In the context of today's digital production, the quality inspection of printed materials has become a key technology to improve printing efficiency and quality of finished products. Especially with the rapid deve...
详细信息
ISBN:
(数字)9798331533694
ISBN:
(纸本)9798331533700
In the context of today's digital production, the quality inspection of printed materials has become a key technology to improve printing efficiency and quality of finished products. Especially with the rapid development of the printing industry, the traditional manual inspection method has been difficult to meet the needs of large-scale, high-efficiency production. In order to solve this problem, the automatic inspection system of print defects based on machine vision comes into being, which can not only greatly improve the detection speed and accuracy, but also effectively reduce the labor cost. This paper proposes an efficient defect detection method for printed materials, combining key technologies such as image differencing, binarization, mathematical morphology algorithms, Blob analysis and connectivity analysis to realize automatic identification and classification of minor defects in printed materials. The design and experimental results of the system show that the method has significant advantages in real-time and detection accuracy, and is expected to play an important role in future printing quality control.
This study presents an integrated framework combining 1D-CNN-LSTM-Autoencoder-based anomaly detection with identity authentication using machine learning classifiers. The 1D-CNN-LSTM Autoencoder enhances system reliab...
详细信息
ISBN:
(数字)9798331510473
ISBN:
(纸本)9798331510480
This study presents an integrated framework combining 1D-CNN-LSTM-Autoencoder-based anomaly detection with identity authentication using machine learning classifiers. The 1D-CNN-LSTM Autoencoder enhances system reliability by identifying and excluding faulty intervals in timeseries data caused by system instability or random movements. The dataset, collected under a controlled protocol, features scenarios such as Resting and Valsalva maneuvers for training and testing. To address measurement data interference, which can affect identity recognition accuracy, anomaly detection filters out corrupted signals, maintaining system stability and reliability. Among the machine learning classifiers, Cubic SVM demonstrated superior performance, achieving an accuracy of 8 8. 7 %. This integrated approach enhances system robustness, offering promising applications in secure access control, smart environments, and healthcare monitoring.
This paper demonstrates a brushless DC motor (BLDCM) fed water pumping system driven by the solar photovoltaic array (SPVA) under dynamic partial shading conditions. For extraction of maximum power from SPVA, a zeta c...
详细信息
ISBN:
(数字)9798331542108
ISBN:
(纸本)9798331542115
This paper demonstrates a brushless DC motor (BLDCM) fed water pumping system driven by the solar photovoltaic array (SPVA) under dynamic partial shading conditions. For extraction of maximum power from SPVA, a zeta converter (ZC) is utilized. However, under partial shading conditions, the SPVA experience multiple maximum power points (MPP). The conventional MPP tracking methods are ineffective in identifying the global MPP points as they converge to the local MPP points. Therefore, the utmost power cannot be extracted, when SPVA working under partially shaded conditions. Thus, this paper demonstrates the use of hybrid perturb & observe and particle swarm optimization techniques to track the global MPP. In this work, the SPVA's power extracted by ZC is fed to BLDCM for water pumping application using VSI. The VSI of a BLDCM typically functions at a significantly high frequency. This work proposes operating the VSI at a fundamental switching frequency to alleviate difficulties associated with high switching frequency. The suggested system is studied in MATLAB®/Simulink environment to validate its performance under various operational instances.
The integration of Information and Communication technology (ICT) into India's education system represents a transformative approach toward fostering inclusive education. This paper explores the evolution of ICT i...
详细信息
ISBN:
(数字)9798331521691
ISBN:
(纸本)9798331521707
The integration of Information and Communication technology (ICT) into India's education system represents a transformative approach toward fostering inclusive education. This paper explores the evolution of ICT in Indian education, highlighting its implementation in rural and aspirational districts as part of the Aspirational Districts Program (ADP). While ICT has shown promise in bridging educational disparities by promoting access, equity, and quality, challenges such as digital divides and resource limitations persist, particularly in underdeveloped regions. Through case studies and programmatic insights, this paper evaluates ICT's role as a catalyst for social change, offering policy recommendations for enhancing ICT-enabled learning in rural India. The findings underscore ICT's potential to address systemic barriers, driving progress toward equitable and inclusive education nationwide.
This study describes an enhanced PV grid tied system featuring PSO based MPPT controller and PI controller for efficient power conversion and grid support. A Luo converter regulates DC voltage, while a single phase VS...
详细信息
ISBN:
(数字)9798331507671
ISBN:
(纸本)9798331507688
This study describes an enhanced PV grid tied system featuring PSO based MPPT controller and PI controller for efficient power conversion and grid support. A Luo converter regulates DC voltage, while a single phase VSI connects to grid. The PSO based MPPT optimizes the Luo converter's duty cycle for maximum power extraction, and the PI controller stabilizes power flow by managing active and reactive power. The proposed system demonstrates superior dynamic response and adaptability to changing environmental conditions, enabling efficient energy utilization and reliable grid integration. The Matlab/Simulink program is utilized to acquire the simulation results, which are then used to evaluate the circuit's efficacy. Simulation results highlight the performance improvements in power extraction and grid stability compared to traditional MPPT methods. When the controllers are compared, the THD value of the intended task is 1.58%, and the efficiency achieved with the Luo converter is 93.5%.
