High-precision System Research Articles

Movie Recommendation System Based on Word Embedding

Abstract. Amidst the swift progression of Internet and big data technologies, recommendation systems have emerged as crucial conduits linking users to products across various digital platforms. This study delves into the deployment of neural collaborative filtering within the realm of movie recommendation systems, with the objective of constructing a system of high precision. Utilizing the MovieLens dataset, this investigation applies one-hot encoding and embedding techniques within the PyTorch-Lightning framework to effectively model user behaviors and predict cinematic preferences. The neural collaborative filtering (NCF) model leverages deep learning to extract latent features of users and items, exhibiting a notable enhancement in performance compared to traditional collaborative filtering approaches. Empirical results indicate that the NCF model attains an accuracy of 86% on the validation dataset, underscoring its efficacy in extensive recommendation scenarios.

Validation and optimization of a solar district heating system with large scale heat storage

Solar district heating systems with large-scale heat storage can contribute to a sustainable future. Currently, there are few mature systems and a lack of suitable tools, hindering large-scale applications. High-precision system models and efficient control strategies are necessary for designing optimal plants. This study developed a TRNSYS model of a large solar heating plant with components like a solar collector field, pit heat storage, heat pump, boilers, piping, pumps, and a MATLAB control system. The model is validated using a solar district heating system in Dronninglund, Denmark, showing good agreement with the measurement, with a difference in the solar thermal production of only 0.3% and an average temperature difference in the pit storage of 1 K. The model of the absorption chiller is improved for wide heat pump simulation, yielding a difference of approx. 5% compared to the measured coefficient of performance. The predicted solar fraction is 0.51, differing by 1.5% from the measurement. The study also proposed two new control strategies: adaptive low-temperature operation strategy and full-time heat pump operation strategy. These optimized strategies are compared with the original control strategy. Results show that the low-temperature and full-time optimization strategies improve the heat pump efficiency by 20%, the collector efficiency by 10%, and the solar utilization by 15%. The economic and environmental performance of the solar heating plant will also be enhanced with a maximum of 27% lower heat costs and 32 kg/MWh lower carbon emissions compared to the original system. In contrast, without the absorption heat pump, the solar heat production decreases by 10%. The system does not meet carbon neutrality if natural gas is used as the auxiliary heat source. This study aims to provide new simulation models and control strategies, which could be utilized for design of optimal large-scale solar thermal applications.

Investigation of Unsafe Construction Site Conditions Using Deep Learning Algorithms Using Unmanned Aerial Vehicles.

The rapid adoption of Unmanned Aerial Vehicles (UAVs) in the construction industry has revolutionized safety, surveying, quality monitoring, and maintenance assessment. UAVs are increasingly used to prevent accidents caused by falls from heights or being struck by falling objects by ensuring workers comply with safety protocols. This study focuses on leveraging UAV technology to enhance labor safety by monitoring the use of personal protective equipment, particularly helmets, among construction workers. The developed UAV system utilizes the tensorflow technique and an alert system to detect and identify workers not wearing helmets. Employing the high-precision, high-speed, and widely applicable Faster R-CNN method, the UAV can accurately detect construction workers with and without helmets in real-time across various site conditions. This proactive approach ensures immediate feedback and intervention, significantly reducing the risk of injuries and fatalities. Additionally, the implementation of UAVs minimizes the workload of site supervisors by automating safety inspections and monitoring, allowing for more efficient and continuous oversight. The experimental results indicate that the UAV system's high precision, recall, and processing capabilities make it a reliable and cost-effective solution for improving construction site safety. The precision, mAP, and FPS of the developed system with the R-CNN are 93.1%, 58.45%, and 27 FPS. This study demonstrates the potential of UAV technology to enhance safety compliance, protect workers, and improve the overall quality of safety management in the construction industry.

Changes in ROS/RNS Levels in Endothelial Cells in Experimental Bacteremia.

A high-precision system was developed for the quantification of biological analytes in single cells (reactive oxygen species (ROS) and reactive nitrogen species (RNS)) based on the electrochemical amperometric method. The efficacy of this system was evaluated using an experimental bacteremia model. Endothelial cells exhibited increased ROS/RNS production when stimulated by Staphylococcus aureus. However, they remained inactive when exposed to either unprimed or primed neutrophils that had been pre-incubated with bacteria. It is noteworthy that the sequential stimulation of endothelial cells with bacteria followed by neutrophils resulted in a significant increase in the ROS/RNS level, which demonstrated a correlation with the number of neutrophils in contact with the endothelial cells. These results highlight the potential of our system to quantitatively assess ROS/RNS dynamics in complex biological systems. They also offer insights into the interplay between various cellular components in experimental bacteremia.

