In recent years, deep learning has taken the spotlight in automated medical bioimaging. However, the performance of current state-of-the-art score stems primarily from well-tuned parameters and architecture. There is still only limited research focused on dynamic data augmentation, even in the fields of machine learning and computer vision. In this study, we propose a dynamic training and testing augmentation capable of increasing performance significantly. The searching augmentation framework used in this study requires fewer GPU hours than a conventional search algorithm, which needs to train a new model every time augmentation is proposed. Speeding up of the search algorithm is achieved by using Bayesian optimization on a trained model, so we do not have to train a new model every time a new augmentation policy is proposed. The performance of our method is compared with that of a single model and the ensemble model that happens to be the winner of the ISIC 2019 challenge. Furthermore, we use the latest compact yet significantly accurate network architecture EfficientNet as the backbone system. Our method delivers a superior result, and this study also shares the searched augmentation policy utilized, which requires extraordinary resources. Thus, other researchers can use the searched augmentation policies for dermoscopic images to improve performance.

No abstract

It is widely known that deep neural networks (DNNs) can perform well in many applications, and can sometimes exceed human ability. However, their cost limits their impact in a variety of realworld applications, such as IoT and mobile computing. Recently, many DNN compression and acceleration methods have been employed to overcome this problem. Most methods succeed in reducing the number of parameters and FLOPs, but only a few can speed up expected inference times because of either the overhead generated from using such methods or DNN framework deficiencies. Edge-cloud computing has recently emerged and presents an opportunity for new model acceleration and compression techniques. To address the aforementioned problem, we propose a novel technique to speed up expected inference times by using several networks that perform the exact same task with different strengths. Although our method is based on edge-cloud computing, it is suitable for any other hierarchical computing paradigm. Using a simple yet strong enough estimator, the system predicts whether the data should be passed to a larger network or not. Extensive experimental results demonstrate that the proposed technique can speed up expected inference times and beat almost all state-of-the-art compression techniques, including pruning, low-rank approximation, knowledge distillation, and branchy-type networks, on both CPUs and GPUs. INDEX TERMS Edge computing, mobile computing, network compression and acceleration.

In 2019, Depok Municipality in Indonesia has participated for the second times in PROKLIM (Program Kampung Iklim-bahasa) which is focussed in RW 10 Baktijaya Village. In previous year, community activities in biopori holes, family herbal planting (TOGA) and rainwater infiltration well (RIW) was difficult to be updated. Therefore, in this study unmanned aerial vehicle (UAV) is applied to acquire location of PROKLIM in Baktijaya village with very high resolution image. Herein, DJI Phantom 4 Pro was flown at 100 m height to capture images of participated houses. The image from UAV then processed with Agisoft Photoscan to generate orthophoto image. With the guiandce from local community leader, biopori hole, TOGA and RIW locations were tagged using Avenza Maps and input into ArcGIS. Layers from UAV images and field survey then integrated to produce maps of biopori hole, TOGA and RIW activities. The map of PROKLIM activities was successfully generated from UAV image and Avenza Maps application. Resulted maps are very useful for updating submission to PROKLIM registration website in Indonesia’s Ministry of Environment and Forestry.

No abstract