Author(s):Simiao Zhao, Xuanyue Mao, Hanghong Lin, Hao Yin, Peixuan Xu
ABSTRACT:Cancer-beating molecules (CBMs) are abundant in many types of food and potentially anti-cancer therapeutic agents. In the previous work, researchers introduced a network-based machine learning platform to identify the cancer-beating molecules, for example, comparing the similarities in the molecular network between approved anticancer drug and food molecules. Herein, we aim to build on this work to enhance the accuracy of predicting food molecules. In this project, we improve supervised learning approaches by applying Soft Voting algorithm to seven machine learning algorithms: Support Vector Machine with Radial Basis Function (SVM with RBF kernel), multilayer perceptron neural network (MLP), Random forest, Decision trees, Gaussian Naive Bayes, Adaboosting, and Bagging. As a result, the accuracy in the dataset of 50 food molecules utilized increased from 82% to 87%, achieving a significant improvement in the precision of predicting anti-cancer molecules.Download as PDF
Author(s):Jiaxin Gao, Zirui Zhou, Jiangshan Ai, Bingxin Xia, Stephen Coggeshall
ABSTRACT:Credit card fraud is a wide-ranging issue for financial institutions, involving theft and fraud committed using a payment card. In this paper, we explore the application of linear and nonlinear statistical modeling and machine learning models on real credit card transaction data. The models built are supervised fraud models that attempt to identify which transactions are most likely fraudulent. We discuss the processes of data exploration, data cleaning, variable creation, feature selection, model algorithms, and results. Five different supervised models are explored and compared including logistic regression, neural networks, random forest, boosted tree and support vector machines. The boosted tree model shows the best fraud detection result (FDR = 49.83%) for this particular data set. The resulting model can be utilized in a credit card fraud detection system. A similar model development process can be performed in related business domains such as insurance and telecommunications, to avoid or detect fraudulent activity.Download as PDF
Author(s):Ziyue Zhang, Tong Wu, Miranda Zhong, Jiawen Xiao, Ziyu Dong
ABSTRACT:Hepatitis E caused by the Hepatitis E Virus (HEV) is a liver disease resulting in over 20 million cases every year. Hepatitis E is now considered by some scientists as an emerging issue as HEV is not only prevalent in developing countries but is increasingly detected in industrialized nations. In this paper, we try to provide evidence for this notion and what actions may need to be implemented to prevent further spreading of HEV. The prevalence of HEV, including its distinct genotype distribution in different geographic regions (including both developing countries and industrialized countries) will be discussed; further discussions of HEV treatments will include the availability and the mechanism of HEV vaccines and antiviral treatments used to treat and contain the disease. Additionally, the prevention and spreading of Hepatitis E disease will be discussed in the later section of the paper. With the presentation of HEV transmission route, infection regions, and treatment, we aim to raise the awareness of the general public toward this liver disease and discuss whether the high prevalence disease is an emerging disease worldwide. According to the data we collected, the rate of HEV infection is high and shows a trend of increasing, which leads to our conclusion and proves our hypothesis that Hepatitis E is a re-emerging disease.Download as PDF
Author(s):Simeng Li1, Qiaofeng Liu, Haoyu Yuan
ABSTRACT:Hand-coloring is very useful when people draw pictures or produce movies, but it is also very time-consuming and expensive. Therefore, with the development of segmentation algorithms and deep learning, a lot of computer-assisted colorization algorithms have been invented, including user-guided colorization, semi-automatic colorization and automatic colorization. In this survey paper, we will only focus on scribble-based colorization in user-guided colorization and review the development on it. We will discuss various principles and methods among different kinds of scribble-based colorization algorithms. We will also compare visual result and performance of algorithms among colorization on grayscale image, colorization on sketch and colorization with networks to conclude their advantages and disadvantages.Download as PDF
Author(s):Zhuolin Li
ABSTRACT:The paper, presenting the distinctions between Chinese and Japanese textbooks and museums’ descriptions on Second Sino-Japanese War, tends to offer explanations for the different presentations of the war. Textbooks from high school mandatory world history courses from Ikeda Senior High School attached to Osaka Koku University in Osaka, Japan and ChenJingLun High School in Beijing, China are chosen to compare. For war-relating museums, the Unit 731 Museum in Harbin, China and the Peace Memorial Museums of Hiroshima, Japan are both one of the most important and profound war museums in both nations. Chinese textbook straightforwardly points out Japanese territorial expansion, Japanese brutal atrocities, and the successful achievement CPC made in the war. However, the Japanese textbook describes Japan’s domestic economic crisis during WWII, Chinese Civil War between the CPC and Kuomintang, and Japanese diplomacy. For the museums, the Hiroshima Peace Memorial Hall’s Main Building tells tragedies caused by the A-bomb, survivors’ emotional stories, and the huge mental and physical damage to the civilian population. The Unit 731 Museum’s Bacteriological Exhibit Hall reveals the human experiments in the secluded Unit 731 military base. Assuming the government-approved mandatory history textbooks in both nations convey the historical information preferred by current national government, and museums serve as the repository of abundant documents and visual evidences, the paper further analyzes the distinctions from social, historical, and political aspects; national war memories, Japanese sense of excluded national pride, postwar US-Japanese relation, and government legitimacy are factors examined to be accounted for the notable distinctions between Chinese and Japanese textbooks and museums’ descriptions of the war.Download as PDF
Author(s):Yuhui Wang, Hongbo Zhu, Zechun Wang, Haolong Li, Guangyao Li
