This paper presents a voice-activated health monitoring system implemented using a Raspberry Pi. The prototype consists of two nodes: a medical sensor node with the user and a processing node, which communicates via a radio link. This system relies on speech recognition as the basis of its voice-activated design. It uses Mel-frequency cepstral coefficients for feature extraction and a dynamic time-warping algorithm for keyword recognition and comparing reference patterns. The system offers a stable, secure, and cloud-independent solution, achieving a keyword spotting accuracy of 95%.

Internet of Things (IoT) technology and its incorporation in healthcare have improved their coverage and effectiveness. Now, medical research aims to enhance its industry with the next technological trend. Another paradigm shift started with Large Language Models (LLMs). Notably, its ability to produce intelligent and reliable information through contextual learning has shown the potential to create more responsive patient support systems. Incorporating LLMs trained with the proper medical data alleviates the need for constant medical consultations by providing an effective alternative through their deployment in the IoT network. However, this combination runs into issues with scalability and security due to the vulnerabilities of the IoT network and the high processor demands of the LLM. This work presents an edge and private blockchain-based medical LLM deployment platform to address these concerns and create a secure and scalable patient support system. This work tests the feasibility of these design approaches by measuring their responsiveness compared to other configurations. The results showed the platform’s scalability and security using the edge-based and private blockchain approach.

The Internet of Things (IoT) has enabled many services and applications that benefit the urban landscape. One of these services is urban noise monitoring. Noise pollution is an issue that can disrupt the lifestyle and well-being of the populace. An urban noise monitoring system can help analyze the noise levels around the different areas in the city to isolate and address disruptive locations. However, it is a service that heavily relies on its training data. It must remain secure to keep the monitoring system accurate and reliable. So, we propose a secure urban noise monitoring system using a private blockchain and Federated Learning (FL)-based edge-IoT platform. It combines the immutability of blockchain technology with the privacypreserving capabilities of FL, reinforcing the security of training data within an IoT network. Based on our tests, our proposed platform was able to preserve the security, privacy, and integrity of the urban noise monitoring system.

IoT networks have become widespread in different technological industries due to the development of 6G networks. In this paradigm shift, industries like healthcare and autonomous vehicle research have incorporated Large Language Models (LLMs) into their applications and services. This combination has improved the effectiveness of Internet of Thing (IoT)-driven applications requiring intelligent interactions between humans and machines, bridging these wireless services to real-time intractability. However, as the IoT network grows, scalability and security issues arise. We present a private blockchain-based edge IoT platform to address these concerns in IoT-based LLM services. We evaluated our design's feasibility by testing its responsiveness and analyzing its security contributions. The results show the potential of our platform to improve the scalability of the IoT network through edge computing and reinforce its security through the private blockchain.

Integrating smart technologies in vehicles has brought rise to connected and autonomous vehicles (CAVs), One of the services impacted by this paradigm shift is driving assistance. Most systems use learning-based approaches such as object recognition to improve transportation quality. So, these services require exchanging and sharing data along the CAV network, which raises security issues. Within this work is a federated learning (FL)-based platform as a step towards secure CAV systems. It uses FL to secure client data locally and alleviate pressure on CAV servers and services against targeted attacks. A testbed evaluates the platform's feasibility in preserving the integrity of its implemented classifier while keeping a level of security of its training data. According to experimental results, the FL-based implementation can maintain the integrity of the classifier's accuracy even after introducing its distributive scheme. Also, security evaluations present the benefits of FL reinforcing network security and improving client data privacy. Based on the results, the proposed platform proves its feasibility as an integrity-preserving and secure option for object recognition-based driving assistance services in CAVs.

The usage of social media is increasing daily. Users tend to interact with social media content through a plethora of devices, from laptops and personal computers to smartphones, tablets, and wearables. However, these devices have different technical characteristics that affect the overall user experience. In this work, we introduce SocialNetView, a mobile application to acquire and present the user with information based on their usage of social media and provide recommendations on the available and most efficient network connection. We developed the application for smartphones and smartwatches. In order to examine its performance, we conducted experiments with 30 users on a University campus. We evaluate the efficiency of the proposed approach while user location and historical social media interaction are used for the network selection. According to experimental data, SocialNetView can deliver higher Quality of Experience (QoE) to the user, when it is used for network recommendation.

Healthcare has moved towards integrating wireless technology to create and enable more services for the patients' convenience. Among the new and popular services is the formulation of wearable Internet of Things (IoT)-enabled telemedicine. However, when the number of IoT devices entering the network increases, it creates concerns about the service's ability to keep its data secure and preserve its real-time capabilities. To address these issues, in this work, we propose a fog-based IoT platform incorporating blockchain technology and smart contracts. We evaluated our design's ability to keep the real-time capabilities of wearable IoT-enabled telemedicine services through experimentation. According to the results, the introduced platform can effectively reduce the overall latency of data transactions compared to other standard network configurations. We further evaluated and observed the contributions of our design to the security of the telemedicine service. Through experimentation, we prove the feasibility of the proposed platform in addressing the highlighted issues of wearable IoT-enabled telemedicine services.

The plethora of online applications and mobile communication systems helps in the increase of the everyday usage of social networks. More people tend to use social media and join social networks. At the same time, several people suffer from mental stress while they either receive or create social media content. In this work, we examine the feasibility of detecting stress related to social media content, with the use of wearable devices. We use Electrodermal Activity (EDA) signals collected from wrist-based devices and we examine any correlation between them and the social media content. We conducted experiments in different environments with self-reported data from the users. According to preliminary results, the relationship between EDA and stress levels related to social media content can be identified.

