Efficient Local Cloud-Based Solution for Liver Cancer detection using Deep Learning

Liver cancer is one the most common forms of cancer. As per statistics in 2018 published by World Health Organization, a quarter of all cancer cases are caused by infections, particularly prevalent in developing countries, including hepatitis B, which is linked to liver cancer. The mortality rate is higher in liver cancer as compared to other types of cancer. Quick and reliable diagnosis tools are of paramount importance for detecting and treating liver cancer in early stage, thus improving the likely course of a medical condition of patient. We have developed a cloud-based solution for liver tumour Segmentation, Classification and Detection in CT images based on GoogleNet architecture of Convolutional Neural Network. Experiment is carried out with training and test sets derived from TCIA repository. The results yield 96.7% accuracy for classification of tumour cells. GoogleNet architecture is used for implementation. The GoogleNet has 70,000 images in diagnosis of malignant tumor in liver cancer, providing a rich database for testing. Our algorithm has been deployed in Azure cloud.

An all-sky camera images classification method using cloud cover features

The all-sky camera (ASC) images can reflect the local cloud cover information, and the cloud cover is one of the first factors considered for astronomical observatory site selection. Therefore, the realization of automatic classification of the ASC images plays an important role in astronomical observatory site selection. In this paper, three cloud cover features are proposed for the TMT (Thirty Meter Telescope) classification criteria, namely cloud weight, cloud area ratio and cloud dispersion. After the features are quantified, four classifiers are used to recognize the classes of the images. Four classes of ASC images are identified: “Clear”, “Inner”, “Outer” and “Covered”. The proposed method is evaluated on a large dataset, which contains 7328 ASC images taken by an all-sky camera located in Xinjiang (38.19° N, 74.53° E). In the end, the method achieves an accuracy of 97.28 % and F1_score of 96.97 % by a random forest (RF) classifier, which greatly improves the efficiency of automatic processing of the ASC images.

Analysis of climate indicator association with hotspots in Indonesia using heterogeneous correlation map

In several regions, land and forest fires of Indonesia occurred almost annually during the drought season. The severity of Indonesia's drought season is mainly influenced by the Australian Monsoon, local cloud formation controlled by Sea Surface Temperature (SST) around Indonesia. Moreover, it affects the severity of land and forest fires itself indirectly. This research aims to examine the association of the Australian Monsoon and local SST with land and forest fires in Indonesia. This research uses the Australian Monsoon Index (AUSMI) as an indicator for the Australian Monsoon and SST in the Karimata Strait and the Java Sea as indicators of local SST. An indicator of land and forest fires that will be used is the number of hotspots. A heterogeneous Correlation Map (HCM) is used to describe hotspots associated with AUSMI and local SST. The analysis shows that the east wind pattern of AUSMI associated with hotspots in Indonesia, especially in years when zonal winds enter an upward phase more slowly. Karimata Strait’s SST is associate with hotspots in the coastal part of Riau. Meanwhile, Java Sea’s SST is associate with hotspots in Lampung, South Sumatra, Jambi, and Kalimantan.

Efficient Local Cloud-Based Solution for Diabetic Retinopathy Detection

Damage of blood vessels in retina due to diabetes is known as diabetic retinopathy. It is one of the one of the important origins of blindness for adults. Loss of vision can be avoided by detecting damage of retina (leaking fluid or blood). Efficient local cloud-based solution for diabetic retinopathy detection is designed in the work, where convolution neural network is used for training and classification module and achieved an accuracy of 86% using kappa metric. Fundus images are used for training and classification. System network architecture is derived from VGGNet. Network is trained using 80,000 images. Since everything is automated, a doctor is only required for treatment, not for diagnosis.

