Precise Output Research Articles

Object detection: review and improvement based on deep learning

In recent years, with the quantum leap in deep learning, self-driving vehicle as one of its applications has been gaining tremendously increasing popularity as well as making a multitude of achievements. Object detection, which has made significant contribution to driver-less vehicle, has had been applied to a tremendously wide range of fields. However, reports relevant to automatic vehicle stating that accidents are caused by Automatic driving technology, present problems pointing out that existing target detection algorithms, which are already fairly well reliable, can probably be interfered by adverse conditions such as high temperature, raise dust and transmission loss, and be not capable of providing precise output. This paper recaps on these previous classic algorithms, and their large-scale application domain. Meanwhile, this paper presents improvements focusing on enhancing the robustness of these algorithms to overcome these problems caused by adverse conditions and improve the accuracy. Thus these improvements could augment the security of these driver-less vehicles, and eventually reduce traffic accident mortality relative to self-driving vehicles and safeguard road safety, and may potentially benefit to further research.

ChatGPT in medical research: challenging time ahead.

Since its launch, ChatGPT, an artificial intelligence-powered language model tool, has generated significant attention in research writing. The use of ChatGPT in medical research can be a double-edged sword. ChatGPT can expedite the research writing process by assisting with hypothesis formulation, literature review, data analysis and manuscript writing. On the other hand, using ChatGPT raises concerns regarding the originality and authenticity of content, the precision and potential bias of the tool's output, and the potential legal issues associated with privacy, confidentiality and plagiarism. The article also calls for adherence to stringent citation guidelines and the development of regulations promoting the responsible application of AI. Despite the revolutionary capabilities of ChatGPT, the article highlights its inability to replicate human thought and the difficulties in maintaining the integrity and reliability of ChatGPT-enabled research, particularly in complex fields such as medicine and law. AI tools can be used as supplementary aids rather than primary sources of analysis in medical research writing.

A Methodology for Fault-tolerant Pareto-optimal Approximate Designs of FPGA-based Accelerators

Approximate Computing Techniques (ACTs) take advantage of resilience computing applications to trade off among output precision, area, power, and performance. ACTs can lead to significant gains at affordable costs when efficiently implemented on Field Programmable Gate Array– (FPGA) based accelerators. Although several novel ACTs works have been proposed for FPGA accelerators, their applicability to high-assurance systems has not been explored as much. ACTs are becoming necessary in many critical Edge computing systems, such as self-driving cars and Earth observation satellites, to increase computational efficiency. However, an important question comes to mind when targeting critical systems: Does ACT optimization negatively affect the reliability of the system and how can one find optimal design architectures that blend classic mitigation techniques like Triple Modular Redundancy with approximation- and precise-based arithmetic hardware units to achieve the best possible computational efficiency without compromising dependability? This work aims to solve this research problem by introducing a Design Space Exploration (DSE) methodology that employs ACTs in arithmetic units of the design and identifies Pareto-optimal microarchitectures that balance all relevant gains of ACTs, such as area, speed, power, failure rate, and precision, by inserting the correct amount of approximation in the design. In a nutshell, our DSE methodology has formulated the DSE with a Multi-Objective Optimization Problem (MOP). Each Pareto-optimal solution of our tool finds which arithmetic units of the design to implement with precise and approximate circuits and which units to selectively triplicate to remove single points of failure that compromise system reliability below acceptable thresholds. We also suggest another formulation of the DSE into a Single-Objective constraint Optimization Problem (ScOP) producing a single optimal point, and that the user may demand, as a less time-consuming alternative to the MOP if a complete Pareto-front is not needed. Our methodology generates fault-tolerant versions of the Pareto-optimal approximate designs (or simple optimized approximate designs if the ScOP choice is picked) by selectively applying mitigation techniques in a way that the overheads of redundant resources for fault-tolerance do not negate the gains of approximation in comparison to the fault-tolerant versions of the precise design. We evaluate our method on two FPGA-based accelerators: a JPEG encoder and an H.264/Advanced Video Coding decoder. Our experimental results show significant gains in area, frequency, and power consumption without compromising output quality and system reliability compared to classic solutions that replicate all or a part of the resources of the precise design to increase dependability metrics.

