Processing Requirements Research Articles

Autonomous traffic sign detection for self-driving car system using convolutional neural network algorithm

The accurate detection of traffic signs is a critical component of self-driving systems, enabling safe and efficient navigation. In the literature, various methods have been investigated for traffic sign detection, among which deep learning-based approaches have demonstrated superior performance compared to other techniques. This paper justifies the widespread adoption of deep learning due to its ability to provide highly accurate results. However, the current research challenge lies in addressing the need for high accuracy rates and real-time processing requirements. In this study, we propose a convolutional neural network based on the YOLOv8 algorithm to overcome the aforementioned research challenge. Our approach involves generating a custom dataset with diverse traffic sign images, followed by conducting training, validation, and testing sets to ensure the robustness and generalization of the model. Experimental results and performance evaluation demonstrate the effectiveness of the proposed method. Extensive experiments show that our model achieved remarkable accuracy rates in traffic sign detection, meeting the real-time requirements of the input data.

Application of diglycolamide extractant in rare-earth extraction

Diglycolamide (DGA) extractant is a kind of rare-earth extractant with promising applications that has the advantages of high extraction capacity, ease of synthesis, good thermal stability and good radiation stability. It is a green extractant that contains only four elements, C, H, O and N, and produces no residue after incineration. The properties of DGAs containing branched N,N′-alkyl substituents have been much studied in recent years, and it has been shown that branched side chains lead to better separation. The introduction of structurally rigid elements in DGA provides new possibilities for separation of rare earth elements (REEs). Owing to the tiny differences in the chemical properties of adjacent REES, the simple use of DGA extractant cannot meet all separation requirements, and a masking agent is added to the aqueous phase to improve the separation by coextraction to meet the requirements of different processes. This review presents the structural analysis of the complexes and crystals of diglycolamide extractants with rare-earth ions through different characterization means, and the effects of different structural extractants, solvents, nitric acid and phase modifiers on extraction behavior are reviewed. This review pays special attention to the effect of the side chain structure of diglycolamide on extraction behavior, which provides a theoretical basis and guiding direction for the field of separation of the REEs by diglycolamide extractants.

A Novel Vision-Based Outline Extraction Method for Hull Components in Shipbuilding

The diverse nature of hull components in shipbuilding has created a demand for intelligent robots capable of performing various tasks without pre-teaching or template-based programming. Visual perception of a target’s outline is crucial for path planning in robotic edge grinding and other processes. Providing the target’s outline from point cloud or image data is essential for autonomous programming, requiring a high-performance algorithm to handle large amounts of data in real-time construction while preserving geometric details. The high computational cost of triangulation has hindered real-time industrial applications, prompting efforts to improve efficiency. To address this, a new improvement called Directive Searching has been proposed to enhance search efficiency by directing the search towards the target triangle cell and avoiding redundant searches. Another improvement, Heritable Initial, reduces the search amount by inheriting the start position from the last search. Combining Directive Searching and Heritable Initial into a new method called DSHI has led to a significant efficiency advancement, with a calculation efficiency improvement of nearly 300–3000 times compared to the ordinary Bowyer–Watson method. In terms of outlines extraction, DSHI has improved the extraction efficiency by 4–16 times compared to the ordinary Bowyer–Watson methods, while ensuring stable outlines results, and has also increased the extraction efficiency by 2–4 times compared to PCL. The DSHI method is also applied to actual ship component edge-grinding equipment, and its effect meets the shipbuilding process requirements. It could be inferred that the new method has potential applications in shipbuilding and other industries, offering satisfying efficiency and robustness for tasks such as automatic edge grinding.

