connected to a multi-sensor fusion arithmetic system through a wireless network. This study crosses domains and integrates related engineering automation, network security technology, multi-sensor fusion calculation design, and the LoRa localization technique, and the research findings are expected to contribute to the network security of the defense industry and research on the LoRa IoT localization system.

This paper proposes the adaptive functional coupling recurrent cerebellar model articulation controller (AFCRC). The AFCRC system contains an integrated error function, a TSK fuzzy compensator, and a novel cerebellar model articulation controller (CMAC), which is developed based on the concept of a recurrent neural networks (RNNs) and a functional coupling NN (FCNN). This study uses the proposed AFCRC to control the direct torque control drive system of a switched reluctance motor (SRM), and compares it with the traditional CMAC and FCMAC. The experimental results reveal that the root mean square error (RMSE) is used as a performance index for comparing of the traditional CMAC, FCMAC, and AFCRC, respectively. The results show that the proposed AFCRC exhibits the robustness against external disturbances. Thus, the proposed control strategy is advantageous at various speed commands and has improved dynamic responses.

A novel adaptive sliding diagonal recurrent fuzzy cerebellar model articulation controller (ASDRC) is proposed by this study. ASDRC includes the inputs by a sliding surface into a diagonal recurrent fuzzy cerebellar model articulation controller (DRCMAC). The ASDRC enables cerebellar model articulation controller (CMAC) to exhibit both static and dynamic characteristics, indicating that the use of DRCMAC improves the disadvantage of conventional CMAC while exhibiting the advantages of fuzzy CMAC (FCMAC). Regarding the proposed ASDRC, the adaptive update law determining the memory weights, means of Gaussian functions, and standard deviations of Gaussian functions is yielded by the Lyapunov stability theory; moreover, the gradient descent method is applied to yield the recurrent weight update law. Using the adaptive update law and recurrent weight update law of the ASDRC to implement online adjustment ensures system stability. To demonstrate the performance of the proposed ASDRC, this study applies it to the direct torque control (DTC) systems of an induction motor to perform experiments. The root-mean-square error is used as an assessment indicator to compare the results of the proposed controller with those of the FCMAC. The experimental results prove that the ASDRC has more excellent response, and its performance is superior to that of the FCMAC.

This study aims to design an adaptive output recurrent cerebellar model articulation controller (AORCMAC), which is embedded into the direct torque control (DTC) system of an induction motor as the speed controller. Similar to the conventional cerebellar model articulation controller (CMAC), the designed AORCMAC also has the advantages of rapid learning, simple architecture, online training, and nonlinear learning abilities. In addition, by incorporating the Gaussian function and recursion, the AORCMAC provides satisfactory dynamic response. This study compares the AORCMAC with the adaptive fuzzy CMAC (AFCMAC) and uses the root mean square error as the indicator for performance assessment. The experiment results verify that the proposed AORCMAC has rapid speed response, and its performance is superior to that of the AFCMAC. The AORCMAC maintains excellent robustness despite changes to the motor parameters and the addition of external load disturbances.

This paper investigates the type-2 T-S fuzzy multiple feedback-loop guaranteed cost controller design for uncertain singular systems with transmission and state delays. Based on the type-2 T-S fuzzy theory, this work constructs a mathematical model for a class of nonlinear uncertain singular time-delay systems. Using the parallel distributed compensation concept with Lyapunov theory and linear matrix inequality technique, a robust guaranteed cost fuzzy controller is designed with the multiple feedback-loop structure to stabilize the considered system with guaranteed cost performance. Finally, an optimization procedure is presented to reduce the upper bound of guaranteed cost. According to the simulation results, when parametric uncertainties and transmission and state delays exist simultaneously, it indicates that the proposed guaranteed cost controller demonstrates better design flexibility. Also, the closed-loop system is robustly stable and the upper bound of guaranteed cost is decreased.

This paper presents an adaptive sliding self-organizing fuzzy controller (ASSOFC) designed using fuzzy theory and a self-organizing algorithm. Composed of a conventional fuzzy controller (FC) and self-organizing algorithm, the ASSOFC adopts the sliding surface signal as an input, uses the algorithm to adjust the central position of the output consequent membership function of the FC, and, by fuzzy control, regulates the learning rate and fuzzy rules in real time to improve control performance. The ASSOFC is embedded into the direct torque control system of a switched reluctance motor (SRM) as a speed controller, and the performance and feasibility of the controller were validated. The experimental results indicate that the root mean square error values for the ASSOFC at various speed ranges are lower than those for a conventional FC, indicating that the proposed controller provides a superior speed response for SRMs.

