Wi-Fi Data Research Articles

Forecasting short-term subway passenger flow using Wi-Fi data: comparative analysis of advanced time-series methods

Accurately monitoring passenger demand fluctuations is crucial for streamlined operations of subway systems and informed decision-making. This study presents a detailed Time Series Analysis of the Toronto subway system using Wi-Fi data connection from devices as a predictor of passenger volume. Various time series models were tested for short-term forecasting, including Linear Regression, Exponential Smoothing, ARIMA, Random Forest, N-BEATS, and T-GCN. An end-to-end modeling implementation process was carried out, and the performance of each model was evaluated. The primary objective was to assess the effectiveness of short-term prediction models for univariate time series at the system level and discuss deployment challenges. While conventional time series models are fast to implement and interpretable, they require a more in-depth data exploration phase for validation, making scaling at the system level difficult. Additionally, maintenance is more challenging with conventional models, and their exploratory analysis phases need to be repeated when the models degrade over time. Prediction difficulty varied across each subway station, indicating the need for a more thorough calibration or hybrid approach, especially for transfer stations. Despite the different uses and qualities of each model in our scenario, Random Forest and Exponential Smoothing emerged as the best performers and could be a satisfactory option for robust demand forecasting at the system level.

Enhancing Digital Twins with Human Movement Data: A Comparative Study of Lidar-Based Tracking Methods

Digitals twins, used to represent dynamic environments, require accurate tracking of human movement to enhance their real-world application. This paper contributes to the field by systematically evaluating and comparing pre-existing tracking methods to identify strengths, weaknesses and practical applications within digital twin frameworks. The purpose of this study is to assess the efficacy of existing human movement tracking techniques for digital twins in real world environments, with the goal of improving spatial analysis and interaction within these virtual modes. We compare three approaches using indoor-mounted lidar sensors: (1) a frame-by-frame method deep learning model with convolutional neural networks (CNNs), (2) custom algorithms developed using OpenCV, and (3) the off-the-shelf lidar perception software package Percept version 1.6.3. Of these, the deep learning method performed best (F1 = 0.88), followed by Percept (F1 = 0.61), and finally the custom algorithms using OpenCV (F1 = 0.58). Each method had particular strengths and weaknesses, with OpenCV-based approaches that use frame comparison vulnerable to signal instability that is manifested as “flickering” in the dataset. Subsequent analysis of the spatial distribution of error revealed that both the custom algorithms and Percept took longer to acquire an identification, resulting in increased error near doorways. Percept software excelled in scenarios involving stationary individuals. These findings highlight the importance of selecting appropriate tracking methods for specific use. Future work will focus on model optimization, alternative data logging techniques, and innovative approaches to mitigate computational challenges, paving the way for more sophisticated and accessible spatial analysis tools. Integrating complementary sensor types and strategies, such as radar, audio levels, indoor positioning systems (IPSs), and wi-fi data, could further improve detection accuracy and validation while maintaining privacy.

Wi-Fi Fingerprint Indoor Localization by Semi-Supervised Generative Adversarial Network.

Wi-Fi fingerprint indoor localization uses Wi-Fi signal strength measurements obtained from a number of access points. This method needs manual data collection across a positioning area and an annotation process to label locations to the measurement sets. To reduce the cost and effort, this paper proposes a Wi-Fi Semi-Supervised Generative Adversarial Network (SSGAN), which produces artificial but realistic trainable fingerprint data. The Wi-Fi SSGAN is based on a deep learning, which is extended from GAN in a semi-supervised learning manner. It is designed to create location-labeled Wi-Fi fingerprint data, which is different to unlabeled data generation by a normal GAN. Also, the proposed Wi-Fi SSGAN network includes a positioning model, so it does not need a external positioning method. When the Wi-Fi SSGAN is applied to a multi-story landmark localization, the experimental results demonstrate a 35% more accurate performance in comparison to a standard supervised deep neural network.

