Abstract Point-of-interest (POI) recommendation systems play an important role in various location-based services by improving the user experience. Previous research has leveraged large-scale visit records to predict a user’s next visit POI based on the behavior of similar users. However, with the increasing emphasis on privacy preservation, there is a shift towards zero-shot recommendation that does not require training and only uses individual visit history data. As a better alternative to traditional zero-shot recommender systems, this paper proposes a novel zero-shot recommender system leveraging the ability of pre-trained large language models (LLMs) to understand human behavior called ZeroPOIRec . ZeroPOIRec involves a profiler module that enables LLMs to extract individual user preferences from multiple aspects, including spatio-temporal patterns and individual characteristics, and a recommender module that enhances the zero-shot POI recommendation performance via candidate refinement and prioritization. Through experiments using a benchmark dataset and a newly introduced real-world dataset with semantic variables, we demonstrate that, despite ZeroPOIRec being a zero-shot approach, it outperforms state-of-the-art methods in terms of recommendation performance.

In this paper, we design an energy efficient MAC protocol for mobile sensor networks. In our MAC protocol, to reduce idle listening, each node has its listen-sleep schedule. A subset of nodes that follow the same schedule forms a virtual cluster. The network consists of multiple virtual clusters and nodes in one virtual cluster may follow a different listen- sleep schedule from that of nodes in another virtual cluster. Hence, to support a mobile sensor node that moves into a new virtual cluster that follows a different listen-sleep schedule, it is necessary to have a fast and energy efficient listen-sleep schedule adaptation protocol. To this end, in our MAC protocol, we utilize schedule information on border nodes between virtual clusters. This allows us to implement fast and energy efficient listen- sleep schedule adaptation, which consists of two main functions: energy efficient secondary listen period and smart scheduling adaptation. Simulation results show that our protocol can provide fast scheduling adaptation while achieving energy efficiency.

The IEEE 802.15.4 standard specifies the physical and medium access control layers designed for low-rate wireless personal area networks. Its operational frequency band includes the 2.4 GHz industrial, scientific and medical band, which is also used by other IEEE 802 wireless standards. This paper presents the coexistence model of IEEE 802.15.4 with IEEE 802.1 lb interference in fading channels and proposes two adaptive channel allocation schemes. The first avoids the IEEE 802.15.4 interference only and the second avoids both of the IEEE 802.15.4 and the IEEE 802.11b interferences. Numerical results show that by selecting a channel which gives the maximum signal to noise ratio to the system, the proposed algorithms are effective for avoiding the interferences and for max-imizing the network capacity.