Gesture-Controlled Robotic Arm for Agricultural Harvesting Using a Data Glove with Bending Sensor and OptiTrack Systems.

This paper presents a gesture-controlled robotic arm system designed for agricultural harvesting, utilizing a data glove equipped with bending sensors and OptiTrack systems. The system aims to address the challenges of labor-intensive fruit harvesting by providing a user-friendly and efficient solution. The data glove captures hand gestures and movements using bending sensors and reflective markers, while the OptiTrack system ensures high-precision spatial tracking. Machine learning algorithms, specifically a CNN+BiLSTM model, are employed to accurately recognize hand gestures and control the robotic arm. Experimental results demonstrate the system's high precision in replicating hand movements, with a Euclidean Distance of 0.0131 m and a Root Mean Square Error (RMSE) of 0.0095 m, in addition to robust gesture recognition accuracy, with an overall accuracy of 96.43%. This hybrid approach combines the adaptability and speed of semi-automated systems with the precision and usability of fully automated systems, offering a promising solution for sustainable and labor-efficient agricultural practices.

Design and performance evaluation of a novel parallel kinematic micromanipulator

The targeted placement of selected carbon nanotubes is associated with low throughput rates. Hence, this paper presents a novel stage design for the fully automatic assembly of carbon nanotube field-effect transistors (CNTFETs) via mechanical dry transfer. It constitutes the core module of an assembly machine for the precise deployment of nanotubes onto a prefabricated wafer. The mechanical dry transfer approach allows high level of carbon nanotube selectivity with the aim of enabling a high-volume fabrication of ultra-clean devices. The previous production rate of such ultra-clean devices is less than one per hour, which offers a high potential for improvement. The stage consists of a parallel kinematic mechanism (PKM) with 3 degrees of freedom (X2Y2C1) carrying two additional stacked axes (Z1C2). The PKM is suspended on a vacuum preloaded aerostatic bearing, voice coil motors (VCM) and flexure hinges. Together with a combination of high precision and resolution touch probe measurement systems close to its tool center point (TCP), high accuracy and low settling time can be achieved. Based on realistic manufacturing tolerances, a sensitivity analysis of the mechanism’s pseudo rigid body model (PRBM) suggests a theoretical closed-loop error below 0.15μm over the entire XY workspace of 20mm×2.8mm. Measurements of positioning motions show that the settling time can be decreased by the compensation of friction resistances inside the internal bearings of the VCMs.

Advancing UAV Sensor Fault Diagnosis based on Prior Knowledge and Graph Convolutional Network

Unmanned Aerial Vehicles (UAVs) are commonly equipped with multiple sensors to facilitate control and navigation. However, due to the complexity of the flight environment, the UAV sensors are prone to damage, which can cause serious accidents or even economic losses. Therefore, it is of great importance to propose an effective UAV sensor fault diagnosis method. The following weaknesses are obtained by the existing fault diagnosis methods: 1) The model-based methods, such as parameter estimation, state estimation, and equivalent space method, require introducing high-precision system models and expert knowledge. 2) Conventional graph convolutional network (GCN)-based methods fail to guarantee the accuracy of association graphs. To address the above two challenges, the dynamics model of quadrotor as prior knowledge is proposed in this paper to construct the association graph first. Then, a spatial-temporal difference graph convolutional network (STDGCN) consisting of a difference layer and multiple spatial-temporal graph convolutional modules is built. The difference layer enhances the feature extraction of the graph nodes, while the spatial-temporal graph convolutional modules extract the spatial-temporal dependencies of sensor data. Finally, the robustness and effectiveness of STDGCN are demonstrated in fault diagnosis compared with the commonly used data-driven methods. The experimental result shows that the proposed STDGCN method exhibits outstanding feature extraction ability with the highest diagnostic accuracy.

