Ambient Intelligence Applications Research Articles

Ambient intelligent framework for modelling critical medical events based on context awareness

With the rapid pace of communication technology, the modern communication system still encounters challenges in meeting the dynamic requirements of users. Facilitating emergency services for patients without a caretaker side by is quite challenging. This work contributes a solution towards state-of-the-art research problems by introducing a novel architecture using collaboration, coordination and user activity detection using contextual information. A prototype is built and experiment is carried out to emphasize the importance of real-time activity-based context awareness in ambient intelligence (AmI) applications. The primary contributions of this work are introduction of novel architecture and usage of both static and dynamic activity-based contextual parameters. The secondary contribution of this model is to integrate ambient intelligence with context awareness to offer higher accuracy in determining the critical condition of a patient. Initially, analytical models are built using the context-based attributes that consider both clinical and non-clinical entities based on the minimal and essential vital information of patient. This paper further discusses the experimental model, which is highly cost-efficient both from an operational and usage viewpoint. Different assessment environments have been used for assessing the performance of the model.

User gait biometrics in smart ambient applications through wearable accelerometer signals: an analysis of the influence of training setup on recognition accuracy

Gait recognition can exploit the signals from wearables, e.g., the accelerometers embedded in smart devices. At present, this kind of recognition mostly underlies subject verification: the incoming probe is compared only with the templates in the system gallery that belong to the claimed identity. For instance, several proposals tackle the continuous recognition of the device owner to detect possible theft or loss. In this case, assuming a short time between the gallery template acquisition and the probe is reasonable. This work rather investigates the viability of a wider range of applications including identification (comparison with a whole system gallery) in the medium-long term. The first contribution is a procedure for extraction and two-phase selection of the most relevant aggregate features from a gait signal. A model is trained for each identity using Logistic Regression. The second contribution is the experiments investigating the effect of the variability of the gait pattern in time. In particular, the recognition performance is influenced by the benchmark partition into training and testing sets when more acquisition sessions are available, like in the exploited ZJU-gaitacc dataset. When close-in-time acquisition data is only available, the results seem to suggest re-identification (short time among captures) as the most promising application for this kind of recognition. The exclusive use of different dataset sessions for training and testing can rather better highlight the dramatic effect of trait variability on the measured performance. This suggests acquiring enrollment data in more sessions when the intended use is in medium-long term applications of smart ambient intelligence.

Reducing the Power Consumption of Edge Devices Supporting Ambient Intelligence Applications

Having as a main objective the exploration of power efficiency of microcontrollers running machine learning models, this manuscript contrasts the performance of two types of state-of-the-art microcontrollers, namely ESP32 with an LX6 core and ESP32-S3 with an LX7 core, focusing on the impact of process acceleration technologies like cache memory and vectoring. The research employs experimental methods, where identical machine learning models are run on both microcontrollers under varying conditions, with particular attention to cache optimization and vector instruction utilization. Results indicate a notable difference in power efficiency between the two microcontrollers, directly linked to their respective process acceleration capabilities. The study concludes that while both microcontrollers show efficacy in running machine learning models, ESP32-S3 with an LX7 core demonstrates superior power efficiency, attributable to its advanced vector instruction set and optimized cache memory usage. These findings provide valuable insights for the design of power-efficient embedded systems supporting machine learning for a variety of applications, including IoT and wearable devices, ambient intelligence, and edge computing and pave the way for future research in optimizing machine learning models for low-power, embedded environments.