In recent years, healthcare systems have included the Internet of Things (IoT) technology in their services, such as in remote patient monitoring systems. Wearable IoT devices can provide information regarding the patient's health that are accurate and time-sensitive. However, vulnerabilities are evident as more IoT devices connect to the network. For healthcare services, the security of patient data is an issue. At the same time, with real-time data transmissions, the network runs into manageability concerns. In this work, we propose a private blockchain-based Wireless Body Area Network (WBAN) platform to aid wearable IoT devices in healthcare services. We chose this blockchain technology due to its strengths in security. Then, we enable a distributive architecture using WBANs to introduce a decentralized configuration that can ensure privacy among wearable IoT devices within the network. To evaluate the feasibility of the proposed platform in terms of latency and throughput, we conducted experiments with several wearable IoT devices. The results show that integrating a WBAN to create a fog server improves the network performance with an increasing number of IoT devices and packet size. Also, the blockchain showed its ability to address security threats in healthcare services. We evaluate our proposed platform through a performance test and a STRIDE threat model, and we prove its feasibility in improving the security and manageability of wearable IoT devices in healthcare.

What advancements might Next Generation Networks (NGN) unleash that existing ones cannot? NGNs are envisioned to empower the connection between billions of people and zillions of heterogeneous Internet of Things (IoT) devices while consolidating intelligence and autonomy. However, several security-related challenges will be introduced and apparently, the security solutions and architectures used in previous network generations will not be sufficient. The Cloud Security Alliance's (CSA) Software Defined Perimeter (SDP) is a potential candidate to provide the much-needed security framework for next-generation networks. However, the lack of a scalable SDP controller will be a considerable drawback for the wide adoption of the SDP framework. Therefore, this paper focuses on modeling a multi-SDP controller placement problem as a VNF-FGE in a Geo-distributed NFV-based environment as a potential solution to secure next-generation networks. Due to its NP-hard nature, this type of problem can be addressed by extending the NCO approach via Reinforcement Learning (RL) to optimize the reward policy in accordance with the constraints of the problem. The agent developed can learn the placement decisions of the SDP controllers by inference (i.e., policy strategy) through the RL process. The experiment's analysis reveals the RL approach's superiority over the well-known Gecode optimization solver.

Several signals can be collected from wearable devices containing important physiological and psychological information. Understanding various physiological signals is significant for computers to recognize human emotional states. Electrodermal Activity (EDA), originating from the spontaneous activation of sweat glands in the skin, is closely related to mood, arousal, and attention and is the most widely used measurement in the physiological response system for emotional state detection. However, extracting valuable features from EDA signals and making accurate emotional classification predictions has always been challenging. With the continuous development of models with representation learning capabilities, the use of deep learning models to automatically learn physiological signal features and perform classification learning is promising. In order to improve the shortcomings of traditional emotion recognition methods, which require a deep understanding of physiological signals and artificial extraction of relevant features, this paper proposed a Recurrent Neural Network (RNN) -based method for automatic feature extraction from EDA's spectrograms. A Convolutional Neural Network (CNN) is used to learn the extracted features further and output the determined emotional state. The results show that the classification accuracy for arousal and valence has reached 83.4% and 81.2%, respectively, which is promising in extracting features automatically and tackling the emotional state classification problem.

Over the years, the popularity and usage of wearable Internet of Things (IoT) devices in several healthcare services are increased. Among the services that benefit from the usage of such devices is predictive analysis, which can improve early diagnosis in e-health. However, due to the limitations of wearable IoT devices, challenges in data privacy, service integrity, and network structure adaptability arose. To address these concerns, we propose a platform using federated learning and private blockchain technology within a fog-IoT network. These technologies have privacy-preserving features securing data within the network. We utilized the fog-IoT network’s distributive structure to create an adaptive network for wearable IoT devices. We designed a testbed to examine the proposed platform’s ability to preserve the integrity of a classifier. According to experimental results, the introduced implementation can effectively preserve a patient’s privacy and a predictive service’s integrity. We further investigated the contributions of other technologies to the security and adaptability of the IoT network. Overall, we proved the feasibility of our platform in addressing significant security and privacy challenges of wearable IoT devices in predictive healthcare through analysis, simulation, and experimentation.

Stress is an inevitable part of modern life. While stress can negatively impact a person's life and health, positive and under-controlled stress can also enable people to generate creative solutions to problems encountered in their daily lives. Although it is hard to eliminate stress, we can learn to monitor and control its physical and psychological effects. It is essential to provide feasible and immediate solutions for more mental health counselling and support programs to help people relieve stress and improve their mental health. Popular wearable devices, such as smartwatches with several sensing capabilities, including physiological signal monitoring, can alleviate the problem. This work investigates the feasibility of using wrist-based electrodermal activity (EDA) signals collected from wearable devices to predict people's stress status and identify possible factors impacting stress classification accuracy. We use data collected from wrist-worn devices to examine the binary classification discriminating stress from non-stress. For efficient classification, five machine learning-based classifiers were examined. We explore the classification performance on four available EDA databases under different feature selections. According to the results, Support Vector Machine (SVM) outperforms the other machine learning approaches with an accuracy of 92.9 for stress prediction. Additionally, when the subject classification included gender information, the performance analysis showed significant differences between males and females. We further examine a multimodal approach for stress classifications. The results indicate that wearable devices with EDA sensors have a great potential to provide helpful insight for improved mental health monitoring.

