Collaborative filtering recommender systems (CFRSs) are the key components of successful e-commerce systems. Actually, CFRSs are highly vulnerable to attacks since its openness. However, since attack size is far smaller than that of genuine users, conventional supervised learning based detection methods could be too "dull" to handle such imbalanced classification. In this paper, we improve detection performance from following two aspects. First, we extract well-designed features from user profiles based on the statistical properties of the diverse attack models, making hard classification task becomes easier to perform. Then, refer to the general idea of re-scale Boosting (RBoosting) and AdaBoost, we apply a variant of AdaBoost, called the rescale AdaBoost (RAdaBoost) as our detection method based on extracted features. RAdaBoost is comparable to the optimal Boosting-type algorithm and can effectively improve the performance in some hard scenarios. Finally, a series of experiments on the MovieLens-100K data set are conducted to demonstrate the outperformance of RAdaBoost comparing with some classical techniques such as SVM, kNN and AdaBoost. 2[29] and AdaBoost [9, 10], we apply a variant of Boosting algorithm, called the re-scale AdaBoost (RAdaBoost) as our detection method based on extracted features. RBoosting is theoretically and experimentally proved to be better than the classical Boosting algorithm [17]. Furthermore, the theoretical near optimality of the numerical convergence of RBoosting among all the variants of the Boosting-type algorithms was also specified. This means that if the parameter is appropriately selected, RBoosting is comparable to the optimal Boosting-type algorithm. And AdaBoost [9, 10] is one of the most popular ensemble techniques paradigm and has been shown to be very effective in practice in some hard scenarios [13]. Typically, AdaBoost employs re-weighted loss function for gradually increasing emphasis (or weights) on misclassifications (i.e., concerned attackers) and can distinctly improve the predictive performance on a difficult data set. Thus, with the help of the re-scale operator, RAdaBoost can be used in conjunction with many other types of learning algorithms (or weak learners) to improve the performance in "shilling" attacks detection. Finally, a series of experiments on the MovieLens-100K dataset are conducted to demonstrate the outperformance (i.e., classification error, detection rate and false alarm rate) of RAdaBoost comparing with conventional classification techniques such as SVM, kNN and the original non-rescale AdaBoost version. The experimental results show that RAdaBoost can effectively improve the performance.

This paper investigates total-factor energy efficiency and analyses the trends of the efficiency changes in China's agricultural production across 30 provinces and three regions from 2001 to 2011, based on data envelopment analysis (DEA) approach. The potential amount of energy savings and five potential factors for energy efficiency improvement are also empirically studied by Tobit regression model. The findings show that (1) total-factor energy efficiency in China's agricultural sector is increasing over years but performs heterogeneously across regions; (2) agriculture intensive regions and energy abundant provinces tend to be relatively energy inefficient in agricultural production; and (3) economic structure, agricultural production structure, technological progress and income effect are major potentials for improving energy efficiency, whereas energy price is not a significant factor. This phenomenon results from the divergence of economic development, endowment effects as well as the scale of agricultural production. Policy implications drawn from this research are to upgrade industrial structure and promote agricultural transformation to enhance farmers' income as well as to establish a land market with entitling land property rights to farmers. This conclusion can assist to form more scientific rural energy policy decision-making in China and also can be extended to other developing economies for sustainable agriculture.

Insufficient and high variability in rice yield is a threat to food security in China, prompting the need for strategies to mitigate yield variability and increase productivity. This study investigates the presence of production risk and technical inefficiency for a sample of rice farms in the Xiangyang city of China using a stochastic production frontier framework. Results from the risk function reveal that labor and better soil quality have significant risk-reducing effects while machinery exerts a significant risk-increasing effect on rice production. The estimated mean technical efficiency score is 84%, suggesting that, on average, farmers could increase their rice production by 16%, without increasing the existing input levels by improving their management techniques. Factors that significantly affect technical efficiency are the age of farmers, female ratio, access and use of extension services, off-farm income, and the size of cultivated land. Results from this study suggest that yield variability and technical inefficiency in rice production can be reduced by appropriate choice of input combinations and elimination of mistakes in the production process through efficient management practices. Strategies, such as providing better extension services, loosening liquidity constraints facing farmers, and expanding rice farmers' producing area, would help to achieve minimum inefficiency in production.

Abstract-Personalization collaborative filtering recommender systems (CFRSs) are the crucial components of popular e-commerce services. In practice, CFRSs are also particularly vulnerable to "shilling" attacks or "profile injection" attacks due to their openness. The attackers can carefully inject chosen attack profiles into CFRSs in order to bias the recommendation results to their benefits. To reduce this risk, various detection techniques have been proposed to detect such attacks, which use diverse features extracted from user profiles. However, relying on limited features to improve the detection performance is difficult seemingly, since the existing features can not fully characterize the attack profiles and genuine profiles. In this paper, we propose a novel detection method to make recommender systems resistant to the "shilling" attacks or "profile injection" attacks. The existing features can be briefly summarized as two aspects including rating behavior based and item distribution based. We firstly formulate the problem as finding a mapping model between rating behavior and item distribution by exploiting the least-squares approximate solution. Based on the trained model, we design a detector by employing a regressor to detect such attacks. Extensive experiments on both the MovieLens-100K and MovieLens-ml-latest-small datasets examine the effectiveness of our proposed detection method. Experimental results were included to validate the outperformance of our approach in comparison with benchmarked method including KNN.

This paper examines the impacts of off-farm employment on irrigation water efficiency (IWE) with a set of household level data collected in Hebei Province in North China. A major finding is that households with higher shares of laborers working off-farm locally seem to achieve higher IWEs. The effect of local off-farm employment is greater among those households that have made more efforts to use furrow irrigation. We also find that households with higher shares of elderly laborers and those with larger land holding are associated with lower IWEs. Households with better soil quality and those that pump from deeper wells are associated with higher IWEs.