School of Electronic Information Engineering, Changchun University of Science and Technology, Changchun, China.
PLoS One. 2024 Sep 13;19(9):e0310101. doi: 10.1371/journal.pone.0310101. eCollection 2024.
It is critical to identify and detect hazardous, flammable, explosive, and poisonous gases in the realms of industrial production and medical diagnostics. To detect and categorize a range of common hazardous gasses, we propose an attention-based Long Short term memory Full Convolutional network (ALSTM-FCN) in this paper. We adjust the network parameters of ALSTM-FCN using the Sparrow search algorithm (SSA) based on this, by comparison, SSA outperforms Particle Swarm Optimization (PSO) Algorithm, Genetic Algorithm (GA), Gray Wolf Optimization (GWO) Algorithm, Cuckoo Search (CS) Algorithm and other traditional optimization algorithms. We evaluate the model using University of California-Irvine (UCI) datasets and compare it with LSTM and FCN. The findings indicate that the ALSTM-FCN hybrid model has a better reliability test accuracy of 99.461% than both LSTM (89.471%) and FCN (96.083%). Furthermore, AdaBoost, logistic regression (LR), extra tree (ET), decision tree (DT), random forest (RF), K-nearest neighbor (KNN) and other models were trained. The suggested approach outperforms the conventional machine learning model in terms of gas categorization accuracy, according to experimental data. The findings indicate a potential for a broad range of polluting gas detection using the suggested ALSTM-FCN model, which is based on SSA optimization.
在工业生产和医疗诊断领域，识别和检测危险、易燃、易爆和有毒气体至关重要。为了检测和分类一系列常见的危险气体，我们在本文中提出了一种基于注意力的长短期记忆全卷积网络（ALSTM-FCN）。我们基于此使用麻雀搜索算法（SSA）调整 ALSTM-FCN 的网络参数，通过比较，SSA 优于粒子群优化算法（PSO）、遗传算法（GA）、灰狼优化算法（GWO）、布谷鸟搜索算法（CS）等传统优化算法。我们使用加利福尼亚大学欧文分校（UCI）数据集评估模型，并将其与 LSTM 和 FCN 进行比较。研究结果表明，ALSTM-FCN 混合模型的可靠性测试准确率为 99.461%，优于 LSTM（89.471%）和 FCN（96.083%）。此外，我们还训练了 AdaBoost、逻辑回归（LR）、极端随机树（ET）、决策树（DT）、随机森林（RF）、K-近邻（KNN）等模型。根据实验数据，与传统机器学习模型相比，所提出的方法在气体分类准确率方面表现更优。研究结果表明，基于 SSA 优化的所提出的 ALSTM-FCN 模型具有广泛应用于污染气体检测的潜力。