Bluetooth Low Energy (BLE) beacons are designed to operate for years on a coin-cell battery. However, the formation of a mesh network, overlaying on the existing Bluetooth Low Energy (BLE) beacons infrastructure, can severely degrade the lifetime of underlying beacons owing to the excessive current drawn by the scanning event. Even though we can sustain the lifetime of the underlying beacon with duty-cycle scanning, such duty-cycle scanning imposes another challenge to the overlay mesh in disseminating the packet. To this end, this paper proposes a novel overlay protocol that: 1) employs duty-cycle scanning to guarantee the lifetime of the underlying beacon, while 2) defining a set of scanning policies to increase the packet dissemination rate through the overlay mesh network. The duty-cycle scanning defines the scanning time slot based on the lowest feasible duty cycle unveiled through a comprehensive analysis of energy consumed by advertising and scanning events. The scanning policies, on the other hand, allow each node to explore all possible time slots before locking their scanning event to a particular time slot that is most likely to hear the incoming packet. Extensive experiments with practical implementation demonstrate the feasibility of our proposed overlay mesh for real-world use cases.

This paper presents a nonlinear location estimation to infer the position of a user holding a smartphone. We consider a large location with$M$number of grid points, each grid point is labeled with a unique fingerprint consisting of the received signal strength (RSS) values measured from$N$number of Bluetooth Low Energy (BLE) beacons. Given the fingerprint observed by the smartphone, the user’s current location can be estimated by finding the top-k similar fingerprints from the list of fingerprints registered in the database. Besides the environmental factors, the dynamicity in holding the smartphone is another source to the variation in fingerprint measurements, yet there are not many studies addressing the fingerprint variability due to dynamic smartphone positions held by human hands during online detection. To this end, we propose a nonlinear location estimation using the kernel method. Specifically, our proposed method comprises of two steps: 1) a beacon selection strategy to select a subset of beacons that is insensitive to the subtle change of holding positions, and 2) a kernel method to compute the similarity between this subset of observed signals and all the fingerprints registered in the database. The experimental results based on large-scale data collected in a complex building indicate a substantial performance gain of our proposed approach in comparison to state-of-the-art methods. The dataset consisting of the signal information collected from the beacons is available online.

In the fast pace of life, emotion recognition systems are essential to help monitor mental health and well-being. The continuous development of the Internet of Things (IoT) and Human-Computer Interaction (HCI) improve the availability and accessibility to devices that can capture the facial expressions of a user, while wearable devices can also capture physiological signals and use them for emotion recognition. Meanwhile, machine learning and deep learning methods can provide emotion prediction models. However, the training of the models relies heavily on massive amounts of labeled data. The accuracy of data labels affects the success of the overall system. Research targeting emotion recognition uses the participants' self-reports as labels. However, participants often fail to give accurate self-reports, thus affecting the accuracy of the analysis. In this study, we examine the performance of the self-reports and external annotations for emotion recognition based on visual and physiological signals. Specifically, we use video data, as well as the Electrodermal Activity (EDA), Electroencephalogram (EEG), and Electrocardiogram (ECG) signals collected from wearable devices. We use two machine learning and three deep learning methods to process the signals and train the classifiers. The results show that the classifiers trained with external annotations offer better emotion recognition accuracy than self-reports. Also, the classifiers trained on facial expression offer better emotion prediction accuracy than the physiological signals, and the Deep Convolutional Network model shows the best results.

This paper presents a human activity recognition (HAR) system with wearable devices. While various approaches have been suggested for HAR, most of them focus on either 1) the inertial sensors to capture the physical movement or 2) subject-dependent evaluations that are less practical to real world cases. To this end, our work integrates sensing in-puts from physiological sensors to compensate the limitation of inertial sensors in capturing the human activities with less physical movements. Physiological sensors can capture physiological responses reflecting human behaviors in executing daily activities. To simulate a realistic application, three different evaluation scenarios are considered, namely All-access, Cross-subject and Cross-activity. Lastly, we propose a Hierarchical Deep Learning (HDL) model, which improves the accuracy and stability of HAR, compared to conventional models. Our proposed HDL with fusion of inertial and physiological sensing inputs achieves 97.16%, 92.23%, 90.18% average accuracy in All-access, Cross-subject, Cross-activity scenarios, which confirms the effectiveness of our approach.

The recent pandemic has brought tremendous changes to everyone’s life, causing stress about losing loved ones, losing jobs, and having changes in sleep or eating habits. This study investigates the feasibility of utilizing Electrodermal Activity (EDA) collected from wearable devices to detect people’s stress. EDA can quantify the changes in sympathetic dynamics by measuring sweat produced by our sweat glands. Currently, the adoption of EDA sensors to commercially off-the-shelf smart-watches is still in the infancy stage, and only a few brands have the EDA sensors implemented into their smartwatch. To facilitate our feasibility study, we need the datasets that contain the EDA signals collected from wearable devices. This paper uses two publicly available datasets containing the EDA signals collected from research-grade wearable devices. We cast the stress detection problem as a binary classification problem and trained the classifiers with three popular machine learning methods: K-Nearest Neighbor, Logistic Regression, and Random Forests. According to experimental results, Random Forests achieves an accuracy of 85.7% to classify stress from non-stress status. The results verified that wearable devices with EDA sensors have the potential to predict stress status.