Smart Waiting Room: A Systematic Literature Review and a Proposal

In the past decade, Internet of Things (IoT) technologies have become more and more pervasive, allowing the development of Ambient Intelligence and Context Awareness applications. While the smart home is the chosen scenario for such technologies, a variety of environments could potentially benefit from the synergies between IoT and digital applications. Among them, the clinical waiting rooms is an environment facing several challenges, particularly after the COVID-19 pandemic. Clinical waiting rooms are crowded places associated with stress and anxiety, often linked to patients’ idling time. Nonetheless, the rise of IoT-enabled telehealth has focused attention on the possibility of changing the functions of clinical waiting rooms. In this work, we conducted a systematic literature review to identify the existing solutions for “smart waiting rooms”. The review process started with 278 works, and it identified 16 papers relevant to the topic of smart clinical waiting rooms. Moreover, the results of this review underlined that waiting rooms are a neglected research area that could take advantage of IoT and Artificial Intelligence (AI) technologies to enhance patients’ experience and support the diagnostic process. Leveraging the research directions identified in the review process, this work proposes a “Smart Waiting Room” that exploits virtual reality (VR), AI, and IoT technologies to support the diagnostic process (via a cognitive assessment) and the personalization of the patient’s context—taking into account the features of the physical environment. The prototypical smart waiting room constitutes an example of the potentialities of novel technologies applied to healthcare and can contribute to shaping the future of clinical waiting rooms.

Human Behavior Recognition via Hierarchical Patches Descriptor and Approximate Locality-Constrained Linear Coding.

Human behavior recognition technology is widely adopted in intelligent surveillance, human-machine interaction, video retrieval, and ambient intelligence applications. To achieve efficient and accurate human behavior recognition, a unique approach based on the hierarchical patches descriptor (HPD) and approximate locality-constrained linear coding (ALLC) algorithm is proposed. The HPD is a detailed local feature description, and ALLC is a fast coding method, which makes it more computationally efficient than some competitive feature-coding methods. Firstly, energy image species were calculated to describe human behavior in a global manner. Secondly, an HPD was constructed to describe human behaviors in detail through the spatial pyramid matching method. Finally, ALLC was employed to encode the patches of each level, and a feature coding with good structural characteristics and local sparsity smoothness was obtained for recognition. The recognition experimental results on both Weizmann and DHA datasets demonstrated that the accuracy of five energy image species combined with HPD and ALLC was relatively high, scoring 100% in motion history image (MHI), 98.77% in motion energy image (MEI), 93.28% in average motion energy image (AMEI), 94.68% in enhanced motion energy image (EMEI), and 95.62% in motion entropy image (MEnI).

Toward Ambient Intelligence: Federated Edge Learning With Task-Oriented Sensing, Computation, and Communication Integration

With the breakthroughs in deep learning and contactless sensors, the recent years have witnessed a rise of ambient intelligence applications and services, spanning from healthcare delivery to intelligent home. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Federated edge learning</i> (FEEL), as a privacy-enhancing paradigm of collaborative learning at the network edge, is expected to be the core engine to achieve ambient intelligence. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sensing, computation, and communication</i> (SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> ) are highly coupled processes in FEEL and need to be jointly designed in a task-oriented manner to achieve the best FEEL performance under stringent resource constraints at edge devices. However, this remains an open problem as there is a lack of theoretical understanding on how the SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resources jointly affect the FEEL performance. In this paper, we address the problem of joint SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resource allocation for FEEL via a concrete case study of human motion recognition based on wireless sensing in ambient intelligence. First, by analyzing the wireless sensing process in human motion recognition, we find that there exists a thresholding value for the sensing transmit power, exceeding which yields sensing data samples with approximately the same satisfactory quality. Then, the joint SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resource allocation problem is cast to maximize the convergence speed of FEEL, under the constraints on training time, energy supply, and sensing quality of each edge device. Solving this problem entails solving two subproblems in order: the first one reduces to determine the joint sensing and communication resource allocation that maximizes the total number of samples that can be sensed during the entire training process; the second one concerns the partition of the attained total number of sensed samples over all the communication rounds to determine the batch size at each round for convergence speed maximization. The first subproblem on joint sensing and communication resource allocation is converted to a single-variable optimization problem by exploiting the derived relation between different control variables (resources), which thus allows an efficient solution via one-dimensional grid search. For the second subproblem, it is found that the number of samples to be sensed (or batch size) at each round is a decreasing function of the loss function value attained at the round. Based on this relationship, the approximate optimal batch size at each communication round is derived in closed-form as a function of the round index. Finally, extensive simulation results are provided to validate the superiority of the proposed joint SC <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{2}$</tex-math></inline-formula> resource allocation scheme over baseline schemes in terms of FEEL performance.

