In recent years, the use of accelerometers embedded in smartphones for Human Activity Recognition (HAR) has been well considered. Nevertheless, the role of the sensor placement is yet to be explored and needs to be further investigated. In this study, we investigated the role of sensor placements for recognizing various types of physical activities using the accelerometer sensor embedded in the smartphone. In fact, most of the reported work in HAR utilized traditional multi-class classification approaches to determine the types of activities. Hence, this study was to recognize the activity based on the best sensor placements that are appropriate to the activity performed. The traditional multi-class classification approach required more manual work and was time consuming to run the experiment separately. Thus, this study proposed the multilabel classification technique with the Label Combination (LC) approach in order to tackle this issue. The result was compared
Abstract:In various classification areas, the curse of dimensionality becomes a major challenge among the researchers. Thus, feature selection plays an important role in overcoming dimensionality problem. Relief-f is one of the filter methods to rank the most significant features based on their relevance. Although relief-f proved to be a powerful technique in filter strategy, but this method only rank the features based on their significant level. Hence, feature selection is embedded to select the most meaningful features based on their rank. Differential evolution (DE) is one of the evolutionary algorithms that are widely used in various classification domains. Simple and powerful in implementation, we combined relief-f with DE in our proposed feature selection method to solving the optimization problem. In this work, population size and generation size were adaptively determined from the number of features from relief-f. The performance of proposed method is compared with several feature selection techniques in order to prove their superiority using ten datasets obtained from UCI machine learning repository.
In gastronomic tourism, food is viewed as the central tourist attraction. Specifically, indigenous food is known to represent the expression of local culture and identity. To promote gastronomic tourism, it is critical to have a model for the food business analytics system. This research undertakes an empirical evaluation of recent transfer learning models for deep learning feature extraction for a food recognition model. The VIREO-Food172 Dataset and a newly established Sabah Food Dataset are used to evaluate the food recognition model. Afterwards, the model is implemented into a web application system as an attempt to automate food recognition. In this model, a fully connected layer with 11 and 10 Softmax neurons is used as the classifier for food categories in both datasets. Six pre-trained Convolutional Neural Network (CNN) models are evaluated as the feature extractors to extract essential features from food images. From the evaluation, the research found that the EfficientNet feature extractor-based and CNN classifier achieved the highest classification accuracy of 94.01% on the Sabah Food Dataset and 86.57% on VIREO-Food172 Dataset. EFFNet as a feature representation outperformed Xception in terms of overall performance. However, Xception can be considered despite some accuracy performance drawback if computational speed and memory space usage are more important than performance.
Activity recognition in smart home environment is becoming challenging when it is involving more than one resident living in the same space. It is not merely recognizing and tracking the multi-resident activity, but the interaction between them are also need to address in order to provide the great autonomous ambient intelligence (AmL) system. It is a challenging task due to diversity and complexity level of human activity and resident interaction using only binary data from ambient-based type sensors. Strong approach is needed to identify types of interaction based on activity performed either it is individual, parallel or cooperative. Previously, researchers tend to simplify the problem and define the parallel as individual activity due to the sensors type are unobtrusive and open to noise in nature. Hence, we address this issue as separate interaction. This research presents the rule-based approach to recognize complex activity recognition in multi-resident scenario in a smart home setting. It has been tested on the real smart home datasets using multi-label classification technique using Enhanced Label Combination method with random forest as its base classifier. The quality of the classification is selected as evaluation metrics to measure the proposed solution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.