The Determination of Effective Modes of Wind-Bridge Coupling System Based on Stabilization Clustering Method

Modal identification is the core content of the full-bridge aeroelastic model wind tunnel test. Modal consistency is the most direct and effective basis to ensure that the model and the real bridge meet the similarity criteria. Accurate, simple and fast identification of modal parameters has very important practical significance for the evaluation and correction of aeroelastic models. In this paper, the eigensystem realization algorithm (ERA) and stochastic subspace identification (SSI) is improved, and the automatic identification theory of effective modes of bridge aeroelastic model based on stable clustering method is proposed. The stable diagram eliminates the unstable modes by comparing the results of different system orders, and the pedigree clustering further polarizes the stable modes to obtain multi-order and high-precision system modes. Numerical simulation examples and wind tunnel engineering examples show that the method has high accuracy and good adaptability, and can solve the problem of unstable damping identification results to a certain extent. In the wind tunnel test, the stable clustering method is one of the effective methods to identify the modal of the bridge aeroelastic model excited by the wind environment.

EFFECTIVE RECOGNITION OF MISINFORMATION WITH THE HELP OF NEURAL NETWORKS: FOCUS ON THE DETECTION OF EMOTIONAL IMPACT

The research focuses on the study of effective methods for automated disinformation recognition using advanced neural network and natural language processing techniques. Particular emphasis is placed on identifying the emotional impact that often accompanies disinformation content. The study applies innovative approaches to text analysis to identify hidden techniques for manipulating the emotional state of the audience used by disseminators of false information. The result of the study is the development of high-precision systems for recognising and categorising the emotional colouring of disinformation-related content. Such systems are able to effectively detect and filter potentially harmful materials, thereby strengthening the resilience of the information environment. The proposed solutions can make an important contribution to the fight against the spread of disinformation and contribute to improving cybersecurity by ensuring the reliability and integrity of the information space. The findings have the potential to improve the means of countering disinformation and strengthening trust in the information environment. The study also includes an analysis of the ethical aspects of using neural networks to recognise disinformation and the development of appropriate standards aimed at protecting user privacy. This comprehensive work offers a robust system for filtering and responding to potential disinformation threats, opening up new perspectives for improving cybersecurity and ensuring the reliability of the information environment.

Development of a High-Precision, Portable and Automated Mobile Laser Scanner for the Recording and Digitation of Texture and Micro-marks in Archaeological and Heritage Stone

The use of laser tools to digitise cultural heritage items is becoming more widespread but is generally limited to manual systems that rely on the user’s movement or expensive automated equipment that is designed to scan large items but is not always able to accurately measure or reproduce specific details of small size. In this paper we present the novel high-precision system PALLAS, which allows the automatic digitisation of three-dimensional detailed surfaces. The equipment has been built using a set of motors and linear axes, control electronics and a line laser scanner that can be moved along the XY working plane. It is battery-powered for ease of use in the field and uses a standard laptop to communicate via Wi-Fi network. Custom software has been developed to automatically calculate paths, control the movement and store the profiles generated by the scanner. The software can also be used to reconstruct the surface from the set of scanner profiles, allowing the XYZ coordinates of any point on the surface to be measured and to obtain areal roughness parameters to characterise the finish and texture of the stone surface. Preliminary results obtained from masons’ marks, rock engravings and petroglyphs are presented.

A Sub-1 ppm/°C dual-reference small-area bandgap reference comprising an enhanceable piecewise curvature compensation circuit

This paper presents a low-temperature coefficient (TC) dual-reference CMOS bandgap reference (BGR) for high-performance systems working under a wide temperature range. It consists of a correction approach to eliminate the high-order inaccuracy, in which an enhanceable curvature compensation circuit is adopted to extend the operating temperature range and generate reference voltages with sub-1 ppm/°C TC. In addition, a voltage level shifter (VLS) is used to generate the latter compensated reference voltage but no need for an additional compensation circuit. The proposed BGR designed in a 0.18-µm CMOS process has a simulated TC of 0.75 ppm/°C and 0.28 ppm/°C for the first and second reference outputs, respectively, over a wide temperature range of −50 °C to 130 °C. The proposed BGR occupies a 0.0079-mm2 silicon area. The overheads make the BGR appropriate to provide reference voltages in diverse chips with high-precision systems.