Deep reinforcement learning-based controller for dynamic positioning of an unmanned surface vehicle

Dynamic positioning (DP) system is of great significance for the unmanned surface vehicle (USV) to achieve fully autonomous navigation. Traditional control schemes have problems such as model accuracy, parameter tuning, and complex design. In addition, although the deep reinforcement learning (DRL) is widely used in the field of vessel motion control, the learning efficiency is not high, and insufficient robustness in the face of changing environmental. In order to improve the anti-disturbance ability, robustness and convergence speed of the controller during training, a deep reinforcement learning control method based on priority experience replay (PER) is proposed for dynamic positioning of the USV. The mathematical models are established based on the kinematic and dynamic of the USV. Markov decision process (MDP) models are constructed according to the DP tasks. The simulation results show that compared with other DRL algorithms, the proposed method has higher reward value, faster convergence speed, higher control precision and smoother control output.

Design and implementation of high precision servo channel loading card for fatigue testing of aircraft wings

SummaryA servo channel loading card (SCLC) with high precision data acquisition and output is developed for static and fatigue testing of aircraft wings. A high‐performance processor field programmable gate array (FPGA) is at the core to control the excitation source (ES) output circuit to provide excitation for the force and displacement sensor. To improve the precision of the ES output circuit, a 3DA‐based ES auto‐calibration circuit is designed. Simulation results show that the 3DA improves the precision of the automatic calibration of the ES circuit. The sensor signals are collected through high precision analog channels, and the signals are automatically zero calibrated and numerical control gain processed. Ultimately, a voltage or current signal is generated through the drive circuit to control the electro‐hydraulic servo loading system to complete a high precision force loading test on the aircraft wings. The experimental results show that the board designed has high reliability in both acquisition and output. The ES output achieved a precision of 0.1375 mV/V, the precision of signal acquisition achieves a precision of −0.175 mV/V, and the servo drive output achieves a precision of −0.06 mV/V, meeting the expected design precision of 1 mV/V.

A Fuzzy Controller for PFN Trigger Time Sequence in Electromagnetic Railgun System

For the electromagnetic launch system, how to realize the wide pulse, fast rise, and small fluctuation of pulse forming network output current is a core problem. A trigger time sequence control method based on fuzzy theory for the pulse forming network is proposed in this paper. First, circuit models of pulse forming unit, pulse forming network, and electromagnetic rail launcher is established. Second, a fuzzy trigger time sequence controller model for pulse forming network is designed by using Simulink. Third, fixed time sequence discharge tests consisting of 20 pulsed forming units on the linear simulation load are carried out to verify the accuracy of the simulation model. Finally, discharge tests on the linear simulation load and launch tests on the electromagnetic railgun are carried out to verify the precision of the fuzzy controller output respectively. The results show that the designed fuzzy trigger time sequence controller can obtain the ideal trigger time sequence, which demonstrates the pragmatic and reliability of fuzzy control algorithm.

Impact of Microfluidic Chip Electrophoresis in Modern Analysis: An Update on Recent Trends

Abstract: The recent development of microfluidics and lab-on-a-chip technology has substantially raised interest in analytical chemistry. Since, they have demonstrated to be extraordinarily adept at precise fluid control, cell manipulation, and signal output, microfluidic chips are a useful tool for quick and in-depth single-cell investigation. This technique is cost-effective, less time-consuming, automatic, high mobility, and fast separation technique. Due to the internal chip sizes, which range from micrometers to millimeters, consumption of the samples and reagents occurs at the nanoliter and picoliter levels. The microfluidic device can fit a variety of functions onto a few centimeter-long chips. In this article, we discussed numerous preparations of microfluidic chip electrophoresis and its recent advancements. This method is useful for the detection of various small amounts of content with less time and greater efficacy. It is also useful in cancer studies, 3D inkjet printing, immunoassay investigation in cell-cell interactions, analysis of nanoparticles, dielectrophoretic particle separation, plant alkaloids, and forensic science applications. This review, therefore, examines the use of various microfluidic chips in electrophoretic separation during 2017–2022. There are various papers found by search, indicating continuous activity in the research area along with studies to explain its material, method, and its efficacy.

