Archive
Archive |
|
In the swiftly evolving landscape of Internet of Things IoT technology the demand for adaptive noncontact sensing has seen a considerable surge Traditional human perception technologies such as visionbased approaches often grapple with problems including lack of sensor versatility and suboptimal accuracy To address these issues this paper introduces a novel noncontact method for human presence perception relying on WiFi This innovative approach involves a sequential process beginning with the preprocessing of collected Channel State Information CSI followed by feature extraction and finally classification By establishing signal models that correspond to varying states this method enables the accurate perception and recognition of human presence Remarkably this technique exhibits a high level of precision with sensing accuracy reaching up to 99
The potential applications of this approach are extensive proving to be particularly beneficial in contexts such as smart homes and healthcare amongst various other everyday scenarios This underscores the significant role this novel method could play in enhancing the sophistication and effectiveness of human presence detection and recognition systems in the IoT era
Similar content being viewed by others
OPERAnet a multimodal activity recognition dataset acquired from radio frequency and visionbased sensors
Article Open access
03 August 2022
Elderly and visually impaired indoor activity monitoring based on WiFi and Deep Hybrid convolutional neural network
Article Open access
18 December 2023
Visiondriven metasurfaces for perception enhancement
Article Open access
22 February 2024
Introduction
In contemporary society the observation and interpretation of human activities carry substantial societal value The choice of appropriate technologies for human perception has emerged as a significant area of modern research123 Conventional human perception technologies mainly include vision4 sensors5 and infrared6 Visionbased methods entail collecting images or videos through a camera followed by the application of image processing algorithms for recognition and perception Despite its high accuracy this technique is notably vulnerable to lighting conditions variability and the capture of video images may encroach on individual privacy The sensorbased approach requires users to constantly wear sensors potentially causing interruptions in their daily activities Infraredbased methods employing infrared sensors for human perception are plagued by a high frequency of false alarms and are easily obstructed
In 2011 aiming to surmount the limitations of traditional technologies Halperin et al7 developed a WiFi device firmware based on the IEEE 80211n standard This pioneering effort aimed to simplify the collection of CSI laying the groundwork for human perception recognition Subsequent to this advancement various research groups and scholars have thoroughly explored CSIbased human perception technologies892425 In 2016 the WiFi ID method proposed by Zhang et al10 utilized Fourier transformation and the relief algorithm to extract gait information performing gait recognition via the Support Vector Machine SVM algorithm and achieving an average accuracy rate of
93
In 2017 Shi et al11 executed human identification using a neural network model attaining an accuracy rate of
94
Despite the swift progression in the theoretical foundation and practical application of wireless sensing technology1213 significant challenges such as inadequate robustness low accuracy and limited universality continue to prevail262728 This paper introduces a cuttingedge noncontact human presence detection technology based on wireless sensing The interpretation of the gathered sensing information allows for the identification of individuals within the sensing area thereby enabling highprecision noncontact sensing
System block diagram
The block diagram of the WiFibased noncontact human presence sensing system proposed in this paper is presented in Fig 1 Initially a network card with modified firmware is utilized to gather channel state information Following this noise is mitigated using a lowpass filter and wavelet transform Subsequently an algorithm founded on a neural network is employed to extract distinguishing features Ultimately machine learning techniques are used to classify and identify human states
Figure 1
figure 1
System block diagram
Full size image
Relevant theories
According to the IEEE 80211 standard the process of WiFi signal transmission is segmented into various subcarriers each operating at a distinct frequency The propagation paths of these subcarriers through the environment differ leading to the diversity observed in the CSI data14 The CSI encompasses a range of data including the time delay amplitude attenuation and phase shift experienced during the signals transmission and reception Essentially CSI represents the physical layer information of the subcarriers characterizing the cumulative effect on wireless signals at the receiver after undergoing reflection refraction and scattering across different environmental paths29