The number of embedded devices that connect to a wireless network has been growing for the past decade. This interaction creates a network of Internet-of-Things (IoT) devices where data travel continuously. With the increase of devices and the need for the network to extend via fog computing, we have fog-based IoT networks. However, with more endpoints introduced to it, the network becomes open to malicious attackers. This work attempts to protect fog-based IoT networks by creating a platform that secures the endpoints through public-key encryption. The servers are allowed to mask the data packets shared within the network. To be able to track all of the encryption processes, we incorporated the use of permissioned blockchains. This technology completes the security layer by providing an immutable and automated data structure to function as a hyper ledger for the network. Each data transaction incorporates a handshake mechanism with the use of a public-key pair. This design guarantees that only devices that have proper access through the keys can use the network. Hence, management is made convenient and secure. The implementation of this platform is through a wireless server–client architecture to simulate the data transactions between devices. The conducted qualitative tests provide an in-depth feasibility investigation on the network’s levels of security. The results show the validity of the design as a means of fortifying the network against endpoint attacks.

Artificial intelligence (AI) and 5G system have been two hot technical areas that are changing the world. On the deep convergence of computing and communication, networking systems of AI (NSAI) is presenting a paradigm shift, where distributed AI becomes immersive in all elements of the network, i.e., cloud, edge, and terminal devices, which make AI virtually operating as a networking system. On the other hand, by the evolution of the communication systems, a network is becoming a service-specific system interweaved with AI, i.e., the network operates as an AI system, enabling real-time smart services. With the developing technology trends of “AI as a network and network as an AI,” the ecosystem of NSAI can be presenting the next-generation waves of both AI systems and B5G-6G communication networks. In this article, we mainly aim to provide a comprehensive survey on the system architecture, key technologies, application scenarios, challenges, and opportunities of NSAI, which can shed light on the future developments of both telecommunications and AI computing. The contributions of this article also include: 1) providing a unified framework for the deep convergence of computing and communications, where the network and application/service can be jointly optimized as a single integrated system and 2) suggesting the roadmap and open research problems in realizing the online-evolutive integration of cyberspace, physical world, and human society, toward the ubiquitous brain networks (UBNs), which are requiring the joint efforts from both research communities of computing and communication.

With the rise of IoT-based sensor networks, there is an increasing need for proper security mechanisms and efficient management of crucial resources, such as energy. At the same time, as more services are integrated, more sensors are introduced into the network. As a consequence, the architecture that manages these sensors need to be improved. Blockchains can be a solution in terms of data security. To cater to the inexpensive devices used as sensors in most IoT-based sensor networks, usually, permissioned blockchains are used as its base data management structure. However, due to the diverse collection of sensors that can be incorporated into a network, a static database is not enough. A more sustainable and automative system is needed as its service administrator. Therefore, we chose to integrate smart contracts to enable adaptive and dynamic automation. Lastly, to manage the reception of all the incoming data, a proper interface is required. Therefore, we chose to encapsulate the blockchain within a REST API to enable a systematic allocation of network resources. With these technologies, we propose a low-cost platform to address the management issues of current IoT-based sensor networks. We tested our design against a commercial REST API service and standard socket communication to test its feasibility. The testing metrics were latency and throughput. Based on the results, our platform proved to be the most stable and proficient among the configurations. Therefore, our proposed design shows promise as a low-cost, secure, and systematic means of managing IoT-based sensor networks.

The paper is motivated by the importance of the Smart Cities (SC) concept for future management of global urbanization and energy consumption. Multi-agent Reinforcement Learning (RL) is an efficient solution to utilize large amount of sensory data provided by the Internet of Things (IoT) infrastructure of the SCs for city-wide decision making and managing demand response. Conventional ModelFree (MF) and Model-Based (MB) RL algorithms, however, use a fixed reward model to learn the value function rendering their application challenging for ever changing SC environments. Successor Representations (SR)-based techniques are attractive alternatives that address this issue by learning the expected discounted future state occupancy, referred to as the SR, and the immediate reward of each state. SR-based approaches are, however, mainly developed for single agent scenarios and have not yet been extended to multi-agent settings. The paper addresses this gap and proposes the Multi-Agent Adaptive Kalman Filtering-based Successor Representation (MAKF-SR) framework. The proposed framework can adapt quickly to the changes in a multi-agent environment faster than the MF methods and with a lower computational cost compared to MB algorithms. The proposed MAKF-SR is evaluated through a comprehensive set of experiments illustrating superior performance compared to its counterparts.

While many technologies (e.g., RFID, QR code, etc.) have been developed for items identification, they fail to provide continuous monitoring for items in transit. This paper introduces a Bluetooth Low Energy (BLE) beacon-based system, which can be deployed easily with any off-the-shelf smartphone without modification on the existing infrastructures. However, it is an elusive challenge to achieve a fast item identification and counting involving massive items stacked up inside a confined space (e.g., a container), resulting in an ultra-dense beacon network (UDBN). To this end, we propose a novel beaconing solution capable of informing the receiver about their own presence as well as the presence of their neighboring beacons for identification purpose. Specifically, our proposed solution provides a well-designed yet innovative protocol data unit (PDU) which allows the beacon to encapsulate its neighboring information into its own advertising packet. A prototype consisting of 300 beacons is implemented to demonstrate the feasibility of our proposed solution for real-world applications. The extensive experiment confirm the superiority of our proposed solution in delivering a fast item identification and counting in UDBN.

