Content uploaded by Dominique Fresneau
Author content
All content in this area was uploaded by Dominique Fresneau
Content may be subject to copyright.
A preview of the PDF is not available
Mining RFID Behavior Data using Unsupervised Learning
Abstract and Figures
Radio Frequency IDentification (RFID) is an advanced tracking technology that can be used to study the spatial organization of individual’s spatio-temporal activity. The aim of this work is firstly to build a new RFID-based autonomous system which can follow individuals’ spatio-temporal activity, a tool not currently available. Secondly, the authors aim to develop new tools for automatic data mining. In this paper, they study how to transform these data to investigate the division of labor, the intra-colonial cooperation and conflict in an ant colony. They also develop a new unsupervised learning data mining method (DS2L-SOM: Density based Simultaneous Two-Level - Self Organizing Map) to find homogeneous clusters (i.e., sets of individual which share a similar behavior). According to the experimental results, this method is very fast and efficient. It also allows a very useful visualization of the results.
Figures - uploaded by Dominique Fresneau
Author content
All figure content in this area was uploaded by Dominique Fresneau
Content may be subject to copyright.
... It gives information about when and where the pattern occurs, and what entities are involved. Clustering is a common approach to the extraction of the movement patterns involving groups of objects moving together and detection of possible interactions between group members especially when there is no possibility to obtain patterns of normal behavior by making observations on normal and abnormal behavior of the entities [14,15]. The obtained clusters are then used to describe the normal behavior model for anomaly detection. ...
... To simplify the analysis of the SOM output, authors supplemented each SOM view with a special matrix-based image that provides information either on temporal or spatial attributes of an object. In Ref. [15], a modified SOM, named as Density-based Simultaneous Two-Level Self Organizing Map, is applied to reveal the social organization of the ant colony. ...
... However, unlike [32], the authors use SOM clustering technique for revealing possible patterns in employees' movement and apply statistics-based mechanism for ranking detected deviations in employee's route considering the periodicity of their occurrence. Unlike [15], the SOM is applied to the analysis of trajectories extracted from the proximity switch logs, and considers both spatial and temporal attributes of the movement. The graphical presentation of the SOM is enforced by the special glyph that gives brief characteristics on entities belonging to one cluster. ...
Employees of different critical infrastructures, including energy systems, are considered to be a security resource, and understanding their behavior patterns may leverage user and entity behavior analytics and improve organization capabilities in information threat detection such as insider threat and targeted attacks. Such behavior patterns are particularly critical for power stations and other energy companies. The paper presents a visual analytics approach to the exploratory analysis of the employees’ routes extracted from the logs of the access control system. Key elements of the approach are interactive self-organizing Kohonen maps used to detect groups of employees with similar movement trajectories, and heat maps highlighting possible anomalies in their movement. The spatiotemporal patterns of the routes are presented using a Gantt chart-based visualization model named BandView. The paper also discusses the results of efficiency assessment of the proposed analysis and visualization models. The assessment procedure was implemented using artificially generated and real-world data. It is demonstrated that the suggested approach may significantly increase the efficiency of the exploratory analysis especially under the condition when no prior information on existing employees’ moving routine is available.
... Fundamental research about machine learning is currently very active Sublime et al., 2017). Data science techniques have become very popular and are now used in several domains, both in academics and industry, such as geospatial imagery (Grozavu et al., 2015;Zhong et al., 2018), telephone communication, face or voice recognition (Bennani, 1998;Kumar et al., 2019), entomology (Cabanes et al., 2010;Hu et al., 2018), and ecology (Thessen, 2016). We decided to apply machine learning algorithms to thermochronology data mining, which had never been used previously to our knowledge. ...
