Mobile Phone Dataset Research Articles

An Extended Method Based on the Geometric Position of Salient Image Features: Solving the Dataset Imbalance Problem in Greenhouse Tomato Growing Scenarios

Machine vision has significant advantages in a wide range of agricultural applications; however, acquiring a large number of high-quality image resources is often challenging in actual agricultural production due to environmental and equipment conditions. Therefore, crop image augmentation techniques are particularly important in crop growth analysis. In this paper, greenhouse tomato plants were used as research subjects to collect images of their different fertility stages with flowers and fruits. Due to the different durations of each fertility period, there is a significant difference in the number of images collected. For this reason, this paper proposes a method for balanced amplification of significant feature information in images based on geometric position. Through the geometric position information of the target in the image, different segmentation strategies are used to process the image and supervised and unsupervised methods are applied to perform balanced augmentation of the image, which is combined with the YOLOv7 algorithm to verify the augmentation effect. In terms of the image dataset, the mixed image dataset (Mix) is supplemented with mobile phone images on top of in situ monitoring images, with precision increased from 70.33% to 82.81% and recall increased from 69.15% to 81.25%. In terms of image augmentation, after supervised balanced amplification, the detection accuracy is improved from 70.33% to 77.29%, which is suitable for supervised balanced amplification. For the mobile phone dataset (MP), after amplification, it was found that better results could be achieved without any amplification method. The detection accuracy of the mixed dataset with different data sources matching the appropriate amplification method increased slightly from 82.81% to 83.59%, and accurate detection could be achieved when the target was shaded by the plant, and in different environments and light conditions.

Analyzing the impacts of cultural backgrounds on migrants' acculturation strategies in mobile phone social networks

By employing a large-scale mobile phone dataset and constructing a social network with 6,351,033 nodes and 14,735,425 ties, this research empirically studies how the individualistic and collectivistic (I-C) cultural backgrounds of migrants influence their acculturation strategies under different contexts. We introduced the rice theory and developed new network-based constructs to measure their acculturation strategies, I-C cultural backgrounds, and socioeconomic status. We found that migrants with more collectivistic cultural backgrounds tend to interact more with people from their hometowns rather than locals of their host societies. Surprisingly, this relationship is contingent on cultural distance: when a migrant's cultural background is similar to the host society, this migrant tends to interact more with local friends than people from her hometown. Moreover, higher socioeconomic status is found to decrease the cultural conservatism tendencies of migrants with more collectivistic cultural backgrounds. These findings can help stakeholders to devise more refined policies to better integrate migrants with diverse backgrounds and reduce potential cultural conflicts.

Intercity Traffic Travel Mode Identification Method Based on Mobile Signalling Data

With the popularity of mobile devices, the signalling data generated by them provides significant opportunities for studying intercity travel behaviour in terms of data scale and information continuity. However, due to the low quality of the data in spatial accuracy, temporal frequency, and traffic semantics, the accuracy of identifying individual travel modes is low and it is difficult to extend to complex traffic scenarios. In this paper, we propose a new framework for identifying individual intercity travel modes based on mobile signalling data. The framework includes components for data pre-processing, geo-information mapping, feature and attribute extraction, and travel mode recognition. We utilize a comprehensive detection model to identify users’ multimodal intercity transport behaviour. Using two modules, Random Forest Embedding (RFE) and Bidirectional Long Short-Term Memory (Bi-LSTM), the model can capture the spatiotemporal characteristics and complex multi-stage associations in intercity travel chains. A large-scale mobile phone dataset from Jiangsu Province, China, was used for verification. The results showed that, on average, the method was able to detect travel mode with 92% accuracy. This study provides valuable support for further research on individual travel behaviour and the enhancement of transportation planning.

