Beijing Wuzi University

About: Beijing Wuzi University is a education organization based out in Beijing, China. It is known for research contribution in the topics: Supply chain & Computer science. The organization has 1210 authors who have published 1092 publications receiving 6370 citations.

EdgeLD: Locally Distributed Deep Learning Inference on Edge Device Clusters

Abstract: Deep Neural Networks (DNN) have been widely used in a large number of application scenarios. However, DNN models are generally both computation-intensive and memory-intensive, thus difficult to be deployed on resource-constrained edge devices. Most previous studies focus on local model compression or remote cloud offloading, but overlook the potential benefits brought by distributed DNN execution on multiple edge devices. In this paper, we propose EdgeLD, a new framework for locally distributed execution of DNN-based inference tasks on a cluster of edge devices. In EdgeLD, DNN models’ time cost will be firstly profiled in terms of computing capability and network bandwidth. Guided by profiling, an efficient model partition scheme is designed in EdgeLD to balance the assigned workload and the inference runtime among different edge devices. We also propose to employ layer fusion to reduce communication overheads on exchanging intermediate data among devices. Experiment results show that our proposed partition scheme saves up to 15.82% of inference time with regard to the conventional solution. Besides, applying layer fusion can speedup the DNN inference by 1.11-1.13X. When combined, EdgeLD can accelerate the original inference time by 1.77-3.57X on a cluster of 2-4 edge devices.

A Research on Fresh-Keeping Strategies for Fresh Agricultural Products from the Perspective of Green Transportation

Abstract: This paper studies the impact of fresh-keeping effort (FKE) investment strategies from the perspective of green transportation on a fresh-product supply chain (FSC) system for the purpose of reducing the emission of harmful gases and waste of resources. A supplier–buyer structure in an FSC system is modeled under two approaches consisting of the fixed FKE model and the variable FKE model. Then the paper analyzes the effect of optimal FKE level on retailer’s profit and product freshness under two different approaches, and finds that there is space to be improved in the two approaches which were further optimized. Finally, the proposed models are approved with a dataset from a real-life case study. Under the above two approaches, not only profits can be increased in retail enterprises but also the freshness level of fresh agricultural products (FAP) can be improved and reduced the consumption of resources. The results show that there is an optimal investment level of FKE under different strategies, and the maximum profit could be obtained by keeping fresh at this level. Moreover, the fixed FKE will not increase the average freshness of fresh produce in a sales cycle, and the adjusted FKE can effectively improve the average freshness.

A novel depressor useful for flotation separation of diaspore and kaolinite

Abstract: The floatation of the minerals diaspore and kaolinite was investigated using dodecylamine as the collector. Separating diaspore and kaolinite in a neutral pH pulp is difficult since they then have similar floatability. A depressor consisting of an AlCl3/Na2SiO3 mixture is demonstrated to solve this problem. Diaspore sinking may be seen when the ratio of AlCl3 to Na2SiO3 is 3:1. We refer to this mixture as ATNO. The influence of Al/Si ratio in the feedstock and the grain size of fed minerals on separation was examined. An Al/Si ratio in the concentrate greater than 11 may be obtained when the Al/Si ratio of the feed is between 2.53 and 4.96. However, the grain size of the diaspore greatly influences the concentrate grade. Finer grain size of the diaspore (<40 μm) in pulp makes the flotation separation less than ideal, no matter what the kaolinite grain size.

A Novel Hybrid Algorithm for Multiobjective Location-Allocation Problem in Emergency Logistics

Abstract: Increased frequency of disasters keeps reminding us of the importance of effective resource distribution in postdisaster. To reduce the suffering of victims, this paper focuses on how to establish an effective emergency logistics system. We first propose a multiobjective optimization model in which the location and allocation decisions are made for a three-level logistics network. Three objectives, deprivation costs, unsatisfied demand costs, and logistics cost, are adopted in the proposed optimization model. Several cardinality and flow balance constraints are considered simultaneously. Then, we design a novel effective IFA-GA algorithm by combining the firefly algorithm and genetic algorithm to solve this complex model effectively. Furthermore, three schemes are proposed to improve the effectiveness of the IFA-GA algorithm. Finally, the numerical results provide several insights on the theory and practice of relief distribution, which also illustrate the validity of the proposed solution algorithm.