Predicting user's movement path in indoor environments using the stacked deep learning method and the fuzzy soft‐max classifier

Abstract

Accurate prediction of a user's movement path has various advantages for many applications, such as optimising a nurse's trajectory in a hospital and assisting elderly or disabled people and making them feel secure and protected in the places where they live. Recently, researchers have suggested techniques based on machine learning and deep learning in this field. However, these approaches have drawbacks such as their low accuracy in classifying the extracted features into associated movement paths, high sensitivity to noisy data, and ignoring time dependencies within raw data. In this work, a threephase stacked method named CNN-LSTM-FSC is proposed, which uses the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Fuzzy Soft-max Classifier (FSC) to overcome the mentioned constraints. In the first phase, the CNN structure extracts time dependencies within raw data using the stacked convolutional and pooling layer. In the second phase, the long-term time dependency of the user's movement path is learnt using the LSTM layers, and the user path is determined using a new innovated fuzzy soft-max classifier. Finally, in the post-processing phase, by performing a majority voting technique on the k-adjacent sample predictions of the classifier, the authors have tried to reduce the effects of noise in identifying the user's movement path. Experiments were conducted on the MovementAAL_RSS dataset. The proposed method has successfully reached 93.86%, 93.71%, and 93.26% accuracy rate on the Move-mentAAL_RSS datasets, with 0%, 5%, and 10% Gaussian noise, respectively, and demonstrates superior results in comparison to the previous literature research. K E Y W O R D Sconvolutional neural network, fuzzy soft-max classifier, long short-term memory, user's movement path | INTRODUCTIONDifferent user movement prediction methods attempt to derive patterns within input data that predict future events [1][2][3]. These patterns can be used effectively to optimise resources and provide intelligent services. Today, motion prediction methods are widely used in a variety of fields, including wireless cellular networks, Location-based Services (LBS) (which include navigation services, social networking services, monitoring and tracking objects in warehouses) [4,5], Ambient Assisted Living (AAL) [6,13] and various applications (including utilities-based applications, health care, safety systems, and alert applications). Two key components in movement prediction systems include hardware environment with its indoor positioning technique and its prediction or classification technique. Hardware environments with indoor positioning can be made in different ways, such as Wireless Sensor Networks (WSN) [5] or Ultra-Wideband (UWB) [7]. A WSN-based system consists of small sensors armed with environmental power sources, sensing devices, radio, and processor units. User's movement is predicted by utilising Received Signal Strength (RSS) information [8] between some WSN and a user of wearable sensors. Then data-drivenThis is an ope...

Fall Detection using Deep Learning Algorithms and Analysis of Wearable Sensor Data by Presenting a New Sampling Method

“…Tao and Yun [20] proposed the Long Short Term Memory (LSTM) model and Skeleton Data, recorded by Kinect, to predict the fall. This model reports a value of 91.7% for the sensitivity parameter and 75% for the specificity parameter, which indicates that this model can detect most pre-impact falls but has a high false alarm rate [30].…”

“…Of course, the main challenge of fall detection systems is to reduce false positive (FP) warnings and also to reduce false negative (FN) warnings [24][25][26][27]. There are various criteria for evaluating the performance of machine learning algorithms for classification problems; the following parameters can be mentioned [28][29][30]. The sensitivity criterion describes the ability to detect a fall, and the specificity criterion describes the FDS's ability to prevent false alarms.…”

Diagnosing of Parkinson's disease based on hand drawing analysis using Bi‐Directional LSTM equipped with fuzzy inferential soft‐max classifier

“…Data trained late in the LSTM neural network responds better in the test phase than data trained early in the neural network. Therefore, the data is trained once from beginning to end and from the end to the beginning 29,31 . This structure allows networks to have back and forth information about the sequence at any point in time.…”

“…Graves and Schmidhuberl first proposed Bi-LSTM for phoneme classification. [29][30][31] In B-LSTM (Figure 4), in the first round, LSTM is applied forward, and in the second round, it is reversed, that is, backward. Data trained late in the LSTM neural network responds better in the test phase than data trained early in the neural network.…”

“…Therefore, the data is trained once from beginning to end and from the end to the beginning. 29,31 This structure allows networks to have back and forth information about the sequence at any point in time. The output of the LSTM blocks then fed into a classifier to classify the input data as Parkinson or normal.…”