Computer-aided diagnosis (CAD) helps physicians in tumors’ identification into various biomedical tissues, breast is one. Through the last few years, image classification techniques based on deep learning (DL), have obtained noticeable success in differentiating breast ultrasound images automatically. More researches, concerned with breast cancer detection, are representing the output as a black and white segmented image (mask) or a selected region on the breast ultrasound image which will in role submitted to physicians to help them in making a better diagnosis decision. Our paper represents the second step. In this paper: ten pre-trained Convolutional neural networks (CNNs) classification models (ResNet18, ResNet50, ResNet101, InceptionV3, InceptionResNetV2, GoogleNet, MobilenetV2, SqueezeNet, DenseNet201, and Xception) have been utilized to classify segmented breast ultrasound images by transfer learning (TL). A dataset of 375 breast ultrasound images' masks (ground truths), divided as 125 normal, 125 benign, and 125 malignant, has been utilized in training and validation. A dataset of 255 breast ultrasound images' ground truths (masks), divided as 85 normal, 85 benign, and 85 malignant, has been utilized to evaluate the classification accuracy of each CNN model after TL process. Each CNN model's evaluation (over the 255 breast ultrasound images' masks) has represented different accuracy values evaluated. The best accuracy value was for ResNet50 with an accuracy of 97.25 %. The proposed classification scheme for segmented ultrasound images can be regarded as a step that may help in an automatic breast cancer diagnosis system. The produced trained ten CNNs models in this study (input image size: 128 by 128 by 3) are not in their optimum case but it can be considered as a start to any researcher interests in studying the classification of segmented binary images of breast cancers, the ten produced CNNs models are available to researchers at: https://www.kaggle.com/mohammedtgadallah/ten-cnns-classify-segmented-breast-ultrasound.
The increasing prevalence of Internet of Things devices produces substantial volumes of data, thereby demanding the development of advanced machine learning (ML) models to maintain the data securely. Federated learning (FL) is such an advanced distributed ML paradigm that enables multiple devices or data centers to collaboratively train an ML model without the need to share the raw data. In recent years, it has got considerable interest because of its capability to overcome the challenges of traditional centralized ML models, such as data privacy and scalability. Even though there is such growing interest in FL, there are merely very few resources available in the literature to fundamentally understand and implement the FL concepts. In light of this, the objective of this paper is to provide basic guidance that is essential for beginners to develop FL-based solutions. This paper provides a clear intuition behind the FL, which includes a discussion on different types (horizontal FL, vertical FL, and federated transfer learning) and federated averaging (FedAvg) algorithm. It also highlights various key applications of FL. Finally, the paper emphasizes a few research directions that facilitate the development of FL.
Using artificial intelligence (AI) to anticipate electrical consumption is one of the used applications of this technology. The analysis and training of AI models are done using data related to electricity consumption, including consumption itself, temperatures, working hours, the number of inhabitants, etc. AI models can help to reduce electricity expenses and consumption, which helps in identifying peak use periods and creating more efficient energy plans. Another use of artificial intelligence is to advise users on how to use less energy in a more efficient manner. Based on such insight, this study suggests a hybrid model based on a temporal convolutional network and multilayer perceptron (TCN-MLP), to forecast hourly power consumption. The results show that the recommended model can account for the patterns in the historical data relating to hourly power usage. TCN-MLP hybrid model has proved to be better than competing approaches in the coefficient of determination (R 2 ) and the mean absolute percentage error (MAPE%) metrics.