This study proposed a fuzzy excitation controller to reduce noise and torque ripples for switched reluctance motors. The design of the controller is simple and can generate appropriate turn-on and turn-off angles according to the speed of torque error in order to improve the torque response. At the motor speed of 300 rpm with one Nm load, the experimental results showed that the implantation of a fuzzy excitation controller in the driver system substantially improved the steady state torque ripples generated when compared to those generated by traditional controllers (at fixed excitation angles), especially at low speeds.

In a client-server distributed speech recognition (DSR) application, speech features are extracted and quantized at the client-end, and are sent to a remote back-end server for recognition. Although the bandwidth constrains are mostly eliminated, data packets may be lost over error prone channels. In order to reduce the performance degradation because of frame missing, a frequently used error concealment approach is to restore a full frame rate (FFR) observation sequence for recognition at the back-end. In this paper, an alternative approach is proposed to deal with observations with lost frames. This approach at first extracts the most reliable reconstructed reduced-frame-rate (RFR) observation sequence from the received data at the back-end, and then decodes it with an adapted hidden Markov model (HMM) that compensates the mismatch between the FFR trained model and the RFR test data. Experimental results show that a DSR system using the proposed method can achieve the same level of accuracy as an FFR data reconstruction method and significantly lessens the computation time. From the viewpoint of user capacity of a DSR system, we find that the proposed method is capable of serving much more client users without any extra cost of installing new equipment.

This paper applies the Taguchi method to filter out the number of input neurons and increases the training efficiency of the dynamic structural neural networks. In order to avoid that omitting the harmonics may affect the fault diagnosis result, this work establishes an index for the fault identification which is based on the features of the first and second harmonics. Together with the identification results of dynamic structural neural network, the diagnosis can be done. The experimental results indicate the proposed method can reduce the iterations dramatically.

By referencing the adaptive stator flux estimator (ASFE) framework in the model reference adaptive system (MRAS), this study designed an adaptive rotor speed estimator and a stator resistance estimator, and applied the Takagi-Sugeno-Kang (TSK) fuzzy system and projection algorithms to the estimators to establish an induction motor direct torque controlled system without a speed sensor and possessing stator resistance adjustment abilities. In addition, the adaptive TSK fuzzy controller (ATSKFC) was adopted as the speed controller of the system, and was capable of online learning. The transient response was improved by the integration of a refined compensation controller.

This paper proposes a single-stage high-efficacy fly back power-factor-correction (PFC) converter with optimization efficiency control for driving multi-string light-emitting diodes (LEDs). The LED driver consists of a fly back converter with PFC mechanism and a constant-current drive circuit with functionalities of efficiency optimization and dimming control. The proposed single-stage LED driver topology features benefits of high power factor and low total harmonic distortion (THD) in low-cost outlay. The pulse width modulation (PWM) dimming mechanism cooperating with the constant-current control circuit completes the LED dimming control. In order to reduce the power dissipations of the dimming circuits, a dynamic voltage regulation (DVR) control is presented to regulate the LED supply voltage by means of the sensing of the drain voltage of the MOSFET in the current controller. While maintaining the desired LED brightness, the DVR technique can minimize the voltage drop of the dimming circuit to enhance the LED driver efficiency further. A 30W white LED driver is devised and a corresponding driver prototype is realized. Testing results are shown experimentally to verify the effectiveness and performance improved of the proposed scheme.

In this paper, we present a proposed method for analyzing Raman spectra of Functionalized multiwall carbon nano-tubes (MWCNTs) by using empirical model decomposition (EMD). Then, Hilbert-Huang transform (HHT) is adopted to analyze Raman spectra of functionalized MWCNTs. we demonstrate the performance of HHT compare with fast short time Fourier transform (STFT) and enhanced Morlet transform (EMT). The experimental results show that the proposed method performs a good decomposition for identifying D band and G band pattern in MWCNTs.

This paper presents a practical and effective novel approach to solve the Disaster Prevention and Alert (DPA) management problem. The problem is usually caused by the traditional DAC approach in building's Fire Prevention and Fighting (FPF) system. Web-Enabled Interface/Controller (WEIC), Human-Machine Interface (HMI) display and Data Acquisition and Control (DAC) technologies are applied. Techniques of formalization and modeling of WEIC automation are presented. The benefits of Web-page automation philosophy is to aim at Web-view stylistic managing of all critical functions for monitoring, operating and maintaining. Through this process, communication that supports local and/or remote viewing, the real-time data/ information will be indicated on the browser-based terminals anytime and anywhere. The suggested methods of sequent structuring allow HMI/DAC models using algorithm to develop Web-page DPA management effectively are described. In addition, an actual case of WEIC based HMI/DAC automation system in existing building's FPF application is simulated to validate the feasibility of the methods proposed.