With recent breakthroughs in signal processing, communication and networking systems, we are more and more surrounded by smart connected devices empowered by the Internet of Thing (IoT). Bluetooth Low Energy (BLE) is considered as the main-stream technology to perform identification and localization/tracking in IoT applications. Indoor localization applications within smart cities, typically, start by observing messages transmitted by BLE beacons and then utilization of Received Signal Strength Indicator (RSSI) to provide location estimates. RSSI signals are, however, prone to significant fluctuations. The main challenge is that multipath fading and drastic fluctuations in the indoor environment result in complex non-Gaussian RSSI measurements, necessitating the need to smooth RSSIs for development of BLE-based localization applications. In contrary to existing solutions, where RSSIs are assumed to have normal statistical properties, in this paper, a Gaussian Sum Filter (GSF) approach is designed to more realistically model the non-Gaussian nature of RSSIs. To maintain acceptable computational load, the number of components in the GSF is collapsed into a single Gaussian term with a novel Wasserstein Distance (WD)-Based Gaussian Mixture Reduction (GMR) algorithm. The simulation results based on real collected RSSI signals confirm the success of the proposed WD-based GSF framework compared to its conventional counterparts.

An Internet of Things (IoT) network can have different components such as servers, gateways, and the end devices. An important source of performance constraint in such an IoT network is found in the limitations of its gateway. The capability of a gateway can dictate the effectiveness of a network and its services. The capacity, power consumption, and security of an IoT gateway are revealed as sources of network bottlenecks and service constraints. Blockchain technology can create a decentralized structure that can offload these strains. To unify these nodes as gateways under the same network, we need an effective means of communication. This paper proposes a setup that makes use of the decentralized capabilities of private blockchain technology partnered with the low-powered and secure connection of Bluetooth Low Energy (BLE). This provides a more secure means of wireless communication and prevents the nodes from being concentrated within an area. The architecture was compared against a standard WiFi network (2.4GHz) to prove its feasibility in effectively carrying out its functionality. In an experiment that used 4 gateway nodes, BLE proved to be more feasible than WiFi by yielding a better verification packet rate of 14 per minute compared to its counterpart that measured 4 per minute. Also, it showed to be more efficient in terms of power consumption with an average of 1095.40 mW, while the WiFi setup was measured to be 1191.83 mW. These results show promise in using BLE paired with blockchain technology to solve the capacity, power and security issues in IoT networks.

Health care services have become a high demand due to the rise in medical technology. As a result, related resources are being depleted. Hospitals no longer have any space to accommodate for incoming patients. Remote Patient Monitoring (RPM) is a solution to this issue by creating a convenient and easy to access healthcare service. However, RPM systems are constrained by concerns on patient privacy, response time, and patient-service interaction. Patients emphasize their privacy, which requires health care services to maintain the confidentiality of their patient’s information. Wearable health monitors continuously transmit data. This feature results in high volumes of data transmissions towards the servers. In the current state of wearable devices, there is a lack of giving the patient an integrated means of interacting with the healthcare centre and vice versa. In this paper, we propose an architecture that uses fog computing and Internet of Things (IoT) devices to an already existing RPM system and addresses these challenges. The introduced system enables the health care providers to verify any of their data through a local server before it is reported to the main server. Also, this design incorporates a data filter that controls the outgoing data to maintain patient privacy. Finally, the inclusion of a local server offloads the extra data processing that is required from the server for a better flow of data. Tests in latency were executed to investigate the feasibility of a scalable fog architecture against a standard cloud-device setup. The results show that the proposed fog setup yielded significantly lower latencies under an increasing number of RPM rooms compared to the cloud setup. Results further support the fog and IoT-based architecture as a potential option for a scalable RPM.

The quality and safety of food is a great concern to the whole society because it is the most basic guarantee for human health and social development and stability. Ensuring food quality and safety is a complex process, and all stages of food processing must be considered, from cultivating, harvesting and storage to preparation and consumption. Grading is one of the essential processes to control food quality. This paper proposed a two-layer image processing system based on machine learning for banana grading. Support Vector Machine is the first layer to classify bananas based on an extracted feature vector that is composed of colour and texture features and YOLOv3 follows up for further locating the defected area on the peel and determining if the inputs belong to mid-ripened or well-ripened class. The performance of the first layer achieved an accuracy of 98.5% and the accuracy of the second layer is 85.7%. The overall accuracy is 96.4%.

The interconnectedness of all things is continuously expanding which has allowed every individual to increase their level of interaction with their surroundings. Internet of Things (IoT) devices are used in a plethora of context-aware application, such as proximity-based services (PBSs), and location-based services (LBSs). For these systems to perform, it is essential to have reliable hardware and predict a user's position in the area with high accuracy in order to differentiate between individuals in a small area. A variety of wireless solutions that utilize received signal strength indicators (RSSIs) have been proposed to provide PBS and LBS for indoor environments, though each solution presents its own drawbacks. In this article, Bluetooth low energy (BLE) beacons are examined in terms of their accuracy in proximity estimation. Specifically, a mobile application is developed along with three Bayesian filtering techniques to improve the BLE beacon proximity estimation accuracy. This includes a Kalman filter, a particle filter, and a nonparametric information (NI) filter. Since the RSSI is heavily influenced by the environment, experiments were conducted to examine the performance of beacons from three popular vendors in two different environments. The error is compared in terms of mean absolute error (MAE) and root mean squared error (RMSE). According to the experimental results, Bayesian filters can improve proximity estimation accuracy up to 30% in comparison with traditional filtering, when the beacon and the receiver are within 3 m.

