Tongji University

About: Tongji University is a education organization based out in Shanghai, China. It is known for research contribution in the topics: Computer science & Population. The organization has 76116 authors who have published 81176 publications receiving 1248911 citations. The organization is also known as: Tongji & Tóngjì Dàxué.

A feature weighted support vector machine and K-nearest neighbor algorithm for stock market indices prediction

Abstract: This study investigates stock market indices prediction that is an interesting and important research in the areas of investment and applications, as it can get more profits and returns at lower risk rate with effective exchange strategies. To realize accurate prediction, various methods have been tried, among which the machine learning methods have drawn attention and been developed. In this paper, we propose a basic hybridized framework of the feature weighted support vector machine as well as feature weighted K-nearest neighbor to effectively predict stock market indices. We first establish a detailed theory of feature weighted SVM for the data classification assigning different weights for different features with respect to the classification importance. Then, to get the weights, we estimate the importance of each feature by computing the information gain. Lastly, we use feature weighted K-nearest neighbor to predict future stock market indices by computing k weighted nearest neighbors from the historical dataset. Experiment results on two well known Chinese stock market indices like Shanghai and Shenzhen stock exchange indices are finally presented to test the performance of our established model. With our proposed model, it can achieve a better prediction capability to Shanghai Stock Exchange Composite Index and Shenzhen Stock Exchange Component Index in the short, medium and long term respectively. The proposed algorithm can also be adapted to other stock market indices prediction.

Genome-wide CRISPR screen identifies HNRNPL as a prostate cancer dependency regulating RNA splicing.

Abstract: Alternative RNA splicing plays an important role in cancer. To determine which factors involved in RNA processing are essential in prostate cancer, we performed a genome-wide CRISPR/Cas9 knockout screen to identify the genes that are required for prostate cancer growth. Functional annotation defined a set of essential spliceosome and RNA binding protein (RBP) genes, including most notably heterogeneous nuclear ribonucleoprotein L (HNRNPL). We defined the HNRNPL-bound RNA landscape by RNA immunoprecipitation coupled with next-generation sequencing and linked these RBP–RNA interactions to changes in RNA processing. HNRNPL directly regulates the alternative splicing of a set of RNAs, including those encoding the androgen receptor, the key lineage-specific prostate cancer oncogene. HNRNPL also regulates circular RNA formation via back splicing. Importantly, both HNRNPL and its RNA targets are aberrantly expressed in human prostate tumors, supporting their clinical relevance. Collectively, our data reveal HNRNPL and its RNA clients as players in prostate cancer growth and potential therapeutic targets.

Crop diversification and livelihoods of smallholder farmers in Zimbabwe: adaptive management for environmental change

Abstract: This paper demonstrates how crop diversification impacts on two outcomes of climate smart agriculture; increased productivity (legume and cereal crop productivity) and enhanced resilience (household income, food security, and nutrition) in rural Zimbabwe. Using data from over 500 smallholder farmers, we jointly estimate crop diversification and each of the outcome variables within a conditional (recursive) mixed process framework that corrects for selectivity bias arising due to the voluntary nature of crop diversification. We find that crop diversification depends on the land size, farming experience, asset wealth, location, access to agricultural extension services, information on output prices, low transportation costs and general information access. Our results also indicate that an increase in the rate of adoption improves crop productivity, income, food security and nutrition at household level. Overall, our results are indicative of the importance of crop diversification as a viable climate smart agriculture practice that significantly enhances crop productivity and consequently resilience in rural smallholder farming systems. We, therefore, recommend wider adoption of diversified cropping systems notably those currently less diversified for greater adaptation to the ever-changing climate.

Interstitial Point Defect Scattering Contributing to High Thermoelectric Performance in SnTe

Abstract: Due to point defect phonon scattering, formation of solid solutions has long been considered as an effective approach for enhancing thermoelectric performance through reducing the lattice thermal conductivity. The scattering of phonons by point defects mainly comes from the mass and strain fluctuations between the guest and the host atoms. Both the fluctuations can be maximized by point defects of interstitial atoms and/or vacancies in a crystal. Here, a demonstration of phonon scattering by interstitial Cu atoms is shown, leading to an extremely low lattice thermal conductivity of 0.5 W m−1 K−1 in SnTe-Cu2Te solid solutions. This is the lowest lattice thermal conductivity reported in SnTe-based materials so far, which is actually approaching the amorphous limit of SnTe. As a result, a peak thermoelectric figure of merit, zT, higher than 1 is achieved in Sn0.94Cu0.12Te at 850 K, without relying on other approaches for electrical performance enhancements. The strategy used here is believed to be equally applicable in thermoelectrics with interstitial point defects.