Numerous parameters impact apatite (U-Th-Sm)/He (AHe) thermochronological dates, such as radiation damage, chemical content, crystal size and geometry, and their knowledge is essential for better geological interpretations. The present study investigates a new method based on advanced data mining techniques, to unravel the parameters that could play a role in He retention and thus on AHe date. The purpose is to decipher which factors influence the AHe date dispersion, and to exclude the impact of other parameters on helium retention. As an example, we use a dataset previously collected on apatite from basements rocks, sampled in French Brittany, where all samples underwent the same thermal history, and for which were reported a set of physical and chemical parameters. The dataset includes dimension and geometry, He, U, Th, Sm and major and trace element content for ∼35 crystals. The algorithm ranks the parameters according to their influence on helium retention, using predictive trees, which are commonly used in computing sciences. After looking at 100 simultaneous predictions, we compared the predicted and measured He content for each analyzed apatite crystal. For this particular case, the predictions confirmed the prominent role of the parent nuclides in the He production, as AHe dates can be predicted accurately with these parameters (especially U and Th). Additionally, the predictions without knowledge of the apatite chemical composition and dimension provided better results than using all available parameters (median error of 14% instead of 18%). Therefore, for this specific study, the apatite chemistry and crystal dimensions do not influence significantly He retention nor AHe date dispersion. Nevertheless, detailed inspection of analysis results suggests which parameters have the most discrimination ability, which in this study include crystal length, height, and Mn content. The latter may reveal an eventual influence on alpha damage annealing kinetics. Finally, this approach shows that some grains could never achieve good predictions, indicating that for these crystals the input parameters are not enough to predict the He content. We propose that such crystals are statistically different from the remaining dataset, and this suggests that machine learning has a strong potential to correct errors, or to detect anomalies.
... Modeling instrumented logistics is based on applications of the multiple level instrumented physical monitoring platforms that are enabled through RFID technologies and enterprise information systems (Wang et al., 2010;Cabanes et al., 2010). Interconnected logistics is the connection of logistics chains enabled through the physical internet for interconnectivity. ...
Mining and mineral resources help provide the requirements of everyday life by contributing to essential products and services. In the era of fourth industrial revolution, the trend in logistics is toward a smart logistics system. Therefore, it becomes essential to understand how Industry 4.0 resources influence smart logistics, i.e., instrumented logistics, interconnected logistics, and intelligent logistics. This study investigates how Industry 4.0 resources impact smart logistics and further influence dynamic remanufacturing and green manufacturing capability and, the final effect on business logistics sustainability. Survey data were collected from 150 respondents using an online survey of South African executives in firms operating mines, quarries, and processing plants. Partial Least Squares based structural equation modelling (PLS-SEM) was used to test the hypotheses. The findings indicate that Industry 4.0 resources have a strong effect on intelligent logistics compared to its impact on interconnected logistics and instrumented logistics. The impact of intelligent logistics is found to be very high compared to that of interconnected logistics and instrumented logistics on dynamic remanufacturing and green manufacturing capability. Finally, dynamic remanufacturing and green manufacturing capability are found to have a positive influence business logistics sustainability.
... Gonzalez et al. [9] designed a warehousing model that provides RFID data compression and path dependent aggregates. Cabenes et al. [4] used an unsupervised learning approach for mining RFID data, which allows the discovery of a topological space from a set of behavioral observations. Because RFID data is inherently dirty, many solutions have been proposed to clean the RFID data. ...
Radio Frequency Identification (RFID) has evolved as a primary object tracking technology over the years. A Number of real world applications such as airport passenger baggage tracking have adapted RFID as a main technological tool for tracking and monitoring. However, the data generated by the RFID tracking contains errors. Therefore, it is important to remove such errors before data is used for any business processing. The primary focus of this paper is object bouncing problem, which happens when the object with attached RFID tag is detected by two or more RFID readers simultaneously or within a short period of time. Due to the bouncing, object appears to go back and forth between several locations in very short time, which is not realistically possible. To cater bouncing problem we exploit the reachability time constraints implied by the deployed readers in an indoor space. We evaluate the proposed work using the synthetically generated RFID data. The results shows that the approach is effective and efficient.
