An effective and fast hybrid metaheuristic is proposed for solving the pickup and delivery problem with time windows. The proposed approach combines local search, large neighbourhood search and guided ejection search in a novel way to exploit the benefits of each method. The local search component uses a novel neighbourhood operator. A streamlined implementation of large neighbourhood search is used to achieve an effective balance between intensification and diversification. The adaptive ejection chain component perturbs the solution and uses increased or decreased computation time according to the progress of the search. While the local search and large neighbourhood search focus on minimising travel distance, the adaptive ejection chain seeks to reduce the number of routes. The proposed algorithm design results in an effective and fast solution method that finds a large number of new best-known solutions on a well-known benchmark dataset. Experiments are also performed to analyse the benefits of the components and heuristics and their combined use to achieve a better understanding of how to better tackle the subject problem.

Cassava is becoming increasingly important as an industrial raw material in China. However, an insufficient supply of cassava raw materials and the expanding demand for cassava in downstream-processing industries restricts the development of the cassava industry in China. This paper studies how to increase the scale of cassava planting and promoting cassava production efficiency using output-oriented Data Envelopment Analysis (DEA) modeling. Overall Technical Efficiency (OTE), Pure Technical Efficiency (PTE), and Scale Efficiencies (SE) of the cassava-production system in the major cassava production areas of China are calculated using Variable Returns to Scale (VRS). Results reveal that, in addition to the Guangdong province, the OTE of Guangxi, Hainan, Fujian, Yunnan, and Jiangxi is inefficient, with an OTE of less than 1. The largest cassava-planting province, Guangxi, has the lowest SE with 0.551. The PTE of Guangxi is close to the minimum with 0.344. The OTE of Guangxi is also the lowest among the five provinces with 0.190. This study also presents ways to improve production efficiency. Results reveal that Guangxi has a large ratio of transverse adjustment on average. In the Guangxi province, 1.70% of the service cost and 1.72% of the labor cost need to be eliminated to keep the current output scale. Meanwhile, service and labor costs need to be reduced by 3164.85 and 3209.92, respectively, to achieve the best production efficiency. Further industrialization and large-scale cassava cultivation, increased yield, and strengthened cooperation with the Association of South East Asian Nations (ASEAN) and Africa are suggested as policy options to improve the cassava system in China.

Noise in hyperspectral images (HSIs) may degrade the HSI classification result. Robust principal component analysis (RPCA) is an excellent method to obtain low-rank (LR) representation of data and is widely used in image denoising and also in HSI classification. However, data are drawn as a union from multiple subspaces in HSIs, so LR subspace estimation (LRSE) is necessary when using RPCA, which is complicated and time-consuming. To solve this problem, this letter proposes a novel LR-based method for HSI classification called two-branch network combined with RPCA, which combines RPCA with a neural network. Specifically, both the LR component and the sparse component are preserved and used for feature extraction in two independent convolutional branches. This way, we can avoid information loss without using accurate LRSE. A concatenate operation and a pointwise convolution are then adopted to realize the feature fusion. Finally, fused features are constructed to indicate the ground truth of each pixel in the classification process. The proposed method constructs a convenient model for HSI classification by discarding the LRSE and combining denoising, feature extraction, feature fusion, and classification into an end-to-end network. The experimental results on three data sets demonstrate that the proposed method outperforms many state-of-the-art methods including ones based on LR representation and ones based on deep learning. In addition, it maintains good classification performance for the cases of small samples and class imbalance.

As a significant ecological corridor from west to east across China, the Yangtze River Economical Belt (YREB) is in great need of green development and transformation. Rather than only focusing on the overall growth of green productivity, it is important to identify whether the technical change is biased towards economic performance or green performance in promoting green productivity. By employing the biased technical change theory and Malmquist index decomposition method, we analyze the green biased technical change in terms of industrial water resources in YREB at the output side and the input side respectively. We find that the green biased technical change varies during 2006–2015 at both the input side and output side in YREB. At the input side, water-saving biased technical change is generally dominant compared to water-using biased technical change during 2006–2015, presenting the substitution effects of non-water production factors. At the output side, the economy-growth biased technical change is the main force to promote green productivity, whereas the role of water-conservation biased technical change is insufficient. The green performance at the output side needs to be strengthened compared to the economic performance in YREB. A series of water-related environmental policies introduced in China since 2008 have promoted the green biased technical change both at the input side and the output side in YREB, but the policy effects at the output side is still inadequate compared to that at the input side. The technological innovation in sewage treatment and control need to catch up with the economic growth in YREB. Our research gives insights to enable a deeper understanding of the green biased technical change in YREB and will benefit more focused policy-making of green innovation.