Search results

The purpose of this paper is to alleviate the problem of poor robustness and over-fitting caused by large-scale data in collaborative filtering recommendation algorithms.

Interpreting user behavior from the probabilistic perspective of hidden variables is helpful to improve robustness and over-fitting problems. Constructing a recommendation network by variational inference can effectively solve the complex distribution calculation in the probabilistic recommendation model. Based on the aforementioned analysis, this paper uses variational auto-encoder to construct a generating network, which can restore user-rating data to solve the problem of poor robustness and over-fitting caused by large-scale data. Meanwhile, for the existing KL-vanishing problem in the variational inference deep learning model, this paper optimizes the model by the KL annealing and Free Bits methods.

The effect of the basic model is considerably improved after using the KL annealing or Free Bits method to solve KL vanishing. The proposed models evidently perform worse than competitors on small data sets, such as MovieLens 1 M. By contrast, they have better effects on large data sets such as MovieLens 10 M and MovieLens 20 M.

This paper presents the usage of the variational inference model for collaborative filtering recommendation and introduces the KL annealing and Free Bits methods to improve the basic model effect. Because the variational inference training denotes the probability distribution of the hidden vector, the problem of poor robustness and overfitting is alleviated. When the amount of data is relatively large in the actual application scenario, the probability distribution of the fitted actual data can better represent the user and the item. Therefore, using variational inference for collaborative filtering recommendation is of practical value.

In this paper, the main focus is on supply and demand auction systems with resource pooling in modern supply chain from a theoretical modeling perspective. The supply and demand auction systems in modern supply chains among manufacturers and suppliers serve as information sharing mechanisms. The purpose of this paper is to match the supply and demand such that a modern supply chain can achieve incentive compatibility and economic efficiency. The authors design such a supply and demand auction system that can integrate resources to efficiently match the supply and demand.

The authors propose three theoretic models of modern supply chain auctions with resource pooling according to the Vickrey auction principle. They are supply auction model with demand resource pooling, demand auction model with supply resource pooling, and double auction model with demand and supply resource pooling. For the proposed auction models, the authors present three corresponding algorithms to allocate resources in the auction process by linear programming, and study the incentive compatibility and define the Walrasian equilibriums for the proposed auction models. The authors show that the solutions of the proposed algorithms are Walrasian equilibriums.

By introducing the auction mechanism, the authors aim to realize the following three functions. First is price mining: auction is an open mechanism with multiple participants. Everyone has his own utility and purchasing ability. So, the final price reflects the market value of the auction. Second is dynamic modern supply chain construction: through auction, firm can find appropriate partner efficiently. Third is resources integration: in business practices, especially in modern supply chain auctions, auctioneers can integrate resources and ally buyers or sellers to gain more efficiency in auctions.

In the paper, the authors propose three theoretic models and corresponding algorithms of modern supply chain auctions with resource pooling according using the Vickrey auction principle, which achieves three functions: price mining, dynamic modern supply chain construction and resources integrating. Besides, these proposed models are much closer to practical settings and may have potential applications in modern supply chain management.

The purpose of this paper is to propose a framework for data analytics where everything is grey in nature and the associated uncertainty is considered as an essential part in data collection, profiling, imputation, analysis and decision making.

A comparative study is conducted between the available uncertainty models and the feasibility of grey systems is highlighted. Furthermore, a general framework for the integration of grey systems and grey sets into data analytics is proposed.

Grey systems and grey sets are useful not only for small data, but also big data as well. It is complementary to other models and can play a significant role in data analytics.

The proposed framework brings a radical change in data analytics. It may bring a fundamental change in our way to deal with uncertainties.

The proposed model has the potential to avoid the mistake from a misleading data imputation.

The proposed model takes the philosophy of grey systems in recognising the limitation of our knowledge which has significant implications in our way to deal with our social life and relations.

This is the first time that the whole data analytics is considered from the point of view of grey systems.

Feature selection is an essential step in data mining. The core of it is to analyze and quantize the relevancy and redundancy between the features and the classes. In CFR feature selection method, they rarely consider which feature to choose if two or more features have the same value using evaluation criterion. In order to address this problem, the standard deviation is employed to adjust the importance between relevancy and redundancy. Based on this idea, a novel feature selection method named as Feature Selection Based on Weighted Conditional Mutual Information (WCFR) is introduced. Experimental results on ten datasets show that our proposed method has higher classification accuracy.

The purpose of this paper is to produce an intelligent technique for modelling machine tool errors caused by the thermal distortion of Computer Numerical Control (CNC) machine tools. A new metaheuristic method, the cuckoo search (CS) algorithm, based on the life of a bird family is proposed to optimize the GMC(1, N) coefficients. It is then used to predict thermal error on a small vertical milling centre based on selected sensors.

A Grey model with convolution integral GMC(1, N) is used to design a thermal prediction model. To enhance the accuracy of the proposed model, the generation coefficients of GMC(1, N) are optimized using a new metaheuristic method, called the CS algorithm.

The results demonstrate good agreement between the experimental and predicted thermal error. It can therefore be concluded that it is possible to optimize a Grey model using the CS algorithm, which can be used to predict the thermal error of a CNC machine tool.

An attempt has been made for the first time to apply CS algorithm for calibrating the GMC(1, N) model. The proposed CS-based Grey model has been validated and compared with particle swarm optimization (PSO) based Grey model. Simulations and comparison show that the CS algorithm outperforms PSO and can act as an alternative optmization algorithm for Grey models that can be used for thermal error compensation.

The nature of farm animals in the marginalized group of people is varying hurriedly. Livestock is used to add to cash earnings and increase food security, hence helping as a vital component in the household’s source of revenue strategies, particularly at marginal planter’s level. The present study was conducted to assess the numbers of livestock farmers in the study areas, their livelihood options, the value chain of the farmers in different marketing channels and recommendation for the sustainable value chain of the livestock production cycle.

The study precise the baseline condition of marginal livestock farmers for access to value chain activities in terms of inputs, outputs, support services, production, yield, income and enabling environment to enhance livestock farming in the study area. The study was conducted through stratified random sampling of the context using some research tools like in-depth interviews, household surveys, expert opinions and focus group discussions. Structured questionnaires were developed to address issues, such as current livestock farming practices, access to support services, capacity and income.

The study revealed that this particular context is lagging behind to establish goat value chain activities in the targeted areas. The farmers do not have basic knowledge of goat farming, and the value chain actors are not working properly. The support services are not appropriate to turn the goat farming production to a standard level. Value chain of livestock and livestock products and their goals are essential to develop an idea on learning, investment, market access, sales assurance and quality. Variation in institutional contexts of end markets is linked to different types of coordination and control of enabling environment throughout the chains.

Livestock is an integral component of the complex farming system in Bangladesh as it serves as not only a source of meat protein but also a major source of farm power services as well as employment. Strong private sector alliance along with public–private ventures can bring sustainable agriculture value chain development in these most vulnerable coastal communities in Bangladesh. Strengthening the weak financial structure, reducing power imbalances in the governance structures and low political intervention in community-level organizations, and resolving socio-cultural and environmental concerns are the major concerns on the development of value chains in Bangladesh.

Geographical position and climatic condition of Bangladesh have made her coastal areas one of the highly productive areas for livestock production in the world. The study was conducted through qualitative and quantitative analysis, and after finding the authors recommended for sustainable value chain approach for livestock production to a marketing channel for improving the financial condition and self-employment for the communities.