J. Sens. Actuator Netw., Volume 10, Issue 4 (December 2021) – 14 articles

Machine vision is increasingly replacing manual steel surface inspection. The automatic inspection of steel surface defects makes it possible to ensure the quality of products in the steel industry with high accuracy. However, the optimization of inspection time presents a great challenge for the integration of machine vision in high-speed production lines. In this context, compressing the collected images before transmission is essential to save bandwidth and energy, and improve the latency of vision applications. The aim of this paper was to study the impact of quality degradation resulting from image compression on the classification performance of steel surface defects with a CNN. Image compression was applied to the Northeastern University (NEU) surface-defect database with various compression ratios. Three different models were trained and tested with these images to classify surface defects using three different approaches. The obtained results showed that trained and tested models on the same compression qualities maintained approximately the same classification performance for all used compression grades. In addition, the findings clearly indicated that the classification efficiency was affected when the training and test datasets were compressed using different parameters. This impact was more obvious when there was a large difference between these compression parameters, and for models that achieved very high accuracy. Finally, it was found that compression-based data augmentation significantly increased the classification precision to perfect scores (98–100%), and thus improved the generalization of models when tested on different compression qualities. The importance of this work lies in exploiting the obtained results to successfully integrate image compression into machine vision systems, and as appropriately as possible. Full article

The paper investigates retraining options and the performance of pre-trained Convolutional Neural Networks (CNNs) for sound classification. CNNs were initially designed for image classification and recognition, and, at a second phase, they extended towards sound classification. Transfer learning is a promising paradigm, retraining already trained networks upon different datasets. We selected three ‘Image’- and two ‘Sound’-trained CNNs, namely, GoogLeNet, SqueezeNet, ShuffleNet, VGGish, and YAMNet, and applied transfer learning. We explored the influence of key retraining parameters, including the optimizer, the mini-batch size, the learning rate, and the number of epochs, on the classification accuracy and the processing time needed in terms of sound preprocessing for the preparation of the scalograms and spectrograms as well as CNN training. The UrbanSound8K, ESC-10, and Air Compressor open sound datasets were employed. Using a two-fold criterion based on classification accuracy and time needed, we selected the ‘champion’ transfer-learning parameter combinations, discussed the consistency of the classification results, and explored possible benefits from fusing the classification estimations. The Sound CNNs achieved better classification accuracy, reaching an average of 96.4% for UrbanSound8K, 91.25% for ESC-10, and 100% for the Air Compressor dataset. Full article

Many regions of the world benefit from heating, ventilating, and air-conditioning (HVAC) systems to provide productive, comfortable, and healthy indoor environments, which are enabled by automatic building controls. Due to climate change, population growth, and industrialization, HVAC use is globally on the rise. Unfortunately, these systems often operate in a continuous fashion without regard to actual human presence, leading to unnecessary energy consumption. As a result, the heating, ventilation, and cooling of unoccupied building spaces makes a substantial contribution to the harmful environmental impacts associated with carbon-based electric power generation, which is important to remedy. For our modern electric power system, transitioning to low-carbon renewable energy is facilitated by integration with distributed energy resources. Automatic engagement between the grid and consumers will be necessary to enable a clean yet stable electric grid, when integrating these variable and uncertain renewable energy sources. We present the WHISPER (Wireless Home Identification and Sensing Platform for Energy Reduction) system to address the energy and power demand triggered by human presence in homes. The presented system includes a maintenance-free and privacy-preserving human occupancy detection system wherein a local wireless network of battery-free environmental, acoustic energy, and image sensors are deployed to monitor homes, record empirical data for a range of monitored modalities, and transmit it to a base station. Several machine learning algorithms are implemented at the base station to infer human presence based on the received data, harnessing a hierarchical sensor fusion algorithm. Results from the prototype system demonstrate an accuracy in human presence detection in excess of $95\%$; ongoing commercialization efforts suggest approximately 99% accuracy. Using machine learning, WHISPER enables various applications based on its binary occupancy prediction, allowing situation-specific controls targeted at both personalized smart home and electric grid modernization opportunities. Full article

LoRaWAN has established itself as one of the leading MAC layer protocols in the field of LPWAN. Although the technology itself is quite mature, its resource allocation mechanism, the Adaptive Data Rate (ADR) algorithm is still quite new, unspecified and its functionalities still limited. Various studies have shown that the performance of the ADR algorithm gradually suffers in dense networks. Recent studies and proposals have been made as attempts to improve the algorithm. In this paper, the authors proposed a spreading factor congestion status aware ADR version and compared its performance against that of four other related algorithms to study the performance improvements the algorithm brings to LoRaWAN in terms of DER and EC. LoRaSim was used to evaluate the algorithms’ performances in a simple sensing application that involved end devices transmitting data to the gateway every hour. The performances were measured based on how they affected DER as the network size increases. The results obtained show that the proposed algorithm outperforms the currently existing implementations of the ADR in terms of both DER and EC. However, the proposed algorithm is slightly outperformed by the native ADR in terms of EC. This was expected as the algorithm was mainly built to improve DER. The proposed algorithm builds on the existing algorithms and the ADR and significantly improves them in terms of DER and EC (excluding the native ADR), which is a significant step towards an ideal implementation of LoRaWAN’s ADR. Full article