... • The concepts and methods used for the analysis of behavior in electronic games and virtual worlds [49] [71] [72] can be used in the analysis of RFID data, and vice versa. • The methods used for analyzing animal societies based on RFID data [73] can be adopted to analyzing the movement of entities in schedule-based systems in general. • Data from RFID (and other types of sensors) have been used in some literature [4], [74], [75] to (optimally) allocate the RFID readers. ...
A schedule-based system is a system that operates on or contains within a schedule of events and breaks at particular time intervals. Entities within the system show presence or absence in these events by entering or exiting the locations of the events. Given radio frequency identification (RFID) data from a schedule-based system, what can we learn about the system (the events and entities) through data mining? Which data mining methods can be applied so that one can obtain rich actionable insights regarding the system and the domain? The research goal of this paper is to answer these posed research questions, through the development of a framework that systematically produces actionable insights for a given schedule-based system. We show that through integrating appropriate data mining methodologies as a unified framework, one can obtain many insights from even a very simple RFID dataset, which contains only very few fields. The developed framework is general, and is applicable to any schedule-based system, as long as it operates under certain basic assumptions. The types of insights are also general, and are formulated in this paper in the most abstract way. The applicability of the developed framework is illustrated through a case study, where real world data from a schedule-based system is analyzed using the introduced framework. Insights obtained include the profiling of entities and events, the interactions between entity and events, and the relations between events.
... Gonzalez et al. [10] designed a warehousing model that provides RFID data compression and path dependent aggregates. Cabenes et al. [3] used an unsupervised learning approach for mining RFID data, which allows the discovery of a topological space from a set of behavioral observations. Because RFID data is inherently dirty, many solutions have been proposed to clean the RFID data. ...
RFID is widely used for object tracking in indoor environments, e.g., airport baggage tracking. Analyzing RFID data offers insight into the underlying tracking systems as well as the associated business processes. However, the inherent uncertainty in RFID data, including noise (cross readings) and incompleteness (missing readings), pose challenges to high-level RFID data querying and analysis. In this paper, we address these challenges by proposing a learning-based data cleansing approach that, unlike existing approaches, requires no detailed prior knowledge about the spatio-temporal properties of the indoor space and the RFID reader deployment. Requiring only minimal information about RFID deployment, the approach learns relevant knowledge from raw RFID data and uses it to cleanse the data. In particular, we model raw RFID readings as time series that are sparse because the indoor space is only partly covered by a limited number of RFID readers.
We propose the Indoor RFID Multi-variate Hidden Markov Model (IR-MHMM) to capture the uncertainties of indoor RFID data as well as the correlation of moving object locations and object RFID readings. We propose three state space design methods for IR-MHMM that enable the learning of parameters while contending with raw RFID data time series. We solely use raw uncleansed RFID data for the learning of model parameters, requiring no special labeled data or ground truth. The resulting IR-MHMM based RFID data cleansing approach is able to recover missing readings and reduce cross readings with high effectiveness and efficiency, as demonstrated by extensive experimental studies with both synthetic and real data. Given enough indoor RFID data for learning, the proposed approach achieves a data cleansing accuracy comparable to or even better than state-of-the-art techniques requiring very detailed prior knowledge, making our solution superior in terms of both effectiveness and employability.
... The practicability and the effectiveness of the design have been confirmed by empirical study using real RFID systems and datasets. As well, Cabanes et al. (2010) have constructed an autonomous system based on RFID to track the spatio-temporal activity of individuals, a tool not presently existing. In addition tools for automatic data mining have also been created. ...
A fundamental problem with huge potential advantages for object tracking, product procurement processes and customer movement is the storage and extraction of information from RFID datasets. In this paper, we have designed an efficient technique for tracking the customers' walking path sequences using RFID equipped data. The frequent walking path sequences of the customers' movement have been extracted by exposing the most visited areas and walks across the warehouse and the typical products selected along the way. We make use of synthetic RFID datasets to experiment the proposed technique. From the analysis, we showed that the run time and memory usage is outperformed likely by 50% than the previous method. The applications such as analysing the sequential behaviour in telecommunication, market basket analysis, medical data analysis and electronic government used the sequential pattern mining methods.