Activity type detection of mobile phone data based on self-training: Application of the teacher–student cycling model

Incorporating mobile phone data, known for its high spatial and temporal resolution and extensive population coverage, into Activity-Based Models (ABM) for understanding individual travel and activity behaviors is a current research hotspot. However, applying them in ABM building is not straightforward because they miss key information — activity type. In this paper, we present an activity types detection method named the Teacher–Student Cycling model based on a self-training framework. Our model can combine travel survey data with extensive prior knowledge and mobile phone data. We introduce two different resolutions of mobile phone datasets to test the model performance. Our results show that our proposed model can achieve good performance on datasets of different resolutions. Our model, one of the semi-supervised learning models that uses a mixture of labeled and unlabeled knowledge performs better than the supervised learning model that uses labeled knowledge alone. In addition, our model improves the overall detection accuracy by 7% over the second-best semi-supervised learning model and improves the detection accuracy of secondary activities by up to 17%. Our model can be valuable in generating daily activity schedules for agent-based models.

A behavioral explanation of the activity-space segregation: Individuals’ preference of choosing an activity destination

The difference in the individuals’ preference of activity destination choice is a new explanation for the activity-space segregation. This study investigates individuals’ preference in the destination choice for their daily activities. It uses revealed preference survey for the choice of the activity destination, and mobile phone dataset for the ambient population at the activity destination in Guangzhou, China. It has found that (1) the activity-space segregation is strongly influenced by the residential segregation, but disadvantaged populations are more spatially constrained by the distance decay effect; (2) all individuals prefer a destination with high diversity of built environment; and (3) migrant people tend to be self-segregated at the activity space, but people with higher education status prefer to take activities at an integrated place.

Semantic-Enhanced Graph Convolutional Neural Networks for Multi-Scale Urban Functional-Feature Identification Based on Human Mobility

Precise identification of spatial unit functional features in the city is a pre-condition for urban planning and policy-making. However, inferring unknown attributes of urban spatial units from data mining of spatial interaction remains a challenge in geographic information science. Although neural-network approaches have been widely applied to this field, urban dynamics, spatial semantics, and their relationship with urban functional features have not been deeply discussed. To this end, we proposed semantic-enhanced graph convolutional neural networks (GCNNs) to facilitate the multi-scale embedding of urban spatial units, based on which the identification of urban land use is achieved by leveraging the characteristics of human mobility extracted from the largest mobile phone datasets to date. Given the heterogeneity of multi-modal spatial data, we introduced the combination of a systematic data-alignment method and a generative feature-fusion method for the robust construction of heterogeneous graphs, providing an adaptive solution to improve GCNNs’ performance in node-classification tasks. Our work explicitly examined the scale effect on GCNN backbones, for the first time. The results prove that large-scale tasks are more sensitive to the directionality of spatial interaction, and small-scale tasks are more sensitive to the adjacency of spatial interaction. Quantitative experiments conducted in Shenzhen demonstrate the superior performance of our proposed framework compared to state-of-the-art methods. The best accuracy is achieved by the inductive GraphSAGE model at the scale of 250 m, exceeding the baseline by 25.4%. Furthermore, we innovatively explained the role of spatial-interaction factors in the identification of urban land use through the deep learning method.

Intelligent Stock Price Fusion in Mobile Industries

In the tough cell phone business, guessing phone­ prices right is a key but hard job for new companies. Joining different types of info to look at stock prices may help, but we need strong ways to see how phone things and their costs tie together. This study wants to make stock price checking better in the cell phone busine­ss by using ways to join info. The work looks for strong ties between many phone things like memory, camera details, and screen size and how they affect the price. To fix this, very careful work was done to clean and fix the info. The Quadratic Discriminant Analysis rule­ was then used, along with top classifiers, for saying what will happen. Our findings demonstrate the QDA model's ability to detect subtle patterns and nonlinear correlations in the mobile phone data set. The model's resilience and predictive ability are demonstrated through visualizations such as ROC AUC and Precision-Recall curves. Comparative analyses with current approaches highlight the higher performance of the suggested data fusion approach. The use of QDA in data fusion models demonstrates its versatility in capturing complicated interactions, resulting in nuanced insights into mobile phone price factors. This study adds an improved prediction framework for mobile phone price analysis, which is critical for new enterprises looking to gain a competitive advantage in the volatile mobile industry.