Street Crowdedness and Urban Congestion Level by MAC and GPS Data

Wi-Fi is one of the emerging technologies today. Wi-Fi refers to MAC (Media Access Control) address data. A MAC address represents a device number. In other words, it represents the number of people. The system uses MAC address data to determine road traffic congestion and land use, detects the number of terminals using a Wi-Fi scanner, and analyzes vehicle speed using GPS. The purpose of this research is to understand city-level services from traffic services and road congestion status and degree of congestion using Wi-Fi data (MAC addresses). This method was used for this study by providing a Wi-Fi scanner and a GPS scanner inside the bus. A Wi-Fi scanner that collects MAC address data and GPS for calculating bus speed. The congestion hypothesis in this study is that the bus is slow, and the total number of MAC addresses is high at the same time, or vice versa. The results show that the maximum correlation value between speed and total number of MAC addresses is -0.629. Negative correlation leads to slower bus speeds, higher total MAC addresses, and different. The numbers indicate the congested sections around the bus route during the bus operating hours. Several parameters such as travel time, travel speed and standard deviation/variance were analyzed for congestion level. Analyze aspects that link road conditions to good or bad service. Congestion levels can be determined based on RI, which is derived from the standard deviation and average speed of each road link.

A data-driven agent-based model of occupants’ thermal comfort behaviors for the planning of district-scale flexible work arrangements

In a global context of increasing flexibility in the way workplaces and the districts in which they are located are used, there is a need for occupant-driven approaches to plan urban energy systems. Several authors have suggested the use of agent-based models (ABM) of building occupants in urban building energy simulations due to their ability to reproduce emergent behaviors from individual agents’ actions. However, few works in the literature take full advantage of the ABM paradigm, accounting for both occupant presence and energy-relevant behaviors at the district scale. In this work, we propose a methodology to develop a data-driven, agent-based model of building occupants’ activities and thermal comfort in an urban district. Our methodology combines the use of campus-scale Wi-Fi data to derive feasible occupant activity and location plans, along with thermal preference profiles derived from a longitudinal field study where off-the-shelf, non-intrusive sensors were used to capture the right-here-right-now thermal preference of 35 participants in the same case study district. Our model is then used to explore how different district operation strategies could affect building energy performance in the context of increased workspace flexibility. Our results show that by providing a diversity of building operation conditions, with different buildings having different set point temperatures, occupants’ thermal comfort hours could be improved by an average of about 10% with little effect on district energy performance. Meanwhile, a 6%–15% average decrease in space cooling energy use intensity was observed when implementing occupant-driven ventilation and setpoint controls, regardless of location choice scenario.

Juxtaposing individual and group mobility from sparse Wi-Fi signatures with cloud-assisted computing: a case study for a multidisciplinary university campus

ABSTRACT Understanding human mobility undoubtedly enriches common goods. Among available location-aware technologies, Wi-Fi provides a more sustainable and high-resolution means to study human mobility patterns as it has become conspicuous and affordable recently. Whilst existing studies have shed light on facets of personal mobility, the intricate dynamics of group mobility have garnered comparatively scant empirical scrutiny in real-world settings, especially in the juxtaposition with individual mobility. Moreover, they have often overlooked the multifaceted nature of personal attributes influencing daily routines. This study introduces a comprehensive framework that takes advantage of the readily available Wi-Fi connection data and cloud-assisted computing for juxtaposing individual and group mobility. The framework was tested on auniversity campus that provides representative human mobility patterns with diverse attributes. Two tests that aim to demonstrate the framework’s capability to (1) capture individual mobility patterns by using data processing amenable to the spatiotemporal sparseness and to formulate group mobility and (2) differentiate quantitatively the spatiotemporal signatures of distributions, night activities, transitions, and network topologies were conducted. This study uncovers distinct disparities between individuals and groups, and heterogeneities among different attributes in both an empirical and real-world scenario with a reduction in computation time to approximately 6% of the baseline.

