Search

Arc-welding robots are widely used in the production of automotive bracket parts. The large amounts of fumes and toxic gases generated during arc welding can affect the inspection results, as well as causing health problems, and the product needs to be sent to an additional checkpoint for manual inspection. In this work, the framework of a robotic-vision-based defect inspection system was proposed and developed in a cloud–edge computing environment, which can drastically reduce the manual labor required for visual inspection, minimizing the risks associated with human error and accidents. Firstly, a passive vision sensor was installed on the end joint of the arc-welding robot, the imaging module was designed to capture bracket weldments images after the arc-welding process, and datasets with qualified images were created in the production line for deep-learning-based research on steel surface defects. To enhance the detection precision, a redesigned lightweight inspection network was then employed, while a fast computation speed was ensured through the utilization of a cloud–edge-computing computational framework. Finally, virtual simulation and Internet of Things technologies were adopted to develop the inspection and control software in order to monitor the whole process remotely. The experimental results demonstrate that the proposed approach can realize the faster identification of quality issues, achieving higher steel production efficiency and economic profits. [ABSTRACT FROM AUTHOR]

The falling cost of IoT cameras, the advancement of AI-based computer vision algorithms, and powerful hardware accelerators for deep learning have enabled the widespread deployment of surveillance cameras with the ability to automatically analyze streaming video feeds to detect events of interest. While streaming video analytics is currently largely performed in the cloud, edge computing has emerged as a pivotal component due to its advantages of low latency, reduced bandwidth, and enhanced privacy. However, a distinct gap persists between state-of-the-art computer vision algorithms and the successful practical implementation of edge-based streaming video analytics systems. This paper presents a comprehensive review of more than 30 research papers published over the last 6 years on IoT edge streaming video analytics (IE-SVA) systems. The papers are analyzed across 17 distinct dimensions. Unlike prior reviews, we examine each system holistically, identifying their strengths and weaknesses in diverse implementations. Our findings suggest that certain critical topics necessary for the practical realization of IE-SVA systems are not sufficiently addressed in current research. Based on these observations, we propose research trajectories across short-, medium-, and long-term horizons. Additionally, we explore trending topics in other computing areas that can significantly impact the evolution of IE-SVA systems. [ABSTRACT FROM AUTHOR]

Rechargeable lithium-ion batteries are currently the most viable option for energy storage systems in electric vehicle (EV) applications due to their high specific energy, falling costs, and acceptable cycle life. However, accurately predicting the parameters of complex, nonlinear battery systems remains challenging, given diverse aging mechanisms, cell-to-cell variations, and dynamic operating conditions. The states and parameters of batteries are becoming increasingly important in ubiquitous application scenarios, yet our ability to predict cell performance under realistic conditions remains limited. To address the challenge of modelling and predicting the evolution of multiphysics and multiscale battery systems, this study proposes a cloud-based AI-enhanced framework. The framework aims to achieve practical success in the co-estimation of the state of charge (SOC) and state of health (SOH) during the system's operational lifetime. Self-supervised transformer neural networks offer new opportunities to learn representations of observational data with multiple levels of abstraction and attention mechanisms. Coupling the cloud-edge computing framework with the versatility of deep learning can leverage the predictive ability of exploiting long-range spatio-temporal dependencies across multiple scales. [ABSTRACT FROM AUTHOR]

In the construction of new power systems, the traditional network security protection mainly based on boundary protection belongs to static defense and still relies mainly on manual processing in vulnerability repair, threat response, etc. It is difficult to adapt to the security protection needs in large-scale distributed new energy, third-party aggregation platforms, and flexible interaction scenarios with power grid enterprise systems. It is necessary to conduct research on dynamic security protection models for IoT and other Blockchain-based IoT architectures. This article proposes a network security comprehensive protection model P2AEDR based on different interaction modes of cloud–edge interaction and cloud–cloud interaction. Through continuous trust evaluation, dynamic access control, and other technologies, it strengthens the internal defense capabilities of power grid business, shifting from static protection as the core mode to a real-time intelligent perception and automated response mode, and ultimately achieving the goal of dynamic defense, meeting the security protection needs of large-scale controlled terminal access and third-party aggregation platforms. Meanwhile, this article proposes a dynamic trust evaluation algorithm based on deep learning, which protects the secure access and use of various resources in a more refined learning approach based on the interaction information monitored in the system. Through experimental verification of the dynamic trust evaluation algorithm, it is shown that the proposed model has good trust evaluation performance. Therefore, this research is beneficial for trustworthy Power IoT and other Blockchain-based IoT architectures. [ABSTRACT FROM AUTHOR]

Malaria is a leading cause of morbidity and mortality in tropical and sub-tropical regions. This research proposed a malaria diagnosis system based on the you only look once algorithm for malaria parasite detection and the convolutional neural network algorithm for malaria parasite life stage classification. Two public datasets are utilized: MBB and MP-IDB. The MBB dataset includes human blood smears infected with Plasmodium vivax (P. vivax). While the MP-IDB dataset comprises 4 species of malaria parasites: P. vivax, P. ovale, P. malariae, and P. falciparum. Four distinct stages of life exist in every species, including ring, trophozoite, schizont, and gametocyte. For the MBB dataset, detection and classification accuracies of 0.92 and 0.93, respectively, were achieved. For the MP-IDB dataset, the proposed algorithms yielded the accuracies for detection and classification as follows: 0.84 and 0.94 for P. vivax; 0.82 and 0.93 for P. ovale; 0.79 and 0.93 for P. malariae; and 0.92 and 0.96 for P. falciparum. The detection results showed the models trained by P. vivax alone provide good detection capabilities also for other species of malaria parasites. The classification performance showed the proposed algorithms yielded good malaria parasite life stage classification performance. The future directions include collecting more data and exploring more sophisticated algorithms. [ABSTRACT FROM AUTHOR]