A comprehensive survey on age of information in massive IoT networks

Ambient intelligence (AmI) represents the future vision of intelligent computing that can bring intelligence to our daily life through various domains. In such applications, AmI is often subject to the freshness of information collected, which is commonly quantified by a relatively newer metric called age of information (AoI). In the data aggregation and analytics for Internet-of-Things (IoT) AmI, AoI should be well managed, because information update should be as timely as possible to achieve optimal performances. AoI has been studied in various applications using different queuing policies, scheduling algorithms, and multiple access schemes, in which each component of communication and information systems are designed and analyzed to improve the AoI. This paper provides a comprehensive overview of literature on the AoI and its variants in large-scale networks. AoI in IoT systems depends on the arrival rate at the source nodes, queuing policy adopted at the nodes, the scheduling of nodes for information transmission and the access scheme adopted by the nodes. To better design and operate the AmI applications that require the freshness of information, we discuss the impacts of the queuing policy, stochastic modeling, scheduling, and multiple access schemes. In particular, non-orthogonal multiple access (NOMA), which is regarded as one of the key technologies in beyond 5G and 6G, and it hybrid version combined with the conventional orthogonal multiple access (OMA) are discussed in the context of AoI. In addition, we identify promising research opportunities in potential age-sensitive applications. Thus, compared to the existing surveys on AoI, this paper provide more practical and up-to-date design guidelines for the applications with the information freshness requirements.

Multi-Agent Interaction to Assist Visually-Impaired and Elderly People.

A voice-controlled smart home system based on conversational agents can address the specific needs of older people, proactively providing support, compensating for cognitive decline, and coping with solitude, among other features. In particular, Multi-Agent Systems (MAS) platforms provide considerable support for complex adaptive systems that are naturally distributed and situated in dynamic environments, such as Ambient intelligence (AmI) applications. Such autonomous intelligent agents are capable of independent reasoning and joint analysis of complex situations to support high-level interaction with humans, besides providing typical characteristics of MAS, such as cooperation and coordinated action. In this context, we developed an approach using a MAS previously evaluated for visually impaired users, where most of the system’s functionalities are also helpful for the elderly. Our methodology is based on the four steps of the interactive design process. As a result, we determined that our approach has elements that allow for natural interaction with users, and we identified and discussed improvements and new features for future work. We believe that our findings can point to directions for building AmI systems that are capable of more natural interaction with users.

Human gaze-aware attentive object detection for ambient intelligence

Understanding human behavior and the surrounding environment is essential for realizing ambient intelligence (AmI), for which eye gaze and object information are reliable cues. In this study, the authors propose a novel human gaze-aware attentive object detection framework as an elemental technology for AmI. The proposed framework detects users’ attentive objects and shows more precise and robust performance against object-scale variations. A novel Adaptive-3D-Region-of-Interest (Ada-3D-RoI) scheme is designed as a front-end module, and scalable detection network structures are proposed to maximize cost-efficiency. The experiments show that the detection rate is improved up to 97.6% on small objects (14.1% on average), and it is selectively tunable with a tradeoff between accuracy and computational complexity. In addition, the qualitative results demonstrate that the proposed framework detects a user’s single object-of-interest only, even when the target object is occluded or extremely small. Complementary matters for follow-up study are presented as suggestions to extend the results of the proposed framework to further practical AmI applications. This study will help develop advanced AmI applications that demand a higher-level understanding of scene context and human behavior such as human–robot symbiosis, remote-/autonomous control, and augmented/mixed reality.

A One-Dimensional Non-Intrusive and Privacy-Preserving Identification System for Households