A tensor based price evaluation approach for the used mobile phone recycling

The automatic price evaluation is an important and challenging issue for the used mobile phone recycling. However, due to complicated relationships between attributes and price as well as insufficient sample data, current approaches cannot achieve accurate price evaluation for the used mobile phones, which significantly reduce the efficiency for the used mobile phone recycling. To this end, a tensor based approach is proposed in this paper, which can achieve accurate and efficient price evaluation for used mobile phones. In the proposed approach, first, the mutual information based attributes selection mechanism and the boxplot based sample selection mechanism are employed to select the most relevant attributes and suitable price samples from used mobile phone dataset. Then, a tensor model is constructed to establish multi-dimensional relationships between selected attributes and prices of used mobile phones. Finally, the missing values in the constructed tensor model is completed through the gradient descent and CANDECOMP/PARAFAC decomposition algorithms. The completed tensor model can be directly used for the price evaluation of used mobile phones based on their attributes without further calculation. Based on the real price dataset of used mobile phones, the experiments indicate that the proposed approach outperforms most of current approaches for the price evaluation for the used mobile phones.

The rhythms of transient relationships: allocating time between weekdays and weekends.

A fundamental question of any new relationship is, will it last? Transient relationships, recently defined by the authors, are an ideal type of social tie to explore this question: these relationships are characterized by distinguishable starting and ending temporal points, linking the question of tie longevity to relationship finite lifetime. In this study, we use mobile phone data sets from the UK and Italy to analyse the weekly allocation of time invested in maintaining transient relationships. We find that more relationships are created during weekdays, with a greater proportion of them receiving more contact during these days of the week in the long term. The smaller group of relationships that receive more phone calls during the weekend tend to remain active for more time. We uncover a sorting process by which some ties are moved from weekdays to weekends and vice versa, mostly in the first half of the relationship. This process also carries more information about the ultimate lifetime of a tie than the part of the week when the relationship started, which suggests an early evaluation period that leads to a decision on how to allocate time to different types of transient ties.

Unsupervised anomaly detection by densely contrastive learning for time series data

Time series data continuously collected by different sensors play an essential role in monitoring and predicting events in many real-world applications, and anomaly detection for time series has received increasing attention during the past decades. In this paper, we propose an anomaly detection method by densely contrasting the whole time series with its sub-sequences at different timestamps in a latent space. Our approach leverages the locality property of convolutional neural networks (CNN) and integrates position embedding to effectively capture local features for sub-sequences. Simultaneously, we employ an attention mechanism to extract global features from the entire time series. By combining these local and global features, our model is trained using both instance-level contrastive learning loss and distribution-level alignment loss. Furthermore, we introduce a reconstruction loss applied to the extracted global features to prevent the potential loss of information. To validate the efficacy of our proposed technique, we conduct experiments on publicly available time-series datasets for anomaly detection. Additionally, we evaluate our method on an in-house mobile phone dataset aimed at monitoring the status of Parkinson’s disease, all within an unsupervised learning framework. Our results demonstrate the effectiveness and potential of the proposed approach in tackling anomaly detection in time series data, offering promising applications in real-world scenarios.

Sensing Mobility and Routine Locations through Mobile Phone and Crowdsourced Data: Analyzing Travel and Behavior during COVID-19

The COVID-19 pandemic affected many aspects of human mobility and resulted in unprecedented changes in population dynamics, including lifestyle and mobility. Recognizing the effects of the pandemic is crucial to understand changes and mitigate negative impacts. Spatial data on human activity, including mobile phone data, has the potential to provide movement patterns and identify regularly visited locations. Moreover, crowdsourced geospatial information can explain and characterize the regularly visited locations. The analysis of both mobility and routine locations in the same study has seldom been carried out using mobile phone data and linked to the effects of the pandemic. Therefore, in this article we study human mobility patterns within Portugal, using mobile phone and crowdsourced data to compare the population’s mobility and routine locations after the pandemic’s peak. We use clustering algorithms to identify citizens’ stops and routine locations, at an antenna level, during the following months after the pandemic’s first wave and the same period of the following year. Results based on two mobile phone datasets showed a significant difference in mobility in the two periods. Nevertheless, routine locations slightly differ.

