Extreme Learning Machine-Based Deep Model for Human Activity Recognition With Wearable Sensors

It is well-known that solar power depends on many complex parameters such as humidity, radiation, temperature, dust and wind speed. In order to cope with these complex structures and to provide an accurate forecast, the development of reliable and effective forecasting methodology is very significant. In this study, an Artificial Neural Network (ANN)-based system has been developed to forecast very short-term (2 to 4-h) power output of a grid tied Photovoltaic Power Plant (PVPP). An algorithm called Extreme Learning Machine (ELM) has gained increasing interest through its extremely fast learning and good generalization capability. The Kernel Extreme Learning Machine (KELM) which is the improved version of the ELM is proposed to develop a very short-term PVPP power forecast system. The most important feature of KELM is that it has less adjustable parameters and better generalization ability when compared with classical ELM. Experimental studies have been carried out on a grid tied PVPP that has 1 (MW) installed power capacity. The inputs of the KELM-based forecast system are selected as solar power, humidity, radiation and temperature. All data are divided into four parts to analyze the effect of seasons on the performance of the proposed forecast system. The comparison studies are carried out to clearly observe the forecast ability and performance of the KELM. From the experimental studies of the winter season which has not symmetric diurnal mean power curve, Correlation Coefficients (R) values of KELM are calculated as 0.896 for 2-h ahead, 0.865 for 3-h ahead, 0.833 for 4-h ahead. Those of ELM and (Levenberg Marquardt) LM are 0.866–0.812 for 2-h ahead, 0.831–0.669 for 3-h ahead, 0.799–0.502 for 4-h ahead, respectively. Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) values of KELM for winter season are 12.08%-6.14% for 2-h ahead, 14.06%-7.43% for 3-h ahead, 15.33%-7.74% for 4-h ahead, respectively. While these values of ELM are obtained as 13.82%-7.05% for 2-h ahead, 15.52%-8.77% for 3-h ahead, 17.63%-9.33% for 4-h ahead. The RMSE and MAE values of LM are 17.90%-9.14% for 2-h ahead, 20.04%-9.85% for 3-h ahead, 21.22%-10.68% for 4-h ahead. According to the obtained results, it is clearly seen that KELM provides a more powerful and reliable forecasting performance.

Human Activity Recognition (HAR) based on data from wearable sensors has become an attractive research topic thanks to its applications in different fields such as healthcare and smart environments. Recently, the advancement of deep learning with capability to perform automatically high-level feature extraction has achieved promising results. However, the performance of the deep learning models depends deeply on the characteristics of the datasets such as the number of classes, the inter-similarity and intra-variation. Therefore, directly comparing these models has become difficult since a wide variety of experimental protocols, evaluation metrics, and datasets are employed. In this paper, for the first time, a systematic evaluation of several deep learning models for HAR from wearable sensors is provided. In particular, three models named Convolutional Neural Network (CNN) [1], DeepConvLSTM - a combination of CNN and Long Short Term Memory (LSTM) [2], and SensCapsNet - a Capsule Neural Network for wearable sensor-based HAR [3] were implemented and evaluated on three benchmark datasets that are 19NonSens, CMDFall, and UCI-HAR dataset. Moreover, to have an intuitive explanation of deep learning models, a visualization of features learnt from these models is given. The evaluation codebase and results will be made publicly available for community use.

Spectra data classification with kernel extreme learning machine

This paper proposes two deep learning modes which combine sparse auto-encoder with extreme learning machine (ELM) and kernel extreme learning machine (KELM), namely as Stacked Sparse Auto-encoder-Extreme Learning Machine and Stacked Sparse Auto-encoder-Kernel Extreme Learning Machine. The proposed models are applied to the image recognition task. To learn features from the original input data, SSAE with deep architecture is employed. Then, to construct a unified neural network learning model, ELM and KELM are selected to classify the extracted features. To evaluate the performance of the two proposed models, we carry out experiments on three different image data sets respectively. The results show that the proposed models’ performance can be not only superior to the shallow architecture models of Support Vector Machine, ELM and KELM but also better than the deep architecture models, such as Stacked Auto-encoder, Deep Belief Network and Stacked Denoising Auto-encoder.