This paper studies the solution methods of mathematical programming problems based on intelligent optimization algorithms, focusing on the application and performance of GA and PSO in complex mathematical programming....
详细信息
ISBN:
(数字)9798350389579
ISBN:
(纸本)9798350389586
This paper studies the solution methods of mathematical programming problems based on intelligent optimization algorithms, focusing on the application and performance of GA and PSO in complex mathematical programming. First, a hybrid intelligent algorithm that integrates the characteristics of genetic algorithm and particle swarm optimization is designed. By optimizing the coding structure, selection strategy and crossover mutation operator, the global search ability and convergence speed of the algorithm are improved. Secondly, a mathematical model suitable for integer programming and nonlinear programming is constructed, and experimental verification of problems of different scales is carried out in combination with the simulation platform. Experiments show that in typical test functions and actual application scenarios, the improved algorithm improves the solution accuracy by 15.3% and shortens the convergence time by 18.7 % compared with the traditional method. The simulation results prove the effectiveness and robustness of the improved algorithm through quantitative data analysis, especially in solving high-dimensional nonlinear problems. The research in this paper not only expands the application of intelligent optimization algorithms in the field of mathematical programming, but also provides a theoretical basis and practical reference for solving actual engineering optimization problems.
Epileptic seizure recognition (ESR) is a vital area in healthcare, neurology, and patient monitoring, particularly for managing epilepsy in real time. While deep learning (DL) models have shown exceptional performance...
详细信息
ISBN:
(数字)9798331542108
ISBN:
(纸本)9798331542115
Epileptic seizure recognition (ESR) is a vital area in healthcare, neurology, and patient monitoring, particularly for managing epilepsy in real time. While deep learning (DL) models have shown exceptional performance in recognizing seizures from EEG signals, processing sequential and time-series data remains challenging. This study proposes a hybrid deep learning framework combining one-dimensional convolutional neural networks (1D CNN) and bidirectional long short-term memory (BiLSTM) networks to enhance seizure recognition. The 1D CNN efficiently captures localized temporal features from EEG data, while the BiLSTM models bidirectional long-range dependencies, improving temporal feature representation. Tested on a benchmark dataset, the model achieves an outstanding accuracy of 98.18%, surpassing existing state-of-the-art methods. These results underscore the effectiveness of integrating CNN for feature extraction and BiLSTM for sequence modeling, offering a robust and reliable approach for automated ESR in clinical applications.
We investigate an internet-of-things system where energy-harvesting devices send status updates to a common receiver using the irregular repetition slotted ALOHA (IRSA) protocol. Energy shortages in these devices may ...
详细信息
ISBN:
(数字)9798350368369
ISBN:
(纸本)9798350368376
We investigate an internet-of-things system where energy-harvesting devices send status updates to a common receiver using the irregular repetition slotted ALOHA (IRSA) protocol. Energy shortages in these devices may lead to transmission failures that are unknown to the receiver, disrupting the decoding process. To address this issue, we propose a method for the receiver to perfectly identify such failures. Furthermore, we optimize the degree distribution of the protocol to enhance the freshness of the status updates. Our optimized degree distribution mitigates the adverse effects of potential transmission failures. Numerical results demonstrate that, despite energy-harvesting constraints, IRSA can achieve a level of information freshness comparable to systems with unlimited energy.
This paper presents a chatbot model designed to detect stress in users through simple yes-or-no questions. Utilizing a Support Vector Machine (SVM) algorithm, the model achieves high accuracy in identifying stress lev...
详细信息
ISBN:
(数字)9798331529833
ISBN:
(纸本)9798331529840
This paper presents a chatbot model designed to detect stress in users through simple yes-or-no questions. Utilizing a Support Vector Machine (SVM) algorithm, the model achieves high accuracy in identifying stress levels and provides users with actionable advice or medical recommendations. The chatbot’s user-friendly interface is built using Anaconda Navigator and Python, ensuring ease of use for non-technical users. The model achieves a 100% accuracy rate on the given dataset, making it a promising tool for stress detection and early intervention.
Stillbirth remains a critical issue in obstetrics, with various underlying factors contributing to fetal mortality. Early detection of potential risks can significantly improve clinical outcomes. This paper presents a...
详细信息
ISBN:
(数字)9798331520762
ISBN:
(纸本)9798331520779
Stillbirth remains a critical issue in obstetrics, with various underlying factors contributing to fetal mortality. Early detection of potential risks can significantly improve clinical outcomes. This paper presents a simple framework for detecting stillbirth risks using fetal heart rate and fetal movement data. The framework is implemented as a Java-based software system that analyzes heart rate and fetal movement data, offering a preliminary model for monitoring fetal health. This approach aims to support clinicians in their decision-making process and foster further development of more sophisticated monitoring systems in the future. The proposed system is not intended to replace medical professionals but rather serves as an auxiliary tool for early detection of potential stillbirth risks based on available monitoring data.
暂无评论