An Investigation of Tool-Wear Monitoring Machining Process Using IBM SPSS Statistics

Monitoring Machining Process. Introduction: The process of monitoring a CNC machine involves keeping tabs on its productivity, resource analysis, and performance. Since turning, milling, drilling, and other machining operations are performed on CNC machines. These devices are regarded as high precision systems since they make it possible to manufacture complex products. However, it is crucial to guarantee the proper functioning of a number of operations in order to produce high-quality complicated CNC production. Therefore, two elements are monitored in this Cnc monitoring procedure in order to achieve the desired production result. Let's talk about the two primary aspects of Numerical control monitoring and the corresponding monitoring tools. Research significance: Monitoring both machining parameters and tool quality is becoming more and more crucial in the modern industrial area to further develop item quality, efficiency, process mechanization, and compensation costs. The core technologies and cutting-edge developments for monitoring the machining process are presented generally used misbrands for monitoring the machining process are described in section "Misbrands and Sensors," including max torque as well as present, force, speed, acoustic radiation, vibrations, picture, heat, displacement, strain, etc. Also included are the appropriate detectors for these misbrands and the need for signal processing. Methodology: SPSS statistics is a data management, advanced analytics, multivariate analytics, business intelligence, and criminal investigation developed by IBM for a statistical software package. A long time, spa inc. was created by, IBM purchased it in 2009. Evaluation parameters: Integrated broaching process, DAQ system, Characterization package, Condition Monitoring Package, Feature Extraction Package, Monitoring system. Results: The Cronbach's Alpha Reliability result. The overall Cronbach's Alpha value for the model is .711 which indicates 71% reliability. From the literature review, the above 79% Cronbach's Alpha value model can be considered for analysis. Conclusion: the outcome of Cronbach's Alpha Reliability. The model's total Cronbach's Alpha score is. 711, which denotes a 71% dependability level. The 79% Cronbach's Alpha value model mentioned above from the literature review may be used for analysis.

Experimental Test of the Acoustic Thermometry Method on a Long Track in the Sea of Japan

Methodological and technical possibilities of monitoring temperature fields along a 1000-km track in the Sea of Japan using acoustic thermometry are presented. The proposed tomographic method for monitoring the dynamics and structure of waters is based on emission and reception of complex phase-shift keyed signals on a diagnosed path with determination of the propagation time along various ray trajectories with further measurement of the speed of sound and temperature. The physical prerequisites for practical use of thermometric studies at large distances are based on the acoustic “mudslide” effect: the phenomenon of the transition of acoustic energy from the bottom shelf area to an underwater sound signal of the deep ocean. A high-precision system of acoustic thermometry on the basis of tomographic schemes with mobile and stationary hydroacoustic emitters and receiving systems is proposed and tested with the example of the Sea of Japan.

Research on Head Pursuit Interception Strategy for Hypersonic Target

In the wake of countries competing to develop high-efficiency offensive weapons, high-precision systems have also developed. Due to the high speed and high maneuverability of hypersonic targets, it is always difficult to meet the accuracy and rapidity requirements by using the traditional interception mode. In order to improve the accuracy of the hypersonic target interception, a head pursuit guidance strategy is developed for hypersonic target interception in this study. Firstly, a dynamic model is established by analyzing the relative motion between the interceptor and the target, which needs to place the low-speed interceptor before the high-speed target. Subsequently, a head pursuit interception guidance strategy is presented, which controls the interceptor flight trajectory by controlling its normal acceleration to achieve a successful interception target. Finally, for the maneuvering and non-maneuvering targets, the dynamic characteristics of interceptor are analyzed, respectively, and full trajectory dynamic simulations under different conditions for the hypersonic target interception are worked out to illustrate the feasibility and robustness of the proposed guidance strategy.

Research on In-phase Signal Combining Method for Improving Phase Noise

In high-precision system design, the realization of target precision is often limited by the design of the frequency source. In the design and testing of frequency sources, phase noise is often listed as an assessment item that can characterize the performance of frequency sources. Due to the current design and manufacturing level of devices and circuits, it is difficult for conventional methods to get a significant improvement in the phase noise index. This paper explains the concept, source and characteristics of phase noise. According to the different combining characteristics of the main signal and the phase noise, an in-phase signal combining method is proposed to improve the phase noise index. Multiple S-band frequency sources were used to build the verification platform. This platform is used to verify the improvement of the in-phase signal combining method in phase noise index. Finally, this paper presents the difficulties and methods of in-phase signal combining in practical design and applications.

