Marco Mobilio

Alessandro Tundo, Marco Mobilio, Shashikant Ilager et al.

The advent of edge devices dedicated to machine learning tasks enabled the execution of AI-based applications that efficiently process and classify the data acquired by the resource-constrained devices populating the Internet of Things. The proliferation of such applications (e.g., critical monitoring in smart cities) demands new strategies to make these systems also sustainable from an energetic point of view. In this paper, we present an energy-aware approach for the design and deployment of self-adaptive AI-based applications that can balance application objectives (e.g., accuracy in object detection and frames processing rate) with energy consumption. We address the problem of determining the set of configurations that can be used to self-adapt the system with a meta-heuristic search procedure that only needs a small number of empirical samples. The final set of configurations are selected using weighted gray relational analysis, and mapped to the operation modes of the self-adaptive application. We validate our approach on an AI-based application for pedestrian detection. Results show that our self-adaptive application can outperform non-adaptive baseline configurations by saving up to 81\% of energy while loosing only between 2% and 6% in accuracy.

Hamza Amrani, Daniela Micucci, Marco Mobilio et al.

Several techniques have been proposed to address the problem of recognizing activities of daily living from signals. Deep learning techniques applied to inertial signals have proven to be effective, achieving significant classification accuracy. Recently, research in human activity recognition (HAR) models has been almost totally model-centric. It has been proven that the number of training samples and their quality are critical for obtaining deep learning models that both perform well independently of their architecture, and that are more robust to intraclass variability and interclass similarity. Unfortunately, publicly available datasets do not always contain hight quality data and a sufficiently large and diverse number of samples (e.g., number of subjects, type of activity performed, and duration of trials). Furthermore, datasets are heterogeneous among them and therefore cannot be trivially combined to obtain a larger set. The final aim of our work is the definition and implementation of a platform that integrates datasets of inertial signals in order to make available to the scientific community large datasets of homogeneous signals, enriched, when possible, with context information (e.g., characteristics of the subjects and device position). The main focus of our platform is to emphasise data quality, which is essential for training efficient models.

Oliviero Riganelli, Paolo Saltarel, Alessandro Tundo et al.

Hierarchical Temporal Memory (HTM) is an unsupervised learning algorithm inspired by the features of the neocortex that can be used to continuously process stream data and detect anomalies, without requiring a large amount of data for training nor requiring labeled data. HTM is also able to continuously learn from samples, providing a model that is always up-to-date with respect to observations. These characteristics make HTM particularly suitable for supporting online failure prediction in cloud systems, which are systems with a dynamically changing behavior that must be monitored to anticipate problems. This paper presents the first systematic study that assesses HTM in the context of failure prediction. The results that we obtained considering 72 configurations of HTM applied to 12 different types of faults introduced in the Clearwater cloud system show that HTM can help to predict failures with sufficient effectiveness (F-measure = 0.76), representing an interesting practical alternative to (semi-)supervised algorithms.

Alessandro Tundo, Chiara Castelnovo, Marco Mobilio et al.

Systems of systems are highly dynamic software systems that require flexible monitoring solutions to be observed and controlled. Indeed, operators have to frequently adapt the set of collected indicators according to changing circumstances, to visualize the behavior of the monitored systems and timely take actions, if needed. Unfortunately, dashboard systems are still quite cumbersome to configure and adapt to a changing set of indicators that must be visualized. This paper reports our initial effort towards the definition of an automatic dashboard generation process that exploits metamodel layouts to create a full dashboard from a set of indicators selected by operators.

Marco Mobilio, Oliviero Riganelli, Daniela Micucci et al.

Mobile operating systems evolve quickly, frequently updating the APIs that app developers use to build their apps. Unfortunately, API updates do not always guarantee backward compatibility, causing apps to not longer work properly or even crash when running with an updated system. This paper presents FILO, a tool that assists Android developers in resolving backward compatibility issues introduced by API upgrades. FILO both suggests the method that needs to be modified in the app in order to adapt the app to an upgraded API, and reports key symptoms observed in the failed execution to facilitate the fixing activity. Results obtained with the analysis of 12 actual upgrade problems and the feedback produced by early tool adopters show that FILO can practically support Android developers.FILO can be downloaded from https://gitlab.com/learnERC/filo, and its video demonstration is available at https://youtu.be/WDvkKj-wnlQ.

Anna Ferrari, Daniela Micucci, Marco Mobilio et al.

In the recent years there has been a growing interest in techniques able to automatically recognize activities performed by people. This field is known as Human Activity recognition (HAR). HAR can be crucial in monitoring the wellbeing of the people, with special regard to the elder population and those people affected by degenerative conditions. One of the main challenges concerns the diversity of the population and how the same activities can be performed in different ways due to physical characteristics and life-style. In this paper we explore the possibility of exploiting physical characteristics and signal similarity to achieve better results with respect to deep learning classifiers that do not rely on this information.

