Multisource Heterogeneous Data Fusion Analysis of Regional Digital Construction Based on Machine Learning

In modern urban construction, digitalization has become a trend, but the single source of information of traditional algorithms can not meet people’s needs, so the data fusion technology needs to draw estimation and judgment from multisource data to increase the confidence of data, improve reliability, and reduce uncertainty. In order to understand the influencing factors of regional digitalization, this paper conducts multisource heterogeneous data fusion analysis based on regional digitalization of machine learning, using decision tree and artificial neural network algorithm, compares the management efficiency and satisfaction of school population under different algorithms, and understands the data fusion and construction under different algorithms. According to the results, decision-making tree and artificial neural network algorithms were more efficient than traditional methods in building regional digitization, and their magnitude was about 60% higher. More importantly, the machine learning-based methods in multisource heterogeneous data fusion have been better than traditional calculation methods both in computational efficiency and misleading rate with respect to false alarms and missed alarms. This shows that machine learning methods can play an important role in the analysis of multisource heterogeneous data fusion in regional digital construction.

Deep Learning Based Emotion Recognition and Visualization of Figural Representation

This exploration aims to study the emotion recognition of speech and graphic visualization of expressions of learners under the intelligent learning environment of the Internet. After comparing the performance of several neural network algorithms related to deep learning, an improved convolution neural network-Bi-directional Long Short-Term Memory (CNN-BiLSTM) algorithm is proposed, and a simulation experiment is conducted to verify the performance of this algorithm. The experimental results indicate that the Accuracy of CNN-BiLSTM algorithm reported here reaches 98.75%, which is at least 3.15% higher than that of other algorithms. Besides, the Recall is at least 7.13% higher than that of other algorithms, and the recognition rate is not less than 90%. Evidently, the improved CNN-BiLSTM algorithm can achieve good recognition results, and provide significant experimental reference for research on learners’ emotion recognition and graphic visualization of expressions in an intelligent learning environment.

OMNeT++ Framework for Simulation of Centralized and Distributed Algorithms in Multi-Hop Networks

Theoretical applications and practical network algorithms are not very cost-effective, and most of the algorithms in the commercial market are implemented in the cutting-edge devices. Open-source network simulators have gained importance in recent years due to the necessity to implement network algorithms in more realistic scenarios with reasonable costs, especially for educational purposes and scientific researches. Although there have been various simulation tools, NS2 and NS3, OMNeT++ is more suitable to demonstrate network algorithms because it is convenient for the model establishment, modularization, expandability, etc. OMNeT++ network simulator is selected as a testbed in order to verify the correctness of the network algorithms. The study focuses on the algorithms based on centralized and distributed approaches for multi-hop networks in OMNeT++. Two network algorithms, the shortest path algorithm and flooding-based asynchronous spanning tree algorithm, were examined in OMNeT++. The implementation, analysis, and visualization of these algorithms have also been addressed.

A Study on the Application and the Advancement of Deep Neural Network Algorithm

Deep neural network is a new type of learning algorithm, which has both global and local aspects and performs well in pattern recognition and computational speed. In recent years, deep neural network algorithm has been widely used in scientific research and real life, but its complexity, parallelism and other characteristics lead it to be a very challenging and innovative research area. This study briefly introduces the basic principles and theoretical knowledge of deep neural network algorithms, and mainly discusses their applications and Advancement of feature extraction in the field.

Waveform processing using neural network algorithms on the front-end electronics

In a multi-channel radiation detector readout system, waveform sampling, digitization, and raw data transmission to the data acquisition system constitute a conventional processing chain. The deposited energy on the sensor is estimated by extracting peak amplitudes, area under pulse envelopes from the raw data, and starting times of signals or time of arrivals. However, such quantities can be estimated using machine learning algorithms on the front-end Application-Specific Integrated Circuits (ASICs), often termed as “edge computing”. Edge computation offers enormous benefits, especially when the analytical forms are not fully known or the registered waveform suffers from noise and imperfections of practical implementations. In this work, we aim to predict peak amplitude from a single waveform snippet whose rising and falling edges containing only 3 to 4 samples. We thoroughly studied two well-accepted neural network algorithms, Multi-Layer Perceptron (MLP) and Convolutional Neural Network (CNN) by varying their model sizes. To better fit front-end electronics, neural network model reduction techniques, such as network pruning methods and variable-bit quantization approaches, were also studied. By combining pruning and quantization, our best performing model has the size of 1.5 KB, reduced from 16.6 KB of its full model counterpart. It can reach mean absolute error of 0.034 comparing to that of a naive baseline of 0.135. Such parameter-efficient and predictive neural network models established feasibility and practicality of their deployment on front-end ASICs.

Comparative Evaluation of Predicting Energy Consumption of Absorption Heat Pump with Multilayer Shallow Neural Network Training Algorithms

The performance of various multilayer neural network algorithms to predict the energy consumption of an absorption chiller in an air conditioning system under the same conditions was compared and evaluated in this study. Each prediction model was created using 12 representative multilayer shallow neural network algorithms. As training data, about a month of actual operation data during the heating period was used, and the predictive performance of 12 algorithms according to the training size was evaluated. The prediction results indicate that the error rates using the measured values are 0.09% minimum, 5.76% maximum, and 1.94 standard deviation (SD) for the Levenberg–Marquardt backpropagation model and 0.41% minimum, 5.05% maximum, and 1.68 SD for the Bayesian regularization backpropagation model. The conjugate gradient with Polak–Ribiére updates backpropagation model yielded lower values than the other two models, with 0.31% minimum, 5.73% maximum, and 1.76 SD. Based on the results for the predictive performance evaluation index, CvRMSE, all other models (conjugate gradient with Fletcher–Reeves updates backpropagation, one-step secant backpropagation, gradient descent with momentum and adaptive learning rate backpropagation, gradient descent with momentum backpropagation) except for the gradient descent backpropagation model yielded results that satisfy ASHRAE (American Society of Heating, Refrigerating and Air-Conditioning Engineers) Guideline 14. The results of this study confirm that the prediction performance may differ for each multilayer neural network training algorithm. Therefore, selecting the appropriate model to fit the characteristics of a specific project is essential.

Analysis of Algorithms for Searching Objects in Images Using Convolutional Neural Network

The problem of finding objects in images using modern computer vision algorithms has been considered. The description of the main types of algorithms and methods for finding objects based on the use of convolutional neural networks has been given. A comparative analysis and modeling of neural network algorithms to solve the problem of finding objects in images has been conducted. The results of testing neural network models with different architectures on data sets VOC2012 and COCO have been presented. The results of the study of the accuracy of recognition depending on different hyperparameters of learning have been analyzed. The change in the value of the time of determining the location of the object depending on the different architectures of the neural network has been investigated.