Intelligent mobile image sensing powered by deep learning analyzes images captured by cameras from mobile devices, such as smartphones or smartwatches. It supports numerous mobile applications, such as image classification, face recognition, and camera scene detection. Unfortunately, mobile devices often lack the resources necessary for deep learning, leading to increased inference latency and rapid battery consumption. Moreover, the inference accuracy may decline over time due to potential data drift. To address these issues, we introduce a new cost-efficient framework, called Corun, designed to simultaneously handle multiple inference queries and continual model retraining/fine-tuning of a pre-trained model on a single commodity GPU in an edge server to significantly improve the inference throughput, upholding the inference accuracy. The scheduling method of Corun undertakes offline profiling to find the maximum number of concurrent inferences that can be executed along with a retraining job on a single GPU without incurring an out-of-memory error or significantly increasing the latency. Our evaluation verifies the cost-effectiveness of Corun. The inference throughput provided by Corun scales with the number of concurrent inference queries. However, the latency of inference queries and the length of a retraining epoch increase at substantially lower rates. By concurrently processing multiple inference and retraining tasks on one GPU instead of using a separate GPU for each task, Corun could reduce the number of GPUs and cost required to deploy mobile image sensing applications based on deep learning at the edge. [ABSTRACT FROM AUTHOR]

Malaria is a disease that affects millions of people worldwide with a consistent mortality rate. The light microscope examination is the gold standard for detecting infection by malaria parasites. Still, it is limited by long timescales and requires a high level of expertise from pathologists. Early diagnosis of this disease is necessary to achieve timely and effective treatment, which avoids tragic consequences, thus leading to the development of computer-aided diagnosis systems based on artificial intelligence (AI) for the detection and classification of blood cells infected with the malaria parasite in blood smear images. Such systems involve an articulated pipeline, culminating in the use of machine learning and deep learning approaches, the main branches of AI. Here, we present a systematic literature review of recent research on the use of automated algorithms to identify and classify malaria parasites in blood smear images. Based on the PRISMA 2020 criteria, a search was conducted using several electronic databases including PubMed, Scopus, and arXiv by applying inclusion/exclusion filters. From the 606 initial records identified, 135 eligible studies were selected and analyzed. Many promising results were achieved, and some mobile and web applications were developed to address resource and expertise limitations in developing countries. [ABSTRACT FROM AUTHOR]

Effective air quality monitoring and forecasting are essential for safeguarding public health, protecting the environment, and promoting sustainable development in smart cities. Conventional systems are cloud-based, incur high costs, lack accurate Deep Learning (DL)models for multi-step forecasting, and fail to optimize DL models for fog nodes. To address these challenges, this paper proposes a Fog-enabled Air Quality Monitoring and Prediction (FAQMP) system by integrating the Internet of Things (IoT), Fog Computing (FC), Low-Power Wide-Area Networks (LPWANs), and Deep Learning (DL) for improved accuracy and efficiency in monitoring and forecasting air quality levels. The three-layered FAQMP system includes a low-cost Air Quality Monitoring (AQM) node transmitting data via LoRa to the Fog Computing layer and then the cloud layer for complex processing. The Smart Fog Environmental Gateway (SFEG) in the FC layer introduces efficient Fog Intelligence by employing an optimized lightweight DL-based Sequence-to-Sequence (Seq2Seq) Gated Recurrent Unit (GRU) attention model, enabling real-time processing, accurate forecasting, and timely warnings of dangerous AQI levels while optimizing fog resource usage. Initially, the Seq2Seq GRU Attention model, validated for multi-step forecasting, outperformed the state-of-the-art DL methods with an average RMSE of 5.5576, MAE of 3.4975, MAPE of 19.1991%, R2 of 0.6926, and Theil's U1 of 0.1325. This model is then made lightweight and optimized using post-training quantization (PTQ), specifically dynamic range quantization, which reduced the model size to less than a quarter of the original, improved execution time by 81.53% while maintaining forecast accuracy. This optimization enables efficient deployment on resource-constrained fog nodes like SFEG by balancing performance and computational efficiency, thereby enhancing the effectiveness of the FAQMP system through efficient Fog Intelligence. The FAQMP system, supported by the EnviroWeb application, provides real-time AQI updates, forecasts, and alerts, aiding the government in proactively addressing pollution concerns, maintaining air quality standards, and fostering a healthier and more sustainable environment. [ABSTRACT FROM AUTHOR]

Defect detection is very important for guaranteeing the quality and pricing of fabric. A considerable amount of fabric is discarded as waste because of defects, leading to substantial annual losses. While manual inspection has traditionally been the norm for detection, adopting an automatic defect detection scheme based on a deep learning model offers a timely and efficient solution for assessing fabric quality. In real-time manufacturing scenarios, datasets lack high-quality, precisely positioned images. Moreover, both plain and printed fabrics are being manufactured in industries simultaneously; therefore, a single model should be capable of detecting defects in all kinds of fabric. So training a robust deep learning model that detects defects in fabric datasets generated during production with high accuracy and lower computational costs is required. This study uses an indigenous dataset directly sourced from Chenab Textiles, providing authentic and diverse images representative of actual manufacturing conditions. The dataset is used to train a computationally faster but lighter state-of-the-art network, i.e., YOLOv8. For comparison, YOLOv5 and MobileNetV2-SSD FPN-Lite models are also trained on the same dataset. YOLOv8n achieved the highest performance, with a mAP of 84.8%, precision of 0.818, and recall of 0.839 across seven different defect classes. [ABSTRACT FROM AUTHOR]

Audio classification using deep learning models, which is essential for applications like voice assistants and music analysis, faces challenges when deployed on edge devices due to their limited computational resources and memory. Achieving a balance between performance, efficiency, and accuracy is a significant obstacle to optimizing these models for such constrained environments. In this investigation, we evaluate diverse deep learning architectures, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for audio classification tasks on the ESC 50, UrbanSound8k, and Audio Set datasets. Our empirical findings indicate that Mel spectrograms outperform raw audio data, attributing this enhancement to their synergistic alignment with advanced image classification algorithms and their congruence with human auditory perception. To address the constraints of model size, we apply model-compression techniques, notably magnitude pruning, Taylor pruning, and 8-bit quantization. The research demonstrates that a hybrid pruned model achieves a commendable accuracy rate of 89 percent, which, although marginally lower than the 92 percent accuracy of the uncompressed CNN, strikingly illustrates an equilibrium between efficiency and performance. Subsequently, we deploy the optimized model on the Raspberry Pi 4 and NVIDIA Jetson Nano platforms for audio classification tasks. These findings highlight the significant potential of model-compression strategies in enabling effective deep learning applications on resource-limited devices, with minimal compromise on accuracy. [ABSTRACT FROM AUTHOR]