In the frequency domain the communication model for a system employing multiple transmitting and receiving antennas characterized by narrowband flat fading is represented as follows
y
H
x
n
1
Here y denotes the received signal x symbolizes the transmitted signal n represents noise and H is the signal transformation matrix This matrix H reflects the impact of the external physical environment on the transmitted signal x as it propagates from the transmitter to the receiver transforming into y The matrix H can also be estimated using the following equation
H
y
x
2
CSI is essentially a representation of H At the receiver the CSI for each subcarrier can be quantified in terms of amplitude and phase as per the equation
H
i
H
i
exp
j
H
i
3
In this notation
H
i
signifies the value of the
i
t
h
subcarrier in the Channel State Information
H
i
represents the amplitude of the
i
t
h
subcarrier and
H
i
denotes the phase of the
i
t
h
subcarrier30 The SignaltoNoise Ratio SNR plays a critical role in this context as it quantifies the level of the desired signal relative to the background noise which is crucial in analyzing the quality and reliability of the communication channel Variations in the environmental conditions during the wireless signal transmission can lead to multipath propagation encompassing a lineofsight path and several paths involving reflection and refraction1522 The crux of this paper is to analyze the alterations in channel propagation induced by environmental changes during the propagation process to facilitate the detection of human presence
Methodology
Pretreatment
The channel state information acquired directly is susceptible to lowpass noise and therefore cannot be directly employed for human presence detection Accordingly a lowpass filtering method is chosen20 This technique exploits the characteristics of inductors with high resistance at low frequencies and capacitors with low resistance at high frequencies to perform data denoising The formula is as follows
f
c
1
2
R
C
4
L
s
2
f
c
2
f
c
s
5
where R is the resistance l is the load series inductor C is the parallel capacitor at both ends of the load resistance and
f
c
is the cutoff frequency
To augment the detection of indoor human activities wavelet transforms17 recognized for their aptitude to differentiate high and lowfrequency components are employed for noise reduction The core principle hinges on signal extraction through localized transformations in both spatial and frequency domains By employing scaling and translation the CSI is analyzed multiscale This approach distinctly segregates high and lowfrequency components enhancing the robustness and precision of the sensing technologyThe mathematical representations of the hard
hard
and soft
soft
thresholding functions are shown in Eqs 6 and 7 respectively
hard
0
6
soft
sgn
0
7
where
is the wavelet coefficient
the threshold value and
sgn
denotes the signum function In hard thresholding the coefficient is nullified if its absolute value is below the threshold while preserved otherwise In contrast the soft thresholding reduces the absolute value of each coefficient by
and sets it to zero if the result is nonpositive
Feature extraction
While preprocessing significantly improves signal quality the extensive volume of data complicates the direct classification and interpretation of human activities A selforganizing neural network18 utilizing unsupervised learning with a competitive approach skillfully extracts channel state information features following preprocessing This network primarily consists of input and output layers dedicated to classification and clustering tasks The operation sequence is as follows
The data first undergoes normalization to facilitate uniformity in subsequent processes This step is mathematically represented as
X
X
X
8
Postnormalization a similarity metric identifies the most relevant neurons This involves the normalization of the weight vectors expressed as
W
j
W
j
W
j
9
where
X
and
W
j
denote the normalized input and weight vectors respectively
The core of the competitive learning algorithm is to minimize the distance between the input vector and the weight vector of the selected neuron This is encapsulated by the following equation
X
W
j
min
j
1
2
3
n
X
W
j
10
where
j
represents the index of the winning neuron
Subsequently the output values are updated as follows
y
j
t
1
1
if
j
j
0
if
j
j
11
where
y
j
t
1
denotes the output of the
j
t
h
neuron at time
t
1
For the winning neuron the weight vector is refined using the equation
W
j
t
1
W
j
t
X
W
j
12
Here
W
j
t
is the weight vector at time t adjusted to reduce the disparity with the input vector
X
The term
representing the learning rate falls within the range 0 1 It regulates the adaptation pace and magnitude of the weight vectors
As the iteration count t progresses the learning rate