A Cross-Scale Representation of Tourist Activity Space

Destination, as a key concept in tourism geography, has largely determined the scale at which tourist activity space was modeled and studied. Existing studies usually focused on investigating tourists’ activities and movements either at the intradestination (e.g., within a city) or interdestination scale. Although useful in numerous research contexts, these models based on fixed spatial scales are incapable of portraying the complex spatial structure of tourist activity spaces, which sometimes exhibit hierarchical structures, and could span across different spatial scales. In this study, we propose a new representation of tourist activity space to bridge these gaps. The representation takes tourists’ accommodation locations as key reference points. At the macroscale, the sequence of accommodation locations forms the backbone of tourist activity space, denoted as itinerary type. At the microscale, we introduce the concept of territory to describe how individuals organize activities around these overnight “base camps” (i.e., accommodation locations). We apply this representation over a large-scale mobile phone data set of international travelers visiting South Korea to demonstrate its capability. Results show that four generic itinerary types capture the activity space structure of 89 percent of the tourists. The interrelationships of territories and their topological structures further categorize activity spaces into subtypes, leading to a new method of tourist classification based on their spatiotemporal activity patterns. We believe the proposed representation could enrich new perspectives and debates on how tourist activities can be studied. The representation can also be extended as a generic framework to delineate complex forms of human activity space.

Modelling exposure between populations using networks of mobility during COVID-19

The use of mobile phone call detail records and device location data for the calling patterns, movements, and social contacts of individuals, have proven to be valuable for devising models and understanding of their mobility and behaviour patterns. In this study we investigate weighted exposure networks of human daily activities in the capital region of Finland as a proxy for contacts between postal code areas during the pre-pandemic year 2019 and pandemic years 2020, 2021 and early 2022. We investigate the suitability of gravity and radiation type models for reconstructing the exposure networks based on geo-spatial and population mobility information. For this we use a mobile phone dataset of aggregated daily visits from a postal code area to cellphone grid locations, and treat it as a bipartite network to create weighted one mode projections using a weighted co-occurrence function. We fit a classical gravity model and a radiation model to the averaged weekly and yearly projection networks with geo-spatial and socioeconomic variables of the postal code areas and their populations. We also consider an extended gravity type model comprising of additional postal area information such as distance via public transportation and population density. The results show that the co-occurrence of human activities, or exposure, between postal code areas follows both the gravity and radiation type interactions, once fitted to the empirical network. The effects of the pandemic beginning in 2020 can be observed as a decrease of the overall activity as well as of the exposure of the projected networks. These effects can also be observed in the network structure as changes towards lower clustering and higher assortativity. Evaluating the parameters of the fitted models over time shows on average a shift towards a higher exposure of areas in closer proximity as well as a higher exposure towards areas with larger population. In general, the results show that the postal code level networks changed to be more proximity weighted after the pandemic began, following the government imposed non-pharmaceutical interventions, with differences based on the geo-spatial and socioeconomic structure of the areas.

How does socioeconomic status influence social relations? A perspective from mobile phone data

Socioeconomic status (SES) and social relations are two important aspects of human social life. Does socioeconomic status influence social relations? If some relationship exists, it will help us understand various social issues such as economic mobility, social segregation, and disparity in health outcomes. Despite long-term efforts, our knowledge about how SES influences the strength and types of social relations is still limited. In this study, we used a large mobile phone dataset in Beijing, China, to study the relationship between SES and the strength and types of social relations at an urban population level. Specifically, we divided the social relations into three types based on users’ spatiotemporal mobility similarity: (1) family members with high similarity on weekday nights and weekends; (2) coworkers with high similarity on weekdays during the daytime; (3) friends with low similarity all the time. An individual’s SES was represented by the housing price in the home location. The results showed that people of higher SES (living in areas with higher housing prices) tend to interact less with others and allocate more time with friends but less time with family and coworkers than people of lower SES. Besides, people of higher SES split their time more unevenly to different social relationships. These findings shed light on solutions related to SES and inequality. For example, people of low SES could learn to expand their social circles by connecting with people who are different from their daily environment, which may bring upward social mobility and improve their well-being.