In recent years, the rapid evolution of transportation electrification has been propelled by the widespread adoption of lithium-ion batteries (LIBs) as the primary energy storage solution. The critical need to ensure the safe and efficient operation of these LIBs has positioned battery management systems (BMS) as pivotal components in this landscape. Among the various BMS functions, state and temperature monitoring emerge as paramount for intelligent LIB management. This review focuses on two key aspects of LIB health management: the accurate prediction of the state of health (SOH) and the estimation of remaining useful life (RUL). Achieving precise SOH predictions not only extends the lifespan of LIBs but also offers invaluable insights for optimizing battery usage. Additionally, accurate RUL estimation is essential for efficient battery management and state estimation, especially as the demand for electric vehicles continues to surge. The review highlights the significance of machine learning (ML) techniques in enhancing LIB state predictions while simultaneously reducing computational complexity. By delving into the current state of research in this field, the review aims to elucidate promising future avenues for leveraging ML in the context of LIBs. Notably, it underscores the increasing necessity for advanced RUL prediction techniques and their role in addressing the challenges associated with the burgeoning demand for electric vehicles. This comprehensive review identifies existing challenges and proposes a structured framework to overcome these obstacles, emphasizing the development of machine-learning applications tailored specifically for rechargeable LIBs. The integration of artificial intelligence (AI) technologies in this endeavor is pivotal, as researchers aspire to expedite advancements in battery performance and overcome present limitations associated with LIBs. In adopting a symmetrical approach, ML harmonizes with battery management, contributing significantly to the sustainable progress of transportation electrification. This study provides a concise overview of the literature, offering insights into the current state, future prospects, and challenges in utilizing ML techniques for lithium-ion battery health monitoring. [ABSTRACT FROM AUTHOR]

With the increasing dissemination of the Internet of Things and 5G, mobile edge computing has become a novel scheme to assist terminal devices in executing computation tasks. To elevate the coverage and computation capability of edge computing, a collaborative computation offloading and resource management architecture was proposed in space–air–ground integrated networking (SAGIN). In this manuscript, we established a novel model considering the computation offloading cost constraints of the communication, computing and cache model in the SAGIN. To be specific, the joint optimization problem of collaborative computation offloading and resource management was modeled as a mixed integer nonlinear programming problem. To address this issue, this paper proposed a computation offloading and resource allocation strategy based on deep reinforcement learning (DRL). Differing from traditional methods, DRL does not need a well-established formulation or previous information, and it is capable of revising the strategy adaptively according to the environment. The simulation results demonstrate the proposed approach can achieve the optimal reward values in the case of different terminal device numbers. Furthermore, this manuscript provided the analysis with variant parameters of the proposed approach. [ABSTRACT FROM AUTHOR]

Livestock's live body dimensions are a pivotal indicator of economic output. Manual measurement is labor-intensive and time-consuming, often eliciting stress responses in the livestock. With the advancement of computer technology, the techniques for livestock live body dimension measurement have progressed rapidly, yielding significant research achievements. This paper presents a comprehensive review of the recent advancements in livestock live body dimension measurement, emphasizing the crucial role of computer-vision-based sensors. The discussion covers three main aspects: sensing data acquisition, sensing data processing, and sensing data analysis. The common techniques and measurement procedures in, and the current research status of, live body dimension measurement are introduced, along with a comparative analysis of their respective merits and drawbacks. Livestock data acquisition is the initial phase of live body dimension measurement, where sensors are employed as data collection equipment to obtain information conducive to precise measurements. Subsequently, the acquired data undergo processing, leveraging techniques such as 3D vision technology, computer graphics, image processing, and deep learning to calculate the measurements accurately. Lastly, this paper addresses the existing challenges within the domain of livestock live body dimension measurement in the livestock industry, highlighting the potential contributions of computer-vision-based sensors. Moreover, it predicts the potential development trends in the realm of high-throughput live body dimension measurement techniques for livestock. [ABSTRACT FROM AUTHOR]

Product quality inspection is a crucial element of industrial manufacturing, yet flaws such as blemishes and stains frequently emerge after the product is completed. Most research has utilized detection models and avoided segmenting networks due to the unequal distribution of faulty information. To overcome this challenge, this work presents a rapid segmentation-based technique for surface defect detection. The proposed model is based on a modified U-Net, which introduces a hybrid residual module (SAFM), combining an improved spatial attention mechanism and a feedforward neural network in place of the remaining downsampling layers, except for the first layer of downsampling in the encoder, and applies this residual module to the decoder structure. Dilated convolutions are also incorporated in the decoder to obtain more spatial information about the feature defects and to reduce the gradient vanishing problem of the model. An improved hybrid loss function with Dice and focal loss is introduced to alleviate the small defect segmentation problem. Comparative experiments were conducted on different segmentation-based inspection methods, revealing that the Dice coefficient (DSC) evaluated by the proposed approach is better than previous generic segmentation benchmarks on KolektorSDD, KolektorSDD2, and RSDD datasets, with fewer parameters and FLOPs. Additionally, the detection network displays higher precision in recognizing the characteristics of minor flaws. This paper proposes a practical and effective technique for anomaly segmentation in surface defect identification, delivering considerable improvements over previous methods. [ABSTRACT FROM AUTHOR]

Cloud computing and relevant emerging technologies have presented ordinary methods for processing edge-produced data in a centralized manner. Presently, there is a tendency to offload processing tasks as close to the edge as possible to reduce the costs and network bandwidth used. In this direction, we find efforts that materialize this paradigm by introducing distributed deep learning methods and the so-called Federated Learning (FL). Such distributed architectures are valuable assets in terms of efficiently managing resources and eliciting predictions that can be used for proactive adaptation of distributed applications. In this work, we focus on deep learning local loss functions in multi-cloud environments. We introduce the MulticloudFL system that enhances the forecasting accuracy, in dynamic settings, by applying two new methods that enhance the prediction accuracy in applications and resources monitoring metrics. The proposed algorithm's performance is evaluated via various experiments that confirm the quality and benefits of the MulticloudFL system, as it improves the prediction accuracy on time-series data while reducing the bandwidth requirements and privacy risks during the training process. [ABSTRACT FROM AUTHOR]