A High-Efficiency Satellite Image Classification Method for Real-Time Application Using Augmented Incremental Transfer Learning

Researchers have put forth a range of models for processing satellite images, each with distinct data formats and processing requirements. One limitation arises from variations in the forms of modules, such as the image capturing and feature extraction modules, impacting accuracy and scalability in real-time scenarios. This passage introduces and explores a pioneering very competent temporal engine crafted specifically for classification of real-time satellite images. The proposed approach utilizes augmented incremental transfer learning, aiming to mitigate the limitations associated with diverse processing requirements. This approach involves capturing real-time satellite data through Google’s Earth Engine and subsequently processing it using a Convolutional Neural Network (CNN) based on transfer learning. The CNN employs backscatter coefficient analysis, utilizing coefficients derived from Precision Image's average intensity value across a distributed target. By integrating incremental learning and CNN for classification, the model achieves an impressive average accuracy of 98.06% in detecting crop type and severity of damage. Comparative analysis with state-of-the-art approaches reveals the superiority of the proposed model. It outperforms existing models by 5% in accuracy, showcasing its efficacy in satellite image processing and classification.

A CHECKLIST DEFINITION FOR ASSESSING MECHANICAL RISKS USING NTP 330 IN A REPAVEMENT CONSTRUCTION PROCESS

In a construction project, such as a road repaving process, skilled and unskilled labor are the fundamental axis for the development of the project. Their intervention must be supervised by the probability of occurrence of occupational accidents due to the use of equipment, heavy machinery and tools required throughout the activities, which can have negative consequences on workers, manifested through temporary, permanent, and even fatal disabilities, and to contractors and employers, due to delays and economic losses in the project, in addition to possible sanctions by control agencies. Occupational hazards must be managed by a legal requirement in all countries. Hence, the need to identify, evaluate and propose risk control measures in all types of constructions. In this case, the study focuses on generating checklists to measure deficiency levels of mechanical hazards in the construction process of replacing flexible pavement with rigid concrete, according to the NTP 330 methodology, which is based on the application of the NTP 324 methodology of the National Institute of Safety and Health at Work (INSST) in Spain. These checklists will be the input for the assessment of mechanical risks by verifying the safety actions and conditions adopted in the construction project. Likewise, compliance with the requirements of these checklists will determine the basic requirements of the mechanical risk control process, prioritizing urgent prevention activities. Keywords: accident rate, risk probability, hazard, hazard level

Coffee Agro-Technopark Development Strategy in Tabanan Regency to Strengthen Agriculture and Tourism Synergism

Tabanan Regency has various superior agricultural commodities, including coffee plantations and potential tourist attractions. Tabanan’s agriculture and tourism sectors have not been fully exploited, so the two have not yet run synergistically. Planning for an agro-technopark (ATP) is expected to create a production area based on agricultural technology, livestock and natural beauty. The ATP will leverage the potential of upstream and downstream agribusiness, infrastructure, and supporting services in coffee production, processing, and marketing. The research objective was to identify the sub-system of input, process, output, and development strategy of coffee ATP in Munduk Temu, Tabanan Regency. Data collection was carried out in two stages: secondary data collection with document study methods and primary data collection in the field using observation and interview methods. Data were analyzed using SWOT and strategic priority determination using Quantitative Strategic Planning Matrix (QSPM) analysis. The results showed that coffee cultivation with an integrated system supporting coffee ATP in Muduk Temu Tabanan fulfills input, process, and output requirements. Still, the quantity and quality of each sub-system need to be improved. The strategic position of coffee ATP development is in quadrant I (SO Strategy). Strategic priorities with the highest TAS value: 1) implementing technological innovations for managing pre-harvest and post-harvest Robusta coffee to support product diversification (st5 = TAS 6.94); 2) Policies from the local government in regulation and providing assistance to Subak Abian in supporting the development of ATP Coffee (st1= TAS 6.87); 3) Implementing crop-livestock integration to optimize resource potential (st3=TAS 6.86); 4) Implementing research results and studies based on superior products (st.4 = TAS 6.62). It is necessary to strengthen the institutional synergy between Village Owned Enterprises (Bumdes) managers, Subak Abian, and tourism stakeholders in improving the agricultural sector in synergy with the tourism sector.