DominoCIM: A 28nm 138.04TOPS/W Spike-Domain Computing-in-Memory 6T-SRAM Macro for AI and Embedded Applications

The realization of computing in memory based on SRAM(SRAM-CIM) can be divided into three domains: analog domain (AD-CIM), time domain (TD-CIM), and digital domain (DD-CIM). However, there exist corresponding disadvantages to the above methods. For AD-CIM, the calculation accuracy is poor. Moreover, the output stability of TD-CIM is limited. With a large overhead area, the layout and wiring of DD-CIM are complicated. Aiming to solve the shortcomings, this paper proposes a spike-domain circuit based on a pulse edge counting scheme. The circuit uses digital logic to realize the MAC operation, which is less affected by power, voltage, and temperature (PVT) and performs higher calculation accuracy. The circuit is transmitted serially through the delay chain to achieve a smaller area overhead. At 28 nm, the circuit accomplishes energy efficiency (EF) with 138.04TOPS/W for 4-bit multiplication and addition (MAC) operations, enabling full precision output and 3.42 times less energy consumption per operation than the previous SRAM-CIM.

Cardiac output estimated from an uncalibrated radial blood pressure waveform: validation in an in-silico-generated population.

Background: Cardiac output is essential for patient management in critically ill patients. The state-of-the-art for cardiac output monitoring bears limitations that pertain to the invasive nature of the method, high costs, and associated complications. Hence, the determination of cardiac output in a non-invasive, accurate, and reliable way remains an unmet need. The advent of wearable technologies has directed research towards the exploitation of wearable-sensed data to improve hemodynamical monitoring. Methods: We developed an artificial neural networks (ANN)-enabled modelling approach to estimate cardiac output from radial blood pressure waveform. In silico data including a variety of arterial pulse waves and cardiovascular parameters from 3,818 virtual subjects were used for the analysis. Of particular interest was to investigate whether the uncalibrated, namely, normalized between 0 and 1, radial blood pressure waveform contains sufficient information to derive cardiac output accurately in an in silico population. Specifically, a training/testing pipeline was adopted for the development of two artificial neural networks models using as input: the calibrated radial blood pressure waveform (ANNcalradBP), or the uncalibrated radial blood pressure waveform (ANNuncalradBP). Results: Artificial neural networks models provided precise cardiac output estimations across the extensive range of cardiovascular profiles, with accuracy being higher for the ANNcalradBP. Pearson's correlation coefficient and limits of agreement were found to be equal to [0.98 and (-0.44, 0.53)L/min] and [0.95 and (-0.84, 0.73)L/min] for ANNcalradBP and ANNuncalradBP, respectively. The method's sensitivity to major cardiovascular parameters, such as heart rate, aortic blood pressure, and total arterial compliance was evaluated. Discussion: The study findings indicate that the uncalibrated radial blood pressure waveform provides sample information for accurately deriving cardiac output in an in silico population of virtual subjects. Validation of our results using in vivo human data will verify the clinical utility of the proposed model, while it will enable research applications for the integration of the model in wearable sensing systems, such as smartwatches or other consumer devices.

Research on high‐precision synchronous output technology of multi‐reference source weighted synthesis in power system

AbstractThe massive perception data based on efficient analysis and intelligent decision have put forward higher requirements for high‐precision time synchronisation with the construction and development of smart power grid. However, multi‐reference source time‐frequency synchronisation of power system only selects the best method after comparison, which cannot make the most efficient use of the existing resources. It also cannot meet the need for high‐precision time synchronisation of future power system. The existing multi‐reference source synthesis algorithms cannot take into account both long‐term stability and high‐precision synchronous output. This article presents a multi‐reference source weighted improved noise model and the high‐precision output method. The multi‐reference source error after classification is eliminated by leading into classification vector and classification coefficient. The synthesised frequency offset or the time precision of output can be optimised as the objective function by weighted classification algorithm and genetic algorithm. A simulation example based on the synthesis of two satellite system clock sources and three local caesium reference sources shows that the peak value of long‐term output accuracy is controlled within 10 ns after classification weighted synthesis and optimisation, which is better than that of any single reference source.

