Search

Industry 4.0 introduced new concepts, technologies, and paradigms, such as Cyber Physical Systems (CPSs), Industrial Internet of Things (IIoT) and, more recently, Artificial Intelligence of Things (AIoT). These paradigms ease the creation of complex systems by integrating heterogeneous devices. As a result, the structure of the production systems is changing completely. In this scenario, the adoption of reference architectures based on standards may guide designers and developers to create complex AIoT applications. This article surveys the main reference architectures available for industrial AIoT applications, analyzing their key characteristics, objectives, and benefits; it also presents some use cases that may help designers create new applications. The main goal of this review is to help engineers identify the alternative that best suits every application. The authors conclude that existing reference architectures are a necessary tool for standardizing AIoT applications, since they may guide developers in the process of developing new applications. However, the use of reference architectures in real AIoT industrial applications is still incipient, so more development effort is needed in order for it to be widely adopted.

High-pressure pipelines are critical for transporting hazardous materials over long distances, but they face threats from third-party interference activities. Preventive measures are implemented, but interference accidents can still occur, making the need for high-quality detection strategies vital. This paper proposes an end-to-end Artificial Intelligence of Things (AIoT) solution to detect potential interference threats in real time. The solution involves developing a smart visual sensor capable of processing images using state-of-the-art computer vision algorithms and transmitting alerts to pipeline operators in real time. The system’s core is based on the object-detection model (e.g., You Only Look Once version 4 (YOLOv4) and DETR with Improved deNoising anchOr boxes (DINO)), trained on a custom Pipeline Visual Threat Assessment (Pipe-VisTA) dataset. Among the trained models, DINO was able to achieve the best Mean Average Precision (mAP) of 71.2% for the unseen test dataset. However, for the deployment on a limited computational-ability edge computer (i.e., the NVIDIA Jetson Nano), the simpler and TensorRT-optimized YOLOv4 model was used, which achieved a mAP of 61.8% for the test dataset. The developed AIoT device captures the image using a camera, processes on the edge using the trained YOLOv4 model to detect the potential threat, transmits the threat alert to a Fleet Portal via LoRaWAN, and hosts the alert on a dashboard via a satellite network. The device has been fully tested in the field to ensure its functionality prior to deployment for the SEA Gas use-case. The AIoT smart solution has been deployed across the 10km stretch of the SEA Gas pipeline across the Murray Bridge section. In total, 48 AIoT devices and three Fleet Portals are installed to ensure the line-of-sight communication between the devices and portals.

In recent years, environmental sound classification (ESC) has prevailed in many artificial intelligence Internet of Things (AIoT) applications, as environmental sound contains a wealth of information that can be used to detect particular events. However, existing ESC methods have high computational complexity and are not suitable for deployment on AIoT devices with constrained computing resources. Therefore, it is of great importance to propose a model with both high classification accuracy and low computational complexity. In this work, a new ESC method named BSN-ESC is proposed, including a big–small network-based ESC model that can assess the classification difficulty level and adaptively activate a big or small network for classification as well as a pre-classification processing technique with logmel spectrogram refining, which prevents distortion in the frequency-domain characteristics of the sound clip at the joint part of two adjacent sound clips. With the proposed methods, the computational complexity is significantly reduced, while the classification accuracy is still high. The proposed BSN-ESC model is implemented on both CPU and FPGA to evaluate its performance on both PC and embedded systems with the dataset ESC-50, which is the most commonly used dataset. The proposed BSN-ESC model achieves the lowest computational complexity with the number of floating-point operations (FLOPs) of only 0.123G, which represents a reduction of up to 2309 times in computational complexity compared with state-of-the-art methods while delivering a high classification accuracy of 89.25%. This work can achieve the realization of ESC being applied to AIoT devices with constrained computational resources.

