A Survey on Deep Learning for Human Activity Recognition

Human activity recognition is a key to a lot of applications such as healthcare and smart home. In this study, we provide a comprehensive survey on recent advances and challenges in human activity recognition (HAR) with deep learning. Although there are many surveys on HAR, they focused mainly on the taxonomy of HAR and reviewed the state-of-the-art HAR systems implemented with conventional machine learning methods. Recently, several works have also been done on reviewing studies that use deep models for HAR, whereas these works cover few deep models and their variants. There is still a need for a comprehensive and in-depth survey on HAR with recently developed deep learning methods.

Comparative Study of Convolutional Neural Network and Conventional Machine Learning Methods for Landslide Susceptibility Mapping

Landslide susceptibility mapping (LSM) is a useful tool to estimate the probability of landslide occurrence, providing a scientific basis for natural hazards prevention, land use planning, and economic development in landslide-prone areas. To date, a large number of machine learning methods have been applied to LSM, and recently the advanced convolutional neural network (CNN) has been gradually adopted to enhance the prediction accuracy of LSM. The objective of this study is to introduce a CNN-based model in LSM and systematically compare its overall performance with the conventional machine learning models of random forest, logistic regression, and support vector machine. Herein, we selected Zhangzha Town in Sichuan Province, China, and Lantau Island in Hong Kong, China, as the study areas. Each landslide inventory and corresponding predisposing factors were stacked to form spatial datasets for LSM. The receiver operating characteristic analysis, area under the curve (AUC), and several statistical metrics, such as accuracy, root mean square error, Kappa coefficient, sensitivity, and specificity, were used to evaluate the performance of the models. Finally, the trained models were calculated, and the landslide susceptibility zones were mapped. Results suggest that both CNN and conventional machine learning-based models have a satisfactory performance. The CNN-based model exhibits an excellent prediction capability and achieves the highest performance but also significantly reduces the salt-of-pepper effect, which indicates its great potential for application to LSM.

QNet: A Scalable and Noise-Resilient Quantum Neural Network Architecture for Noisy Intermediate-Scale Quantum Computers

Quantum machine learning (QML) is promising for potential speedups and improvements in conventional machine learning (ML) tasks. Existing QML models that use deep parametric quantum circuits (PQC) suffer from a large accumulation of gate errors and decoherence. To circumvent this issue, we propose a new QML architecture called QNet. QNet consists of several small quantum neural networks (QNN). Each of these smaller QNN’s can be executed on small quantum computers that dominate the NISQ-era machines. By carefully choosing the size of these QNN’s, QNet can exploit arbitrary size quantum computers to solve supervised ML tasks of any scale. It also enables heterogeneous technology integration in a single QML application. Through empirical studies, we show the trainability and generalization of QNet and the impact of various configurable variables on its performance. We compare QNet performance against existing models and discuss potential issues and design considerations. In our study, we show 43% better accuracy on average over the existing models on noisy quantum hardware emulators. More importantly, QNet provides a blueprint to build noise-resilient QML models with a collection of small quantum neural networks with near-term noisy quantum devices.

Automated Corn Seed Fusarium Disease Classification System Using Hybrid Feature Space and Conventional Machine Learning Techniques

The purpose of this learning is to detect the Corn Seed Fusarium Disease using Hybrid Feature Space and Conventional machine learning (ML) approaches. A novel machine learning approach is employed for the classification of a total of six types of corn seed are collected which contain Infected Fusarium (moniliforme, graminearum, gibberella, verticillioides, kernel) as well as healthy corn seed, based on a multi-feature dataset, which is the grouping of geometric, texture and histogram features extracted from digital images. For each corn seed image, a total of twenty-five multi-features have been developed on every area of interest (AOI), sizes (50 × 50), (100 × 100), (150 × 150), and (200 × 200). A total of seven optimized features were selected by using a machine learning-based algorithm named “Correlation-based Feature Selection”. For experimentation, “Random forest”, “BayesNet” and “LogitBoost” have been employed using an optimized multi-feature user-supplied dataset divided with 70% training and 30 % testing. A comparative analysis of three ML classifiers RF, BN, and LB have been used and a considerably very high classification ratio of 96.67 %, 97.22 %, and 97.78 % have been achieved respectively when the AOI size (200×200) have been deployed to the classifiers.

A Demand-Side Load Event Detection Algorithm Based on Wide-Deep Neural Networks and Randomized Sparse Backpropagation

Event detection is an important application in demand-side management. Precise event detection algorithms can improve the accuracy of non-intrusive load monitoring (NILM) and energy disaggregation models. Existing event detection algorithms can be divided into four categories: rule-based, statistics-based, conventional machine learning, and deep learning. The rule-based approach entails hand-crafted feature engineering and carefully calibrated thresholds; the accuracies of statistics-based and conventional machine learning methods are inferior to the deep learning algorithms due to their limited ability to extract complex features. Deep learning models require a long training time and are hard to interpret. This paper proposes a novel algorithm for load event detection in smart homes based on wide and deep learning that combines the convolutional neural network (CNN) and the soft-max regression (SMR). The deep model extracts the power time series patterns and the wide model utilizes the percentile information of the power time series. A randomized sparse backpropagation (RSB) algorithm for weight filters is proposed to improve the robustness of the standard wide-deep model. Compared to the standard wide-deep, pure CNN, and SMR models, the hybrid wide-deep model powered by RSB demonstrates its superiority in terms of accuracy, convergence speed, and robustness.