In many ambient-intelligence applications, including intelligent homes and cities, awareness of an inhabitant’s presence and identity is of great importance. Such an identification system should be non-intrusive and therefore seamless for the user, especially if our goal is ubiquitous and pervasive surveillance. However, due to privacy concerns and regulatory restrictions, such a system should also strive to preserve the user’s privacy as much as possible. In this paper, a novel identification system is presented based on a network of laser sensors, each attached on top of the room entry. Its sensor modality, a one-dimensional depth sensor, was chosen with privacy in mind. Each sensor is mounted on the top of a doorway, facing towards the entrance, at an angle. This position allows acquiring the user’s body shape while the user is crossing the doorway, and the classification is performed by classical machine learning methods. The system is non-intrusive, non-intrusive and preserves privacy—it omits specific user-sensitive information such as activity, facial expression or clothing. No video or audio data are required. The feasibility of such a system was tested on a nearly 4000-person, publicly available database of anthropometric measurements to analyze the relationships among accuracy, measured data and number of residents, while the evaluation of the system was conducted in a real-world scenario on 18 subjects. The evaluation was performed on a closed dataset with a 10-fold cross validation and showed 98.4% accuracy for all subjects. The accuracy for groups of five subjects averaged 99.1%. These results indicate that a network of one-dimensional depth sensors is suitable for the identification task with purposes such as surveillance and intelligent ambience.

Breaking the Limits of Transportation Mode Detection: Applying Deep Learning Approach With Knowledge-Based Features

Activity recognition and transportation mode detection are the key research areas for context-aware systems. In smart environments such as cities, buildings, transportation systems etc., ambient intelligence applications watch on human activities in order to increase the quality of transportation, health, traffic and human-oriented services. Literature review shows that existing studies typically deal with recognition of motorized and non-motorized daily activities under the name of human activity recognition and transport mode detection. Only few studies worked on these problems with rich datasets in terms of the number of classes. To the best of our knowledge, for the first time, a study examines nearly the whole motorized/non-motorized transportation modes of people including still, walk, run, climbing upstairs, climbing downstairs, bicycle, motorbike, car, metro, train, high speed rail (HSR), tram and metrobus, excluding ferry and airplane. To outperform existing solutions on such a large dataset, an extended version of the well-known HTC dataset, especially consisting of similar classes, such as train, metro, tram and high speed rail, we propose a combined solution of an Long Short-Term Memory network and Healing algorithm. In our experiments, we first reveal the limits of traditional machine learning algorithms on such number of classes. In addition to that, apart from other studies exploiting deep learning approach, we then examine the potential input types for LSTM network, including raw sensor data, knowledge-based features and features obtained via Auto Encoder. Experimental results show that our proposed idea, feeding knowledge-based features into frames of LSTM network make a remarkable difference and bring out a robust, orientation-independent and generic solution for these well-known problems including activity recognition and transport mode detection. Besides, we examined the hyper-parameters of our deep learning approach and specified the effective parameter set including window size, number of frames, unit size, dropout rate and batch size. Our test results reveal that we could achieve a success rate of 95.5% and outperform the state-of-the art solutions for 12 different transportation modes with the help of our former algorithm, namely Healing, on a totally journey-independent dataset where instances for train, validation and test datasets are selected from different journeys.

A collaborative healthcare framework for shared healthcare plan with ambient intelligence

The fast propagation of the Internet of Things (IoT) devices has driven to the development of collaborative healthcare frameworks to support the next generation healthcare industry for quality medical healthcare. This paper presents a generalized collaborative framework named collaborative shared healthcare plan (CSHCP) for cognitive health and fitness assessment of people using ambient intelligent application and machine learning techniques. CSHCP provides support for daily physical activity recognition, monitoring, assessment and generate a shared healthcare plan based on collaboration among different stakeholders: doctors, patient guardians, as well as close community circles. The proposed framework shows promising outcomes compared to the existing studies. Furthermore, the proposed framework enhances team communication, coordination, long-term plan management of healthcare information to provide a more efficient and reliable shared healthcare plans to people.

Artificial Intelligence-Driven Composition and Security Validation of an Internet of Things Ecosystem

Key challenges in Internet-of-Things (IoT) system design and management include the secure system composition and the calculation of the security and dependability level of the final system. This paper presents an event-based model-checking framework for IoT systems’ design and management, called CompoSecReasoner. It invokes two main functionalities: (i) system composition verification, and (ii) derivation and validation of security, privacy, and dependability (SPD) metrics. To measure the SPD values of a system, we disassemble two well-known types of security metrics—the attack surface methodologies and the medieval castle approach. The first method determines the attackable points of the system, while the second one defines the protection level that is provided by the currently composed system-of-systems. We extend these techniques and apply the Event Calculus method for modelling the dynamic behavior of a system with progress in time. At first, the protection level of the currently composed system is calculated. When composition events occur, the current system status is derived. Thereafter, we can deploy reactive strategies and administrate the system automatically at runtime, implementing a novel setting for Moving Target Defenses. We demonstrate the overall solution on a real ambient intelligence application for managing the embedded devices of two emulated smart buildings.