In recent years, the Internet of Things (IoT) has grown to include the tracking of devices through the use of indoor positioning systems (IPSs) and location-based services (LBSs). When designing an IPS, a popular approach involves using wireless networks to calculate the approximate location of the target from devices with predetermined positions. In many smart building applications, LBS is necessary for efficient workspaces to be developed. In this article, we examine two memoryless positioning techniques,K-nearest neighbor (KNN) and Naive Bayes, and compare them with simple trilateration, in terms of accuracy, precision, and complexity. We present a comprehensive analysis between the techniques through the use of three popular IoT wireless technologies: 1) ZigBee; 2) Bluetooth low energy (BLE); and 3) WiFi (2.4-GHz band), along with three experimental scenarios to verify results across multiple environments. According to experimental results, KNN is the most accurate localization technique as well as the most precise. The received signal strength indicator data set of all the experiments is available online.

As technology gets cheaper and wireless networks grow, more efforts have been put into developing smart buildings and homes. A key characteristic of these smart buildings is to provide indoor navigation and localization services to its occupants. As this demand increases, simple, scalable solutions are sought after. Current localization technologies, such as GPS, do not work in indoor environments, nor does it provide the level of accuracy required for an effective indoor navigation solution. This paper explores the feasibility of a wireless indoor location system based on Bluetooth Low Energy beacons (BLE). Five popular BLE beacon devices are compared in terms of energy consumption and proximity accuracy. Experiments are conducted in three different rooms and three filtering techniques are also examined, to improve the performance of each beacon. According to experimental results, a proper selection of the filtering technique can help to improve their proximity estimation.

Recent advancements in signal processing and communication systems have resulted in evolution of an intriguing concept referred to as Internet of Things (IoT). By embracing the IoT evolution, there has been a surge of recent interest in localization/tracking within indoor environments based on Bluetooth Low Energy (BLE) technology. The basic motive behind BLE-enabled IoT applications is to provide advanced residential and enterprise solutions in an energy efficient and reliable fashion. Although recently different state estimation (SE) methodologies, ranging from Kalman filters, Particle filters, to multiple-modal solutions, have been utilized for BLE-based indoor localization, there is a need for ever more accurate and real-time algorithms. The main challenge here is that multipath fading and drastic fluctuations in the indoor environment result in complex non-linear, non-Gaussian estimation problems. The paper focuses on an alternative solution to the existing filtering techniques and introduces/discusses incorporation of the Belief Condensation Filter (BCF) for localization via BLE-enabled beacons. The BCF is a member of the universal approximation family of densities with performance bound achieving accuracy and efficiency in sequential SE and Bayesian tracking. It is a resilient filter in harsh environments where nonlinearities and non-Gaussian noise profiles persist, as seen in such applications as Indoor Localization.

Many areas like smart buildings, crowd flow, action recognition, and assisted living rely on occupancy information. Although the use of smart cameras can alleviate the problem and provide accurate occupancy information, at the same time it can be cost prohibitive, invasive and not easy to scale or generalize to different environments. An alternative solution should bring similar accuracy while minimizing the previous problems. This work presents a candidate wireless sensor network for indirect occupancy measurements in a smart building. A prototype was built, that consists of CO2, temperature and humidity sensors. The prototype was placed in a complex indoor environment to collect data for a week. Then, the data was analyzed to examine potential correlation between sensor data and occupancy information. According to experimental results, CO2can be used for indirect occupancy measurements.

In accommodation of the expanding amount of WiFi-enabled products and services, the availability of Wi-Fi connectivity is rising. As available networks increase in quantity and overlapping coverage, a user's selection for connection becomes increasingly influential in the quality of their experience. In order for users to make effective decisions for their needs, they must be provided with information on these networks. In this work, we present NetView, a mobile application to acquire and present users with information based on their own usage context to make these informed decisions. Deployment of NetView in a university campus setting is used to demonstrate how user location and historical readings may be used with current network strength readings to shape policies for network selection.

Wellness is an affective state that plays a significant role in our everyday lives, influencing our behaviour, social communication and performance, and even more. Although technological advancements are used to help our society to become more health conscious, wellness and mental health is still lacking in adequate resources, particularly among the student population. In this study, we collected data from 21 participants using mobile sensors and phones. The mobile sensors collected data regarding the temperature, humidity and luminosity of the environment, while the phone provide location information and data processing. The experimental data were analyzed through Perceived Stress Scale (PSS), Pittsburgh Sleep Quality Index (PSQI) and General Well-Being Scale (GWBS). We assess the impact of the location on PSS and PSQI, and the impact of environmental conditions on GWBS. According to experimental results and correlation analysis among the data, luminosity has stronger impact on the wellness than the other two environmental parameters.

In a smart home, the home status, as well as the human activities, can be observed through a number of sensors. A wireless network can transfer the data to an information system and the commands from the information system to the sensors and actuators. In small areas such as smart homes, four types of noise may form in communication system. In this work, we explore how the noise can be resolved by integrating the Wireless Sensor Network (WSN) management with the smart home information system. The result is to smoothen the wireless communication. Additionally, the sensors and actuators are applied efficiently, since the information system places them automatically in the right place at right time. The proposed Opportunistic Mesh (OPM) wireless method avoids signal interference/ collision in small rooms, in order to minimize interference with home regular wireless services, such as WiFi. A model to vector the mobile agent in the smart home is proposed and a mobile agent is used to automatically approach the target positions.