A multi-level rectifier with voltage balancing capability for EV charging

ABSTRACT In two-stage electric vehicle (EV) battery chargers, ac-dc conversion stage contributes significantly in determining the power quality. At this stage, multilevel rectifiers (MLRs) featuring switches with lower voltage rating and better input voltage waveform quality can be adopted. However, balancing capacitor voltage in MLR is an important challenge. In this paper, a single-phase five-level power factor correction (PFC) rectifier with self-balancing capacitor is implemented for EV battery charging. The complimentary switching scheme adopted for rectifier reduces number of gate driver circuits and ensures capacitor voltage balancing. The rectifier shows added benefit of reduced voltage stress across switches and not requiring an external filter at the dc side as the load is parallelly connected with one of the capacitors. The operating principle, control strategy, modulation technique and design features of the implemented five-level rectifier is discussed in detail. The implemented control scheme enhances rectifier performance by establishing precise output voltage regulation during load fluctuations while maintaining unity power factor at input side. The five-level rectifier is validated experimentally and compared with other existing multilevel and non-multilevel rectifier topologies. The peak efficiency of 93.8% is achieved at 2 kW of output power.

A method to address beam cross coupling errors in phased array Doppler sonar

Performance of Doppler sonar is degraded by beam cross coupling errors. This performance degradation presents itself as the loss of precision and bias of velocity estimates output by the system. A model is proposed here to reveal the physical essence of the beam cross coupling. Specifically, the model can analyze the effects of environmental conditions and vehicle attitude on the coupling bias. Based on this model, a phase assignment method is also proposed to reduce the beam cross coupling bias. The results obtained for various settings validate the efficacy of the proposed method.

Toward the Multiple Constant Multiplication at Minimal Hardware Cost

Multiple Constant Multiplication (MCM) over integers is a frequent operation arising in embedded systems that require highly optimized hardware. An efficient way is to replace costly generic multiplication by bit-shifts and additions, i.e. a multiplierless circuit. In this work, we improve the state-of-the-art optimal approach for MCM, based on Integer Linear Programming (ILP). We introduce a new low-level hardware cost metric, which counts the number of one-bit adders and demonstrate that it is strongly correlated with the LUT count. This new model permitted us to consider intermediate truncations that permit to significantly save resources when a full output precision is not required. We incorporate the error propagation rules into our ILP model to guarantee a user-given error bound on the MCM results. The proposed ILP models for multiple flavors of MCM are implemented as an open-source tool and, combined with an automatic code generator, provide a complete coefficient-to-VHDL flow. We evaluate our models in extensive experiments, and propose an in-depth analysis of the impact that design metrics have on synthesized hardware.

Development of a flexible embedded neurostimulator for animal robots

The neural stimulator is a core component of animal robots. While the control effect of animal robots is influenced by various factors, the performance of the neural stimulator plays a decisive role in regulating animal robots. In order to optimize animal robots, embedded neural stimulators had been developed using flexible printed circuit board technology. This innovation not only enabled the stimulator to generate parameter-adjustable biphasic current pulses through control signals, but also optimized its carrying mode, material, and size, overcoming the disadvantages of traditional backpack or head-inserted stimulators, which have poor concealment and are prone to infection. Static, in vitro, and in vivo performance tests of the stimulator demonstrated that it not only had precise pulse waveform output capability, but also was lightweight and small in size. It had excellent in vivo performance in both laboratory and outdoor environments. Our study has high practical significance for the application of animal robots.