Smartphone based human activity monitoring and recognition using ML and DL: a comprehensive survey

Human activity monitoring and recognition (HAMR) based on smartphone sensor data is a field that promotes a lot of observation in current era due to its notable desire in various Ambient Intelligent applications such as healthcare, sports, surveillance, and remote health monitoring. In this context, many research works have unveiled incredible results using various smartphone sensors such as accelerometer, gyroscope, magnetometer, digital compass, microphone, GPS and camera. The waveform of sensor motion is quite different in several smartphone placements even for the identical activity. This makes it challenging to apprehend varied completely different activities with high precision. Due to the difference in behavioral habits, gender and age, the movement patterns of various individuals vary greatly, which boosts the problem of dividing boundaries of various activities. In HAMR, the main computational tasks are quantitative analysis of human motion and its automatic classification. These cause the inception of Machine Learning (ML) and Deep Learning (DL) techniques to automatically recognize various human activity signals collected using smartphone sensors. This paper presents a comprehensive survey of smartphone sensor based human activity monitoring and recognition using various ML and DL techniques to address the above mentioned challenges. This study unveils the “research gaps in the field of HAMR, to provide the future research directions in HAMR.

MobileTrust

Vehicular Ad hoc NETworks (VANET) are becoming popular due to the emergence of the Internet of Things and ambient intelligence applications. In such networks, secure resource sharing functionality is accomplished by incorporating trust schemes. Current solutions adopt peer-to-peer technologies that can cover the large operational area. However, these systems fail to capture some inherent properties of VANETs, such as fast and ephemeral interaction, making robust trust evaluation of crowdsourcing challenging. In this article, we propose MobileTrust—a hybrid trust-based system for secure resource sharing in VANETs. The proposal is a breakthrough in centralized trust computing that utilizes cloud and upcoming 5G technologies to provide robust trust establishment with global scalability. The ad hoc communication is energy-efficient and protects the system against threats that are not countered by the current settings. To evaluate its performance and effectiveness, MobileTrust is modelled in the SUMO simulator and tested on the traffic features of the small-size German city of Eichstatt. Similar schemes are implemented in the same platform to provide a fair comparison. Moreover, MobileTrust is deployed on a typical embedded system platform and applied on a real smart car installation for monitoring traffic and road-state parameters of an urban application. The proposed system is developed under the EU-founded THREAT-ARREST project, to provide security, privacy, and trust in an intelligent and energy-aware transportation scenario, bringing closer the vision of sustainable circular economy.

Ethical and Legal Aspects of Ambient Intelligence in Hospitals

Ambient intelligence in hospitals is an emerging form of technology characterized by a constant awareness of activity in designated physical spaces and of the use of that awareness to assist health care workers such as physicians and nurses in delivering quality care. Recently, advances in artificial intelligence (AI) and, in particular, computer vision, the domain of AI focused on machine interpretation of visual data, have propelled broad classes of ambient intelligence applications based on continuous video capture. One important goal is for computer vision-driven ambient intelligence to serve as a constant and fatigue-free observer at the patient bedside, monitoring for deviations from intended bedside practices, such as reliable hand hygiene and central line insertions. While early studies took place in single patient rooms, more recent work has demonstrated ambient intelligence systems that can detect patient mobilization activities across 7 rooms in an ICU ward and detect hand hygiene activity across 2 wards in 2 hospitals. As computer vision–driven ambient intelligence accelerates toward a future when its capabilities will most likely be widely adopted in hospitals, it also raises new ethical and legal questions. Although some of these concerns are familiar from other health surveillance technologies, what is distinct about ambient intelligence is that the technology not only captures video data as many surveillance systems do but does so by targeting the physical spaces where sensitive patient care activities take place, and furthermore interprets the video such that the behaviors of patients, health care workers, and visitors may be constantly analyzed. This Viewpoint focuses on 3 specific concerns: (1) privacy and reidentification risk, (2) consent, and (3) liability.