IMU-Based Approach to Detect Spastic Cerebral Palsy in Infants at Early Stages

INTRODUCTION: Cerebral Palsy (CP) is a non-progressive neurological disorder affecting muscle control in early childhood, leading to permanent alterations in body posture and movement. Early identification is crucial for accurate diagnosis and therapy-based interventions. In recent years, an automated monitoring system has been developed to facilitate the health assessment of infants, enabling early recognition of neurological dysfunctions in high-risk infants. However, the interpretation of these assessments lacks standardization and is subject to examiner bias.
 OBJECTIVES: Many infants with CP exhibit increased tonic stretch reflexes due to Upper Motor Neuron Syndrome (UMNS), resulting from motor neuron damage that disrupts muscle signalling.
 METHOD: To detect abnormal muscle reactions, our team employed an Inertial Measurement Unit (IMU) sensor, comprising three tri-axial sensors (accelerometer, gyroscope, magnetometer) that capture movement data continuously and unobtrusively. IMU sensors are compact, cost-effective, and have low processing requirements, requiring attachment to the infant's body to measure inter-body part angles. Our team analyzed muscle activity and posture using IMU sensors, collecting tri-axial data from 43 infants in real-time. Additional factors like age, stride length, and leg length were incorporated into the dataset.
 RESULTS: Our team has applied various supervised machine learning approaches to predict CP in infants due to the limited dataset size, validating models through k-fold cross-validation. Among the models, Naive Bayes (NB) outperformed Logistic Regression (LR), Decision Tree (DT), Linear Discriminant Analysis (LDA), k-Nearest Neighbors (kNN), and Support Vector Machine (SVM), achieving an accuracy of 88%. CONCLUSION: This research contributes to the early detection and intervention of CP in infants, potentially improving their long-term outcomes.

Toward smart acoustic spaces: embedded machine learning for sound event detection and classification in the built environment

Edge computing integrated into the built environment will enable the development of smart acoustic spaces in which the flexural vibrations of the walls and screens that define a space may be employed to generate and monitor sound and serve as unobtrusive and convenient audio interfaces. Integration of data processing and neural decision making on compact, low- power embedded hardware-software systems will make it possible to mediate real-time, personalized acoustic interactions of a user with their environment without the need to connect to the cloud, thus providing privacy and security. In this presentation we show how embedded machine learning (ML) models combined with vibroacoustic control and monitoring of elastic panels may be employed to perform various tasks such as speech recognition, sound source localization, or the detection of acoustic signatures of specific events such as a fall or other health emergencies. The selection of vibroacoustic features, the associated signal processing requirements, and the computational resources utilized by the ML models for various acoustic tasks will be discussed. We also highlight how the distributed modal response of extended flat panels can simplify the sensing and signal processing requirements in such systems.

Assembly of Large Flip Chip Die in Ceramic Packages

Hermetic packaging is required to ensure the reliability of processors and application specific integrated circuit (ASIC) chips that are used in strategic systems, whose operating lifetimes typically exceed thirty years. Performance requirements for emerging system applications are dictating the need for one thousand or more I/O, which precludes the use of wire bonded devices. These packaging requirements can be met by flip chip bonding die onto multilayer, high temperature cofired ceramic substrates. The hermetic environment is provided by a Kovar metal ring that is brazed onto the ceramic and sealed in the final assembly step, by welding on a metal cover. Several process and design requirements must be met to achieve high reliability flip chip assemblies. Reflowed devices must be free of flux residues because they are corrosive, provide a path for ion diffusion, are a source of moisture and degrade the adhesion of underfill to chip and substrate. Removal of flux residues by cleaning is problematic because the gap between chip and substrate is very small relative to chip area. A better approach is to bond chips without flux, as we do, by reflowing them in a formic acid environment. An important reliability requirement for strategic hardware is the ability to sustain many cycles over extended temperature ranges. Temperature cycles induce plastic deformation in the solder connections as a result of stresses generated by the mismatch in thermal expansion coefficients of the chip and package. These stresses can be reduced significantly by underfilling the bonded chip with a filled adhesive. Choice of material as well as process execution impact the effectiveness of underfill enhancement of reliability. Optimization of both the physical design and composition of the solder connections is essential to producing reliable flip chip assemblies. We make extensive use of finite element analyses (FEA) in which we track the accumulation of plastic strain energy in the solder connections as they are subjected to temperature cycle induced stresses. Good correlations between the energy accumulated per cycle and the number of cycles to failure can be achieved if accurate state models of the solder are used. We have a catalog of Anand models for the solder compositions that we use in our FEA simulations. One of the more challenging aspects of designing high performance flip chip packages is matching the size and pitch of the bond pads on the ceramic with those on the chip. Current devices use 90 micron diameter pads on 200 micron pitch, but newer designs are migrating towards 80 micron diameter pads on 180 micron pitch. It challenging to maintain tight tolerances on pad geometries in these higher density packages and to route all the additional signals. Thermal management is also an important component of the package design. Thermal vias and thermally conductive underfills are used to remove heat from the front side of the chip. On the backside of the chip, the gap between chip and cover is minimized and filled with a high thermal conductivity interface material. High fidelity FEA modeling is necessary to ensure that the chip can be adequately cooled in its hermetic environment. This paper discusses the impact of these design and assembly factors on the reliability of high performance, hermetically packaged flip chip assemblies.

