Deep Learning (DL) algorithms are an extremely promising instrument in artificial intelligence. To foster their adoption in new applications and markets, a step forward is needed towards the implementation of DL inference on low-power embedded systems, enabling a shift to the edge computing paradigm. The main goal of ALOHA is to facilitate implementation of DL algorithms on heterogeneous low-energy computing platforms providing automation for optimal algorithm selection, resource allocation and deployment.

ALOHA Use cases

Speech recognition in smart industry

This scenario refers to Smart Industry, where Deep Learning is used for speech recognition. The objective of this use case is to develop an embedded speech recognition system that would activate/deactivate PLC-controlled tooling machinery or collaborative robot in an industrial environment, without relying on a cloud backend.

Read more and see the videos...

Surveillance of Critical Infrastructures

This scenario refers to Critical Infrastructures surveillance, where Deep Learning is meant to be used to define an intelligent video-based detection system for security in and around the critical infrastructure. A specific challenge is to use deep learning methods to enable technician after a short training to utilize advanced capabilities of modern surveillance techniques.


Medical decision assistant

This use-case refers to a DL-based smart assistant, which supports emergency room situations, identifying acute intracranial bleeds in non-contrast CT images. The consortium wants to assess the benefits provided by the ALOHA tool flow within the development of an embedded medical decision assistant, considering the requirements posed by the specific application in terms of accuracy and performance.



The features of the architecture that will execute the inference are taken into account during the whole development process, starting from the early stages such as pre-training hyperparameter optimization and algorithm configuration.


The tool flow implements support for agile development methodologies, to be easily adopted by SMEs and midcaps.


The development process considers that the system should adapt to different operating modes at runtime.


The development process is conceived to support novel processing platforms to be exploitable beyond the end of the project.


The development process automates the introduction of algorithm features and programming techniques improving the resilience of the system to attacks.

Parsimonious inference

In DL, good precision levels can be also obtained using algorithms with reduced complexity. All the optimization utilities in the ALOHA tool flow will consider the effects of algorithm simplification on precision, execution time, energy and power.

Latest News & Events

ALOHA use cases - Surveillance of Critical Infrastructures - Updates

Recent updates on the ALOHA Use case aimed at improving the Surveillance of Critical Infrastructures (Correctional Facilities, Central Banks, Transportation Systems, Public Health Facilities, Energy and Water supply chains).

Whithin the ALOHA project, PKE is working on Deep Learning based technologies to develop and improve intelligent video-based intrusion detection systems to secure such infrastructures. In this scenario, a currently open issue is the long time that lasts between the installation of a system at a specific site and the point in time at which it becomes reliable. Usually, an evaluation period of a few weeks up to multiple months is state of the art. In this period, algorithms are parameterized and tweaked for the optimal state. In the case of video surveillance for critical infrastructures, we deal with large areas and building complexes. Properly monitoring them may require hundreds or even thousands of cameras.

This increases the need for accuracy as a large number of false alarms or missed real alarms will turn the system ineffective. In this context, as the number of system components increases, energy efficiency becomes relevant to limit the overall operational costs. Power consumption becomes a critical element when we envision to use such a system in a mobile configuration, for instance for large events.
Obviously, the security aspect plays a very important role in a surveillance solution. For instance, the resiliency to input manipulations is a critical aspect to consider while planning such systems.


Security surveillance camera (left) and control room with surveillance system (right)

Using deep learning-based solutions for safety and security applications is an upcoming trend in the market. Such solutions are expected to boost the state of the art significantly, which is noted by world market leader HikVision. The market for embedded devices with deep learning accelerators is very dynamic at the moment with many Smart Camera producers announcing new products or including such technologies in their development roadmaps. The SAST platform, developed by a Bosch backed startup is an example of effort in this direction.

We expect the ALOHA Toolflow to improve our surveillance systems by providing efficient deep learning models tailored for our specific hardware needs. Another important expected benefit is the simplification of the design process as the ALOHA Toolflow is designed to automatically generate efficient deep learning models without the need of highly specialized knowledge.
In the surveillance use case, we are evaluating the use of the Toolflow to automatically design and train deep neural network models for object detection targeting smart cameras with dedicated deep learning accelerators.

We use state of the art object detection DNNs such as Yolo as a starting point. Based on that, the Toolflow generates design points that are similar to the initial model but better suited to the target hardware platform, according to input constrains such as power consumption, accuracy and security. Those models are trained and analyzed by the Toolflow according to those criteria and the resulting trained model can be ported to the target platform.


Toolflow surveillance project preset (left) and Surveillance use case Toolflow training outputs (right)


Visualization of detection results during training process (left) and Surveillance pre-set results (right)

As target platforms, we are evaluating the Xilinx Zynq-7000 SoC ZC706 and most recently, a smart camera with a Qualcomm hexagon 685 DSP featuring the android based SAST ecosystem for developing security camera applications.


SAST camera (left) and detection results from PKE dataset (right)

In the surveillance use case, we are also investigating the use of deep learning based behavior analysis to improve the quality of detections, reducing the number of false alarms. An important part of this analysis is the creation of our synthetic dataset for behavior analysis. With this concept, we want to mitigate the difficulty in acquiring a meaningful amount of positive data samples for training machine learning based algorithms.


Artificial images dataset for behaviour analysis


Project Coordinator
Giuseppe Desoli - STMicroelectronics

Scientific Coordinator
Paolo Meloni - University of Cagliari, EOLAB

Dissemination Manager
Francesca Palumbo - University of Sassari, IDEA Lab