The Zhuang ethnic minority in China possesses its own ethnic language and no ethnic script. Cultural exchange and transmission encounter hurdles as the Zhuang rely exclusively on oral communication. An online cloud-based platform was required to enhance linguistic communication. First, a database of 200 h of annotated Zhuang speech was created by collecting standard Zhuang speeches and improving database quality by removing transcription inconsistencies and text normalization. Second, SAformerNet, a more efficient and accurate transformer-based automatic speech recognition (ASR) network, is achieved by inserting additional downsampling modules. Subsequently, a Neural Machine Translation (NMT) model for translating Zhuang into other languages is constructed by fine-tuning the BART model and corpus filtering strategy. Finally, for the network's responsiveness to real-world needs, edge-computing techniques are applied to relieve network bandwidth pressure. An edge-computing private cloud system based on FPGA acceleration is proposed to improve model operation efficiency. Experiments show that the most critical metric of the system, model accuracy, is above 93%, and inference time is reduced by 29%. The computational delay for multi-head self-attention (MHSA) and feed-forward network (FFN) modules has been reduced by 7.1 and 1.9 times, respectively, and terminal response time is accelerated by 20% on average. Generally, the scheme provides a prototype tool for small-scale Zhuang remote natural language tasks in mountainous areas. [ABSTRACT FROM AUTHOR]

The union of Edge Computing (EC) and Artificial Intelligence (AI) has brought forward the Edge AI concept to provide intelligent solutions close to the end-user environment, for privacy preservation, low latency to real-time performance, and resource optimization. Machine Learning (ML), as the most advanced branch of AI in the past few years, has shown encouraging results and applications in the edge environment. Nevertheless, edge-powered ML solutions are more complex to realize due to the joint constraints from both edge computing and AI domains, and the corresponding solutions are expected to be efficient and adapted in technologies such as data processing, model compression, distributed inference, and advanced learning paradigms for Edge ML requirements. Despite the fact that a great deal of the attention garnered by Edge ML is gained in both the academic and industrial communities, we noticed the lack of a complete survey on existing Edge ML technologies to provide a common understanding of this concept. To tackle this, this paper aims at providing a comprehensive taxonomy and a systematic review of Edge ML techniques, focusing on the soft computing aspects of existing paradigms and techniques. We start by identifying the Edge ML requirements driven by the joint constraints. We then extensively survey more than twenty paradigms and techniques along with their representative work, covering two main parts: edge inference, and edge learning. In particular, we analyze how each technique fits into Edge ML by meeting a subset of the identified requirements. We also summarize Edge ML frameworks and open issues to shed light on future directions for Edge ML. [ABSTRACT FROM AUTHOR]

Over the past ten years, breakthroughs in battery technology have dramatically propelled the evolution of electric vehicle (EV) technologies. For EV applications, accurately estimating the state-of-charge (SOC) is critical for ensuring safe operation and prolonging the lifespan of batteries, particularly under complex loading scenarios. Despite progress in this area, modeling and forecasting the evaluation of multiphysics and multiscale electrochemical systems under realistic conditions using first-principles and atomistic calculations remains challenging. This study proposes a solution by designing a specialized Transformer-based network architecture, called Bidirectional Encoder Representations from Transformers for Batteries (BERTtery), which only uses time-resolved battery data (i.e., current, voltage, and temperature) as an input to estimate SOC. To enhance the Transformer model's generalization, it was trained and tested under a wide range of working conditions, including diverse aging conditions (ranging from 100% to 80% of the nominal capacity) and varying temperature windows (from 35 °C to −5 °C). To ensure the model's effectiveness, a rigorous test of its performance was conducted at the pack level, which allows for the translation of cell-level predictions into real-life problems with hundreds of cells in-series conditions possible. The best models achieve a root mean square error (RMSE) of less than 0.5 test error and approximately 0.1% average percentage error (APE), with maximum absolute errors (MAE) of 2% on the test dataset, accurately estimating SOC under dynamic operating and aging conditions with widely varying operational profiles. These results demonstrate the power of the self-attention Transformer-based model to predict the behavior of complex multiphysics and multiscale battery systems. [ABSTRACT FROM AUTHOR]

Connected and autonomous vehicles (CAVs) present exciting opportunities for the improvement of both the mobility of people and the efficiency of transportation systems. The small computers in autonomous vehicles (CAVs) are referred to as electronic control units (ECUs) and are often perceived as being a component of a broader cyber–physical system. Subsystems of ECUs are often networked together via a variety of in-vehicle networks (IVNs) so that data may be exchanged, and the vehicle can operate more efficiently. The purpose of this work is to explore the use of machine learning and deep learning methods in defence against cyber threats to autonomous cars. Our primary emphasis is on identifying erroneous information implanted in the data buses of various automobiles. In order to categorise this type of erroneous data, the gradient boosting method is used, providing a productive illustration of machine learning. To examine the performance of the proposed model, two real datasets, namely the Car-Hacking and UNSE-NB15 datasets, were used. Real automated vehicle network datasets were used in the verification process of the proposed security solution. These datasets included spoofing, flooding and replay attacks, as well as benign packets. The categorical data were transformed into numerical form via pre-processing. Machine learning and deep learning algorithms, namely k-nearest neighbour (KNN) and decision trees, long short-term memory (LSTM), and deep autoencoders, were employed to detect CAN attacks. According to the findings of the experiments, using the decision tree and KNN algorithms as machine learning approaches resulted in accuracy levels of 98.80% and 99%, respectively. On the other hand, the use of LSTM and deep autoencoder algorithms as deep learning approaches resulted in accuracy levels of 96% and 99.98%, respectively. The maximum accuracy was achieved when using the decision tree and deep autoencoder algorithms. Statistical analysis methods were used to analyse the results of the classification algorithms, and the determination coefficient measurement for the deep autoencoder was found to reach a value of R2 = 95%. The performance of all of the models that were built in this way surpassed that of those already in use, with almost perfect levels of accuracy being achieved. The system developed is able to overcome security issues in IVNs. [ABSTRACT FROM AUTHOR]