Large-scale Wi-Fi and Bluetooth data collection for reconstructing passenger flows

ABSTRACT For a public transport operator, estimating passenger flows is vital to plan inclusive and efficient service. Understanding where and when to optimally allocate resources results in better customer experiences, further shaping and optimizing public transport services. To this end, the project Mobile Data Fusion aims at developing a technique to collect, process, and merge data from different sources. The data are used to inform public transport operators about passenger demand, by combining Wi-Fi and Bluetooth signals from customer devices with time-of-flight counting sensors. The project had access to a large study area in Kassel, Germany, with a fleet of 50 vehicles servicing eight passenger lines, all equipped with automatic passenger counting sensors. In the course of this study, we found out that Bluetooth signals did not offer any significant insight , while Wi-Fi signals could be used to reconstruct a trend, albeit not the absolute occupancy level. In this paper, we present our hardware setup and a subset of our data set to show how the Wi-Fi and Bluetooth signals correlate with the measured occupancy. The ongoing data collection will provide additional material for future studies, and answer some of the pending questions discussed in this work.

Factors Affecting the Digital Readiness and Adoption of Digital Marketing of Vegetable Farmers in CALABARZON, Philippines

Purpose - The paper analyzed the factors affecting the digital readiness and adoption of digital marketing by vegetable farmers in CALABARZON, Philippines. It assessed knowledge on different digital marketing technologies, evaluated access to and use of digital devices and marketing platform, and determined the cost of digital marketing adoption. Design/Methodology/Approach - A total of 773 vegetable farmers were selected using disproportionate stratified random sampling, and then personally interviewed. Adapting the methodologies of Horrigan (2016) and Roberts and Hernandez (2019), farmers were categorized based on digital readiness. Correlation and Probit analyses were performed to determine the factors affecting digital readiness and adoption of digital marketing. Findings - Results revealed the following: unprepared (0.33%), traditional (14.49%), reluctant (25.00%), cautious clickers (53.33%), and digitally ready (6.85%). Only 14 percent were digital platform users; the most common gadget used was mobile phone, and while home Wi-Fi and cellular data were the most popular connections, they were still unstable. Adoption of digital marketing lessened vegetable marketing cost. Those single with a higher level of education, household income, and larger household had higher digital readiness level. Digital marketing adoption was positively affected by level of education and digital readiness, but the cost of adoption had negative effect. Research Implications - The results suggest the implementation of location- and readiness level-specific training and digital literacy programs; improvement of Internet infrastructure in major producing areas; and the provision of institutional support to prevent scam and fraudulent transactions to enhance the digital readiness and adoption of digital marketing by farmers.

A Machine Learning Approach to Estimate Public Transport Ridership Using Wi-Fi Data

A Machine Learning Approach to Estimate Public Transport Ridership Using Wi-Fi Data

Estimating Bus Passenger Mobility with Wi-Fi Data and Clustering

Thanks to Wi-Fi technology, it is possible to gather passive mobility data over a long time and to analyze travel behaviors variability. However, the main challenge is to identify relevant data, in a way that is efficient whatever the chosen period of network. Our research evaluates the replicability of a method, based on a partitioning algorithm, that allows to identify signals emitted by passengers from those emitted by non-passengers automatically. The findings show that this algorithm is easily replicable and useful to study individual mobility from passive data. It is hence a good opportunity for understanding travel demand.

WiAi-ID: Wi-Fi-Based Domain Adaptation for Appearance-Independent Passive Person Identification

Wi-Fi signal-based person identification has become a hot research topic due to the widespread deployment of Wi-Fi devices and the fact that these approaches are non-contact, passive, and privacy-preserving. While the existing related methods and systems have achieved good performance for person identification, they also encounter many significant challenges in practical applications. Due to the propagation properties of Wi-Fi signals, the signal at the receiver will change significantly when the user’s appearance changes. This makes single-appearance trained models unusable for cross-appearance recognition tasks. To address this challenge, we propose a deep learning-based framework for appearance-independent identification using Wi-Fi signals (WiAi-ID), the core of which lies in the fact that the domain discriminator and feature extractor are trained together in an adversarial manner, thus forcing the model to extract identity-inherent features independent of human appearance, and introduces a multi-scale CNN adaptation module to capture time-span-based features. We collected Wi-Fi signal data of pedestrians with different appearances. The experimental results show that WiAi-ID can effectively eliminate the impact on identification due to pedestrian appearance variations and accordingly outperforms the current state-of-the-art video and wireless signal-based recognition methods.

