Skin cancer can be fatal if it is found to be malignant. Modern diagnosis of skin cancer heavily relies on visual inspection through clinical screening, dermoscopy, or histopathological examinations. However, due to similarity among cancer types, it is usually challenging to identify the type of skin cancer, especially at its early stages. Deep learning techniques have been developed over the last few years and have achieved success in helping to improve the accuracy of diagnosis and classification. However, the latest deep learning algorithms still do not provide ideal classification accuracy. To further improve the performance of classification accuracy, this paper presents a novel method of classifying skin cancer in clinical skin images. The method consists of four blocks. First, class rebalancing is applied to the images of seven skin cancer types for better classification performance. Second, an image is preprocessed by being split into patches of the same size and then flattened into a series of tokens. Third, a transformer encoder is used to process the flattened patches. The transformer encoder consists of N identical layers with each layer containing two sublayers. Sublayer one is a multihead self-attention unit, and sublayer two is a fully connected feed-forward network unit. For each of the two sublayers, a normalization operation is applied to its input, and a residual connection of its input and its output is calculated. Finally, a classification block is implemented after the transformer encoder. The block consists of a flattened layer and a dense layer with batch normalization. Transfer learning is implemented to build the whole network, where the ImageNet dataset is used to pretrain the network and the HAM10000 dataset is used to fine-tune the network. Experiments have shown that the method has achieved a classification accuracy of 94.1%, outperforming the current state-of-the-art model IRv2 with soft attention on the same training and testing datasets. On the Edinburgh DERMOFIT dataset also, the method has better performance compared with baseline models.

Due to increasing demands for ensuring the safety and reliability of a system, fault detection (FD) has received considerable attention in modern industries to monitor their machines. Bulk materials are transported worldwide using belt conveyors as an essential transport system. The majority of conveyor components are monitored continuously to ensure their reliability, but idlers remain a challenge to monitor due to the large number of idlers (rollers) distributed throughout the working environment. These idlers are prone to external noises or disturbances that cause a failure in the underlying system operations. The research community has begun using machine learning (ML) to detect idler’s defects to assist industries in responding to failures on time. Vibration and acoustic measurements are commonly employed to monitor the condition of idlers. However, there has been no comprehensive review of FD for belt conveyor idlers. This paper presents a recent review of acoustic and vibration signal-based fault detection for belt conveyor idlers using ML models. It also discusses major steps in the approaches, such as data collection, signal processing, feature extraction and selection, and ML model construction. Additionally, the paper provides an overview of the main components of belt conveyor systems, sources of defects in idlers, and a brief introduction to ML models. Finally, it highlights critical open challenges and provides future research directions.

Early detection of skin cancer from skin lesion images using visual inspection can be challenging. In recent years, research in applying deep learning models to assist in the diagnosis of skin cancer has achieved impressive results. State-of-the-art techniques have shown high accuracy, sensitivity and specificity compared with dermatologists. However, the analysis of dermoscopy images with deep learning models still faces several challenges, including image segmentation, noise filtering and image capture environment inconsistency. After making the introduction to the topic, this paper firstly presents the components of machine learning-based skin cancer diagnosis. It then presents the literature review on the current advance in machine learning approaches for skin cancer classification, which covers both the traditional machine learning approaches and deep learning approaches. The paper also presents the current challenges and future directions for skin cancer classification using machine learning approaches.

Skin cancer is a significant global health concern, with melanoma being the most dangerous form, responsible for the majority of skin cancer-related deaths. Early detection of skin cancer is critical, as it can drastically improve survival rates. While deep learning models have achieved impressive results in skin cancer classification, there remain challenges in accurately distinguishing between benign and malignant lesions. In this study, we introduce a novel multi-scale attention-based performance booster inspired by the Vision Transformer (ViT) architecture, which enhances the accuracy of both ViT and convolutional neural network (CNN) models. By leveraging attention maps to identify discriminative regions within skin lesion images, our method improves the models’ focus on diagnostically relevant areas. Additionally, we employ ensemble learning techniques to combine the outputs of several deep learning models using majority voting. Our skin cancer classifier, consisting of ViT and EfficientNet models, achieved a classification accuracy of 95.05% on the ISIC2018 dataset, outperforming individual models. The results demonstrate the effectiveness of integrating attention-based multi-scale learning and ensemble methods in skin cancer classification.

