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.

This research compares the facial expression recognition accuracy achieved using image features extracted (a) manually through handcrafted methods and (b) automatically through convolutional neural networks (CNNs) from different depths, with and without retraining. The Karolinska Directed Emotional Faces, Japanese Female Facial Expression, and Radboud Faces Database databases have been used, which differ in image number and characteristics. Local binary patterns and histogram of oriented gradients have been selected as handcrafted methods and the features extracted are examined in terms of image and cell size. Five CNNs have been used, including three from the residual architecture of increasing depth, Inception_v3, and EfficientNet-B0. The CNN-based features are extracted from the pre-trained networks from the 25%, 50%, 75%, and 100% of their depths and, after their retraining on the new databases. Each method is also evaluated in terms of calculation time. CNN-based feature extraction has proved to be more efficient since the classification results are superior and the computational time is shorter. The best performance is achieved when the features are extracted from shallower layers of pre-trained CNNs (50% or 75% of their depth), achieving high accuracy results with shorter computational time. CNN retraining is, in principle, beneficial in terms of classification accuracy, mainly for the larger databases by an average of 8%, also increasing the computational time by an average of 70%. Its contribution in terms of classification accuracy is minimal when applied in smaller databases. Finally, the effect of two types of noise on the models is examined, with ResNet50 appearing to be the most robust to noise.

The On-Board Diagnostics II (OBD-II) system, driven by a wide range of embedded sensors, has revolutionized the automotive industry by enabling real-time monitoring of key vehicle parameters such as engine load, vehicle speed, throttle position, and diagnostic trouble codes. Concurrently, recent advancements in machine learning (ML) have further expanded the capabilities of OBD-II applications, unlocking advanced, intelligent, and data-centric functionalities that significantly surpass those of conventional methodologies. This paper presents a comprehensive investigation into ML-based applications that leverage OBD-II sensor data, aiming to enhance sustainability, operational efficiency, safety, and security in modern vehicular systems. To this end, a diverse set of ML approaches is examined, encompassing supervised, unsupervised, reinforcement learning (RL), deep learning (DL), and hybrid models intended to support advanced driving analytics tasks such as fuel optimization, emission control, driver behavior analysis, anomaly detection, cybersecurity, road perception, and driving support. Furthermore, this paper synthesizes recent research contributions and practical implementations, identifies prevailing challenges, and outlines prospective research directions.

The advent of computer networks and the internet has drastically altered the means by which we share information and interact with each other. However, this technological advancement has also created opportunities for malevolent behavior, with individuals exploiting vulnerabilities to gain access to confidential data, obstruct activity, etc. To this end, intrusion detection systems (IDSs) are needed to filter malicious traffic and prevent common attacks. In the past, these systems relied on a fixed set of rules or comparisons with previous attacks. However, with the increased availability of computational power and data, machine learning has emerged as a promising solution for this task. While many systems now use this methodology in real-time for a reactive approach to mitigation, we explore the potential of configuring it as a proactive time series prediction. In this work, we delve into this possibility further. More specifically, we convert a classic IDS dataset to a time series format and use predictive models to forecast forthcoming malign packets. We propose a new architecture combining convolutional neural networks, long short-term memory networks, and attention. The findings indicate that our model performs strongly, exhibiting an F1 score and AUC that are within margins of 1% and 3%, respectively, when compared to conventional real-time detection. Also, our architecture achieves an ∼8% F1 score improvement compared to an LSTM (long short-term memory) model.

Feta cheese is a Greek protected designation of origin (PDO) product that is produced in three main phases: milk collection, cheese preparation and maturation, and product packaging. Each phase must be aligned with quantitative rules, stemming from the legislation framework and best practices. The production complexity, the increased production cost, centralised and monolithic traceability systems, and the lack of a systematic monitoring framework have made dairy products a commodity with increased frequency of food fraud. Given the context of the dairy section in Greece, this study aims to examine (a) whether it is possible to model the end-to-end process of PDO feta cheese considering production rules to develop a trustworthy blockchain-based traceability system (b) how to associate the (‘easy-to-retrieve’, operational) traceability data with the (difficult-to-assess) product characteristics meaningful to the consumer, (c) how to design a technical solution ensuring that information is accessible by the stakeholders and the consumer, while minimising blockchain-related delay, and (d) how to design a graphical user interface and offer tools to consumers so that traceability information is communicated effectively and they can verify it through access to the blockchain. In terms of methods, we analyse and model the process steps, identify measurable, operational parameters and translate the legislative framework into rules. These rules are designed and codified as blockchain smart contracts that ensure the food authenticity and compliance with legislation. The blockchain infrastructure consists of the private Quorum blockchain that is anchored to the public infrastructure of Ethereum. Mechanisms to address scalability in terms of dynamic data volumes, effective data coding, and data verification at the edge as well as relevant limitations are discussed. Consumers are informed about traceability information by using QR codes on food packaging and can verify the data using the blockchain tools and services.