Internet of things (IoT)-enabled wireless body area network (WBAN) is an emerging technology that combines medical devices, wireless devices, and non-medical devices for healthcare management applications. Speech emotion recognition (SER) is an active research field in the healthcare domain and machine learning. It is a technique that can be used to automatically identify speakers' emotions from their speech. However, the SER system, especially in the healthcare domain, is confronted with a few challenges. For example, low prediction accuracy, high computational complexity, delay in real-time prediction, and how to identify appropriate features from speech. Motivated by these research gaps, we proposed an emotion-aware IoT-enabled WBAN system within the healthcare framework where data processing and long-range data transmissions are performed by an edge AI system for real-time prediction of patients' speech emotions as well as to capture the changes in emotions before and after treatment. Additionally, we investigated the effectiveness of different machine learning and deep learning algorithms in terms of performance classification, feature extraction methods, and normalization methods. We developed a hybrid deep learning model, i.e., convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), and a regularized CNN model. We combined the models with different optimization strategies and regularization techniques to improve the prediction accuracy, reduce generalization error, and reduce the computational complexity of the neural networks in terms of their computational time, power, and space. Different experiments were performed to check the efficiency and effectiveness of the proposed machine learning and deep learning algorithms. The proposed models are compared with a related existing model for evaluation and validation using standard performance metrics such as prediction accuracy, precision, recall, F1 score, confusion matrix, and the differences between the actual and predicted values. The experimental results proved that one of the proposed models outperformed the existing model with an accuracy of about 98%. [ABSTRACT FROM AUTHOR]

For rapidly developing smart manufacturing, Industrial ICT Systems (IICTSs) have become critical to safe and reliable production, and effective monitoring of complex IICTSs in practice is necessary but challenging. Since such monitoring data are organized generally as semi-structural logs, log parsing, the fundamental premise of advanced log analysis, has to be comprehensively addressed. Because of unrealistic assumptions, high maintenance costs, and the incapability of distinguishing homologous logs, existing log parsing methods cannot simultaneously fulfill the requirements of complex IICTSs simultaneously. Focusing on these issues, we present LogParser, a deep learning-based framework for both online and offline parsing of IICTS logs. For performance evaluation, we conduct extensive experiments based on monitoring log sets from 18 different real-world systems. The results demonstrate that LogParser achieves at least a 14.5% higher parsing accuracy than the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This study proposes and develops a secured edge-assisted deep learning (DL)-based automatic COVID-19 detection framework that utilizes the cloud and edge computing assistance as a service with a 5G network and blockchain technologies. The development of artificial intelligence methods through services at the edge plays a significant role in serving many applications in different domains. Recently, some DL approaches have been proposed to successfully detect COVID-19 by analyzing chest X-ray (CXR) images in the cloud and edge computing environments. However, the existing DL methods leverage only local and small training datasets. To overcome these limitations, we employed the edges to perform three tasks. The first task was to collect data from different hospitals and send them to a global cloud to train a DL model on massive datasets. The second task was to integrate all the trained models on the cloud to detect COVID-19 cases automatically. The third task was to retrain the trained model on specific COVID-19 data locally at hospitals to improve and generalize the trained model. A feature-level fusion and reduction were adopted for model performance enhancement. Experimental results on a public CXR dataset demonstrated an improvement against recent related work, achieving the quality-of-service requirements. [ABSTRACT FROM AUTHOR]

As solar energy generation has become more and more important for the economies of numerous countries in the last couple of decades, it is highly important to build accurate models for forecasting the amount of green energy that will be produced. Numerous recurrent deep learning approaches, mainly based on long short-term memory (LSTM), are proposed for dealing with such problems, but the most accurate models may differ from one test case to another with respect to architecture and hyperparameters. In the current study, the use of an LSTM and a bidirectional LSTM (BiLSTM) is proposed for dealing with a data collection that, besides the time series values denoting the solar energy generation, also comprises corresponding information about the weather. The proposed research additionally endows the models with hyperparameter tuning by means of an enhanced version of a recently proposed metaheuristic, the reptile search algorithm (RSA). The output of the proposed tuned recurrent neural network models is compared to the ones of several other state-of-the-art metaheuristic optimization approaches that are applied for the same task, using the same experimental setup, and the obtained results indicate the proposed approach as the better alternative. Moreover, the best recurrent model achieved the best results with R 2 of 0.604, and a normalized MSE value of 0.014, which yields an improvement of around 13% over traditional machine learning models. [ABSTRACT FROM AUTHOR]

The multi-microgrid (MMG) system has attracted more and more attention due to its low carbon emissions and flexibility. This paper proposes a multi-agent reinforcement learning algorithm for real-time energy management of an MMG. In this problem, the MMG is connected to a distribution network (DN). The distribution network operator (DSO) and each microgrid (MG) are modeled as autonomous agents. Each agent makes decisions to suit its interests based on local information. The decision-making problem of multiple agents is modeled as a Markov game and solved by the prioritized multi-agent deep deterministic policy gradient (PMADDPG), where only local observation is required for each agent to make decisions, the centralized training mechanism is applied to learn coordination strategy, and a prioritized experience replay (PER) strategy is adopted to improve learning efficiency. The proposed method can deal with the non-stationary problems in the process of a multi-agent game with partial observable information. In the execution stage, all trained agents are deployed in a distributed manner and make decisions in real time. Simulation results show that according to the proposed method, the training process of a multi-agent game is accelerated, and multiple agents can make optimal decisions only by local information. [ABSTRACT FROM AUTHOR]

Self-driving cars and autonomous vehicles are revolutionizing the automotive sector, shaping the future of mobility altogether. Although the integration of novel technologies such as Artificial Intelligence (AI) and Cloud/Edge computing provides golden opportunities to improve autonomous driving applications, there is the need to modernize accordingly the whole prototyping and deployment cycle of AI components. This paper proposes a novel framework for developing so-called AI Inference Engines for autonomous driving applications based on deep learning modules, where training tasks are deployed elastically over both Cloud and Edge resources, with the purpose of reducing the required network bandwidth, as well as mitigating privacy issues. Based on our proposed data driven V-Model, we introduce a simple yet elegant solution for the AI components development cycle, where prototyping takes place in the cloud according to the Software-in-the-Loop (SiL) paradigm, while deployment and evaluation on the target ECUs (Electronic Control Units) is performed as Hardware-in-the-Loop (HiL) testing. The effectiveness of the proposed framework is demonstrated using two real-world use-cases of AI inference engines for autonomous vehicles, that is environment perception and most probable path prediction. [ABSTRACT FROM AUTHOR]