The Critical Role of Cloud–Infrared Radiation Feedback in Tropical Cyclone Development

<p>The deep convective clouds of developing tropical cyclones (TCs) are highly effective at trapping the infrared (or longwave) radiation welling up from the surface. This “cloud greenhouse effect” locally warms the lower–mid-troposphere relative to the TC’s surroundings – an effect that manifests in all stages of the TC lifecycle. While idealized studies suggest the importance of this feedback for TC formation, this issue has remained unexplored for TCs in nature, where non-zero background flow, wind shear, and synoptic-scale variability are known to greatly constrain TC development.</p><p>To address this gap, we examine the potential role of this cloud–infrared (or longwave) radiation feedback in the context of two archetypal storms: Super Typhoon Haiyan (2013) and Hurricane Maria (2017). We conduct a set of numerical model experiments for both storms with a convection-resolving model (WRF-ARW) from the very early stages of TC development. We examine sensitivity experiments wherein this cloud–radiation feedback is removed at various lead-times prior to TC genesis and the onset of rapid intensification (RI). In both storms, removing this cloud–radiation feedback at a lead-time of ~1 day or less leads to delayed and/or weaker intensification than in the control case. When this feedback is removed with a lead-time of two days or longer, however, the storms altogether fail to development and intensify. This local cloud greenhouse effect strengthens the thermally direct transverse circulation of the incipient storm, in turn both promoting saturation within its core and accelerating the spin-up of its surface tangential circulation via angular momentum convergence. These findings indicate that the cloud greenhouse effect plays a critical role in accelerating and promoting TC development in nature. Progress in the prediction of TC formation and intensification has been very limited in recent decades. Cloud–radiation feedback represents a large source of uncertainty in models, which hence manifests as uncertainty in the prediction of TC development. Our findings highlight the pressing need to better constrain this feedback in models. Doing so holds promise for advancing our ability to forecast TCs.</p>

Rancang Bangun Local Cloud Server Dengan NextCloud Pada Centos 7 Di SRH Training Center

The file becomes an important thing in any case. Especially in the world of education which is something that can’t be avoided that students must be able to create and save files correctly, both assignments and reports. Files stored on a computer do not guarantee that the data will be forever stored, because every month a computer maintenance must be held in a computer laboratory. Local cloud server technology with Nextcloud that uses the CentOs 7 operating system is very suitable to be applied in the SRH Training Center laboratory as a means of storing files and managing files in a Local Area Network. In this study the local cloud server was built with apache web server and mysql database and also with several packages supporting the Nextcloud application. With the construction of a local cloud server system with Nextcloud, students and teaching staff can easily manage the required learning files. Keywords: CentOs 7, Local Area Network, Local Cloud Server, Nextcloud, Web Server. Abstrak: File menjadi suatu hal yang penting dalam hal apapun. Apalagi di dunia pendidikan yang menjadi suatu hal yang tidak bisa dihindari bahwa siswa harus mampu membuat dan menyimpan file dengan benar, baik itu tugas maupun laporan. File yang disimpan dalam komputer tidak menjamin data akan selamanya tersimpan, karena setiap bulan pasti diadakan maintenance komputer yang ada di laboratorium komputer. Teknologi local cloud server dengan Nextcloud yang menggunakan sistem operasi CentOs 7 sangat cocok diterapkan dalam laboratorium SRH Training Center sebagai sarana penyimpanan file dan memanajemen file dalam satu jaringan Local Area Network. Pada penelitian ini local cloud server dibangun dengan web server apache dan database mysql dan juga dengan beberapa paket pendukung aplikasi Nextcloud. Dengan dibangunnya sistem local cloud server dengan Nextcloud, maka siswa-siswi dan tenaga pengajar dapat mudah dalam memanejemen file pembelajaran yang dibutuhkan. Kata Kunci: CentOs 7, Local Area Network, Local Cloud Server, Nextcloud, Web Server.

Characterization of Physicochemical Properties of Feedlot Dust Ice Crystal Residuals (ICRs)

This study considers how feedlot dust size and composition contribute to atmosphericice nucleation and the formation of local cloud and precipitation in the Texas Panhandle. [...]