Optimizing the Neural Structure and Hyperparameters of Liquid State Machines Based on Evolutionary Membrane Algorithm

Design and Development of an Imitation Detection System for Human Action Recognition Using Deep Learning

Human action recognition (HAR) is a rapidly growing field with numerous applications in various domains. HAR involves the development of algorithms and techniques to automatically identify and classify human actions from video data. Accurate recognition of human actions has significant implications in fields such as surveillance and sports analysis and in the health care domain. This paper presents a study on the design and development of an imitation detection system using an HAR algorithm based on deep learning. This study explores the use of deep learning models, such as a single-frame convolutional neural network (CNN) and pretrained VGG-16, for the accurate classification of human actions. The proposed models were evaluated using a benchmark dataset, KTH. The performance of these models was compared with that of classical classifiers, including K-Nearest Neighbors, Support Vector Machine, and Random Forest. The results showed that the VGG-16 model achieved higher accuracy than the single-frame CNN, with a 98% accuracy rate.

High speed human action recognition using a photonic reservoir computer

The recognition of human actions in videos is one of the most active research fields in computer vision. The canonical approach consists in a more or less complex preprocessing stages of the raw video data, followed by a relatively simple classification algorithm. Here we address recognition of human actions using the reservoir computing algorithm, which allows us to focus on the classifier stage. We introduce a new training method for the reservoir computer, based on "Timesteps Of Interest", which combines in a simple way short and long time scales. We study the performance of this algorithm using both numerical simulations and a photonic implementation based on a single non-linear node and a delay line on the well known KTH dataset. We solve the task with high accuracy and speed, to the point of allowing for processing multiple video streams in real time. The present work is thus an important step towards developing efficient dedicated hardware for video processing.

Application of Chaos Mutation Adaptive Sparrow Search Algorithm in Edge Data Compression

In view of the large amount of data collected by an edge server, when compression technology is used for data compression, data classification accuracy is reduced and data loss is large. This paper proposes a data compression algorithm based on the chaotic mutation adaptive sparrow search algorithm (CMASSA). Constructing a new fitness function, CMASSA optimizes the hyperparameters of the Convolutional Auto-Encoder Network (CAEN) on the cloud service center, aiming to obtain the optimal CAEN model. The model is sent to the edge server to compress the data at the lower level of edge computing. The effectiveness of CMASSA performance is tested on ten high-dimensional benchmark functions, and the results show that CMASSA outperforms other comparison algorithms. Subsequently, experiments are compared with other literature on the Multi-class Weather Dataset (MWD). Experiments show that under the premise of ensuring a certain compression ratio, the proposed algorithm not only has better accuracy in classification tasks than other algorithms but also maintains a high degree of data reconstruction.

An Enhanced Proximal Policy Optimization-Based Reinforcement Learning Method with Random Forest for Hyperparameter Optimization

For most machine learning and deep learning models, the selection of hyperparameters has a significant impact on the performance of the model. Therefore, deep learning and data analysis experts have to spend a lot of time on hyperparameter tuning when building a model for accomplishing a task. Although there are many algorithms used to solve hyperparameter optimization (HPO), these methods require the results of the actual trials at each epoch to help perform the search. To reduce the number of trials, model-based reinforcement learning adopts multilayer perceptron (MLP) to capture the relationship between hyperparameter settings and model performance. However, MLP needs to be carefully designed because there is a risk of overfitting. Thus, we propose a random forest-enhanced proximal policy optimization (RFEPPO) reinforcement learning algorithm to solve the HPO problem. In addition, reinforcement learning as a solution to HPO will encounter the sparse reward problem, eventually leading to slow convergence. To address this problem, we employ the intrinsic reward, which introduces the prediction error as the reward signal. Experiments carried on nine tabular datasets and two image classification datasets demonstrate the effectiveness of our model.