The number of electric vehicles (EVs) is increasingly growing day by day and the charging infrastructure for covering this growing number of EVs should be developed. The construction of charging stations is one of the main solutions for supporting EVs while it costs huge investments for installation. Thus, this is not financially logical to invest in charging stations in remote areas with lower demands. An alternative way of constructing charging stations is to provide a peer-to-peer (P2P) energy exchange system in order to support out-of-charge EVs. In this paper, a private cloud-edge emergency energy trading framework is proposed to facilitate energy exchange among consumers and providers. Furthermore, a bidding system is suggested to encourage EVs with extra charges to exchange their energy. Moreover, a matching strategy for pairing consumers and providers is suggested in this paper that considers the benefit of both consumers and providers. In the proposed matching system, a measurement strategy is also suggested for considering the effect of the reliability and punctuality of the providers. To develop the accuracy and efficiency of the proposed framework, employing deep learning methods is also suggested in different layers of the framework. The performance of the proposed framework is evaluated on several case studies in the presence of EVs with realistic features to prove its efficiency, feasibility, and scalability. [ABSTRACT FROM AUTHOR]

Given its advantages in low latency, fast response, context-aware services, mobility, and privacy preservation, edge computing has emerged as the key support for intelligent applications and 5G/6G Internet of things (IoT) networks. This technology extends the cloud by providing intermediate services at the edge of the network and improving the quality of service for latency-sensitive applications. Many AI-based solutions with machine learning, deep learning, and swarm intelligence have exhibited the high potential to perform intelligent cognitive sensing, intelligent network management, big data analytics, and security enhancement for edge-based smart applications. Despite its many benefits, there are still concerns about the required capabilities of intelligent edge computing to deal with the computational complexity of machine learning techniques for big IoT data analytics. Resource constraints of edge computing, distributed computing, efficient orchestration, and synchronization of resources are all factors that require attention for quality of service improvement and cost-effective development of edge-based smart applications. In this context, this paper aims to explore the confluence of AI and edge in many application domains in order to leverage the potential of the existing research around these factors and identify new perspectives. The confluence of edge computing and AI improves the quality of user experience in emergency situations, such as in the Internet of vehicles, where critical inaccuracies or delays can lead to damage and accidents. These are the same factors that most studies have used to evaluate the success of an edge-based application. In this review, we first provide an in-depth analysis of the state of the art of AI in edge-based applications with a focus on eight application areas: smart agriculture, smart environment, smart grid, smart healthcare, smart industry, smart education, smart transportation, and security and privacy. Then, we present a qualitative comparison that emphasizes the main objective of the confluence, the roles and the use of artificial intelligence at the network edge, and the key enabling technologies for edge analytics. Then, open challenges, future research directions, and perspectives are identified and discussed. Finally, some conclusions are drawn. [ABSTRACT FROM AUTHOR]

An effective energy oversight represents a major concern throughout the world, and the problem has become even more stringent recently. The prediction of energy load and consumption depends on various factors such as temperature, plugged load, etc. The machine learning and deep learning (DL) approaches developed in the last decade provide a very high level of accuracy for various types of applications, including time-series forecasting. Accordingly, the number of prediction models for this task is continuously growing. The current study does not only overview the most recent and relevant DL for energy supply and demand, but it also emphasizes the fact that not many recent methods use parameter tuning for enhancing the results. To fill the abovementioned gap, in the research conducted for the purpose of this manuscript, a canonical and straightforward long short-term memory (LSTM) DL model for electricity load is developed and tuned for multivariate time-series forecasting. One open dataset from Europe is used as a benchmark, and the performance of LSTM models for a one-step-ahead prediction is evaluated. Reported results can be used as a benchmark for hybrid LSTM-optimization approaches for multivariate energy time-series forecasting in power systems. The current work highlights that parameter tuning leads to better results when using metaheuristics for this purpose in all cases: while grid search achieves a coefficient of determination ( R 2 ) of 0.9136, the metaheuristic that led to the worst result is still notably better with the corresponding score of 0.9515. [ABSTRACT FROM AUTHOR]

Huge low earth orbit (LEO) satellite networks can achieve global coverage with low latency. In addition, mobile edge computing (MEC) servers can be mounted on LEO satellites to provide computing offloading services for users in remote areas. A multi-user multi-task system model is modeled and the problem of user's offloading decisions and bandwidth allocation is formulated as a mixed integer programming problem to minimize the system utility function expressed as the weighted sum of the system energy consumption and delay. However, it cannot be effectively solved by general optimizations. Thus, a deep learning-based offloading algorithm for LEO satellite edge computing networks is proposed to generate offloading decisions through multiple parallel deep neural networks (DNNs) and store the newly generated optimal offloading decisions in memory to improve all DNNs to obtain near-optimal offloading decisions. Moreover, the optimal bandwidth allocation scheme of the system is theoretically derived for the user's bandwidth allocation problem. The simulation results show that the proposed algorithm can achieve a good convergence effect within a small number of training steps, and obtain the optimal system utility function values compared with the comparative algorithms under different system parameters, and the time cost of the system and DNNs is very satisfactory. [ABSTRACT FROM AUTHOR]

Recurrent neural networks (RNNs) are widely used to process sequence-related tasks such as natural language processing. Edge cloud computing systems are in an asymmetric structure, where task managers allocate tasks to the asymmetric edge and cloud computing systems based on computation requirements. In such a computing system, cloud servers have no energy limitations, since they have unlimited energy resources. Edge computing systems, however, are resource-constrained, and the energy consumption is thus expensive, which requires an energy-efficient method for RNN job processing. In this paper, we propose a low-overhead, energy-aware runtime manager to process tasks in edge cloud computing. The RNN task latency is defined as the quality of service (QoS) requirement. Based on the QoS requirements, the runtime manager dynamically assigns RNN inference tasks to edge and cloud computing systems and performs energy optimization on edge systems using dynamic voltage and frequency scaling (DVFS) techniques. Experimental results on a real edge cloud system indicate that in edge systems, our method can reduce the energy up to 45% compared with the state-of-the-art approach. [ABSTRACT FROM AUTHOR]