Decentralized fault tolerant source localization without sensor parameters in wireless sensor networks

In this paper, we study the source (event) localization problem in decentralized wireless sensor networks (WSNs) under faulty sensor nodes without knowledge of the sensor parameters. Source localization has many applications, such as localizing WiFi hotspots and mobile users. Some works in the literature localize the source by utilizing the knowledge or estimates of the fault probability of each sensor node or the region of influence of the source. However, this paper proposes two approaches: the hitting set and feature selection for estimating the source location without any knowledge of the sensor parameters under faulty sensor nodes in WSN. The proposed approaches provide better or comparable source localization performances. For the hitting set approach, we also derive a lower bound on the required number of samples. In addition, we extend the proposed methods for localizing multiple sources. Finally, we provide extensive simulations to illustrate the performances of the proposed methods against the centroid, maximum likelihood (ML), fault-tolerant ML (FTML), and subtract on negative add on positive (SNAP) estimators. The proposed approaches significantly outperform the centroid and maximum likelihood estimators for faulty sensor nodes while providing comparable or better performance to FTML or SNAP algorithm. In addition, we use real-world WiFi data set to localize the source in comparison to the support vector machine based estimator in the literature, where the proposed methods outperformed the estimator.

ОРГАНИЗАЦИЯ СИСТЕМЫ УПРАВЛЕНИЯ ОФИСНЫМ ОСВЕЩЕНИЕМ С ВОЗМОЖНОСТЬЮ ТОЧЕЧНОЙ НАСТРОЙКИ

This article describes a specific approach to organizing the artificial light environment of an office space with a common space. The main criteria of modern lighting systems are given, which must be taken into account when designing. It is proposed to create an energy-efficient system with great functionality to integrate a lighting control module into the existing system, which includes LED lamps with built-in microcontrollers. To control the level of illumination and the color spectrum emitted by the LED lighting device in real time, it is proposed to use a portable small-sized sensor. The system for monitoring and controlling lighting parameters is built using Wi-Fi wireless data transmission technology. The control system will make it possible to carry out point individual adjustment, taking into account the specified operating parameters and user requirements.

Tracking people across ultra populated indoor spaces by matching unreliable Wi-Fi signals with disconnected video feeds

Tracking in dense indoor environments where several thousands of people move around is an extremely challenging problem. In this paper, we present a system — DenseTrack for tracking people in such environments. DenseTrack leverages data from the sensing modalities that are already present in these environments — Wi-Fi (from enterprise network deployments) and Video (from surveillance cameras). We combine Wi-Fi information with video data to overcome the individual errors induced by these modalities. More precisely, the locations derived from video are used to overcome the localization errors inherent in using Wi-Fi signals where precise Wi-Fi MAC IDs are used to locate the same devices across different levels and locations inside a building. Typically, localization in dense environments is a computationally expensive process when done with just video data; hence hard to scale. DenseTrack combines Wi-Fi and video data to improve the accuracy of tracking people that are represented by video objects from non-overlapping video feeds. DenseTrack is a scalable and device-agnostic solution as it does not require any app installation on user smartphones or modifications to the Wi-Fi system. At the core of DenseTrack, is our algorithm — inCremental Association of Independent Variables under Uncertainty (CAIVU). CAIVU is inspired by the multi-armed bandits model and is designed to handle various complex features of practical real-world environments. CAIVU matches the devices reported by an off-the-shelf Wi-Fi system using connectivity information to specific video blobs obtained through a computationally efficient analysis of video data. By exploiting data from heterogeneous sources, DenseTrack offers an effective real-time solution for individual tracking in heavily populated indoor environments. We emphasize that no other previous system targeted nor was validated in such dense indoor environments. We tested DenseTrack extensively using both simulated data, as well as two real-world validations using data from an extremely dense convention center and a moderately dense university environment. Our simulation results show that DenseTrack achieves an average video-to-Wi-Fi matching accuracy of up to 90% in dense environments with a matching latency of 60 s on the simulator. When tested in a real-world extremely dense environment with over 500,000 people moving between different non-overlapping camera feeds, DenseTrack achieved an average match accuracy of 83% to within a 2-people distance with an average latency of 48 s.