An urban crowd flow model integrating geographic characteristics

Predicting urban crowd flow spatial distributions plays a critical role in optimizing urban public safety and traffic congestion management. The spatial dependency between regions and the temporal dynamics of the local crowd flow are two important features in urban crowd flow prediction. However, few studies considered geographic characteristic in terms of spatial features. To fill this gap, we propose an urban crowd flow prediction model integrating geographic characteristics (FPM-geo). First, three geographic characteristics, proximity, functional similarity, and road network connectivity, are fused by a residual multigraph convolution network to model the spatial dependency relationship. Then, a long short-term memory network is applied as a framework to integrate both the temporal dynamic patterns of local crowd flow and the spatial dependency between regions. A 4-day mobile phone dataset validates the effectiveness of the proposed method by comparing it with several widely used approaches. The result shows that the root mean square error decreases by 15.37% compared with those of the typical models with the prediction interval at the 15-min level. The prediction error increases with the crowd flow size in a local area. Moreover, the error reaches the top of the morning peak and the evening peak and slopes down to the bottom at night.

A dataset to assess mobility changes in Chile following local quarantines

Fighting the COVID-19 pandemic, most countries have implemented non-pharmaceutical interventions like wearing masks, physical distancing, lockdown, and travel restrictions. Because of their economic and logistical effects, tracking mobility changes during quarantines is crucial in assessing their efficacy and predicting the virus spread. Unlike many other heavily affected countries, Chile implemented quarantines at a more localized level, shutting down small administrative zones, rather than the whole country or large regions. Given the non-obvious effects of these localized quarantines, tracking mobility becomes even more critical in Chile. To assess the impact on human mobility of the localized quarantines, we analyze a mobile phone dataset made available by Telefónica Chile, which comprises 31 billion eXtended Detail Records and 5.4 million users covering the period February 26th to September 20th, 2020. From these records, we derive three epidemiologically relevant metrics describing the mobility within and between comunas. The datasets made available may be useful to understand the effect of localized quarantines in containing the COVID-19 pandemic.

How do urban services facilities affect social segregation among people of different economic levels? A case study of Shenzhen city

Social segregation hinders the development of cities and has become a hot topic in urban research. Existing studies have focused on the difference in the distribution of crowd activities to measure segregation but have ignored the impact of the urban environment on crowd gathering and segregation. To study the impact and understand social segregation more comprehensively, we coupled mobile phone datasets and housing price data to divide city dwellers into three socioeconomic levels. Considering that spatial colocation is a necessary condition for interaction among various social groups, spatial colocation probability was proposed to quantitatively describe the degree of social segregation at the community scale. Point-of-interest (POI) data were introduced to represent the urban service facilities. The effect of urban service facilities on the segregation of different groups was analyzed by using geographically weighted regression (GWR). The results indicate three points, as follows. (1) Significant social segregation in Shenzhen mostly occurs in suburban and downtown areas, and the interaction segregation of people mainly occurs between people with high and low socioeconomic levels. (2) More economically inclusive and necessary service facilities (e.g., medical and insurance companies) can promote crowd interaction and ease the segregation of social activities. (3) The impact of service facilities on the interaction of various social groups is related to the development of the area where the activities occur, and the most significant impact is in high-tech industrial zones. This study quantitatively calculated the impacts of different service facilities on different groups of people in different communities and times. From the results, detailed and reasonable suggestions were made for city planners.