Intelligent fault diagnosis for a single wind turbine is hindered by the lack of sufficient useful data, while multi-turbines have various faults, resulting in complex distributions. Collaborative intelligence can better solve these problems. Therefore, a peer-to-peer network is constructed with one node corresponding to one wind turbine in a cluster. Each node is equivalent and functional replicable with a new federated transfer learning method, including model transfer based on multi-task learning and model fusion based on dynamic adaptive weight adjustment. Models with convolutional neural networks are trained locally and transmitted among the nodes. A solution for the processes of data management, information transmission, model transfer and fusion is provided. Experiments are conducted on a fault signal testing bed and bearing dataset of Case Western Reserve University. The results show the excellent performance of the method for fault diagnosis of a gearbox in a wind turbine cluster. [ABSTRACT FROM AUTHOR]

As deep learning technology paves its way, real-world applications that make use of it become popular these days. Edge computing architecture is one of the service architectures to realize the deep learning based service, which makes use of the resources near the data source or client. In Edge computing architecture it becomes important to manage resource usage, and there is research on optimization of deep learning, such as pruning or binarization, which makes deep learning models more lightweight, along with the research for the efficient distribution of workloads on cloud or edge resources. Those are to reduce the workload on edge resources. In this paper, a usage optimization method with batch and model management is proposed. The proposed method is to increase the utilization of GPU resource by modifying the batch size of the input of an inference application. To this end, the inference pipelines are identified to see how the different kinds of resources are used, and then the effect of batch inference on GPU is measured. The proposed method consists of a few modules, including a tool for batch size management which is able to change a batch size with respect to the available resources, and another one for model management which supports on-the-fly update of a model. The proposed methods are implemented on a real-time video analysis application and deployed in the Kubernetes cluster as a Docker container. The result shows that the proposed method can optimize the usage of edge resources for real-time video analysis deep learning applications. [ABSTRACT FROM AUTHOR]

Model compression makes it possible to deploy face detection models on devices with limited computing resources. Edge–cloud collaborative inference, as a new paradigm of neural network inference, can significantly reduce neural network inference latency. Inspired by these two techniques, this paper adopts a two-step acceleration strategy for the CenterNet model. Firstly, the model pruning method is used to prune the convolutional layer and the deconvolutional layer to obtain a preliminary acceleration effect. Secondly, the neural network is segmented by the optimizer to make full use of the computing resources on the edge and the cloud to further accelerate the inference of the neural network. In the first strategy, we achieve a 62.12% reduction in inference latency compared to the state-of-the-art object detection model Blazeface. Additionally, with a two-step speedup strategy, our method is only 26.5% of the baseline when the bandwidth is 500 kbps. [ABSTRACT FROM AUTHOR]

Recent advances in sensor technology are expected to lead to a greater use of wireless sensor networks (WSNs) in industry, logistics, healthcare, etc. On the other hand, advances in artificial intelligence (AI), machine learning (ML), and deep learning (DL) are becoming dominant solutions for processing large amounts of data from edge-synthesized heterogeneous sensors and drawing accurate conclusions with better understanding of the situation. Integration of the two areas WSN and AI has resulted in more accurate measurements, context-aware analysis and prediction useful for smart sensing applications. In this paper, a comprehensive overview of the latest developments in context-aware intelligent systems using sensor technology is provided. In addition, it also discusses the areas in which they are used, related challenges, motivations for adopting AI solutions, focusing on edge computing, i.e., sensor and AI techniques, along with analysis of existing research gaps. Another contribution of this study is the use of a semantic-aware approach to extract survey-relevant subjects. The latter specifically identifies eleven main research topics supported by the articles included in the work. These are analyzed from various angles to answer five main research questions. Finally, potential future research directions are also discussed. [ABSTRACT FROM AUTHOR]

Along with the fourth industrial revolution, smart factories are receiving a great deal of attention. Large volumes of real-time data that are generated at high rates, especially in industries, are becoming increasingly important. Accordingly, the Industrial Internet of Things (IIoT), which connects, controls, and communicates with heterogeneous devices, is important to industrial sites and is now indispensable. To ensure the fairness and quality of the IIoT with limited network resources, the network connection of the IIoT needs to be constructed more intelligently. Many studies are being conducted on the efficient use of the resources that are imposed on IIoT devices. Therefore, in this paper, we propose a collaboration optimization method for heterogeneous devices that is based on cloud–fog–edge architecture. First, this paper proposes a knowledge distillation-based algorithm that can collaborate on cloud–fog–edge computing on the basis of distributed control. Second, to compensate for the shortcomings of knowledge distillation, we propose a framework for combining a soft-label-based alarm level. Finally, the method that is proposed in this paper was verified through several experiments, and it is shown that this method can effectively shorten the response time and solve the problems of existing IIoT networks, and that it can be efficiently applied to heterogeneous devices. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) connects massive smart devices to collect big data and carry out the monitoring and control of numerous things in cyber-physical systems (CPS). By leveraging machine learning (ML) and deep learning (DL) techniques to analyze the collected data, physical systems can be monitored and controlled effectively. Along with the development of IoT and data analysis technologies, a number of CPS (smart grid, smart transportation, smart manufacturing, smart cities, etc.) adopt IoT and data analysis technologies to improve their performance and operations. Nonetheless, directly manipulating or updating the real system has inherent risks. Thus, creating a digital clone of a real physical system, denoted as a Digital Twin (DT), is a viable strategy. Generally speaking, a DT is a data-driven software and hardware emulation platform, which is a cyber replica of physical systems. Meanwhile, a DT describes a specific physical system and tends to achieve the functions and use cases of physical systems. Since DT is a complex digital system, finding a way to effectively represent a variety of things in timely and efficient manner poses numerous challenges to the networking, computing, and data analytics for IoT. Furthermore, the design of a DT for IoT systems must consider numerous exceptional requirements (e.g., latency, reliability, safety, scalability, security, and privacy). To address such challenges, the thoughtful design of DTs offers opportunities for novel and interdisciplinary research efforts. To address the aforementioned problems and issues, in this paper, we first review the architectures of DTs, data representation, and communication protocols. We then review existing efforts on applying DT into IoT data-driven smart systems, including the smart grid, smart transportation, smart manufacturing, and smart cities. Further, we summarize the existing challenges from CPS, data science, optimization, and security and privacy perspectives. Finally, we outline possible future research directions from the perspectives of performance, new DT-driven services, model and learning, and security and privacy. [ABSTRACT FROM AUTHOR]