This paper introduces research that addresses the subjective assessment of Quality of Experience (QoE) during the entire life cycle of a video session. We define a video session life cycle as the time from when a user attempts to initiate playback, until such time that the video ends either from normal video conclusion or through a network-induced failure. We provide a detailed description of our assessment methodology designed to discern whether a user's QoE would be impacted by the presence of failures. To accomphsh this, we carefully select various test conditions to take into consideration the rating scale used, the types of impairments and failures seen by the user, and whether impaired videos are seen together with failed videos in multi-video sessions. The selection and creation of source video sequences are also discussed, as well as the use of between-subjects and within-subjects approaches for running our experiments in a controlled laboratory setting. Statistical analysis was carried out to interpret our experimental results. We compared the results of the between-subjects measures and the results of the within-subjects measures, and concluded that the introduction of a scale with an extended lower bound enabled subjects to more clearly express their dissatisfaction of videos with failures when compared to the traditional ITU 5-point rating scale. In addition, we observed that videos that were simply impaired but concluded normally did not have a statistically significant difference when an extended scale was used.

Quality of Experience (QoE) is a crucial guiding factor for network management of an end-to-end service session. The network provider can control the resources allocated to sessions and in doing so, influence the Technical Quality (TQ), which covers the technical aspects of signal quality during the session. On the other hand, the network provider has no control over the Content Quality (CQ), which pertains to the user's level of interest in a particular video. Together TQ and CQ influence the Overall eXperience (OX) in a session. In this paper, we present results from a user subjective study in which the impact of TQ and CQ on OX was investigated for Over-The-Top (OTT) video sessions from the perspective of a network provider. This perspective places a focus on those elements of QoE that can be controlled by the provider. Various studies have shown that very high interest in a content can strongly influence QoE independent of other factors, so our study uses videos that are neutral with respect to content. We assess the TQ, CQ and OX for video sessions that contain Integrity impairments (in the form of image freezing) and failures in terms of session Accessibility and Retainability. Our findings indicate that TQ and CQ have a strong impact on OX in the presence of impairments, but no failures. On the other hand, TQ is the main determinant of OX when failures are present.

In this demonstration we use a prototype of a Wireless Sensor Node along with a Software Defined Infrastructure to monitor the quality of the air in different classrooms at a University. Specifically, a number of wireless nodes are deployed in different classrooms. Each node has a number of sensors to monitor the air quality in the room. A number of relay nodes forward the data to a vCPE, which delivers the data to a Smart Edge. In the vCPE and the Smart Edge, a monitoring and analytic system, called MonArch, is used for collection, storage and analytic purposes of the monitoring data.

Customer satisfaction is an important factor governing adoption and retention of multimedia products and services, such as Over-The-Top(OTT) video transmission. Quality of Experience involves user-centric evaluation of various services. However, users differ in terms of their ratings of service quality. Some rating differences are due to unreliability (outlier users who are not motivated, or are not sensitive to differences in quality), but others are systematic differences in rating that may reflect different perspectives on quality. In this paper, we explore the use of outlier analysis and clustering as tools for interpreting QoE data. We report on experimental results demonstrating the use of outlier analysis and clustering. In interpreting the clusters, we examine users' opinions on different types of video disruption, and their ability to distinguish the different levels of impairments/failures.

In this paper, we study the relationships between Quality of Service (QoS) and Quality of Experience (QoE) in a session-based Over-The-Top (OTT) video service. A number of Performance Metrics (PMs) with and without the existence of failures during a video are examined. As QoE factors, Technical Quality (TQ) and Acceptability are used. We analyze the correlation between QoS performance metrics and QoE factors, and find new PMs should be employed because failures are included in QoE evaluation. We also summarize the relationships between QoS metrics and QoE factors through machine learning approaches. Using decision tree, we have a general idea about the relationships between PMs and QoE factors. We also understand the impact caused by failures and the value of rating scales.

The increasing availability of low-cost hardware along with the rapid growth of wireless devices has enabled the development of Wireless Multimedia Sensor Networks (WMSNs). Multimedia content such as video and audio streaming is transmitted over a WMSN which can easily be deployed with low cost. However, enabling real-time data applications in those networks demands not only Quality of Service (QoS) awareness, but also efficient energy management. Sensor network devices have limited energy resources. The limited energy poses significant threats on the QoS of WMSNs. In this paper, to improve the efficiency of QoS-aware routing, we examine an angle-based QoS and energy-aware dynamic routing scheme designed for WMSNs. The proposed approach uses the inclination angle and the transmission distance between nodes to optimize the selection of the forwarding candidate set and extend network lifetime. Simulation results indicate that considerable lifetime values can be achieved.

Dynamic routing is considered an attractive solution for many network applications such as monitoring and tracking. In dynamic routing the path between the source and the destination can change dynamically following the network conditions. Next node selection criteria can have a great impact on the selection of each path and as a consequence on the network performance. Moreover, each network application may have different Quality of Service (QoS) requirements. In this paper, we examine the impact of the next node selection criteria on the network performance. Three routing protocols with different approaches along with their routing algorithms are presented. To examine the performance of each approach a discrete event simulator is used. It is shown that the selection criteria should be carefully designed following the QoS requirements of the network application. Furthermore, the obtained performance results can be used as an indicator of the appropriateness of a dynamic protocol for a variety of applications.