Investigation and modelling lean six sigma barriers in service industries: a hybrid ISM-Fuzzy MICMAC approach

PurposeThe success rate of Lean Six Sigma (LSS) in the service industries is dismally poor, and most organisations discontinue LSS initiatives prematurely. This paper aims to identify the LSS barriers (LSSBs) and analyse their interaction via a hierarchical model developed by using interpretive structural modelling (ISM) and Fuzzy Matriced Impacts Croise’s Multiplication Appliqué à un Classement (MICMAC). These allow the LSS execution and implementation to be much more effective and avoid the high cost of implementation.Design/methodology/approachA structural review of the literature and interviews with experts and professionals from the service industries in the UAE supplied data wherewith to identify LSSBs. Sixteen LSSBs were determined and analysed using ISM and the MICMAC approach to discover the strong drivers and highly dependent barriers. The Fuzzy set was included in the MICMAC analysis to obtain a more precise output and create an effective hierarchical model of the barriers.FindingsThe research findings suggest that the top barriers to LSS implementation in service industries are lack of top management commitment, lack of customer focus, resistance to change management and lack of alignment between the LSS and organisational strategy. A deeper analysis using the Fuzzy-MICMAC approach categorises these barriers on the basis of their driving power and dependency.Research limitations/implicationsThe relationships between paired LSSBs were obtained through an experts’ interpretations of limited numbers in one country. Conducting a large-scale survey with a more comprehensive demographic or deep focus in one service industry might deepen our understanding of the interactions of LSSBs and models.Practical implicationsThe developed ISM that model suggests that the dependencies and relationships among the barriers must be accurately determined so as to remove the collaborative effect of barriers on the implementation process is at the earliest opportunity. This would improve service companies’ competitive advantage and profitability, drive out waste and reduce the cost associated with poor quality. Similarly, academicians may advocate ways in various issues can contribute to improve LSSBs for amended LSS implementation now that business services are booming in the fourth industrial revolution.Originality/valueThe structural model was developed holistically on the basis of the inputs from practitioners and academicians to ensure its practical validity. Though the model has theoretical foundations, its practical applicability is a key factor in its development, so this approach was helpful for practitioner wanted to focus on removing the key dominant barriers and be able to deploy LSS concepts smoothly in service industries. The results support the proposition that top management is a crucial factor for LSS project implementation, whatever the complexity of the research methodology and the nature of the service industries.

Dual-Terminal Voltage Feedforward Based Direct Power Control Scheme and Stability Analysis of Dual Active Bridge Converter in DC Microgrid Systems

The dual active bridge (DAB) dc-dc converter plays an important role in energy exchange between DC microgrids integrated with energy storage systems. To directly control the power flow between the adjacent DC microgrids rapidly and accurately, a dual-terminal voltage feedforward based direct power control scheme (DVF-DPC) with single-phase-shift control is proposed for the DAB dc-dc converter. The strategy makes the converter realize rapid and precise output power regulation under the following conditions, including the start-up process, load step-change, the desired output power step-change, and voltage fluctuations. An accurate discrete-time model is applied to analyze the system's dynamic characteristics, and a discrete-time small-signal model of the system is established to design the controller's parameters. In addition, a comprehensive and systematic analysis of all the possible unstable phenomena for adjacent DC microgrids is conducted based on the discrete-time model. Accordingly, the underlying mechanisms are revealed by analyzing the relationships among the state variables, the Floquet multipliers, and system parameters. Hence, the stability-oriented parameter design method is given which can provide guidance in practice. The theoretical analysis is verified in both the time domain and frequency domain. Finally, by comparing the DVF-DPC method with the traditional PI feedback control, the superiority of the proposed strategy is verified through theoretical analysis and experimental results, which demonstrates its application prospect in the field of electric energy dispatch control of the DC power supply network.

The artificially intelligent entrepreneur: ChatGPT, prompt engineering, and entrepreneurial rhetoric creation

To better understand the role of artificial intelligence in the development of entrepreneurial rhetoric, we examine how generative language models such as ChatGPT serve as viable tools for content creation. Using an established framework for examining CEO celebrity (Creator, Transformer, Rebel, and Savior), we illustrate how such models can effectively produce and refine elevator pitches, social media pitches, and crowdfunding pitches commonly used in the study of entrepreneurial rhetoric. We demonstrate ChatGPT's ability to mimic each celebrity CEO archetype by prompting language in the style of exemplars, including Elon Musk, Indra Nooyi, Tony Hsieh, and Lisa Su. Implications of prompt engineering—the fine-tuning of inputs fed into language models to produce precise output—for entrepreneurship research and practice are discussed. We conclude by advancing the idea that the emergent and enduring value of generative models is, at its core, dependent on effective prompt engineering.