Celestial cues, such as the sun or patterns of polarized sky light, appear to have no detectable effect in the precise homing orientation offoragers of Paltothyreus tarsatus. Field and laboratory experiments reveal that canopy patterns are a major influence in the home range orientation of this ponerine ant, a common species in African forests. Canopy orientation appears to be well suited to the restrictive lighting conditions of tropical forests.
Celestial cues, such as the sun or patterns of polarized sky light,
appear to have no detectable effect in the precise homing orientation of
foragers of Paltothyreus tarsatus. Field and laboratory experiments
reveal that canopy patterns are a major influence in the home range
orientation of this ponerine ant, a common species in African forests.
Canopy orientation appears to be well suited to the restrictive lighting
conditions of tropical forests.
1. The African stink ant (Paltothyreus tarsatus) is a scavenger and termite hunter. Although workers appear to forage individually for the most part, they can employ a chemical recruitment system when retrieving large prey items or preying on termites. Field and laboratory experiments demonstrated that successful foragers recruit nestmates by laying chemical trails with secretions from intersegmental sternal glands located between the 6th and 7th, and 5th and 6th abdominal sternites respectively. The trails direct the recruits to the food source, but additional stimuli, presumably emanating from freshly caught prey brought into the nest by the recruiting ant or alarm pheromones originating from the sting glands, appear to be important in inducing the nestmates to leave the nest and follow the trail.
2. P. tarsatus workers employ a very different recruitment system during nest relocation. Recruiting ants lead straying nestmates by the tandem running technique to the target area. Although the basic pattern of tandem running recruitment is very similar to that of other ponerine species previously investigated, the communicative bond between the two individuals in a Paltothyreus tandem-running pair appears to be less rigid, and the leader ant repeats its typical “invitation behavior” in irregular intervals until the pair reaches the target area. The Paltothyreus follower ant seems to respond to chemical stimuli emanating from the leader ant much in the same way as described in several other tandem running ponerine species. Experimental evidence suggests that also in Paltothyreus the tandem running pheromone originates from the pygidial gland of the leader ant.
The Self-Organising Map (SOM) algorithm was introduced by the author in 1981. Its theory and many applications form one of the major approaches to the contemporary artificial neural networks field, and new technologies have already been based on it. The most important practical applications are in exploratory data analysis, pattern recognition, speech analysis, robotics, industrial and medical diagnostics, instrumentation, and control, and literally hundreds of other tasks. In this monograph the mathematical preliminaries, background, basic ideas, and implications are expounded in a manner which is accessible without prior expert knowledge.
The problem of forming perfectly topology preserving maps of feature manifolds is studied. First, through introducing “masked Voronoi polyhedra” as a geometrical construct for determining neighborhood on manifolds, a rigorous definition of the term “topology preserving feature map” is given. Starting from this definition, it is shown that a network G of neural units i, i = 1, …, N has to have a lateral connectivity structure A, A
ij ∈ {0, 1}, i, j = 1,…, N which corresponds to the “induced Delaunay triangulation” of the synaptic weight vectors wi ∈ ℜDin order to form a perfectly topology preserving map of a given manifold M ⊆ ℜD of features v ∈ M. The lateral connections determine the neighborhood relations between the units in the network, which have to match the neighborhood relations of the features on the manifold. If all the weight vectors wi are distributed over the given feature manifold M, and if this distribution resolves the shape of M, it can be shown that Hebbian learning with competition leads to lateral connections i —
j (Aij = 1) that correspond to the edges of the “induced Delaunay triangulation” and, hence, leads to a network structure that forms a perfectly topology preserving map of M, independent of M’s topology. This yields a means for constructing perfectly topology preserving maps of arbitrarily structured feature manifolds.
