A Hybrid Approach for Human Activity Recognition with Support Vector Machine and 1D Convolutional Neural Network

Shuvo, Maruf Hossain; Ahmed, Nafis; Nouduri, Koundinya; Palaniappan, Kannappan

doi:10.1109/aipr50011.2020.9425332

Cited by 48 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The sample points closest to the hyperplane are called the support vector. The classification results of the SVM classifier are mainly affected by the kernel function, including the linear kernel, polynomial kernel and radial basis function kernel (RBF), which also called sigmoid kernels [20]. In this experiment, the SVM classification accuracy without temperature data reached 74%, and this number ascended to 81% after considering temperature.…”

mentioning

confidence: 80%

Body Temperature Monitoring for Regular COVID-19 Prevention Based on Human Daily Activity Recognition

Zhang

Zhu

Jiang

et al. 2021

Sensors

View full text Add to dashboard Cite

Existing wearable systems that use G-sensors to identify daily activities have been widely applied for medical, sports and military applications, while body temperature as an obvious physical characteristic that has rarely been considered in the system design and relative applications of HAR. In the context of the normalization of COVID-19, the prevention and control of the epidemic has become a top priority. Temperature monitoring plays an important role in the preliminary screening of the population for fever. Therefore, this paper proposes a wearable device embedded with inertial and temperature sensors that is used to apply human behavior recognition (HAR) to body surface temperature detection for body temperature monitoring and adjustment by evaluating recognition algorithms. The sensing system consists of an STM 32-based microcontroller, a 6-axis (accelerometer and gyroscope) sensor, and a temperature sensor to capture the original data from 10 individual participants under 4 different daily activity scenarios. Then, the collected raw data are pre-processed by signal standardization, data stacking and resampling. For HAR, several machine learning (ML) and deep learning (DL) algorithms are implemented to classify the activities. To compare the performance of different classifiers on the seven-dimensional dataset with temperature sensing signals, evaluation metrics and the algorithm running time are considered, and random forest (RF) is found to be the best-performing classifier with 88.78% recognition accuracy, which is higher than the case of the absence of temperature data (<78%). In addition, the experimental results show that participants’ body surface temperature in dynamic activities was lower compared to sitting, which can be associated with the possible missing fever population due to temperature deviations in COVID-19 prevention. According to different individual activities, epidemic prevention workers are supposed to infer the corresponding standard normal body temperature of a patient by referring to the specific values of the mean expectation and variance in the normal distribution curve provided in this paper.

show abstract

mentioning

confidence: 80%

Body Temperature Monitoring for Regular COVID-19 Prevention Based on Human Daily Activity Recognition

Zhang

Zhu

Jiang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Each layer has its own calculation technique to produce a certain output at a specific threshold. Although the authors of [22] stated that three convolution layers can provide optimal performance, we employ only one convolution layer because adding more layers only increases complexity but provides no performance benefit. In this study, a 1D-CNN is applied because this research involves a one-dimensional time series data.…”

Section: Methodsmentioning

confidence: 99%

Sales Forecasting Using Convolution Neural Network

Wan Khairul Hazim Wan Khairul Amir,

Afiqah Bazlla Md Soom,

Aisyah Mat Jasin

et al. 2023

ARASET

View full text Add to dashboard Cite

Sales forecasting is an essential component of business management, providing insight into future sales and revenue. It is critical for effective inventory management, cash flow, and business growth planning. While many retailers rely on simple Excel functions or subjective guesses from management, the industry is increasingly turning to machine learning techniques to develop more accurate and reliable prediction models. Among these techniques, Convolutional Neural Networks (CNN) emerged as a suitable option due to their ability to learn and improve accuracy over time. CNN applies several layers to make predictions, adjusting their weights with each input data point to minimize prediction error. As a result, sales forecasting with neural networks can significantly improve market operations and productivity for businesses. The validity of the proposed model is compared with the Facebook Prophet method, which is known as the recent time series forecasting method.

show abstract

“…According to the reported results, CNN combined with LSTM outperforms CNN combined with dense layers. Differently, in [ 47 ], the authors presented a hybrid model for HAR which first identifies the abstract activity by using random forest to classify it as static and moving. For static activities the authors have used SVM, while for moving activities they have adopted 1D CNN.…”

Section: Literature Reviewmentioning

confidence: 99%

Human-Aware Collaborative Robots in the Wild: Coping with Uncertainty in Activity Recognition

Yalçinkaya

Couceiro²,

Soares

et al. 2023

Sensors

View full text Add to dashboard Cite

This study presents a novel approach to cope with the human behaviour uncertainty during Human-Robot Collaboration (HRC) in dynamic and unstructured environments, such as agriculture, forestry, and construction. These challenging tasks, which often require excessive time, labour and are hazardous for humans, provide ample room for improvement through collaboration with robots. However, the integration of humans in-the-loop raises open challenges due to the uncertainty that comes with the ambiguous nature of human behaviour. Such uncertainty makes it difficult to represent high-level human behaviour based on low-level sensory input data. The proposed Fuzzy State-Long Short-Term Memory (FS-LSTM) approach addresses this challenge by fuzzifying ambiguous sensory data and developing a combined activity recognition and sequence modelling system using state machines and the LSTM deep learning method. The evaluation process compares the traditional LSTM approach with raw sensory data inputs, a Fuzzy-LSTM approach with fuzzified inputs, and the proposed FS-LSTM approach. The results show that the use of fuzzified inputs significantly improves accuracy compared to traditional LSTM, and, while the fuzzy state machine approach provides similar results than the fuzzy one, it offers the added benefits of ensuring feasible transitions between activities with improved computational efficiency.

show abstract

A Hybrid Approach for Human Activity Recognition with Support Vector Machine and 1D Convolutional Neural Network

Cited by 48 publications

References 17 publications

Body Temperature Monitoring for Regular COVID-19 Prevention Based on Human Daily Activity Recognition

Body Temperature Monitoring for Regular COVID-19 Prevention Based on Human Daily Activity Recognition

Sales Forecasting Using Convolution Neural Network

Human-Aware Collaborative Robots in the Wild: Coping with Uncertainty in Activity Recognition

Contact Info

Product

Resources

About