New recommendation to predict export value using big data and machine learning technique

Official statistics on monthly export values have a publicity lag between the current period and the published publication. None of the previous researchers estimated the value of exports for the monthly period. This circumstance is due to limitations in obtaining supporting data that can predict the criteria for the current export value of goods. AIS data is one type of big data that can provide solutions in producing the latest indicators to forecast export values. Statistical Methods and Conventional Machine Learning are implemented as forecasting methods. Seasonal ARIMA and Artificial Neural Network (ANN) methods are both used in research to forecast the value of Indonesia’s exports. However, ANN has a weakness that requires high computational costs to obtain optimal parameters. Genetic Algorithm (GA) is effective in increasing ANN accuracy. Based on these backgrounds, this paper aims to develop and select an AIS indicator to predict the monthly export value in Indonesia and optimize ANN performance by combining the ANN algorithm with the genetic algorithm (GA-ANN). The research successfully established five indicators that can be used as predictors in the forecasting model. According to the model evaluation results, the genetic algorithm has succeeded in improving the performance of the ANN model as indicated by the resulting RMSE GA-ANN value, which is smaller than the RMSE of the ANN model.

AttCRISPR: a spacetime interpretable model for prediction of sgRNA on-target activity

Background More and more Cas9 variants with higher specificity are developed to avoid the off-target effect, which brings a significant volume of experimental data. Conventional machine learning performs poorly on these datasets, while the methods based on deep learning often lack interpretability, which makes researchers have to trade-off accuracy and interpretability. It is necessary to develop a method that can not only match deep learning-based methods in performance but also with good interpretability that can be comparable to conventional machine learning methods. Results To overcome these problems, we propose an intrinsically interpretable method called AttCRISPR based on deep learning to predict the on-target activity. The advantage of AttCRISPR lies in using the ensemble learning strategy to stack available encoding-based methods and embedding-based methods with strong interpretability. Comparison with the state-of-the-art methods using WT-SpCas9, eSpCas9(1.1), SpCas9-HF1 datasets, AttCRISPR can achieve an average Spearman value of 0.872, 0.867, 0.867, respectively on several public datasets, which is superior to these methods. Furthermore, benefits from two attention modules—one spatial and one temporal, AttCRISPR has good interpretability. Through these modules, we can understand the decisions made by AttCRISPR at both global and local levels without other post hoc explanations techniques. Conclusion With the trained models, we reveal the preference for each position-dependent nucleotide on the sgRNA (short guide RNA) sequence in each dataset at a global level. And at a local level, we prove that the interpretability of AttCRISPR can be used to guide the researchers to design sgRNA with higher activity.

Online Shopper Intention Analysis Using Conventional Machine Learning And Deep Neural Network Classification Algorithm

The use of e-commerce throughout the world in recent years is very rapid. The continuous increase in sales shows that e-commerce has huge market potential. Store profits are derived from the process of assessing data to identify and classify online shopper intentions. The process of assessing the data uses conventional machine learning algorithms and deep neural networks. Comparison of algorithms in this study using the python programming language by knowing the value of Accuracy, F1-Score, Precision, Recall, and ROC AUC. The test results show that the accuracy of the deep neural network algorithm is 98.48%, the F1 score is 95.06%, precision is 97.36%, recall is 96.81% and AUC is 96.81%. So, based on this research, deep neural network data mining techniques can be an effective algorithm for online shopper intention data sets with cross-validation folds of 10, six hidden layer decoder-encoder variations, relu-sigmoid activation function, adagrad optimizer, and learning rate of 0.01 and no dropout. The value of this deep neural network algorithm is quite dominant compared to conventional machine learning algorithms and related research.

Automatic Diagnosis of Schizophrenia in EEG Signals Using CNN-LSTM Models

Schizophrenia (SZ) is a mental disorder whereby due to the secretion of specific chemicals in the brain, the function of some brain regions is out of balance, leading to the lack of coordination between thoughts, actions, and emotions. This study provides various intelligent deep learning (DL)-based methods for automated SZ diagnosis via electroencephalography (EEG) signals. The obtained results are compared with those of conventional intelligent methods. To implement the proposed methods, the dataset of the Institute of Psychiatry and Neurology in Warsaw, Poland, has been used. First, EEG signals were divided into 25 s time frames and then were normalized by z-score or norm L2. In the classification step, two different approaches were considered for SZ diagnosis via EEG signals. In this step, the classification of EEG signals was first carried out by conventional machine learning methods, e.g., support vector machine, k-nearest neighbors, decision tree, naïve Bayes, random forest, extremely randomized trees, and bagging. Various proposed DL models, namely, long short-term memories (LSTMs), one-dimensional convolutional networks (1D-CNNs), and 1D-CNN-LSTMs, were used in the following. In this step, the DL models were implemented and compared with different activation functions. Among the proposed DL models, the CNN-LSTM architecture has had the best performance. In this architecture, the ReLU activation function with the z-score and L2-combined normalization was used. The proposed CNN-LSTM model has achieved an accuracy percentage of 99.25%, better than the results of most former studies in this field. It is worth mentioning that to perform all simulations, the k-fold cross-validation method with k = 5 has been used.