Surface relief coupled grating design for near-eye display

As the most important optical component in a near-eye display system, the performance of a coupling grating directly determines the imaging quality of the final display system. In order to improve the diffraction efficiency and field of view (FOV) of the coupling device, this study proposes a novel surface relief coupling grating. The structural parameters of the surface relief coupled grating are simulated and calculated by using the finite-element analysis method. The simulation results show that the diffraction efficiency of the coupling grating can reach more than 99.5%. Compared with the traditional rectangular tilted grating, the diffraction efficiency has increased by 6.4%, and the full width at half-maximum of the incident angle has increased by 4°, which proves that the structure has higher diffraction efficiency and a larger FOV. Furthermore, the surface relief coupling grating is insensitive to operating conditions and processing errors, fully meeting the processability requirements. Therefore, this new type of surface relief coupling grating can replace traditional coupling gratings and is expected to become a key coupling component in the next generation of near-eye display systems.

Thyristor-based Rechargeable Battery Charger

In this project, our main objective is to design an automatic battery charger using Silicon-Controlled Rectifier (SCR) and simulate their operation. Batteries play a crucial role in safely storing electricity by converting electrical energy into chemical energy. The primary focus of our project is on thyristor-based rechargeable battery chargers, known for their high quality and competitive pricing. We delve into the design and simulation of automatic battery chargers employing SCR technology. This article encompasses the simulation, implementation, and partial construction of such a charger. The electronic circuit will be tailored to meet specific charging process requirements.

Research of the FLC + PID switching control strategy based on real-time error for the pneumatic polishing force regulating system

This paper designs an active pneumatic polishing force control system and investigates its control strategy. A straightforward method based on the experiments is proposed for identifying and modeling the pneumatic system and a convenient and effective control strategy based on real-time error is proposed for pneumatic polishing force regulating. Corresponding function between the input duty cycles and the output force values is created based on the experiment data tested by the system. Then the pneumatic force regulating system is modeled by the corresponding function. Base on the results of simulations and experiments, a FLC (Fuzzy Logic Control) + PID (Proportion-Integration-Differentiation) switching control strategy is designed with a switching mechanism to choose different control algorithm based on real-time error which can take the advantages of both PID and FLC. The FLC + PID switching controller can eliminate the steady state errors occurring in FLC controller and achieve the same accuracy as the PID controller but with a faster response speed. The approach effectively stabilizes the polishing force, resulting in polishing force errors that are distributed within ± 1 N. The mean errors are less than 0.2 N and the absolute mean errors hover around 0.3 N. The pneumatic polishing force control system regulated by the FLC + PID switching control exhibits effectiveness, stability, high control precision and fast response speed, and satisfies the force control requirements of polishing process.

Through-Space Charge-Transfer-Based Aggregation-Induced Emission and Thermally Activated Delayed Fluorescence in Fused 2H-Chromene Coumarin Congener Generating ROS for Antiviral (SARS-CoV-2) Approach.