Clinicians lack objective means for monitoring if their knee osteoarthritis patients are improving outside of the clinic (e.g., at home). Previous human activity recognition (HAR) models using wearable sensor data have only used data from healthy people and such models are typically imprecise for people who have medical conditions affecting movement. HAR models designed for people with knee osteoarthritis have classified rehabilitation exercises but not the clinically relevant activities of transitioning from a chair, negotiating stairs and walking, which are commonly monitored for improvement during therapy for this condition. Therefore, it is unknown if a HAR model trained on data from people who have knee osteoarthritis can be accurate in classifying these three clinically relevant activities. Therefore, we collected inertial measurement unit (IMU) data from 18 participants with knee osteoarthritis and trained convolutional neural network models to identify chair, stairs and walking activities, and phases. The model accuracy was 85% at the first level of classification (activity), 89–97% at the second (direction of movement) and 60–67% at the third level (phase). This study is the first proof-of-concept that an accurate HAR system can be developed using IMU data from people with knee osteoarthritis to classify activities and phases of activities.

Human action recognition is a fundamental research problem in computer vision. The accuracy of human action recognition has important applications. In this book chapter, the authors use a YOLOv7-based model for human action recognition. To evaluate the performance of the model, the action recognition results of YOLOv7 were compared with those using CNN+LSTM, YOLOv5, and YOLOv4. Furthermore, a small human action dataset suitable for YOLO model training is designed. This data set is composed of images extracted from KTH, Weizmann, MSR data sets. In this book chapter, the authors make use of this data set to verify the experimental results. The final experimental results show that using the YOLOv7 model for human action recognition is very convenient and effective, compared with the previous YOLO model.

This paper considers the accident images and develops a deep learning method for feature extraction together with a mixture of experts for classification. For the first task, the outputs of the last max-pooling layer of a Convolution Neural Network (CNN) are used to extract the hidden features automatically. For the second task, a mixture of advanced variations of Extreme Learning Machine (ELM) including basic ELM, constraint ELM (CELM), On-Line Sequential ELM (OSELM) and Kernel ELM (KELM), is developed. This ensemble classifier combines the advantages of different ELMs using a gating network and its accuracy is very high while the processing time is close to real-time. To show the efficiency, the different combinations of the traditional feature extraction and feature selection methods and the various classifiers are examined on two kinds of benchmarks including accident images’ data set and some general data sets. It is shown that the proposed system detects the accidents with 99.31% precision, recall and F-measure. Besides, the precisions of accident-severity classification and involved-vehicle classification are 90.27% and 92.73%, respectively. This system is suitable for on-line processing on the accident images that will be captured by Unmanned Aerial Vehicles (UAV) or other surveillance systems.

This paper presents an evaluation of the Extreme Learning Machine (ELM), Kernel Extreme Learning Machine (KELM), and the Kernel Extreme Learning Machine optimized by the Whale Optimization Algorithm (WOA-KELM) in the context of fruit image classification. Fruits play a crucial role in everyday life, and the application of machine learning for fruit classification can significantly improve efficiency. The ELM, a single hidden layer feedforward neural network, is the foundation for this comparison. The KELM, an evolution of the ELM, incorporates a kernel function to map input data into a high-dimensional feature space, thereby enhancing performance. The development of WOA-KELM involves optimizing the regularization parameter in KELM and the width parameter of the radial basis function through the Whale Optimization Algorithm, further enhancing its capabilities. In classifying twelve types of fruit images, the ELM achieved a classification accuracy of 77%. In contrast, the WOA-KELM, as proposed in this paper, significantly outperforms with a remarkable classification accuracy of 92%.

