The latest developments in the smartphone-based skin cancer diagnosis application allow simple ways for portable melanoma risk assessment and diagnosis for early skin cancer detection. Due to the trade-off problem (time complexity and error rate) on using a smartphone to run a machine learning algorithm for image analysis, most of the skin cancer diagnosis apps execute the image analysis on the server. In this study, we investigate the performance of skin cancer images detection and classification on android devices using the MobileNet v2 deep learning model. We compare the performance of several aspects; object detection and classification method, computer and android based image analysis, image acquisition method, and setting parameter. Skin cancer actinic Keratosis and Melanoma are used to test the performance of the proposed method. Accuracy, sensitivity, specificity, and running time of the testing methods are used for the measurement. Based on the experiment results, the best parameter for the MobileNet v2 model on android using images from the smartphone camera produces 95% accuracy for object detection and 70% accuracy for classification. The performance of the android app for object detection and classification model was feasible for the skin cancer analysis. Android-based image analysis remains within the threshold of computing time that denotes convenience for the user and has the same performance accuracy with the computer for the high-quality images. These findings motivated the development of disease detection processing on android using a smartphone camera, which aims to achieve real-time detection and classification with high accuracy.

Realizing an effective earthquake early warning system (EEWS) in the case of extensive regions and noisy signals is challenging, particularly in East Java, Indonesia. This letter proposes the rapid detection of the p-wave arrival and determination of the earthquake’s hypocenter and magnitude using deep learning. The Ncheck algorithm is used for noise handling for picking the p-arrival on a multistation waveform as a form of picking target window prediction (PTWP). Then, multitarget regression (MTR) with a hard-shared orthogonal optimization model is proposed for earthquake parameter determination. The data sets used contained data of earthquakes recorded at three stations from the Indonesian seismic network in East Java; 2009–2017 data were used for training and validation, and 2019 data were used for real-time testing. The results show that the PTWP for picking p-arrival has a mean absolute error (MAE) of 0.12 s, and the MTR for earthquake magnitude, longitude, latitude, depth, and origin time detection shows MAEs of 0.21 M, 9.44, 18.72, 27.81 km, and 2.78 s, respectively.

Cardiac cine magnetic resonance imaging (MRI) is a widely used technique for the noninvasive assessment of cardiac functions. Deep neural networks have achieved considerable progress in overcoming various challenges in cine MRI analysis. However, deep learning models cannot be used for classification because limited cine MRI data are available. To overcome this problem, features from cine image settings are derived by handcrafting and addition of other clinical features to the classical machine learning approach for ensuring the model fits the MRI device settings and image parameters required in the analysis. In this study, a novel method was proposed for classifying heart disease (cardiomyopathy patient groups) using only segmented output maps. In the encoder–decoder network, the fully convolutional EfficientNetB5-UNet was modified to perform the semantic segmentation of the MRI image slice. A two-dimensional thickness algorithm was used to combine the segmentation outputs for the 2D representation of images of the end-diastole (ED) and end-systole (ES) cardiac volumes. The thickness images were subsequently used for classification by using a few-shot model with an adaptive subspace classifier. Model performance was verified by applying the model to the 2017 MICCAI Medical Image Computing and Computer-Assisted Intervention dataset. High segmentation performance was achieved as follows: the average Dice coefficients of segmentation were 96.24% (ED) and 89.92% (ES) for the left ventricle (LV); the values for the right ventricle (RV) were 92.90% (ED) and 86.92% (ES). The values for myocardium were 88.90% (ED) and 90.48% (ES). An accuracy score of 92% was achieved in the classification of various cardiomyopathy groups without clinical features. A novel rapid analysis approach was proposed for heart disease diagnosis, especially for cardiomyopathy conditions using cine MRI based on segmented output maps.

Cancer is still a significant problem for people today because it is one of the biggest causes of death in the world. Based on GLOBOCAN data in 2018, breast cancer accounted for the world’s largest cancer mortality rate in women by 6.6% with total deaths amounting to 626,679 from 2,088,849 cases of cancer in the world. The high mortality rate of breast cancer is caused by the lack of effective early detection of the disease. MicroRNAs play an essential role in regulating cell division cycles, apoptosis, senescence, migration and cell invasion, and metastasis. The expression of microRNA in breast cancer shows a pattern compared to normal breasts, thus indicating its role as a potential diagnostic marker. Cancer classification using microRNA as a feature has been done in previous studies using Neural Network Backpropagation, however without optimization and tuning parameters. In this paper, we investigated the best optimization algorithm and tuning parameter of neural network backpropagation for cancer classification using microRNA feature. The optimization algorithms were Gradient Descent, Momentum, AdaGrad, AdaDelta, RMSProp, and Adam. The result of the experiment showed that Adam and RMSPop optimizer produced high accuracy which reached 98.536% and 98.54762% accuracy.

In the quest to understand urban ecosystems, traditional evaluation techniques often fall short due to incompatible data sources and the absence of comprehensive, real-time data. However, with the recent surge in the availability of crowdsourced data, a dynamic view of urban systems has emerged. Recognizing the value of these data, this study illustrates how these data can bridge gaps in understanding urban interactions. Furthermore, the role of urban planners is crucial in harnessing these data effectively, ensuring that derived insights align with the practical needs of urban development. Employing the Design Science Methodology, the research study presents an assessment model grounded in the principles of the city ecosystem, drawing from the General System Theory for Smart Cities. The model is structured across three dimensions and incorporates twelve indicators. By leveraging crowdsourced data, the study offers invaluable insights for urban planners, researchers, and other professionals. This comprehensive approach holds the potential to revolutionize city sustainability assessments, deepening the grasp of intricate urban ecosystems and paving the way for more resilient future cities.