Scalability and sustainability are two fundamental requirements in Wireless Sensor Networks (WSNs). Inch scale sensor nodes can operate unattended for long periods if they have sufficient energy sources. In this work, a Self-Powered Sensor Network (SPSN) testbed is introduced. SPSN is cost-efficient and has large-scale deployability. It combines cognitive networking principles with efficient routing approaches and energy harvesting techniques. SPSN is used for indoor CO2 monitoring as well as for outdoor gas leak detection. The performance of the system for channel estimation at an outdoor environment is examined. Experimental results show that SPSN can be used for a plethora of other applications as well.

An appealing solution for unattended surveillance and monitoring applications is Self-powered Wireless Sensor Networks (WSNs). One of the main reasons is that the energy which is derived from power harvesting can significantly extend the network lifetime. Consequently, the network can work unattended for long periods. However, WSNs are characterized by multi-hop lossy links and resource constrained nodes while they have to face the coexistence problem with other applications. Opportunistic Routing (OR) is a routing paradigm to improve network performance in lossy wireless networks. At the same time, Cognitive Radio (CR) technology enables unlicensed operation in licensed bands. In this work, a combination of these two research approaches in a novel routing protocol is presented. A Spectrum and Energy Aware Opportunistic Routing (SEA-OR) protocol is proposed and designed for Self-powered WSNs. Moreover, a prioritization scheme which balances the packet advancement, the residual energy and the link reliability is introduced. Preliminary results show an improvement in network lifetime and delivery ratio. The performance of the introduced protocol is also evaluated in prototypes.

Subject monitoring and tracking is one of the most appealing classes of applications for Wireless Sensor Networks (WSNs). Numerous inch scale nodes can sense, collect and distribute crucial information with low deployment cost. For instance, the movement of endangered species in a national park can be monitored with a WSN. However, in such applications privacy issues can jeopardize the successful deployment of the network. An adversary might trace the network traffic over the same paths and eventually locate the source in the network. In this paper, we propose a source-location privacy scheme that employs randomly selected intermediate nodes based on inclination angles. The introduced Angle-based Dynamic Routing Scheme (ADRS) is analysed and is compared with the Phantom Single-path Routing Scheme (PSRS). Simulation results demonstrate that ADRS improves the safety period and the packet latency.

In this demonstration proposal we describe a prototype of a Wireless Sensor Network (WSN) for monitoring the air quality of an arbitrary indoor infrastructure environment. Specifically, the proposed demonstration deals with an application of wireless mesh networks for monitoring the carbon dioxide (CO2) levels of an indoor environment, supporting guaranteed real-time data acquisition and display. In the proposed demonstration we will illustrate a number of advantages of opportunistic routing, including dynamic node deployment and dynamic routing path selection, opportunistic resource utilization, robustness to interference and guaranteed multi-hop QoS (Quality of Service) for an indoor gas concentration monitoring network.

Under the cognitive networking architecture, this paper presents an opportunistic routing protocol for cognitive radio in Wireless Sensor Networks (WSNs), which can deliver higher performance and efficiency in multihop wireless communications. Cognitive Networking with Opportunistic Routing, (CNOR), opportunistically routes traffic across paths over all available spectrum. A discrete event simulator is applied to evaluate and compare the proposed scheme against three other routing protocols: traditional routing with single channel, traditional routing with multiple channels and opportunistic routing with single channel. It is shown that by integrating opportunistic routing with cognitive radio much better results can be obtained, with respect to energy consumption, throughput and latency.

Survivability is crucial in Wireless Sensor Networks (WSNs) especially when they are used for monitoring and tracking applications with limited available resources. In this paper we are proposing the use of an energy Efficient Cognitive Unicast Routing (ECUR) protocol that tries to keep a balance between the energy consumption and the packet delay in a WSN. The proposed routing protocol has a next node selection criterion to change the routing path dynamically following the network conditions and the channel availability while the energy consumption per node is also considered. Simulation results are presented that show an increase in network lifetime of up to 30% compared with geographic opportunistic routing while the packet delay remains similar.

Opportunistic routing schemes have been studied over the past decade to provide better performance in multihop wireless networks, by taking the advantage of the broadcasting nature of wireless channels. Simulation tools for such study are important and have been investigated to understand the network behavior. In this paper, we use real and simulated channel data to further elaborate the performance of opportunistic networks. In particular, a channel model is built by radio signal strength measurement in an indoor infrastructure, and the output of the channel model is used to feed an opportunistic network simulator. The paper then compares the performance of multihop wireless communications in opportunistic and traditional schemes.

Wireless sensor networks (WSN) can be an attractive solution for a plethora of communication applications, such as unattended event monitoring and tracking. One of the looming challenges that threaten the successful deployment of these sensor networks is source-location privacy, especially when a network is deployed to monitor sensitive objects. In order to enhance source location privacy in sensor networks, we propose the use of an opportunistic mesh networking scheme and examine four different approaches. Each approach has different selection criteria for the next relay node. In opportunistic mesh networks, each sensor transmits the packet over a dynamic path to the destination. Every packet from the source can therefore follow a different path toward the destination, making it difficult for an adversary to backtrack hop-by-hop to the origin of the sensor communication.

The effect of an arbitrary indoor infrastructure environment on the performance of a wireless multihop network is investigated. To this end, an accurate channel modeling tool based on 3D ray tracing is used first to evaluate the signal strength in different areas of the environment. Then, a discrete event simulator is applied to examine the performance of the network with two classes of routing protocols: traditional vs. opportunistic. It is shown that for an indoor environment, opportunistic routing performs better based on the obtained results, with respect to throughput, delay and delivery ratio.