Breast cancer (BC) is closely linked with the maximum mortality rate for cancer detection across the globe and has become a predominant public health issue. Earlier detection might increase the possibility of survival and successful treatment. However, it is a time-consuming and very challenging task that depends on the diagnostician’s experience. For patients and their prognosis, it is essential that BC cancer can be automatically detected by the analysis of histopathological images. Conventional feature extraction method extracts some lower-level features of images, and preceding knowledge is essential for selecting suitable features that could be heavily impacted by human beings. The deep learning (DL) technique extracts higher-level abstract features from an image automatically. Therefore, this study develops a new Ensemble Learning with Symbiotic Organism Search Optimization Algorithm for Breast Cancer Classification (ELSOSA-BCC) technique on Histopathological Images. In the ELSOSA-BCC technique, the noise is removed using Gabor filtering (GF). In addition, the ELSOSA-BCC technique employs the EfficientNet-B0 model for feature extraction and optimal hyperparameter tuning using the SOS algorithm. Finally, the ensemble learning-based classification process is performed by three classifiers namely deep stacked autoencoder (DSAE), kernel extreme learning machine (KELM), and bidirectional long short-term memory (BiLSTM). In this study, ELSOSA-BCC simulation values are tested on a medical dataset. ELSOSA-BCC has been shown to perform better than other models in the experimental results.

This paper highlights a communal fault detection and isolation framework integrating a convolutional neural network (CNN) with a finite-state machine (FSM). The proposed concepts ensure state-based controlled discriminate pattern recognition and enable the diagnosis of different anomalies in the mobile robot in a multi-robot environment. The framework processes the time-series sensor data through the convolution layer upon experiencing different types of fault and governs different states based on fault diagnosis and recovery. The proposed concept has been validated using a Python 3.11 and Webot environment featuring the shrimp robot in a multi-robot arena. The model obtained an accuracy of 97% in identifying and classifying faults, enabling automated recovery of faulty robots in the multi-robot environment. Experiments conducted on different simulators demonstrate that effective fault management can be achieved with low training loss.