Harvesting triplets in metal-free organic frameworks at ambient conditions and finding appropriate applications are a formidable challenge. Herein, we report a donor-acceptor-type system composed of carbazole and fused 2H-chromene coumarin derivative, exhibiting triplet harvesting thermally activated delayed fluorescence (TADF) and aggregation-induced emission (AIE) behavior in solid and aggregated states, respectively. The presence of an sp3 linker and the introduction of a selected cyano/ester group in the acceptor result in twisted D-A architectures, further assisting in the suppression of nonradiative deactivation via through-space charge transfer and H-bonding interactions, fulfilling the stringent requirements for the simultaneous process of TADF and AIE, successively. Experimental and theoretical results revealed that the participation of the singlet/triplet charge transfer (1CT/3CT) and the higher lying hybrid triplet locally excited charge-transfer state (3LE + 3CT) leads to an efficient TADF. Both of the synthesized AIE-TADF congeners actively participated in the generation of reactive oxygen species (ROS) in nanoaggregate forms and were further explored computationally for antiviral prospects as inhibitors of the SARS-CoV-2 spike protein.

Advancing Ultrasonic Defect Detection in High-Speed Wheels via UT-YOLO.

In the context of defect detection in high-speed railway train wheels, particularly in ultrasonic-testing B-scan images characterized by their small size and complexity, the need for a robust solution is paramount. The proposed algorithm, UT-YOLO, was meticulously designed to address the specific challenges presented by these images. UT-YOLO enhances its learning capacity, accuracy in detecting small targets, and overall processing speed by adopting optimized convolutional layers, a special layer design, and an attention mechanism. This algorithm exhibits superior performance on high-speed railway wheel UT datasets, indicating its potential. Crucially, UT-YOLO meets real-time processing requirements, positioning it as a practical solution for the dynamic and high-speed environment of railway inspections. In experimental evaluations, UT-YOLO exhibited good performance in best recall, mAP@0.5 and mAP@0.5:0.95 increased by 37%, 36%, and 43%, respectively; and its speed also met the needs of real-time performance. Moreover, an ultrasonic defect detection data set based on real wheels was created, and this research has been applied in actual scenarios and has helped to greatly improve manual detection efficiency.

Practices and barriers for big data projects

The adoption of big data analytics is increasing in every major industry, demanding investments in new projects, technologies, architectures, and processes to allow the integration of big data platforms with legacy systems; however, many organizations have failed to incorporate it effectively into their decision-making processes and project benefits have not been adequately captured. This study aims to further investigate how a big data analytics project can be implemented in insurance companies. A case study was conducted on one of the largest insurance companies in Brazil with interviews and document analysis. The study identified five main practices that were adopted to successfully implement a big data analytics project (implement automatic autoscaling alerts, use specialized big data tools, integrate the platform with legacy systems, comply with privacy legislation, and ensure the documentation of technical architecture using business process modeling), as well as four barriers that prevent its proper adoption (complexity of access to multicloud data sources, high processing requirements of unstructured data analysis, failure to attend to business necessities at the right time, and project delays brought by bureaucratic interdepartmental processes); some of these have not previously been identified. Finally, an action plan to address these issues is presented.

An evaluation research of constant false alarm rate algorithm for the application of underwater vehicles management system based on USBL sonar principles in shallow water

The paper presents an overview of underwater traffic management systems utilizing sonar principles. Based on the evaluation of the current situation both domestically and internationally, the research team has proposed the development of a underwater signal processing algorithm based on an adaptive threshold in the Ultra-short Baseline System (USBL). The theoretical results were implemented on FPGA hardware, not only enhancing signal detection capabilities but also meeting real-time signal processing requirements when deployed in complex underwater conditions in various shallow water regions of Vietnam. The research's future direction indicates substantial potential in the practical application of hydroacoustic signal processing algorithms when executing hardware implementations.

Quo vadis higher education? Post-pandemic success digital competencies of the higher educators – a Hungarian university case and actions

The purpose of this paper is to show the necessary competence sets for Higher Education (HE) lecturers in the framework of the COVID and post-COVID. A COVID-situated competence survey was carried out among university lecturers. Exploratory and confirmatory factor analyses (EFA, CFA) were applied to show the significant digital education competence factors. The representative online survey of 322 respondents shows that three big competence sets can be identified: Awareness, Professional, and Digital. Those having higher scores in Professional competencies foresee more digital programs and communications in the future, and not only the digital competencies but also the professional ones should be developed to meet the requirements of the digital education transformation process. The findings emphasize that the forced and drastic changes in the application of digital education to the intensification of COVID-19 should become sustainable and find its proper place and role in the future HE. The structured and closely managed use of the results was followed by a set of digital and professional competence development initiatives carried out within the framework of the Digital Education and Learning Support Centre, founded in 2020 at the University of Pécs.