Geo-Visualization of Spatial Occupancy on Smart Campus Using Wi-Fi Connection Log Data

As a typical and special type of urban setting, the university campus usually faces similar challenges as cities raised by high-density inhabitants. The smart campus has been introduced based on the smart city, as concepts, technologies, and solutions to improve livability and energy efficiency. Inhabitants’ occupancy in buildings and open spaces on campus is critical to optimize campus management and services. Information about spatial occupancy of campus inhabitants can be produced based on various location-based solutions, such as global navigation satellite systems (GNSS), campus cameras, Bluetooth, and Wi-Fi. As an essential component in campus information infrastructure, Wi-Fi network covers almost the entire university campus and has advantages in collecting locations of campus inhabitants. In this paper, geo-visualization of spatial occupancy of campus inhabitants is designed and implemented using anonymized Wi-Fi network log data. First, 3-dimension building models are reconstructed based on LiDAR point clouds and construction drawings. Then, the Wi-Fi network log data are cleaned and preprocessed. Campus inhabitants’ locations are extracted from structural Wi-Fi data. Geo-visualization at room, floor, and building levels is designed and implemented. On a temporal dimension, spatial occupancy can be visualized by each second, minute, hour, or day of the week in 3D buildings. The implementation of the geo-visualization is based on CesiumJS, which offers an interface for 3D-animated visualization and interaction. The research can be used to support university management and educators to implement the smart campus and optimize pedagogical research.

Leveraging campus-scale Wi-Fi data for activity-based occupant modeling in urban energy applications

The widespread availability of open datasets in urban areas is transforming how urban energy systems are planned, simulated, and visualized. Urban energy models, however, require an understanding of urban dwellers, as their activities create the demands for energy in buildings. In this paper, we explore using campus-scale Wi-Fi data to identify typical occupant activity patterns as an input to an agent-based model of building occupants at the district scale. The data is taken from a Singaporean university’s Wi-Fi network at high resolution. Each record comprises a timestamp, a device identifier, the location of the device within the campus, and the access point to which it is connected. The Wi-Fi dataset contains 120 different buildings on campus and 10,300 anonymized individual devices. Activities are then assigned to each location on campus according to the building use type. In order to test the methodology, the activity plans of 27,604 undergraduate students, 8,304 graduate students, and 12,018 employees were simulated over a workweek. The results show the model’s ability to produce plausible activity plans but could be improved by implementing sampling rules and expanding the source dataset to include off-peak dates. Nevertheless, using such an agent-based modeling approach at the district scale appears to be a promising methodology to assess the impacts of different planning strategies on occupant behavior and district energy demand.

Industrial Environment Multi-Sensor Dataset for Vehicle Indoor Tracking with Wi-Fi, Inertial and Odometry Data

This paper describes a dataset collected in an industrial setting using a mobile unit resembling an industrial vehicle equipped with several sensors. Wi-Fi interfaces collect signals from available Access Points (APs), while motion sensors collect data regarding the mobile unit’s movement (orientation and displacement). The distinctive features of this dataset include synchronous data collection from multiple sensors, such as Wi-Fi data acquired from multiple interfaces (including a radio map), orientation provided by two low-cost Inertial Measurement Unit (IMU) sensors, and displacement (travelled distance) measured by an absolute encoder attached to the mobile unit’s wheel. Accurate ground-truth information was determined using a computer vision approach that recorded timestamps as the mobile unit passed through reference locations. We assessed the quality of the proposed dataset by applying baseline methods for dead reckoning and Wi-Fi fingerprinting. The average positioning error for simple dead reckoning, without using any other absolute positioning technique, is 8.25 m and 11.66 m for IMU1 and IMU2, respectively. The average positioning error for simple Wi-Fi fingerprinting is 2.19 m when combining the RSSI information from five Wi-Fi interfaces. This dataset contributes to the fields of Industry 4.0 and mobile sensing, providing researchers with a resource to develop, test, and evaluate indoor tracking solutions for industrial vehicles.

