This appliance enables competitive advantage with respect to performance, scalability, efficiency and cost-savings. The two-fold nature of the appliance makes it appealing to a broad audience of application providers. The success stories include Vodafone Automotive, leader of the automotive market with a vast amount of data collected nowadays on vehicles and later processed via analytics techniques to infer valuable information.
The dimensionality of the input data is initially shrinked by the Principal Component Analysis (PCA) and then the density-based clustering is employed
Addressing the specific challenges in processing and clustering a large amount of data gathered from Internet of Things (IoT) devices
High security based on advanced encryption algorithms
This appliance tackles a hot problem in the automotive sector: the identification of the number of drivers of a specific vehicle. To this end, the IoT appliance provides a turnkey implementation of a data analytics workflow specifically designed to accurately perform this analysis. The analysis employs a set of raw data collected by the devices installed on the vehicles and it is composed of two main steps:
1. Raw data gets aggregated in a set of features aimed at characterizing the driving style;
2. The number of drivers is identified by the number of clusters found in the aggregated data by a high dimensional clustering method provided by the appliance itself.
You can choose from a wide range of modules forming a heterogeneous cluster. These may be microservers with high-performance x86 or ARM64 as well as low-power ARM processors with the latter also providing GPU computing capabilities. In addition to the CPU-based microservers, FPGAs are available for specialized applications. PCIe extension cards are also supported for even further flexibility.
X86_64 multi-core CPUs
ARM multi-core CPUs
GPU (to be evaluated)
Altera Stratix 10 SX Series FPGA for SEEs
Greatly efficient and with lower cost.
9 High-Performance Microservers
48 Low-Power Microservers
Ready for the most demanding challenges.
27 High-Performance Microservers
144 Low-Power Microservers
The most powerful option.
45 High-Performance Microservers
240 Low-Power Microservers