Search

Edge computing, artificial intelligence (AI), and machine learning (ML) concepts have become increasingly prevalent in Internet of Things (IoT) applications. As the number of IoT devices continues to grow, relying solely on cloud computing for real-time data processing and analysis is proving to be more challenging. The synergy between edge computing and AI is particularly intriguing due to AI's reliance on rapid data processing, a capability facilitated by edge computing. Edge AI represents a significant paradigm shift, leveraging AI within edge computing frameworks to reduce reliance on internet connections and mitigate data latency issues. This approach accelerates data processing, supporting use cases that demand real-time inference. Additionally, as cloud storage costs continue to rise, the feasibility of streaming and storing large volumes of data comes into question. Edge AI offers a compelling solution by performing big data analytics closer to the end device where edge computing is deployed. This paper presents a systematic literature review (SLR) of 85 articles published between 2018 and 2023 within Edge AI. The study provides a comprehensive examination of the analysis of measurement environments and assesses factors applied to Edge AI for big data. It offers taxonomies specific to Edge AI within the big data domain, presents case studies, and outlines the challenges and open issues inherent in Edge AI for big data. [ABSTRACT FROM AUTHOR]

Today's factories are considered as smart ecosystems with humans, machines and devices interacting with each other for efficient manufacturing of products. Industry 4.0 is a suite of enabler technologies for such smart ecosystems that allow transformation of industrial processes. When implemented, Industry 4.0 technologies have a huge impact on efficiency, productivity and profitability of businesses. The adoption and implementation of Industry 4.0, however, require to overcome a number of practical challenges, in most cases, due to the lack of modernisation and automation in place with traditional manufacturers. This paper presents a first of its kind case study for moving a traditional food manufacturer, still using the machinery more than one hundred years old, a common occurrence for small- and medium-sized businesses, to adopt the Industry 4.0 technologies. The paper reports the challenges we have encountered during the transformation process and in the development stage. The paper also presents a smart production control system that we have developed by utilising AI, machine learning, Internet of things, big data analytics, cyber-physical systems and cloud computing technologies. The system provides novel data collection, information extraction and intelligent monitoring services, enabling improved efficiency and consistency as well as reduced operational cost. The platform has been developed in real-world settings offered by an Innovate UK-funded project and has been integrated into the company's existing production facilities. In this way, the company has not been required to replace old machinery outright, but rather adapted the existing machinery to an entirely new way of operating. The proposed approach and the lessons outlined can benefit similar food manufacturing industries and other SME industries. [ABSTRACT FROM AUTHOR]

The analysis on economic data based on time series takes an important position in the field of analysis on time-series data and is also an important task of the field of big data and artificial intelligence. Traditional time-series analysis method is of relatively weak competence in dealing with multi-series analysis. In this research, based on the problem associated with the analysis on time-series economic data, efficient handling method and model are put forward in the face of multi-series analysis task. Also, combined with the association rules, trend correlation and self-trend correlation among multiple series, a trend and correlation deep neural network model (TC-DNM) is established and then tested and verified by using three kinds of economic datasets with representativeness based on the trend analysis task handed by multi-series analysis. The results show that the model proposed in this research is effective than a number of baseline models, can be employed to achieve precision–recall balance and also possesses strong reusability. The two correlation models and joint models in this paper are of peculiarity and innovativeness. [ABSTRACT FROM AUTHOR]

A novel data representation method of convolutional neural network (CNN) is proposed in this paper to represent data of different modalities. We learn a CNN model for the data of each modality to map the data of different modalities to a common space and regularize the new representations in the common space by a cross-model relevance matrix. We further impose that the class label of data points can also be predicted from the CNN representations in the common space. The learning problem is modeled as a minimization problem, which is solved by an augmented Lagrange method with updating rules of Alternating direction method of multipliers. The experiments over benchmark of sequence data of multiple modalities show its advantage. [ABSTRACT FROM AUTHOR]

Many biclustering algorithms and bicluster criteria have been proposed in analyzing the gene expression data. However, there are no clues about the choice of a specific biclustering algorithm, which make ensemble biclustering method receive much attention for aggregating the advantage of various biclustering algorithms. Although the method of co-association consensus (COAC) is a landmark of ensemble biclustering, the effectiveness and efficiency are the worst in state-of-the-art methods. In this paper, to improve COAC, we propose spectral ensemble biclustering (SEB) in which an novel method for generating a set of basic biclusters is proposed for generating the basic biclusters with better quality as well as higher diversity and an new consensus method is also adopted for combing the above basic biclusters. In SEB, spectral clustering is directly applied to the co-association matrix and equivalently transformed into the weighted k-means. Experiments on six gene expression data demonstrate that the effectiveness, efficiency and scalability of SEB are the best compared with existing ensemble methods in terms of the biological significance and runtime. [ABSTRACT FROM AUTHOR]

Prediction of time series data is of relevance for many industrial applications. The prediction can be made in one-step and multi-step ahead. For predictive maintenance, multi-step-ahead prediction is of interest for projecting the evolution of the future conditions of the equipment of interest, computing the remaining useful life and taking corresponding maintenance decisions. Recursive prediction is one of the popular strategies for multi-step-ahead prediction. SVM is a popular data-driven approach that has been used for recursive multi-step-ahead prediction. Tuning the hyperparameters in SVM during the training process is challenging, and normally the hyperparameters are tuned by solving an optimization problem. This paper analyses the possible objectives of the optimization for tuning hyperparameters. Through experiments on one synthetic dataset and two real time series data, related to the prediction of wind speed in a region and leakage from the reactor coolant pump in a nuclear power plant, a bi-objective optimization combining mean absolute derivatives and accuracy on all prediction steps is shown to be the best choice for tuning SVM hyperparameters for recursive multi-step-ahead prediction. [ABSTRACT FROM AUTHOR]