Fine-grained crowd distribution forecasting with multi-order spatial interactions using mobile phone data

Fine-grained crowd distribution forecasting benefits smart transportation operations and management, such as public transport dispatch, traffic demand prediction, and transport emergency response. Considering the co-evolutionary patterns of crowd distribution, the interactions among places are essential for modelling crowd distribution variations. However, two issues remain. First, the lack of sampling design in passive big data acquisition makes the spatial interaction characterizations of less crowded places insufficient. Second, the multi-order spatial interactions among places can help forecasting crowd distribution but are rarely considered in the existing literature. To address these issues, a novel crowd distribution forecasting method with multi-order spatial interactions was proposed. In particular, a weighted random walk algorithm was applied to generate simulated trajectories for improving the interaction characterizations derived from sparse mobile phone data. The multi-order spatial interactions among contextual non-adjacent places were modelled with an embedding learning technique. The future crowd distribution was forecasted via a graph-based deep neural network. The proposed method was verified using a real-world mobile phone dataset, and the results showed that both the multi-order spatial interactions and the trajectory data enhancement algorithm helped improve the crowd distribution forecasting performance. The proposed method can be utilized for capturing fine-grained crowd distribution, which supports various applications such as intelligent transportation management and public health decision making.

Short-Term Estimation and Prediction of Pedestrian Density in Urban Hot Spots Based on Mobile Phone Data

Short-term estimation and prediction of pedestrian density in urban hot spots (e.g., railway station, shopping mall, etc.) is an important topic for traffic management and control in densely populated areas. In this paper, we propose a short-term pedestrian density estimation and prediction method based on mobile phone data. Firstly, pedestrian density in hot spots is estimated using mobile phone data. To decrease the positioning errors of mobile phone data, a modified particle filter method, which considers the movements of pedestrians, is applied for pre-processing the data. An efficient spatial access method (i.e., Hilbert R-tree) is adopted to construct pedestrians’ position indexes for realizing the short-term estimation. Secondly, based on the estimation results, the spatiotemporal extended Kalman filter (SEKF) is proposed for the short-term prediction of pedestrian density. A massive mobile phone dataset collected in Nanjing, China is used in the case study. The estimated pedestrian density from Monday to Thursday is used for pedestrian density prediction on Friday. The results show that the proposed method can estimate and predict pedestrian density in hot spots, especially in small-scale sites of hot spots efficiently in a short time. Comparing with classical prediction methods, the proposed SEKF method predicts short-term pedestrian density in urban hot spots more accurately.

Understanding the movement predictability of international travelers using a nationwide mobile phone dataset collected in South Korea

The abilities to predict tourist movements are critical to many urban applications, such as travel recommendations, targeted advertising, and infrastructure planning. Despite its importance, our understanding on the movement predictability of urban tourists and visitors is still limited, partially due to difficulties in accessing large scale mobility observations. In this study, we aim to bridge this gap by analyzing a nationwide mobile phone dataset. The dataset captures movement traces of a large number of international travelers who visited South Korea in 2018. By introducing two prediction models, one being Markov chain and the other with a recurrent neural network architecture, we assess how well travelers’ movements can be predicted under different model settings, and examine how predictability relates to travelers’ length of stay and activeness in travel patterns. Since travelers’ destination choices are quite diverse in South Korea, this enables us to further investigate the geographic variation of the models’ performance. Results show that the Markov chain model achieves an overall accuracy between 33.4% (@Acc1 metric) and 64.2% (@Acc5 metric), compared to 41.9% (@Acc1) and 67.7% (@Acc5) for the recurrent neural network model. The prediction capabilities of both models are largely unequal across individuals, with active travelers being more predictable in general. There is a notable geographic variation in the models’ performance, meaning that travelers’ movements are more predictable in some cities, but less in others. We believe this study represents a new effort in portraying the movement predictability of urban tourists and visitors. The analytical framework can be applied to assist tourism planning and service deployment in cities.