In IoT (Internet of Things) edge computing, task offloading can lead to additional transmission delays and transmission energy consumption. To reduce the cost of resources required for task offloading and improve the utilization of server resources, in this paper, we model the task offloading problem as a joint decision making problem for cost minimization, which integrates the processing latency, processing energy consumption, and the task throw rate of latency-sensitive tasks. The Online Predictive Offloading (OPO) algorithm based on Deep Reinforcement Learning (DRL) and Long Short-Term Memory (LSTM) networks is proposed to solve the above task offloading decision problem. In the training phase of the model, this algorithm predicts the load of the edge server in real-time with the LSTM algorithm, which effectively improves the convergence accuracy and convergence speed of the DRL algorithm in the offloading process. In the testing phase, the LSTM network is used to predict the characteristics of the next task, and then the computational resources are allocated for the task in advance by the DRL decision model, thus further reducing the response delay of the task and enhancing the offloading performance of the system. The experimental evaluation shows that this algorithm can effectively reduce the average latency by 6.25%, the offloading cost by 25.6%, and the task throw rate by 31.7%. [ABSTRACT FROM AUTHOR]

The recent development of smart devices has lead to an explosion in data generation and heterogeneity. Hence, current networks should evolve to become more intelligent, efficient, and most importantly, scalable in order to deal with the evolution of network traffic. In recent years, network softwarization has drawn significant attention from both industry and academia, as it is essential for the flexible control of networks. At the same time, machine learning (ML) and especially deep learning (DL) methods have also been deployed to solve complex problems without explicit programming. These methods can model and learn network traffic behavior using training data/environments. The research community has advocated the application of ML/DL in softwarized environments for network traffic management, including traffic classification, prediction, and anomaly detection. In this paper, we survey the state of the art on these topics. We start by presenting a comprehensive background beginning from conventional ML algorithms and DL and follow this with a focus on different dimensionality reduction techniques. Afterward, we present the study of ML/DL applications in sofwarized environments. Finally, we highlight the issues and challenges that should be considered. [ABSTRACT FROM AUTHOR]

The Industrial Internet of Things (IIoT) refers to the use of smart sensors, actuators, fast communication protocols, and efficient cybersecurity mechanisms to improve industrial processes and applications. In large industrial networks, smart devices generate large amounts of data, and thus IIoT frameworks require intelligent, robust techniques for big data analysis. Artificial intelligence (AI) and deep learning (DL) techniques produce promising results in IIoT networks due to their intelligent learning and processing capabilities. This survey article assesses the potential of DL in IIoT applications and presents a brief architecture of IIoT with key enabling technologies. Several well-known DL algorithms are then discussed along with their theoretical backgrounds and several software and hardware frameworks for DL implementations. Potential deployments of DL techniques in IIoT applications are briefly discussed. Finally, this survey highlights significant challenges and future directions for future research endeavors. [ABSTRACT FROM AUTHOR]

Manufacturers are eager to replace the human inspector with automatic inspection systems to improve the competitive advantage by means of quality. However, some manufacturers have failed to apply the traditional vision system because of constraints in data acquisition and feature extraction. In this paper, we propose an inspection system based on deep learning for a tampon applicator producer that uses the applicator's structural characteristics for data acquisition and uses state-of-the-art models for object detection and instance segmentation, YOLOv4 and YOLACT for feature extraction, respectively. During the on-site trial test, we experienced some False-Positive (FP) cases and found a possible Type I error. We used a data-centric approach to solve the problem by using two different data pre-processing methods, the Background Removal (BR) and Contrast Limited Adaptive Histogram Equalization (CLAHE). We have experimented with analyzing the effect of the methods on the inspection with the self-created dataset. We found that CLAHE increased Recall by 0.1 at the image level, and both CLAHE and BR improved Precision by 0.04–0.06 at the bounding box level. These results support that the data-centric approach might improve the detection rate. However, the data pre-processing techniques deteriorated the metrics used to measure the overall performance, such as F1-score and Average Precision (AP), even though we empirically confirmed that the malfunctions improved. With the detailed analysis of the result, we have found some cases that revealed the ambiguity of the decisions caused by the inconsistency in data annotation. Our research alerts AI practitioners that validating the model based only on the metrics may lead to a wrong conclusion. [ABSTRACT FROM AUTHOR]

Digital twin (DT) and artificial intelligence (AI) technologies have grown rapidly in recent years and are considered by both academia and industry to be key enablers for Industry 4.0. As a digital replica of a physical entity, the basis of DT is the infrastructure and data, the core is the algorithm and model, and the application is the software and service. The grounding of DT and AI in industrial sectors is even more dependent on the systematic and in-depth integration of domain-specific expertise. This survey comprehensively reviews over 300 manuscripts on AI-driven DT technologies of Industry 4.0 used over the past five years and summarizes their general developments and the current state of AI-integration in the fields of smart manufacturing and advanced robotics. These cover conventional sophisticated metal machining and industrial automation as well as emerging techniques, such as 3D printing and human–robot interaction/cooperation. Furthermore, advantages of AI-driven DTs in the context of sustainable development are elaborated. Practical challenges and development prospects of AI-driven DTs are discussed with a respective focus on different levels. A route for AI-integration in multiscale/fidelity DTs with multiscale/fidelity data sources in Industry 4.0 is outlined. [ABSTRACT FROM AUTHOR]

This paper reviews automated visual-based defect detection approaches applicable to various materials, such as metals, ceramics and textiles. In the first part of the paper, we present a general taxonomy of the different defects that fall in two classes: visible (e.g., scratches, shape error, etc.) and palpable (e.g., crack, bump, etc.) defects. Then, we describe artificial visual processing techniques that are aimed at understanding of the captured scenery in a mathematical/logical way. We continue with a survey of textural defect detection based on statistical, structural and other approaches. Finally, we report the state of the art for approaching the detection and classification of defects through supervised and non-supervised classifiers and deep learning. [ABSTRACT FROM AUTHOR]