Using Wi-Fi Connection Data to Analyze Performance of the Subway System in Toronto, Canada

Typical performance measurements of public transit operations make use of vehicle-based data such as automated vehicle location data or passenger-based data at specific fare collection points. Ideally, the performance of a transit system from a reliability perspective and according to passenger experience should be measured through individual passenger journeys. The growing prevalence of smartphones provides one potential source for this analysis, because passive data collection methods such as obtaining Wi-Fi, cellular, and Bluetooth connection data allow us to observe devices as they move throughout the system. In this study we present a collection of methods and performance measures for using Wi-Fi connection data to measure various aspects of customer experience and reliability, including methods for detecting train arrivals at platforms, estimating wait times, measuring origin–destination travel time variation, and developing profiles of various journey types for comparison. In contrast with many other advances toward passenger-based measures, these methods do not require the combination of diverse data sets to generate useful results. These methods are applied to data from the Wi-Fi service in the subway system in Toronto, Canada.

Enhanced Clustering and Indoor Movement Path Generation from Wi-Fi Fingerprint Data Using Bounding Boxes and Grid Cells

Recently, various application fields utilizing Wi-Fi fingerprint data have been under research. However, fingerprint data collected from a specific location does not include relevant information, such as continuity. Therefore, most indoor positioning technologies predict the user’s location based on location signals collected at specific points within the indoor space, without taking into account the user’s movements. Hence, there is a need for technology that improves the accuracy of indoor positioning while moving. This paper proposes a technique to generate movement path data by applying the concepts of “BB” and “Grid Cell” from computer vision to Wi-Fi fingerprint data. This approach represents data points as bounding boxes (BBs), then establishes grid cells and clusters of these BBs to generate adjacency information. Subsequently, movement path data are created based on this information. We utilized the movement path information generated from the dataset as training data for machine learning and introduced an enhanced indoor positioning technology. First, the experiments in this paper assessed the performance of the proposed technology based on the number of paths in the LSTM model. Second, the performance of clustering methods was compared through experiments. Finally, we evaluated the performance of various machine learning models. The experimental results confirmed a maximum accuracy of 94.48% when determining the location based on route information. Clustering performance improved accuracy by up to 3%. In comparative experiments with machine learning models, accuracy improved by up to 2.8%.

Design and Machining Applications of the Piezoelectric Vibration Sensing System

A piezoelectric vibration sensing system (PVSS) was devised in this study and employed for the purpose of vibration sensing in machining. The system comprises three primary components, wherein the sensor is utilized for the collection and conversion of energy, subsequently transmitting it to the data acquisition card (DAC) via a low-noise cable. The crux of the entire system lies in the upper computer-based control application, which facilitates the transmission of instructions to the DAC for data acquisition and transmission. The integration of Wi-Fi data transfer capability between the DAC and the computer serves to eliminate the principal issue associated with employing the sensor as a voltage source. The sensitivity of the designed device was calibrated utilizing commercial accelerometers, while an aluminum workpiece was fabricated to conduct vibration and machining tests in order to verify the performance of the PVSS. The shaker excitation experiment yielded a peak voltage of 0.05 mV, thereby substantiating that the PVSS can more accurately discern the natural frequency of the workpiece below 5000 Hz compared to commercial accelerometers. The experiments verify that the devised PVSS can precisely measure vibrations during the milling process, and can be implemented for the purpose of detecting machining stability.