Forest fires are the main cause of desertification, and they have a disastrous impact on agricultural and forest ecosystems. Modern fire detection and warning systems rely on several techniques: satellite monitoring, sensor networks, image processing, data fusion, etc. Recently, Artificial Intelligence (AI) algorithms have been applied to fire recognition systems, enhancing their efficiency and reliability. However, these devices usually need constant data transmission along with a proper amount of computing power, entailing high costs and energy consumption. This paper presents the prototype of a Video Surveillance Unit (VSU) for recognising and signalling the presence of forest fires by exploiting two embedded Machine Learning (ML) algorithms running on a low power device. The ML models take audio samples and images as their respective inputs, allowing for timely fire detection. The main result is that while the performances of the two models are comparable when they work independently, their joint usage according to the proposed methodology provides a higher accuracy, precision, recall and F1 score (96.15%, 92.30%, 100.00%, and 96.00%, respectively). Eventually, each event is remotely signalled by making use of the Long Range Wide Area Network (LoRaWAN) protocol to ensure that the personnel in charge are able to operate promptly.

Deploying artificial intelligence on edge nodes of Low-Power Wide Area Networks can significantly reduce network transmission volumes, event response latency, and overall network power consumption. However, the edge nodes in LPWAN bear limited computing power and storage space, and researchers have found it challenging to improve the recognition capability of the nodes using sensor data from the environment. In particular, the domain-shift problem in LPWAN is challenging to overcome. In this paper, a complete AIoT system framework referred to as LPAI is presented. It is the first generic framework for implementing AIoT technology based on LPWAN applicable to acoustic scene classification scenarios. LPAI overcomes the domain-shift problem, which enables resource-constrained edge nodes to continuously improve their performance using real data to become more adaptive to the environment. For efficient use of limited resources, the edge nodes independently select representative data and transmit it back to the cloud. Moreover, the model is iteratively retrained on the cloud using the few-shot uploaded data. Finally, the feasibility of LPAI is analyzed, and simulation experiments on the public ASC dataset provide validation that our proposed framework can improve the recognition accuracy by as little as 5% using 85 actual sensor data points.

According to the World Health Organization, about 15% of the world’s population has some form of disability. Assistive Technology, in this context, contributes directly to the overcoming of difficulties encountered by people with disabilities in their daily lives, allowing them to receive education and become part of the labor market and society in a worthy manner. Assistive Technology has made great advances in its integration with Artificial Intelligence of Things (AIoT) devices. AIoT processes and analyzes the large amount of data generated by Internet of Things (IoT) devices and applies Artificial Intelligence models, specifically, machine learning, to discover patterns for generating insights and assisting in decision making. Based on a systematic literature review, this article aims to identify the machine-learning models used across different research on Artificial Intelligence of Things applied to Assistive Technology. The survey of the topics approached in this article also highlights the context of such research, their application, the IoT devices used, and gaps and opportunities for further development. The survey results show that 50% of the analyzed research address visual impairment, and, for this reason, most of the topics cover issues related to computational vision. Portable devices, wearables, and smartphones constitute the majority of IoT devices. Deep neural networks represent 81% of the machine-learning models applied in the reviewed research.

There is a constant risk of iron ore collapsing during its transfer between processing stages in beneficiation plants. Existing instrumentation is not only expensive but also complex and challenging to maintain. In this research, we propose using edge artificial intelligence for early detection of landslide risk based on images of iron ore transported on conveyor belts. During this work, we defined the device edge and the deep neural network model. Then, we built a prototype will to collect images that will be used for training the model. This model will be compressed for use in the device edge. This same prototype will be used for field tests of the model under operational conditions. In building the prototype, a real-time clock was used to ensure the synchronization of image records with the plant’s process information, ensuring the correct classification of images by the process specialist. The results obtained in the field tests of the prototype with an accuracy of 91% and a recall of 96% indicate the feasibility of using deep learning at the edge to detect the type of iron ore and prevent its risk of avalanche.

It is estimated that we spend one-third of our lives at work. It is therefore vital to adapt traditional equipment and systems used in the working environment to the new technological paradigm so that the industry is connected and, at the same time, workers are as safe and protected as possible. Thanks to Smart Personal Protective Equipment (PPE) and wearable technologies, information about the workers and their environment can be extracted to reduce the rate of accidents and occupational illness, leading to a significant improvement. This article proposes an architecture that employs three pieces of PPE: a helmet, a bracelet and a belt, which process the collected information using artificial intelligence (AI) techniques through edge computing. The proposed system guarantees the workers’ safety and integrity through the early prediction and notification of anomalies detected in their environment. Models such as convolutional neural networks, long short-term memory, Gaussian Models were joined by interpreting the information with a graph, where different heuristics were used to weight the outputs as a whole, where finally a support vector machine weighted the votes of the models with an area under the curve of 0.81.

