A Comparative Study on Machine Learning Classification Models for Activity Recognition

Nabian, Mohsen

doi:10.4172/2165-7866.1000209

Cited by 18 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Softmax activation function is habitually employed in the output layer of the neural networks aiming at multiclass classification [17]. Therefore, its use in the network developed during the current study makes the classification of the three different types of melanocytic lesions possible.…”

Section: Resultsmentioning

confidence: 99%

Neural Network Based Classification of Melanocytic Lesions in Dermoscopy: Role of Input Vector Encoding

Ertaş¹

2018

Electrica

View full text Add to dashboard Cite

Melanocytic lesions are the main cause of death from skin cancer, and early diagnosis is the key to decreasing the mortality rate. This study assesses the role of input-vector encoding in neural network-based classification of melanocytic lesions in dermoscopy. Twelve dermoscopic measures from 200 melanocytic lesions are encoded by compact encoding, ACD encoding, 1-of-N encoding, normalized encoding, and raw encoding, resulting in five different input-vector sets. Feed-forward neural networks with one hidden layer and one output layer are designed with several neurons in the hidden layer, ranging from two to twenty-two for each type of input-vector set, to classify a melanocytic lesion into common nevus, atypical nevus, and melanoma. Accordingly, 105 networks are designed and trained using supervised learning and then tested by performing a 10-fold cross validation. All the neural networks achieve high sensitivities, specificities, and accuracies in classification. However, the network with seven neurons in the hidden layer and raw encoded dermoscopic measures as the input vector realizes the highest sensitivity (97.0%), specificity (98.1%), and accuracy (98.0%). The practical use of the network can facilitate lesion classification by retaining the needed expertise and minimizing diagnostic variability among dermatologists.

show abstract

Section: Resultsmentioning

confidence: 99%

Neural Network Based Classification of Melanocytic Lesions in Dermoscopy: Role of Input Vector Encoding

Ertaş¹

2018

Electrica

View full text Add to dashboard Cite

show abstract

“…Regarding human activity recognition approaches, most of the related published studies address such a recognition using supervised learning [18][19][20][21][22] or semisupervised learning [23,24]. Transfer learning has also been investigated, whereby the instances or models for activities in one domain can be transferred to improve the recognition accuracy in another domain for the purpose of reducing the need for training data [25][26][27].…”

Section: Activity Recognition-based Supervised Learningmentioning

confidence: 99%

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Machot

Elkobaisi

Kyamakya

2020

Sensors

View full text Add to dashboard Cite

Due to significant advances in sensor technology, studies towards activity recognition have gained interest and maturity in the last few years. Existing machine learning algorithms have demonstrated promising results by classifying activities whose instances have been already seen during training. Activity recognition methods based on real-life settings should cover a growing number of activities in various domains, whereby a significant part of instances will not be present in the training data set. However, to cover all possible activities in advance is a complex and expensive task. Concretely, we need a method that can extend the learning model to detect unseen activities without prior knowledge regarding sensor readings about those previously unseen activities. In this paper, we introduce an approach to leverage sensor data in discovering new unseen activities which were not present in the training set. We show that sensor readings can lead to promising results for zero-shot learning, whereby the necessary knowledge can be transferred from seen to unseen activities by using semantic similarity. The evaluation conducted on two data sets extracted from the well-known CASAS datasets show that the proposed zero-shot learning approach achieves a high performance in recognizing unseen (i.e., not present in the training dataset) new activities.

show abstract

“…Nabian conducted a comparative study on machine learning classification models for activity recognition [19]. The study used data provided by Baños [20] which consists of body motion recordings from 10 volunteers using sensors placed on the chest, right wrist, and left ankle.…”

Section: Adl Classificationmentioning

confidence: 99%

Recognizing the Activity Daily Living (ADL) for Subject Independent

Zainudin¹,

Kee²,

Idris³

et al. 2019

IJRTE

View full text Add to dashboard Cite

Recently, Human Activity Recognition (HAR) has gained meaningful information for a human being. A wearable sensor like an accelerometer, small and simple to perform, has opened the room for scientists to explore an initial understanding of ubiquitous computing. The wearable sensor has begun to receive attention among researchers in some respects to conduct their studies in a wide area of recognition of human activity. Recent ADL discusses not only simple activities but also cater to the broad categories of complex activities. However, when involving enormous numbers of a subject, the accuracy of recognition tends to reduce. Although a different subject performed the same activity, the acceleration signal acquired considerably differs. This is due to the distinct pattern of action for each subject based on various factors such as subject age, gender, emotion and personality. Thus, by enhancing the accuracy of recognition of ADL, this article proposes the framework for addressing the subject independent matter. The signal acquired from an accelerometer sensor will undergo a segmentation process to extract important features. Some of the characteristics may be meaningless in some instances to determine the class. Therefore, proposing a variety of features to select the most relevant features that can lead to accuracy above 90%. Also, this article outlined a brief empirical evaluation of previous related work. Using several machine learning algorithms, this preliminary work will be examined and analyzed.

show abstract

A Comparative Study on Machine Learning Classification Models for Activity Recognition

Cited by 18 publications

References 10 publications

Neural Network Based Classification of Melanocytic Lesions in Dermoscopy: Role of Input Vector Encoding

Neural Network Based Classification of Melanocytic Lesions in Dermoscopy: Role of Input Vector Encoding

Zero-Shot Human Activity Recognition Using Non-Visual Sensors

Recognizing the Activity Daily Living (ADL) for Subject Independent

Contact Info

Product

Resources

About