Idlers are essential to conveyor systems, as well as supporting and guiding belts to ensure production efficiency. Proper idler maintenance prevents failures, reduces downtime, cuts costs, and improves reliability. Most studies on idler fault detection rely on supervised methods, which depend on large labelled datasets for training. However, acquiring such labelled data is often challenging in industrial environments due to the rarity of faults and the labour-intensive nature of the labelling process. To address this, we propose the chroma-augmented semi-supervised anomaly detection (CASSAD) method, designed to perform effectively with limited labelled data. At the core of CASSAD is the one-class SVM (OC-SVM), a model specifically developed for anomaly detection in cases where labelled anomalies are scarce. We also compare CASSAD’s performance with other common models like the local outlier factor (LOF) and isolation forest (iForest), evaluating each with the area under the curve (AUC) to assess their ability to distinguish between normal and anomalous data. CASSAD introduces chroma features, such as chroma energy normalised statistics (CENS), the constant-Q transform (CQT), and the chroma short-time Fourier transform (STFT), enhanced through filtering to capture rich harmonic information from idler sounds. To reduce feature complexity, we utilize the mean and standard deviation (std) across chroma features. The dataset is further augmented using additive white Gaussian noise (AWGN). Testing on an industrial dataset of idler sounds, CASSAD achieved an AUC of 96% and an accuracy of 91%, surpassing a baseline autoencoder and other traditional models. These results demonstrate the model’s robustness in detecting anomalies with minimal dependence on labelled data, offering a practical solution for industries with limited labelled datasets.

Reliable detection of idler faults in belt conveyor systems is essential for minimising unplanned downtime, improving safety, and optimising maintenance. Conventional vibration- and acoustic-based approaches, which use fixed sensors or handheld microphones, often fail under non-stationary, noisy, or spatially variable conditions. To address these challenges, we propose a robust two-phase transfer learning framework leveraging acoustic drone data for cross-domain, non-invasive idler fault diagnosis. The framework combines pretrained Convolutional Neural Network (CNN) backbones, including ResNet-18, DenseNet-121, ShuffleNet-V2, and EfficientNet-B0, with Transformer encoders to capture local spectral and long-range temporal dependencies. Both Mel-spectrograms and MFCCs are employed to extract discriminative spectral-temporal fault features. A Mean-Covariance Alignment (MCA) mechanism is introduced to facilitate domain-invariant feature learning through two sequential phases: (i) source-domain pretraining on handheld recordings to establish robust acoustic representation and (ii) target-domain fine-tuning on drone data using progressive layer unfreezing and discriminative learning rates. Extensive experiments validate the effectiveness of the proposed framework. In Phase one, the ResNet-18–Transformer hybrid achieved a cross-fold mean accuracy on, with a 95% confidence interval ranging from 96.4% to 97.6%. handheld data, Ensemble learning further improved performance to 98.0%, indicating robust feature learning and effective transferability. In phase two, MCA outperformed the cross-entropy (CE) baseline when fully fine-tuning Mel-spectrogram features. The accuracy went from 84.7% (CE) to 86.0%, and the F1-score went from 83.4% to 85.6%. This was better than other domain adaptation methods like MMD, CMD, CORAL, and SWD. While MFCC features achieved higher baseline performance, they generally experienced drops under MCA adaptation. Across adaptation strategies and fine-tuning setups, Mel-spectrogram features demonstrated greater robustness, often maintaining or slightly improving performance, whereas MFCCs were more sensitive to domain adaptation. An ablation study further confirmed that aligning both first- and second-order statistics is crucial for achieving consistent improvements. These results indicate that MCA enhances CNN-Transformer transferability and highlight the reliability of Mel-spectrogram features for handheld-to-drone fault diagnosis in real industrial environments.