Ubiquitous health management (UHM) is vital in the aging society. The UHM services with artificial intelligence of things (AIoT) can assist home-isolated healthcare in tracking rehabilitation exercises for clinical diagnosis. This study combined a personalized rehabilitation recognition (PRR) system with the AIoT for the UHM of lower-limb rehabilitation exercises. The three-tier infrastructure integrated the recognition pattern bank with the sensor, network, and application layers. The wearable sensor collected and uploaded the rehab data to the network layer for AI-based modeling, including the data preprocessing, featuring, machine learning (ML), and evaluation, to build the recognition pattern. We employed the SVM and ANFIS methods in the ML process to evaluate 63 features in the time and frequency domains for multiclass recognition. The Hilbert-Huang transform (HHT) process was applied to derive the frequency-domain features. As a result, the patterns combining the time- and frequency-domain features, such as relative motion angles in y- and z-axis, and the HHT-based frequency and energy, could achieve successful recognition. Finally, the suggestive patterns stored in the AIoT-PRR system enabled the ML models for intelligent computation. The PRR system can incorporate the proposed modeling with the UHM service to track the rehabilitation program in the future.

Wearable technologies are becoming a profitable means of monitoring a person’s health state, such as heart rate and physical activity. The use of the smartwatch is becoming consolidated, not only as a novelty but also as a very useful tool for daily use. In addition, other devices, such as helmets or belts, are beneficial for monitoring workers and the early detection of any anomaly. They can provide valuable information, especially in work environments, where they help reduce the rate of accidents and occupational diseases, which makes them powerful Personal Protective Equipment (PPE). The constant monitoring of the worker’s health can be done in real-time, through temperature, falls, noise, impacts, or heart rate meters, activating an audible and vibrating alarm when an anomaly is detected. The gathered information is transmitted to a server in charge of collecting and processing it. In the first place, this paper provides an exhaustive review of the state of the art on works related to electronics for human activity behavior. After that, a smart multisensory bracelet, combined with other devices, developed a control platform that can improve operators’ security in the working environment. Artificial Intelligence and the Internet of Things (AIoT) bring together the information to improve safety on construction sites, power stations, power lines, etc. Real-time and historic data is used to monitor operators’ health and a hybrid system between Gaussian Mixture Model and Human Activity Classification. That is, our contribution is also founded on the use of two machine learning models, one based on unsupervised learning and the other one supervised. Where the GMM gave us a performance of 80%, 85%, 70%, and 80% for the 4 classes classified in real time, the LSTM obtained a result under the confusion matrix of 0.769, 0.892, and 0.921 for the carrying-displacing, falls, and walking-standing activities, respectively. This information was sent in real time through the platform that has been used to analyze and process the data in an alarm system.

Running Deep Neural Networks (DNNs) in distributed Internet of Things (IoT) nodes is a promising scheme to enhance the performance of IoT systems. However, due to the limited computing and communication resources of the IoT nodes, the communication efficiency of the distributed DNN training strategy is a problem demanding a prompt solution. In this paper, an adaptive compression strategy based on gradient partition is proposed to solve the problem of high communication overhead between nodes during the distributed training procedure. Firstly, a neural network is trained to predict the gradient distribution of its parameters. According to the distribution characteristics of the gradient, the gradient is divided into the key region and the sparse region. At the same time, combined with the information entropy of gradient distribution, a reasonable threshold is selected to filter the gradient value in the partition, and only the gradient value greater than the threshold is transmitted and updated, to reduce the traffic and improve the distributed training efficiency. The strategy uses gradient sparsity to achieve the maximum compression ratio of 37.1 times, which improves the training efficiency to a certain extent.