Computer Vision on the Edge to Reduce Network Bandwidth Consumption and Computing Resources in Multi-view 3D Industrial Inspection without Hidden Surfaces

Industrial inspection industry requires high precision, fast and reliable systems, where images play a central role. These systems are composed by several hardware and also cyber-physical componentes where complexity increases when multiple heterogeneous sensor inputs are combined. Our 3D industrial inspection scanner is able to reconstruct complete objects without occlusion with use of multiple sensors and actuators using a complex software architecture. Our system allows increasing the throughput by removing the bottleneck network issue, decreasing network data transfer using a new edge systems architecture that segments and optimizes image transferring. Also, this work presents the results of applying technology developed during the FitOptiVis European ECSEL project. FitOptiVis will provide a reference architecture supporting composability built on suitable component abstractions and embedded sensing, actuation and processing devices adhering to those abstractions. The reference architecture will support design portability, on-line multi-objective quality and resource management and run-time adaptation guaranteeing system constraints and requirements based on platform virtualization. The FitOptiVis project will be applied to design the new architecture of the new edge components and develop the runtime system monitoring.

High precision and real-time acquisition system for interface stress measurement in bridge bearing

Since the damage of the bridge structure may cause great disasters, it is necessary to monitor its health status, especially the bridge bearing, the important connecting component of the bridge's upper and lower structures. Nowadays, manual inspection is the main method to get the information of the bridge bearings’ work status. However, occasional damage of bridge bearing may not be detected in time, and sometime the installation position of the bearing makes the manual inspection on bridge bearing difficult and even impossible. Therefore, in order to know the work status of the bridge bearings timely, an intelligent remote monitoring system for the bridge bearing is developed. A 32-channel real-time acquisition system is designed by using an AD7768-1 analog-to-digital converter and Xilinx Spartan-6 Field Programmable Gate Array for interface stress continuously acquired in the bridge bearing. To assure the good linearity and low noise performance of the monitoring system, the data acquisition card is meticulously designed to reduce noise from both hardware and software and realize high-precision acquisition. Through the establishment of the monitoring server, the compressive stress data can be displayed synchronously and the overpressure situation can be alarmed in real-time. The experimental results show that the accuracy of the calibrated sensor is within 1.6%, and the detection error of the acquisition board is less than 200 μV. The acquisition system is deemed to have considerable advantages in accuracy and applicability.

PLC-BASED MODERN PROTECTION SYSTEM OF ELECTRIC MOTORS

In the past, simple protection systems of electric motors based on components such as timers, contactors, electromagnetic switches, and voltage and current transformers were slow and inaccurate, as well as low sensitivity. However, the production of PLCs and their application in this field eliminated the mentioned problems. Extensive operation of motors, being the main executive equipment in the field of application, requires the creation of modern automated protection systems to ensure their reliable and stable operation. Today, PLCs are continuously evolving and striving to be the best choice for various industrial automation applications. Since the PLC-based protection system is a reliable, fast, high-precision system, modern protection systems based on PLC of electric motors are researched in the article.

A High-Precision Real-Time System for Pupil Size Measurement using an Infrared Camera and LED Light Stimulation

This research is dedicated to the exploration of sophisticated methodologies and the creation of a high-precision system for pupil size measurement that is capable of displaying real-time results. The comprehensive system encompasses an infrared camera, an infrared LED light, an LED light box designed for pupil stimulation, and robust control software that enables analysis, measurement, and real-time documentation of results. Our study yielded promising results with a high degree of precision in pupil size measurements, thereby opening new possibilities for intricate vision-related research and applications. With its potential impact, the system can offer profound contributions to areas including eye-health diagnosis, human-computer interaction research, and studies focusing on light-induced pupil response.

Development of NDIR CO2 Gas Sensing System Based on U-Shaped Optical Cavity

In this paper, a proposed carbon dioxide Gas Sensing System of high precision, rapid reaction, compact size and low power consumption rate is presented based on the non-dispersive infrared (NDIR) measurement. This system used to determine CO2 gas concentration in air; it consists of the single broadband light source, U-shape tube optical path cavity as gas cell, thermopile detector, and microcontroller circuit. This study investigates the efficiency of the U-tube optical path cavity at CO2 gas concentrations ranging from (0-5000) ppm. The obtained results show that it has the better thermal response compare to the linear tube and exhibits high sensitivity by change the transmitted light intensity into analog voltage. The proposed system design can be used as an environmental monitoring sensor.