ABSTRACT:Nowadays, many different kinds of delivery companies transport their own kinds of parcels and offer their own services, which have caused a lot waste of resources. In addition, the volume of parcels in all cities that need to be delivered has been grown dramatically. To cope with these problems, a uniform parcel delivery system in a smart city which can offer service to all kinds of customers in the city including manufactures, department stores, restaurants, individual people and so forth was designed. This system uses IoT (Internet of Things) and RFID technology, combining computer network technology, wireless communication and cloud computing. With this system, the whole package delivery process including classification of packages, vehicle scheduling, path planning, transportation monitoring can be intellectualized as well as managed automatically, and the use of both material resources and manpower resources can be reduced accordingly.Download as PDF
Author(s):Yueru Jin, Duanyi Liu, Yuhan Li
ABSTRACT:The Bretton Woods system was abandoned by the U.S. government in 1971. In order to learn to avoid the structural flaws that led to the collapse and ensure a more stable economic condition in the future, this article aims to research the cause of the collapse. It elaborates on the two main causes of the Bretton Woods system: structural ones, such as the incompatible role of the USD and the conflicting sovereign goals, and the operational ones, such as the reluctance of other countries to follow the exchange rate rules. It then displays viewpoints from these two causes, and analyses them, that is, strengthens or undermines them, with facts and reasoning. Finally, it reaches the conclusion that the Bretton Woods system broke down in 1971 due to structural factors instead of operational ones and gives some brief lessons from the failure.Download as PDF
Author(s):Yunfei Zhao1, Xiyun Zhang, Siyi Shu, Yijia Sun, Xiangxiong Feng, Shizhong Zhang
ABSTRACT:Yellow fever (YF) is arguably one of the most notorious infectious diseases in the world. The disease is not only fatal to the human but also several primate species many of which are endangered by now. YF is caused by the yellow fever virus (YFV). While YFV was one of the most feared infectious diseases in the 18th and 19th century, the overall disease burden has been greatly reduced through an effective vector (mosquito) control and the development of the live-attenuated vaccine, YFV-17D. However, recent outbreaks in previously non-endemic areas have risen intense awareness among scientists and the public and remind us that YFV cannot be forgotten and containing it needs to remain a global health priority. Notably, the 11 imported yellow fever cases to China; hence the whole Asia-Pacific region, in 2016 alone, highlight that YFV may pose a threat to a large population which is intensified by increasing human migration and an extremely low vaccination rate. This paper assesses the possibility of a new round of epidemics of YFV, indicating that the virus should indeed be recognized as a re-emerging threat, and offers suggestions on how to prevent it. Stricter vaccine regulation and border check should be applied, as well as further research into alternative vaccines. More attention and efforts should be paid to fighting against the disease.Download as PDF
Author(s):Yifan Fei, Jiawen Jiang
ABSTRACT:Hepatitis C disease is caused by hepatitis C virus (HCV) which causes chronic infections in about 180 million individuals worldwide. HCV has been identified as the etiologic agent of hepatitis C in 1989 and for the longest time it is very difficult to treat chronic carriers who are at risk of developing severe liver disease. Now there are three main combined treatments which can increase curative ratio from 10% to more than 90%. The advents of so called directly, acting antivirals (DAAs) in the last few years has revolutionized HCV treatment as these drug combinations can effectively cure HCV in the great majority of patients. The impact of DAAs on global disease burden has been limited, however, by the very drug prices. In this paper the situation was analyzed in China, Europe and Australia. DAAs have been made available to patients in Europe and Australia for several years and are generally accessible. The treatment is highly subsidized by the government, thereby making it possible for all patients in need to access therapy. DAAs have only been very recently been adopted for treatment of chronic hepatitis C in China. In our research, only the method of literature search from both Chinese websites and Foreign websites including journals, magazines and internet search is used. We analyze and compare the solutions that each of these countries is providing to their respective patient populations. Given the large number of chronic HCV carriers in China and other less developed countries solutions have to be found to produce DAAs most cost effectively.Download as PDF
Author(s):Ziming Chi, Bingyan Zhang
ABSTRACT:In this paper we employ an improved Siamese neural network to assess the semantic similarity between sentences. Our model implements the function of inputting two sentences to obtain the similarity score. We design our model based on the Siamese network using deep Long Short-Term Memory (LSTM) Network. And we add the special attention mechanism to let the model give different words different attention while modeling sentences. The fully-connected layer is proposed to measure the complex sentence representations. Our results show that the accuracy is better than the baseline in 2016. Furthermore, it is showed that the model has the ability to model the sequence order, distribute reasonable attention and extract meanings of a sentence in different dimensions.Download as PDF
Author(s):Yunxiao Xu
ABSTRACT:Scholars have pointed out both positive and negative effects ethnical networks could have on immigrant business performance. By statistically analyzing the difference in income among Chinese and Korean entrepreneurs, this study focuses on the impact of a strong network on immigrant business performance. The results indicate that higher network quality and quantity have negative impacts on business owners’ incomes, yet these negative effects could be offset by stronger overall networks.Download as PDF
Author(s):Rongchuan Tao
ABSTRACT:In the bilateral trading model developed by Myerson [1], an ex post efficient mechanism that satisfies incentive compatibility and individual rationality has been proved to be not existed. This paper is aimed at the discussion of modified bilateral trading model where the buyer and seller’s valuations for the object are assumed to be not independent. Under such assumption, we concern about the existence of an ex post efficient mechanism satisfying individual compatible and individual rational conditions. We will give a necessary condition of such mechanism, not precisely though, to identify the existence. At the end of this paper, we provide some empirical evidences about the non-independent assumption and suggest some directions for further research, both empirical and theoretical.Download as PDF