Bioprocess optimization for enhanced xylitol synthesis by new isolate Meyerozyma caribbica CP02 using rice straw.

The present work models the fermentation process parameters of the newly isolated, Meyerozyma caribbica CP02 for enhanced xylitol production and its fermentability study on rice straw hydrolysate. The study examined the impact of each of the process variables by one variable at a time optimization followed by statistical validation. Temperature of 32°C, pH of 3.5, agitation of 200rpm, 1.5% (v/v) inoculum, 80 gL-1 initial xylose was optimized. Subsequently, a sequential two-stage agitation approach was adopted for fermentation. At these optimized conditions, xylitol yield of 0.77 gg-1 and 0.64 gg-1 was achieved using media containing commercial and rice straw derived xylose, respectively. For scale up, in 3L batch bioreactor, the highest xylitol yield (0.63 gg-1) was attained at 72h with rice straw hydrolysate media containing initial xylose (59.48 ± 0.82 gL-1) along with inhibitors (1.55 ± 0.10 gL-1 aliphatic acids, 0.0.048 ± 0.11 gL-1 furans, 0.64 ± 0.23 gL-1 total phenols). The results imply that even under circumstances characterized by an acidic pH and elevated initial xylose level, M. caribbica CP02, as an isolate, displays robustness and shows favorable fermentability of rice straw hydrolysate. Therefore, isolate CP02 has potential to be used in bio-refineries for high yield xylitol production with minimal hydrolysate processing requirements.

WildARe-YOLO: A lightweight and efficient wild animal recognition model

For the protection of endangered species and successful wildlife population monitoring, wild animal recognition is essential. While deep learning models like YOLOv5 have shown promise in real-time object recognition, their practical applicability may be constrained by their high processing requirements. In this paper, we suggest a faster and lighter version of YOLOv5s for wild animal recognition. To lower computational costs for model parameters and floating-point operations (FLOPs) for the backbone, our suggested model includes Mobile Bottleneck Block modules and an improved StemBlock. We also use Focal-EIoU as a loss function to gauge the accuracy of the predicted bounding boxes during inference and employ a BiFPN-based neck. We tested our technique on three datasets, including Wild Animal Facing Extinction, Fishmarket, and MS COCO 2017. Additionally, our technique is compared with state-of-the-art deep learning models, and from the baseline model we recorded a 17.65% increase in FPS, 28.55% model parameters reduction, and 50.92% in FLOPs reduction. Furthermore, our model has a faster model loading time, which is critical for deployment in remote areas. This enables real-time species recognition on basic hardware, aiding conservation efforts through rapid analysis. The model advances deep learning in ecology by balancing efficiency with performance.

Purines recognition and quantitative analysis by surface-enhanced Raman spectroscopy

The common quantification methods of purines, including high-performance liquid chromatography, micellar electrokinetic chromatography, reverse phase ion pair chromatography, and capillary zone electrophoresis, have been used for the analysis of purines. These conventional techniques are limited by long operation times, large sample volumes, requirements for pretreatment and separation processes, or sophisticated, bulky and expensive equipment. Here, we have developed a simple method to prepare a probe for the quantitative analysis of purines using the surface-enhanced Raman scattering (SERS) method. The SERS probe is a rough Ag wire obtained with simple electrochemical treatment, which is optimized to reach the maximum SERS signal enhancement. The Raman enhancement factor (EF) of Ag wire after roughening can reach ∼106. Under optimized conditions, the rough Ag wire is capable of recognizing four purine bases (namely, guanine, adenine, hypoxanthine, and xanthine) in the range of 10−5 to 10−1 mg/mL with a linear relationship between SERS intensity of signature peak and purine concentration. The recovery rate of each purine base is higher than 80% in the mixture of four purines. The overall method was successfully applied to the monitoring of the level of purines in marketplace beer beverages. The novel wire-based SERS sensor used with portable Raman spectroscopy is prospective in diet safety and personalized point-of-care medical detection.