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.

In the process of the decarbonization of energy production, the use of photovoltaic systems (PVS) is an increasing trend. In order to optimize the power generation, the fault detection and identification in PVS is significant. The purpose of this work is the study and implementation of such an algorithm, for the detection as many as faults arising on the DC side of a photovoltaic system. A machine learning technique was chosen. The dataset used to train the algorithm was based on a year’s worth of irradiance and temperature data, as well as data from the PV cell used. The method uses logistic regression with cross validation as a new approach to detect and identify faults in PVS. It is applied to smart PV arrays, that can transmit voltage and current measurements from each PV cell of the array individually. The results are satisfactory since the algorithm can detect the majority of faults that occur on the DC side of a photovoltaic (open-circuit fault, short-circuit fault, mismatch faults). The accuracy of the algorithm (97.11%) is comparable to other methods presented by the literature. Moreover, the computational cost of the proposed method is significantly lower than the methods presented in the literature. In summary, the performance of the implemented algorithm is considered particularly satisfactory and can be easily applied to PVS.

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.

Monitoring and evaluating engineering learners through computer-based laboratory exercises is a difficult task, especially under classroom conditions. A complete diagnosis requires the capability to assess both the competence of the learner to use the scientific software and the understanding of the theoretical principles. This monitoring and evaluation needs to be continuous, unobtrusive and personalized in order to be effective. This study presents the results of the pilot application of an eLearning environment developed specifically with engineering learners in mind. As its name suggests, the Learner Diagnosis, Assistance, and Evaluation System based on Artificial Intelligence (StuDiAsE) is an Open Learning Environment that can perform unattended diagnostic, evaluation and feedback tasks based on both quantitative and qualitative parameters. The base architecture of the system, the user interface and its effect on the performance of postgraduate engineering learners are being presented.