Design and experiment of a large displacement linear piezoelectric actuator

To increase the output displacement of the linear piezoelectric actuator, a linear piezoelectric actuator with large displacement and three operation modes is proposed. The operating principle of the piezoelectric actuator is presented. The magnification factor of the displacement amplification mechanism is deduced and verified by finite element analysis. To improve the output precision of the actuator, a feedforward PID control model is established. Based on the experimental test platform, the output characteristics of the piezoelectric actuator are tested. Results show the maximum output displacement of the piezoelectric actuator is 558.3 μm under a driving voltage of 150 V with two piezoelectric stacks. When the driving frequencies are less than 3 Hz, the control accuracy of feedforward PID is higher than that of PID, and the error between the measured displacement and the ideal value is less than 10% after applying the control to the piezoelectric actuator.

Climate change effects on Chickpea yield and its variability in Andhra Pradesh, India

Farmers usually do not know the precise output that is affected by climatic factors such as temperature and rainfall and are characterized by inter-annual variability, part of which is caused by global climate change. No study covers the influences of climate factors on yield and yield risk in the context of chickpea farming in Andhra Pradesh, India. In this context, this study aimed to investigate the trends in climate change variables during Rabi season (October to January, 1996-2020) and evaluated their variability on chickpea yields across different agro-climatic zones in Andhra Pradesh by employing Just and Pope production function. Four non-parametric methods-Alexandersson’s Standard Normal Homogeneity Test, Buishand’s Range Test, Pettitt’s Test and Von Neumann’s Ratio Test are applied to detect homogeneity in the data. Mann–Kendall (MK) test and Sen’s slope (SS) method were employed to analyze monthly rainfall trends and minimum and maximum temperature trends. Results of Just and Pope (panel data) quadratic and Cobb-Douglas methods revealed that monthly minimum temperature positively influenced the mean yield of chickpea (0.22% and 0.16%, respectively). However, rainfall (-0.41% and -0.31%) and maximum temperature (-0.08% and -0.04%) negatively influenced the mean yield of chickpea under quadratic and Cobb-Douglas models, respectively. Accordingly, rainfall (0.08% and 0.06%) and maximum temperature (0.83% and 0.72%) positively influenced the yield variability and minimum temperature (-0.77% and -0.67%) reduced yield variability of chickpea under quadratic and Cobb-Douglas models respectively. In view of these findings, it is imperative to advocate the farmers about the importance of cultivating drought-tolerant chickpea varieties, drought-proofing and mitigation strategies, micro-irrigation practices and improving their access to agro-meteorological information towards sustainable chickpea cultivation in Andhra Pradesh.

A new deep learning-based technique for rice pest detection using remote sensing.

Agriculture plays a vital role in the country's economy and human society. Rice production is mainly focused on financial improvements as it is demanding worldwide. Protecting the rice field from pests during seedling and after production is becoming a challenging research problem. Identifying the pest at the right time is crucial so that the measures to prevent rice crops from pests can be taken by considering its stage. In this article, a new deep learning-based pest detection model is proposed. The proposed system can detect two types of rice pests (stem borer and Hispa) using an unmanned aerial vehicle (UAV). The image is captured in real time by a camera mounted on the UAV and then processed by filtering, labeling, and segmentation-based technique of color thresholding to convert the image into greyscale for extracting the region of interest. This article provides a rice pests dataset and a comparative analysis of existing pre-trained models. The proposed approach YO-CNN recommended in this study considers the results of the previous model because a smaller network was regarded to be better than a bigger one. Using additional layers has the advantage of preventing memorization, and it provides more precise results than existing techniques. The main contribution of the research is implementing a new modified deep learning model named Yolo-convolution neural network (YO-CNN) to obtain a precise output of up to 0.980 accuracies. It can be used to reduce rice wastage during production by monitoring the pests regularly. This technique can be used further for target spraying that saves applicators (fertilizer water and pesticide) and reduces the adverse effect of improper use of applicators on the environment and human beings.