This paper proposes a novel artificial neural network called Parallel Layer Perceptron Fast Learning Network (PLP-FLN). In PLP-FLN, a parallel single hidden layer feed-forward neural network is added on the basis of Fast Learning Network (FLN) which is an improved Extreme Learning Machine (ELM). Input weights and hidden layer biases are randomly generated. The weights connect the output nodes and the input nodes, and the weights connect the output nodes and the hidden nodes are analytically determined based on least squares methods. In order to test the PLP-FLN validity, this paper compared it with ELM, FLN, Kernel ELM and Incremental ELM through 12 regression applications and 7 classification problems. By comparing the experimental results, it shows that the PLP-FLN with much more compact networks have demonstrated better approximations, classification performances and generalization ability.

Recently, a significant amount of literature concerning machine learning techniques has focused on automatic recognition of activities performed by people. The main reason for this considerable interest is the increasing availability of devices able to acquire signals which, if properly processed, can provide information about human activities of daily living (ADL). The recognition of human activities is generally performed by machine learning techniques that process signals from wearable sensors and/or cameras appropriately arranged in the environment. Whatever the type of sensor, activities performed by human beings have a strong subjective characteristic that is related to different factors, such as age, gender, weight, height, physical abilities, and lifestyle. Personalization models have been studied to take into account these subjective factors and it has been demonstrated that using these models, the accuracy of machine learning algorithms can be improved. In this work we focus on the recognition of human activities using signals acquired by the accelerometer embedded in a smartphone. The contributions of this research are mainly three. A first contribution is the definition of a clear validation model that takes into account the problem of personalization and which thus makes it possible to objectively evaluate the performances of machine learning algorithms. A second contribution is the evaluation, on three different public datasets, of a personalization model which considers two aspects: the similarity between people related to physical aspects (age, weight, and height) and similarity related to intrinsic characteristics of the signals produced by these people when performing activities. A third and last contribution is the development of a personalization model that considers both the physical and signal similarities. The experiments show that the employment of personalization models improves, on average, the accuracy, thus confirming the soundness of the approach and paving the way for future investigations on this topic.

The problem with bodyweight management is the inability to calculate the number of calories burned and consumed. Many applications can help to calculate it and one of them is implementing Human Activity Recognition using wearable sensors and smartphones. In this paper, an activity recognition model is built using the Reduced Kernel Extreme Learning Machine (RKELM) algorithm using an accelerometer sensor embedded in a smartphone that is used for calculating calories burned. This model was improved from the Extreme Learning Machine with the addition of the Gaussian kernel. The dataset comes from the London py data event in 2016 which consists of five activity labels. The proposed model will be compared with five other models and evaluated using precision, recall, f1score, training time, and testing time. The results have been validated with 10-fold cross-validation. The experimental results show that the RKELM-based recognition model has a higher performance than the other models with acceptable training and testing time, with an f1 score of 97% and less than 0.06 seconds.

Deep neural networks have made significant achievements in representation learning of traditionally man-made features, especially in terms of complex objects. Over the decades, this learning process has attracted thousands of researchers and has been widely used in the speech, visual, and text recognition fields. One deep network multi-layer extreme learning machine (ML-ELM) achieves a good performance in representation learning while inheriting the advantages of faster learning and the approximating capability of the extreme learning machine (ELM). However, as with most deep networks, the ML-ELM’s algorithmic performance largely depends on the probability distribution of the training data. In this paper, we propose an improved ML-ELM made via using the local significant regions at the input end to enhance the contributions of these regions according to the idea of the selective attention mechanism. To avoid involving and exploring the complex principle of the attention system and to focus on the clarification of our local regional enhancement idea, the paper only selects two typical attention regions. One is the geometric central region, which is normally the important region to attract human attention due to the focal attention mechanism. The other is the task-driven interest region, with facial recognition as an example. The comprehensive experiments are done on the three public datasets of MNIST, NORB, and ORL. The comparison experiment results demonstrate that our proposed region-enhanced ML-ELM (RE-ML-ELM) achieves performance increases in important feature learning by utilizing the apriori knowledge of attention and has a higher recognition rate than that of the normal ML-ELM and the basic ELM. Moreover, it benefits from the non-iterative parameter training method of other ELMs, and our proposed algorithm outperforms most state-of-the-art deep networks such as deep belief network(DBN), in the aspects of training efficiency. Furthermore, because of the deep structure with fewer hidden nodes at each layer, our proposed RE-ML-ELM achieves a comparable training efficiency to that of the ML-ELM but has a higher training speed with the basic ELM, which is normally the width single network that has more hidden nodes to obtain the similar recognition accuracy with the deep networks. Based on our idea of combining the apriori knowledge of the human selective attention system with the data learning, our proposed region-enhanced ML-ELM increases the image classification performance. We believe that the idea of intentionally combining psychological knowledge with the most algorithms based on data-driven learning has the potential to improve their cognitive computing ability.

Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently. However, the generalization ability of deep models on complex real-world HAR data is limited by the availability of high-quality labeled activity data, which are hard to obtain. In this article, we design a similarity embedding neural network that maps input sensor signals onto real vectors through carefully designed convolutional and Long Short-Term Memory (LSTM) layers. The embedding network is trained with a pairwise similarity loss, encouraging the clustering of samples from the same class in the embedded real space, and can be effectively trained on a small dataset and even on a noisy dataset with mislabeled samples. Based on the learned embeddings, we further propose both nonparametric and parametric approaches for activity recognition. Extensive evaluation based on two public datasets has shown that the proposed similarity embedding network significantly outperforms state-of-the-art deep models on HAR classification tasks, is robust to mislabeled samples in the training set, and can also be used to effectively denoise a noisy dataset.

Human activity recognition (HAR) identifies people’s motions and actions in daily life. HAR research has grown with the popularity of internet-connected, wearable sensors that capture human movement data to detect activities. Recent deep learning advances have enabled more HAR research and applications using data from wearable devices. However, prior HAR research often focused on a few sensor locations on the body. Recognizing real-world activities poses challenges when device positioning is uncontrolled or initial user training data are unavailable. This research analyzes the feasibility of deep learning models for both position-dependent and position-independent HAR. We introduce an advanced residual deep learning model called Att-ResBiGRU, which excels at accurate position-dependent HAR and delivers excellent performance for position-independent HAR. We evaluate this model using three public HAR datasets: Opportunity, PAMAP2, and REALWORLD16. Comparisons are made to previously published deep learning architectures for addressing HAR challenges. The proposed Att-ResBiGRU model outperforms existing techniques in accuracy, cross-entropy loss, and F1-score across all three datasets. We assess the model using k-fold cross-validation. The Att-ResBiGRU achieves F1-scores of 86.69%, 96.23%, and 96.44% on the PAMAP2, REALWORLD16, and Opportunity datasets, surpassing state-of-the-art models across all datasets. Our experiments and analysis demonstrate the exceptional performance of the Att-ResBiGRU model for HAR applications.

Human Activity Recognition (HAR) systems are devised for continuously observing human behavior - primarily in the fields of environmental compatibility, sports injury detection, senior care, rehabilitation, entertainment, and the surveillance in intelligent home settings. Inertial sensors, e.g., accelerometers, linear acceleration, and gyroscopes are frequently employed for this purpose, which are now compacted into smart devices, e.g., smartphones. Since the use of smartphones is so widespread now-a-days, activity data acquisition for the HAR systems is a pressing need. In this article, we have conducted the smartphone sensor-based raw data collection, namely H-Activity, using an Android-OS-based application for accelerometer, gyroscope, and linear acceleration. Furthermore, a hybrid deep learning model is proposed, coupling convolutional neural network and long-short term memory network (CNN-LSTM), empowered by the self-attention algorithm to enhance the predictive capabilities of the system. In addition to our collected dataset (H-Activity), the model has been evaluated with some benchmark datasets, e.g., MHEALTH, and UCI-HAR to demonstrate the comparative performance of our model. When compared to other models, the proposed model has an accuracy of 99.93% using our collected H-Activity data, and 98.76% and 93.11% using data from MHEALTH and UCI-HAR databases respectively, indicating its efficacy in recognizing human activity recognition. We hope that our developed model could be applicable in the clinical settings and collected data could be useful for further research.