gradually reduces to zero This decline ensures the convergence and stability of the learning algorithm thus preventing any potential overshooting of the optimal weight configuration This methodical reduction in
is pivotal for the efficacy and efficiency of the learning process16
Classification
In the pursuit of classifying and discerning features indicative of human presence this study employs a softmax classifier19 This classifier adeptly computes probabilities for various states corresponding to different feature vectors The operational flow of the softmax classifier is outlined as follows
Initially data is introduced into the input layer It then traverses through two distinct feature layers undergoing processing and transformation Conclusively the softmax function is applied ensuring that each output is normalized to a probability range of 0 to 1 This normalization is formally represented as
Softmax
x
i
e
x
i
j
1
K
e
x
j
13
for an input vector
x
R
K
where i is the index of a particular element and K is the total number of classes
Through this process the classifier effectively transforms raw data into a probability distribution facilitating the interpretation of each output as a conditional probability under various scenarios This probabilistic framework allows for a more nuanced and accurate classification pivotal in the intricate task of human presence feature recognition
Ethics approval
This article does not contain any studies with human participants performed by any of the authors
Experiment and analysis
Experimental setup
In response to the necessity for detailed experimental methodologies and architectural insights this document meticulously delineates the experimental procedures ensuring lucidity and reproducibility
Experimental setup The CSI dimension in our study is 1330 This configuration comprises 1 transmitting antenna and 3 receiving antennas The experimental hardware involves two Lenovo desktop computers each powered by Intel Core i5800 CPUs The transmitting computer is equipped with a single antenna while the receiving computer features three antennas The wireless transceiving system includes a Monitor Point MP for signal reception and an Access Point AP for signal transmission The spatial arrangement of these antennas is illustrated in Fig 2
Software and model construction The model is developed on MATLAB a platform wellregarded for its robust capabilities in algorithm development and simulation To ensure a consistent operational environment both computers utilize Ubuntu 1404 LTS Equipped with Intel 5300 network cards these systems are subjected to precise kernel and driver configurations prior to the installation of the CSI toolbox as referenced in23 This toolbox is instrumental in processing the CSI offering a comprehensive suite of functionalities for analyzing and interpreting wireless signal characteristics It facilitates the extraction and manipulation of CSI data essential for our research Moreover the SelfOrganizing Map neural network employed in our study is configured with a default output dimension of 100 optimizing the performance for our specific application
Data collection environment and process Data was gathered in two distinct environments to evaluate the models versatility and efficacy under various conditions The first environment was a laboratory measuring 65 m by 8 m filled with test benches chairs and computers presenting significant obstructions and strong multipath interference The second was a spacious conference room sized 95 m by 11 m where multipath interference was minimal In each setting 200 datasets representing both occupied and unoccupied states were meticulously collected with each session lasting 180 s and involving the transmission of 100 Channel State Information packets per second The data was collected at different speeds and by different personnel with a training and testing set ratio of 82
Dataset and validation Due to the lack of a standardized dataset for human presence detection our research utilizes a proprietary dataset for model validation This dataset covers two distinct scenarios facilitating a thorough evaluation
Evaluation metrics To comprehensively evaluate the performance of our experiment we utilized the True Positive Rate TPR and False Positive Rate FPR as key metrics The True Positive Rate refers to the probability of successfully detecting the presence of a person in the test set when someone is actually present Conversely the False Positive Rate indicates the probability of incorrectly identifying the presence of a person when in reality no one is present
Figure 2
figure 2
Experimental environment plan
Full size image
Baseline
To benchmark our model the dataset is also utilized in replicating the methodologies outlined in the references FreeSense Wialarm and HAR
FreeSense17 FreeSense identifies human motion by detecting the phase difference of amplitude waveforms on multiple antennas
Wialarm18 Wialarm uses raw channel state information for human motion monitoring and uses SVM for detection
HAR21 In this study the author used CNN to perform edge detection on CSI data enhancing human activity recognition based on WiFi