People Counting by Dense WiFi MIMO Networks: Channel Features and Machine Learning Algorithms.

Subject counting systems are extensively used in ambient intelligence applications, such as smart home, smart building and smart retail scenarios. In this paper, we investigate the problem of transforming an unmodified WiFi radio infrastructure into a flexible sensing system for passive subject counting. We first introduce the multi-dimensional channel features that capture the subject presence. Then, we compare Bayesian and neural network based machine learning tools specialized for subject discrimination and counting. Ensemble classification is used to leverage space-frequency diversity and combine learning tools trained with different channel features. A combination of multiple models is shown to improve the counting accuracy. System design is based on a dense network of WiFi devices equipped with multiple antennas. Experimental validation is conducted in an indoor space featuring up to five moving people. Real-time computing and practical solutions for cloud migration are also considered. The proposed approach for passive counting gives detection results with 99% average accuracy.

RSS-Based Indoor Localization Using Belief Function Theory

Received signal strength (RSS) is a simple and low-cost method of localization in wireless sensor networks (WSNs) and is of significant interest in ambient intelligence technologies. However, RSS-based indoor localization poses important challenges due to the intrinsic characteristics of RSS measurements. This paper proposes a localization approach that accounts for the imperfection of RSS measurements and the reliability of RSS sources to estimate the target node position in an indoor WSN environment. Non-Gaussian probability density functions are used to model RSS deviations more realistically in the context of indoor environments. In addition, the proposed approach uses the Dempster–Shafer theory to represent and combine separate pieces of information (evidence) provided by more or less reliable or conflicting RSS sources (anchor nodes) on the same hypotheses regarding the target node position. Experiments conducted in two different indoor environments demonstrate the effectiveness of the proposed approach in terms of its accuracy, robustness, and computation time and its superiority compared with state-of-the-art methods. Note to Practitioners —This paper was motivated by the problem of indoor localization in the context of ambient intelligence applications. The localization technique proposed in this paper exploits RSS measurements to estimate the target node position. This technology is very attractive to system designers, due to its simplicity and low cost. This paper also suggests a new approach using, on the one hand, the belief function theory to represent and manage the imperfection of RSS measurements and the reliability of the RSS sources, and, on the other hand, a more realistic modeling of the variability of RSS measurements due to interference and attenuation phenomena that strongly affect signal propagation in indoor environments. Experimental results obtained in two different indoor environments (a residential apartment and a laboratory) are provided to demonstrate the effectiveness of the proposed approach and its superiority compared to state-of-the-art localization techniques.

Affordable person detection in omnidirectional cameras using radial integral channel features

Omnidirectional cameras cover more ground than perspective cameras, at the expense of resolution. Their comprehensive field of view makes omnidirectional cameras appealing for security and ambient intelligence applications. Person detection is usually a core part of such applications. Conventional methods fail for omnidirectional images due to different image geometry and formation. In this study, we propose a method for person detection in omnidirectional images, which is based on the integral channel features approach. Features are extracted from various channels, such as LUV and gradient magnitude, and classified using boosted decision trees. Features are pixel sums inside annular sectors (doughnut slice shapes) contained by the detection window. We also propose a novel data structure called radial integral image that allows to calculate sums inside annular sectors efficiently. We have shown with experiments that our method outperforms the previous state of the art and uses significantly less computational resources.

Geomarketing Solution: An Ambient Intelligence Application in Shopping

Nowadays, marketing decision-makers have a large amount and various kinds of data related to their customers. Processing this data through various techniques and analyses and making it meaningful and useful for the enterprises will help them make perfect decisions and strength the relation with the customer through personalized service and promotion plans. In this paper, we present the design framework of a geomarketing solution to be used during the store's visit. The system is based on the interaction between three different components: a) smartphone application, b) beacons; and finally, c) the server application. These components interact in order to detect the location of the customer and generate personalized promotions. Moreover, we will use the concept of social vectors to find similar customers and provide customized marketing messages.