Blockchain’s potential to revolutionize supply chain and logistics with transparency and equitable stakeholder engagement is significant. However, challenges like scalability, privacy, and interoperability persist. This study explores the scarcity of real-world blockchain implementations in supply chain and logistics since we have not witnessed many real-world deployments of blockchain-based solutions in the field. Puzzled by this, we integrate technology, user experience, and operational efficiency to illuminate the complex landscape of blockchain integration. We present blockchain-based solutions in three use cases, comparing them with alternative designs and analyzing them in terms of technical, economic, and operational aspects. Insights from a tailored questionnaire of 50 questions addressed to practitioners and experts offer crucial perspectives on blockchain adoption. One of the key findings from our work shows that half of the companies interviewed agree that they will miss the potential for competitive advantage if they do not invest in blockchain technology, and 61% of the companies surveyed claimed that their customers ask for more transparency in supply chain-related transactions. However, only one-third of the companies were aware of the main features of blockchain technology, which shows a lack of knowledge among the companies that may lead to a weaker blockchain adaption in supply chain use cases. Our readers should note that our study is specifically contextualized in a Netherlands-funded national project. We hope that researchers as well as stakeholders in supply chain and logistics can benefit from the insights of our work.
24 February 2022 in IEEE Open Journal of Signal Processing
With the emerging of e-commerce, package theft is at a high level: It is reported that 1.7 million packages are stolen or lost every day in the U.S. in 2020, which costs $25 million every day for the lost packages and the service. Information leakage during transportation is an important reason for theft since thieves can identify which truck is the target that contains the valuable products. In this paper, we address the privacy and security issues in bin-packing, which is an algorithm used in delivery centers to determine which packages should be loaded together to a certain truck. Data such as the weight of the packages is needed when assigning items into trucks, which can be called bins. However, the information is sensitive and can be used to identify the contents in the package. To provide security and privacy during bin-packing, we propose two different privacy-preserving data publishing methods. Both approaches use differential privacy (DP) to hide the existence of any specific package to prevent it from being identified by malicious users. The first approach combines differential privacy with k-anonymity, and the other one applies clustering before differential privacy. Our extensive analyses and experimental results clearly show that our proposed approaches have better privacy guarantees, better efficiency, and better performance than the existing works that use either differential privacy or k-anonymity.
1 April 2022 in Journal of Physics: Conference Series
Since it does not depend on the starting point selection, data field clustering can perform unsupervised clustering according to the data distribution characteristics. However, due to its drawback of high computational complexity caused by iterative updates, it is not suitable for the scenarios with high real-time requirements such as radar signal sorting. In this paper, an improved method of starting point selection is proposed to address the problems of low timeliness and poor interference immunity of data field clustering in radar signal sorting. The performance of the improved algorithm is simulated and verified in a complex electromagnetic environment, and the results show that the improvement of the data field clustering in this paper improves the performance of the algorithm.
E-commerce platforms generate vast amounts of customer behavior data, such as clicks and purchases, from millions of unique users every day. However, effectively using this data for behavior understanding tasks is challenging because there are usually not enough labels to learn from all users in a supervised manner. This paper extends the BERT model to e-commerce user data for pre-training representations in a self-supervised manner. By viewing user actions in sequences as analogous to words in sentences, we extend the existing BERT model to user behavior data. Further, our model adopts a unified structure to simultaneously learn from long-term and short-term user behavior, as well as user attributes. We propose methods for the tokenization of different types of user behavior sequences, the generation of input representation vectors, and a novel pretext task to enable the pre-trained model to learn from its own input, eliminating the need for labeled training data. Extensive experiments demonstrate that the learned representations result in significant improvements when transferred to three different real-world tasks, particularly compared to task-specific modeling and multi-task representation learning