Today, artificial intelligence (AI) and deep learning (DL) methods are exploited in a wide gamut of products. DL models are trained on GPGPU systems, achieving 5-40x speedup wrt CPU-based servers. ANDREAS develops advanced scheduling solutions optimizing DL training run- time performance and their energy consumption in disaggregated GPGPU clusters. 2x speed-up and 50% energy savings are expected.

LEMON system allows to study existing city infrastructure and patterns of bicycle usage by cyclists to improve city micro-mobility. In addition, it counts with an anti-theft functioning mode. Adaptation of the system to Narrowband-IoT networks will allow to boost the battery autonomy from 40 days to 10-12 months in active tracking mode. The enhanced product will be tested in a pilot in Spain.

BLEeper is a patent-pending approach that utilizes low-cost solar-powered water-proof Bluetooth beacons across geo-fenced shoreline areas (land and on coastal water buoys), in order to deliver high-accuracy location tracking for persons equippedwith any type of low-cost Bluetooth wearable (e.g. wristbands, life-vests). BLEeper delivers superior coastal surveillance, compared to any other available solution, leading to significantly increased levels of safety during shoreline activities.

This TTX considers soil humidity prediction system based on the Received Signal Strength Indicator (RSSI) generated from the underground LoRa beacon and related Machine Learning techniques. As a consequence, given energy efficient solution is cost effective and easier to maintain due to the prolonged battery lifetime. Such robust, but simple technology is a great candidate for becoming a strong competitor in the smart agriculture market.

The goal of the project is to implement a low energy IoT solution for smart home automation. The proposed solution has advantages such as lower price, lower energy consumption, many features, higher reliability, etc. andcould be used for many applications. Our first use case is to develop a smart solar heating controller using ultra low energy processor, cutting-edge techniques and know-how for additional saving.

EnergySequence is an energy efficiency web intelligence platform delivering data driven energy conservation measures for the industry sector, ReMoni’s smart sensors will power up real time performance by customizing its edge computing capabilities, and extend deployment features through an ad-hoc wireless sensor network for heat, electricity and flow, with energy harvesting capabilities.

NplusT intends to extend its product line with a new technology, targeting the high-speed characterization of non-volatile memory (NVM) devices. This feature is essential for mass storage (SSD, ...) makers in the optimization of their products. PCBDesign will transfer its high-speed communication technology, in order to follow the NVM roadmap: increased density, higher speed, lower voltages.

Effective power measurement is critical for the efficient development of Customized Low-Energy Computing (CLEC) systems. The NIPOLECS project will reduce the selling price of NTNU’s non-intrusive Lynsyn power measurement board by 3X and thereby create a competitive product to be sold by Sundance.

The TTX brief description will be published at the end of the TTX.

MIP is a vision of a magnetic data storage technology tailored for industrial applications and consumer products, to be used as a universal rewritable data carrier. This brings an advantage over competing technologies, such as barcodes, etc. Stored information in components can be updated during their life cycle. The information is not visible, and the medium has high temperature and chemical resistances. Hence, the stored data is inherently safe, reliable and suitable in many applications.

ondemand_videoCheck the TTX presentation video

This project presents the REMAP IP, a hardware manager for low-latency chip-to-chip interconnection, targeting low-energy disaggregated platforms and datacenters. REMAP enables on- demand system scaling; processing nodes can dynamically hot- plug remote resources (e.g. memory, accelerators), following application needs on performance and / or dataset sizes. The IP is already tested, has a very light resource / energy footprint, and thus easily fitting into small low-power MPSoCs.

Tooff.in is an IoT integrated platform consisting of a NBIoT multimodal sensoring device for the characterization and position tracking of construction tools. By attaching a universal sensor to the outer casing of any construction tool, we can forecast failures, enforce preventive maintenance and prevent thefts. A SaaS model will be examined that provides progressive tariff billing, therefore incentivizing clients to gradually adopt our service and severely minimize their operational costs.

Based on IIoT Infrastructure and Big Data Analytics technology our portable software solutions enable for highly sensitive process monitoring and optimization of industrial automated (e. g. manufacturing) processes. The implemented tools are based on generic algorithms for data driven modelling and additional process specific services and use information extracted from existing control and process layer data.

This project aims to build urban networks based in intercommunicated nodes made of BLE (Bluetooth Low Energy) trackers to deploy multiple services based in geolocation at low cost and extremely consumption.

The main objective of the Eco-Rural-IoT project is the reduction of the consumption of power, water and even phytosanitary treatments through the research and innovation in techniques and intelligent algorithms which will be incorporated to the unified Nebusens' Rural-IoT platform, aimed at the management of farming resources in the agriculture and livestock sector by means of IoT devices.

NOx emissions are a societal challenge in Europe due to the adverse health effects it causes. Currently the monitoring of such gas is performed by expensive and stationary sensor modules. Nox.Box will offer a mobile low cost, low-power consuming alternative to monitor NOx on large scales and with high temporal and spatial resolution and an online control platform.

ondemand_videoCheck the TTX presentation video

Tomappo is a digital gardening assistant enabling anyone to grow their own vegetables. Within Carrots, Lifely’s social sensors will be customized for use with Tomappo. This will add new dimension to Tomappo leading to a better product for users and new revenue stream for company receiving technology, while also benefit the owner of the technology by providing a new use-case for their sensors.

ondemand_videoCheck the TTX presentation video

The simulation environment enables the full integration of UPMEM’s DPU in a complete DRAM/Controller simulation framework. This is an essential key to maintain a seamless transfer of the RTL based DPU design into DRAM technology.

EVErMORE TTX experiment aims at developing the next generation [GAP-8 IoT processor from GreenWaves Technologies](https://greenwaves-technologies.com/en/gap8-the-internet-of-things-iot-application-processor/). Exploiting the adaptive management architecture for process and temperature compensation developed at University of Bologna, coupled to the low-voltage capabilities of 22nm FD-SOI technology, is expected to improve the energy efficiency of current generation GreenWaves Technology processors by 6x, enabling new applications and opening new market opportunities.

ondemand_videoCheck the TTX presentation video

In the scope of the proposed TTX project, an upgraded system prototype will be implemented, with an actual SAVVY®ECG sensor, by connecting the accelerometer sensor to the SAVVY processor through an available serial interface, by integrating the accelerometer firmware into the SAVVY software and by incorporation the posture and activity data into the existing ECG radio packets.

Integration of the Montr Narrowband IoT equipped emergency button in the Smarthelp ecosystem. With this integration emergency messaging will reach a next level in terms of speeding up the process of alerting emergency services with all the specific information they need.

This TTX will transfer the University of Salento recognized skills on wirelessly-powered Computational-RFID technology for IoT to the SME Spica, by defining a new cost-effective battery-less CLEC-based tag enabling the smart traceability of fresh and frozen fish. By performing computation, communication, and sensing to check the food product integrity, the solution will improve the SME business.