Performance evaluation
Figure 3
figure 3
Overall performance evaluation FPR
Full size image
Figure 4
figure 4
Overall performance evaluation TPR
Full size image
Overall performance evaluation To effectively assess its overall performance the method was compared with FreeSense17 Wialarm18 and HAR21 As shown in Figs 3 and 4 the method achieved the lowest FPR value across different data types averaging approximately 12
with a high TPR of 995
This indicates fewer false alarms triggered by the method when detecting human presence
Performance analysis in different environments The versatility of our approach was further substantiated through a series of experiments conducted in diverse environments and postures as depicted in Fig 5 These figures illustrate the influence of environmental conditions on performance metrics In both conference room and laboratory settings the average TPR for detecting human presence was recorded at 988
and 984
respectively while the average FPR was 13
and 15
This indicates a minor variance in the accuracy of human perception technology across different testing environments The more spacious conference room experienced a reduced multipath effect Conversely the laboratory smaller in size and cluttered with numerous objects exhibited stronger multipath interference leading to a decline in signal quality Nevertheless the overall TPR consistently exceeded 96
Notably the SNR in the conference room was approximately 197 dB compared to 174 dB in the laboratory environment underscoring the methods resilience under varying conditions
Performance analysis across different body types It allowed for the perception of individuals with varying genders weights and heights The experimental results showed no substantial changes due to the posture of the subjects thereby emphasizing the strong versatility of the method As shown in Fig 5
Figure 5
figure 5
FPR under different environment and personnel posture
Full size image
Figure 6
figure 6
TPR at different moving speeds
Full size image
Figure 7
figure 7
FPR at different moving speeds
Full size image
Performance at different movement speeds This study also assessed human motion perception at different speeds such as slow walking normal walking fast walking and sprinting The experimental results were compared side by side with two typical methods as shown in Figs 6 and 7 The findings indicated that the method maintained a stable TPR and FPR across different movement speeds However the FPR significantly increased while the TPR notably decreased for the other three methods when participants moved at slower speeds This outcome can be attributed to the reduced interference characteristics of the wireless signal during the slower speed sampling period causing less impact of the human body on the wireless signals Nevertheless the SelfOrganizing Competitive Neural Network used in this method with its rich feature set maintained stable TPR and FPR proving the robust reliability of the method
Performance under environmental changes To investigate the robustness of our model in the face of environmental changes especially the effect of furniture rearrangement in rooms we conducted targeted experiments We modified the placement of chairs and tables in both lab and conference room settings to evaluate the impact on model performance The results revealed that furniture rearrangement indeed influenced the models performance In the lab setting postadjustment the TPR decreased by about 18 and in the conference room it decreased by approximately 21 These findings suggest that while the model demonstrates considerable robustness it is still somewhat affected by changes in furniture layout Importantly these tests were conducted without retraining the model underscoring its adaptability to environmental shifts However the impact of furniture layout on performance warrants attention In future research we aim to explore this issue more thoroughly with the goal of developing a more stable and efficient model for human presence detection Through optimization and adjustments we aspire to improve its detection accuracy and robustness in diverse settings enhancing its applicability in smart homes healthcare monitoring and other scenarios
Conclusion
Addressing the stability issues and user inconveniences of traditional human perception recognition techniques this study presents a noncontact human presence detection technology By preprocessing extracting features and classifying the CSI signals we can discern different states such as an empty room a room with a present individual and a room where someone has recently been demonstrating robust accuracy and versatility Nevertheless the current study only detects human presence within a room and does not recognize specific movements or simultaneous actions of multiple people which limits its applicability Future research will pivot towards the perception of multiple individuals actions broadening the scope and functionality of this technology