A Comprehensive Evaluation Study on Risk Level Classification of Melanoma by Computer Vision on ISIC 2016-2020 Datasets

Skin cancer is the most common type of cancer. Specifically, melanoma is the cause of 75% of skin cancer deaths, although it is the least common skin cancer. Better detection of melanoma could have a positive impact on millions of people. The ISIC archive contains the largest publicly available collection of dermatoscopic images of skin lesions. In this research, we investigate the efficacy of applying advanced deep learning techniques in computer vision to identify melanoma in images of skin lesions. Through reviewing previous methods, including pre-trained models, deep-learning classifiers, transfer learning, etc., we demonstrate the applicability of the popular deep learning methods on critical clinical problems such as identifying melanoma. Finally, we proposed a processing flow with a validation AUC greater than 94% and a sensitivity greater than 90% on ISIC 2016 - 2020 datasets.

Deep Learning-based approaches for automatic detection of shell nouns and evaluation on WikiText-2

In some areas, such as Cognitive Linguistics, researchers are still using traditional techniques based on manual rules and patterns. Since the definition of shell noun is rather subjective and there are many exceptions, this time-consuming work had to be done by hand in the past when Deep Learning techniques were not mature enough. With the increasing number of networked languages, these rules are becoming less useful. However, there is a better alternative now. With the development of Deep Learning, pre-trained language models have provided a good technical basis for Natural Language Processing. Automated processes based on Deep Learning approaches are more in line with modern needs. This paper collaborates across borders to propose two Neural Network models for the automatic detection of shell nouns and experiment on the WikiText-2 dataset. The proposed approaches not only allow the entire process to be automated, but the precision has reached 94% even on completely unseen articles, comparable to that of human annotators. This shows that the performance and generalization ability of the model is good enough to be used for research purposes. Many new nouns are found that fit the definition of shell noun very well. All discovered shell nouns as well as pre-trained models and code are available on GitHub.

An Anchor-Free Detector for Continuous Speech Keyword Spotting

Continuous Speech Keyword Spotting (CSKWS) is a task to detect predefined keywords in a continuous speech. In this paper, we regard CSKWS as a one-dimensional object detection task and propose a novel anchor-free detector, named AF-KWS, to solve the problem. AF-KWS directly regresses the center locations and lengths of the keywords through a single-stage deep neural network. In particular, AF-KWS is tailored for this speech task as we introduce an auxiliary unknown class to exclude other words from non-speech or silent background. We have built two benchmark datasets named LibriTop-20 and continuous meeting analysis keywords (CMAK) dataset for CSKWS. Evaluations on these two datasets show that our proposed AF-KWS outperforms reference schemes by a large margin, and therefore provides a decent baseline for future research.

Highly Efficient Memory Failure Prediction using Mcelog-based Data Mining and Machine Learning

In the data center, unexpected downtime caused by memory failures can lead to a decline in the stability of the server and even the entire information technology infrastructure, which harms the business. Therefore, whether the memory failure can be accurately predicted in advance has become one of the most important issues to be studied in the data center. However, for the memory failure prediction in the production system, it is necessary to solve technical problems such as huge data noise and extreme imbalance between positive and negative samples, and at the same time ensure the long-term stability of the algorithm. This paper compares and summarizes some commonly used skills and the improvement they can bring. The single model we proposed won the top 14th in the 2nd Alibaba Cloud AIOps Competition belonging to the 25th PAKDD conference. It takes only 30 minutes to pass the online test, while most of the other contestants' solution need more than 3 hours. Codes has been open source to https://www.github.com/ycd2016/acaioc2.