Recently, the data collection problem in wireless sensor networks (WSNs) using mobile sinks has received much attention. The main challenge in such problems is constructing the path that the mobile sink (MS) will use to collect the data. In this paper, an efficient path generation algorithm for the mobile sink based on principal component analysis (PCA) is proposed. The proposed approach was evaluated using two data collection modes—direct and multihop—and it was compared with another approach called the mobile-sink-based energy-efficient clustering algorithm for wireless sensor networks (MECA). When compared with MECA, simulation results have shown that the proposed approach improves the performance of WSN in terms of the number of live nodes and average remaining energy. Full article

Sensor networks that collect data from the environment can be utilized in the development of context-aware applications, bringing into sight the need for data collection, management, and distribution. Boards with microcontrollers, such as Arduino and Raspberry Pi, have gained wide acceptance and are used mainly for educational and research purposes. Utilizing the information available via sensors connected to these platforms requires extended technical knowledge. In this work, we present a sensor management framework, SensoMan, that manages a collection of sensors spread in the environment connected to microcontroller boards. We present the framework’s architecture, a method for sensor data management, and a prototype system. Sensor data can also trigger the execution of actions on actuators. Thus, we further propose a rule engine as well as social connectivity following a scheme where sensors and their data can be shared among users. Our work shows that the creation of such a system is feasible and can use simple equipment (e.g., sensors, controller plugs) that can be replicated in other environments. The use of SensoMan is demonstrated via two scenarios that show its potential in combining simple tools that do not require an extended learning curve. A small-scale user study was also performed. Full article

The design of Wireless Sensor Networks (WSN) requires the fulfillment of several design requirements. The most important one is optimizing the battery’s lifetime, which is tightly coupled to the sensor lifetime. End-users usually avoid replacing sensors’ batteries, especially in massive deployment scenarios like smart agriculture and smart buildings. To optimize battery lifetime, wireless sensor designers need to delineate and optimize active components at different levels of the sensor’s layered architecture, mainly, (1) the number of data sets being generated and processed at the application layer, (2) the size and the architecture of the operating systems (OS), (3) the networking layers’ protocols, and (4) the architecture of electronic components and duty cycling techniques. This paper reviews the different relevant technologies and investigates how they optimize energy consumption at each layer of the sensor’s architecture, e.g., hardware, operating system, application, and networking layer. This paper aims to make the researcher aware of the various optimization opportunities when designing WSN nodes. To our knowledge, there is no other work in the literature that reviews energy optimization of WSN in the context of Smart Energy-Efficient Buildings (SEEB) and from the formerly four listed perspectives to help in the design and implementation of optimal WSN for SEEB. Full article

An autonomous vehicle relies on sensors in order to perceive its surroundings. However, there are multiple causes that would hinder a sensor’s proper functioning, such as bad weather or lighting conditions. Studies have shown that rainfall and fog lead to a reduced visibility, which is one of the main causes of accidents. This work proposes the use of a drone in order to enhance the vehicle’s perception, making use of both embedded sensors and its advantageous 3D positioning. The environment perception and vehicle/Unmanned Aerial Vehicle (UAV) interactions are managed by a knowledge base in the form of an ontology, and logical rules are used in order to detect and infer the environmental context and UAV management. The model was tested and validated in a simulation made on Unity. Full article

Many industries, such as aeronautics construction are still equipped with legacy machines and are not keen to change old, however fully functional, equipment to new ones. Hence, an upgrade must be found to cope the legacy and fully functional machines to IoT technologies. This paper is a contribution to embrace those challenges in a new IoT architecture able to support the creation of solutions for Smart Industries. Internet of Things is increasing acceptance and the infrastructure for them is becoming available. This leads to an insurgence on investments and development of new dedicated IoT infrastructures. Industries need to adapt quickly to this constant technological evolution, implementing measures and connecting machines and robots at critical points to the Internet, instrumenting them using the concept of IoT, with the major goal of implementing a flexible, secure, easy to maintain and capable to evolve infrastructure, when legacy equipment is involved. The availability of machines and other critical assets directly affects the effectiveness of manufacturing operations. The architecture design offers security, flexibility, simplicity of implementation and maintenance, and is resilient to failures or attacks and technologically independent. Field tests are reported to evaluate key aspects of the proposed architecture. Full article

