The design of immersive soundscape experiences, both for artistic and informative purposes, is an established field in Auditory Display. This paper describes the process of designing historically informed soundscapes to be incorporated in modern travel-guide applications. The work stems from the research project TRACCE (TRavelogue with Augmented Cultural & Contemporary Experience), which focuses on the design and development of a platform for augmented cultural routes. Using this platform, hikers can follow the journey of 18th and 19th century travelers, having access to the original travelogues, tracked routes, and a wide variety of modern information. User experience is augmented by means of visual and auditory reconstructions of the original surrounding environments in several identified points of interest in each path. Apart from the creative process and technical details, the paper discusses the design challenges, which mainly stem from a) the limited data available which would allow an accurate and convincing reconstruction of the acoustic environments, b) the need for diverse auditory displays which would grasp the users’ attention, and c) the difficulty in designing soundscapes which would be interesting, appropriate, and informative for a wide audience of various age groups, educational backgrounds, and sensory abilities.

Recommendation engines are widely used in order to predict the rating that a user would give to an item based on the user's past behavior. Modern recommendation engines are based on computational intensive algorithms like collaborative filtering that needs to process huge sparse matrices in order to provide efficient results. This paper presents a novel scheme for the acceleration of Alternating Least Squares-based (ALS) collaborative filtering for recommendation engines that can be used to speedup significantly the processing time and also reduce the energy consumption of computing platforms. The proposed scheme is implemented in reconfigurable logic and is mapped to the Pynq platform that is based on an all-programmable MPSoC Zynq system. The hardware acceleration is integrated with the Spark framework and evaluated on real benchmarks from movielens. The performance evaluation shows that the proposed scheme can achieve up to 120x kernel speedup and up to 12x energy-efficiency compared to the embedded ARM processor of Zynq.