This work proposes an autonomous management system for distributed generation (DG) systems connected to the AC grid, using supervisory control theory (SCT). SCT is used to deal with discrete asynchronous events that modify the properties and operational conditions of these systems. The proposed management layer allows the smart inverters to interact with smart grid managers (SGMs), while guaranteeing operation compliance with the IEEE Standards. The implemented supervisor for the management layer is an automaton that performs the smart inverter manager (SIM) functions in the photovoltaic systems in discrete events. A DSP real-time verification was performed with Typhoon HIL 602+ to demonstrate the smart inverter’s operating dynamics connected to the grid. The results showed the fast response and robust operation of the smart inverter manager to the commands from the smart grid manager. Full article

This paper presents an approach based on radio frequency identification (RFID) and machine learning for contamination sensing of food items and drinks such as soft drinks, alcohol, baby formula milk, etc. We employ sticker-type inkjet printed ultra-high-frequency (UHF) RFID tags for contamination sensing experimentation. The RFID tag antenna was mounted on pure as well as contaminated food products with known contaminant quantity. The received signal strength indicator (RSSI), as well as the phase of the backscattered signal from the RFID tag mounted on the food item, are measured using the Tagformance Pro setup. We used a machine-learning algorithm XGBoost for further training of the model and improving the accuracy of sensing, which is about 90%. Therefore, this research study paves a way for ubiquitous contamination/content sensing using RFID and machine learning technologies that can enlighten their users about the health concerns and safety of their food. Full article

This research aims to provide a high-level software framework for IoT-Edge-Cloud computational continuum-based applications with support for mobile IoT and DevOps integration utilizing the Edge computing paradigms. This is achieved by dividing the system in a modular fashion and providing a loosely coupled service and module descriptions for usage in the respective system layers for flexible and yet trustworthy implementation. The article describes the software architecture for a DevOps-enabled Edge computing solution in the IoT-Edge-Cloud computational continuum with the support for flexible and mobile IoT solutions. The proposed framework is validated on an intelligent transport system use case in the rolling stock domain and showcases the improvements gained by using the proposed IoT-Edge-Cloud continuum framework. Full article

The fast growth of the Internet of Things (IoT) and its diverse applications increase the risk of cyberattacks, one type of which is malware attacks. Due to the IoT devices’ different capabilities and the dynamic and ever-evolving environment, applying complex security measures is challenging, and applying only basic security standards is risky. Artificial Immune Systems (AIS) are intrusion-detecting algorithms inspired by the human body’s adaptive immune system techniques. Most of these algorithms imitate the human’s body B-cell and T-cell defensive mechanisms. They are lightweight, adaptive, and able to detect malware attacks without prior knowledge. In this work, we review the recent advances in employing AIS for the improved detection of malware in IoT networks. We present a critical analysis that highlights the limitations of the state-of-the-art in AIS research and offer insights into promising new research directions. Full article

The increasing complexity of communication systems, following the advent of heterogeneous technologies, services and use cases with diverse technical requirements, provide a strong case for the use of artificial intelligence (AI) and data-driven machine learning (ML) techniques in studying, designing and operating emerging communication networks. At the same time, the access and ability to process large volumes of network data can unleash the full potential of a network orchestrated by AI/ML to optimise the usage of available resources while keeping both CapEx and OpEx low. Driven by these new opportunities, the ongoing standardisation activities indicate strong interest to reap the benefits of incorporating AI and ML techniques in communication networks. For instance, 3GPP has introduced the network data analytics function (NWDAF) at the 5G core network for the control and management of network slices, and for providing predictive analytics, or statistics, about past events to other network functions, leveraging AI/ML and big data analytics. Likewise, at the radio access network (RAN), the O-RAN Alliance has already defined an architecture to infuse intelligence into the RAN, where closed-loop control models are classified based on their operational timescale, i.e., real-time, near real-time, and non-real-time RAN intelligent control (RIC). Different from the existing related surveys, in this review article, we group the major research studies in the design of model-aided ML-based transceivers following the breakdown suggested by the O-RAN Alliance. At the core and the edge networks, we review the ongoing standardisation activities in intelligent networking and the existing works cognisant of the architecture recommended by 3GPP and ETSI. We also review the existing trends in ML algorithms running on low-power micro-controller units, known as TinyML. We conclude with a summary of recent and currently funded projects on intelligent communications and networking. This review reveals that the telecommunication industry and standardisation bodies have been mostly focused on non-real-time RIC, data analytics at the core and the edge, AI-based network slicing, and vendor inter-operability issues, whereas most recent academic research has focused on real-time RIC. In addition, intelligent radio resource management and aspects of intelligent control of the propagation channel using reflecting intelligent surfaces have captured the attention of ongoing research projects. Full article