Marco Mobilio, Oliviero Riganelli, Daniela Micucci et al.

Dealing with the evolution of operating systems is challenging for developers of mobile apps, who have to deal with frequent upgrades that often include backward incompatible changes of the underlying API framework. As a consequence of framework upgrades, apps may show misbehaviours and unexpected crashes once executed within an evolved environment. Identifying the portion of the app that must be modified to correctly execute on a newly released operating system can be challenging. Although incompatibilities are visibile at the level of the interactions between the app and its execution environment, the actual methods to be changed are often located in classes that do not directly interact with any external element. To facilitate debugging activities for problems introduced by backward incompatible upgrades of the operating system, this paper presents FILO, a technique that can recommend the method that must be changed to implement the fix from the analysis of a single failing execution. FILO can also select key symptomatic anomalous events that can help the developer understanding the reason of the failure and facilitate the implementation of the fix. Our evaluation with multiple known compatibility problems introduced by Android upgrades shows that FILO can effectively and efficiently identify the faulty methods in the apps.

Marco Mobilio, Matteo Orrù, Oliviero Riganelli et al.

Cloud systems are complex, large, and dynamic systems whose behavior must be continuously analyzed to timely detect misbehaviors and failures. Although there are solutions to flexibly monitor cloud systems, cost-effectively controlling the anomaly detection logic is still a challenge. In particular, cloud operators may need to quickly change the types of detected anomalies and the scope of anomaly detection, for instance based on observations. This kind of intervention still consists of a largely manual and inefficient ad-hoc effort. In this paper, we present Anomaly Detection as-a-Service (ADaaS), which uses the same as-a-service paradigm often exploited in cloud systems to declarative control the anomaly detection logic. Operators can use ADaaS to specify the set of indicators that must be analyzed and the types of anomalies that must be detected, without having to address any operational aspect. Early results with lightweight detectors show that the presented approach is a promising solution to deliver better control of the anomaly detection logic.

Oliviero Riganelli, Marco Mobilio, Daniela Micucci et al.

Android apps must be able to deal with both stop events, which require immediately stopping the execution of the app without losing state information, and start events, which require resuming the execution of the app at the same point it was stopped. Support to these kinds of events must be explicitly implemented by developers who unfortunately often fail to implement the proper logic for saving and restoring the state of an app. As a consequence apps can lose data when moved to background and then back to foreground (e.g., to answer a call) or when the screen is simply rotated. These faults can be the cause of annoying usability issues and unexpected crashes. This paper presents a public benchmark of 110 data loss faults in Android apps that we systematically collected to facilitate research and experimentation with these problems. The benchmark is available on GitLab and includes the faulty apps, the fixed apps (when available), the test cases to automatically reproduce the problems, and additional information that may help researchers in their tasks.

Daniela Micucci, Marco Mobilio

The rise in life expectancy is one of the great achievements of the twentieth century. This phenomenon originates a still increasing interest in Ambient Assisted Living (AAL) technological solutions that may support people in their daily routines allowing an independent and safe lifestyle as long as possible. AAL systems generally acquire data from the field and reason on them and the context to accomplish their tasks. Very often, AAL systems are vertical solutions, thus making hard their reuse and adaptation to different domains with respect to the ones for which they have been developed. In this paper we propose an architectural solution that allows the acquisition level of an ALL system to be easily built, configured, and extended without affecting the reasoning level of the system. We experienced our proposal in a fall detection system.

Matteo Orrù, Marco Mobilio, Anas Shatnawi et al.

Smart Cities are future urban aggregations, where a multitude of heterogeneous systems and IoT devices interact to provide a safer, more efficient, and greener environment. The vision of smart cities is adapting accordingly to the evolution of software and IoT based services. The current trend is not to have a big comprehensive system, but a plethora of small, well integrated systems that interact one with each other. Monitoring these kinds of systems is challenging for a number of reasons.

Anas Shatnawi, Matteo Orrù, Marco Mobilio et al.

Cloud systems are complex and large systems where services provided by different operators must coexist and eventually cooperate. In such a complex environment, controlling the health of both the whole environment and the individual services is extremely important to timely and effectively react to misbehaviours, unexpected events, and failures. Although there are solutions to monitor cloud systems at different granularity levels, how to relate the many KPIs that can be collected about the health of the system and how health information can be properly reported to operators are open questions. This paper reports the early results we achieved in the challenge of monitoring the health of cloud systems. In particular we present CloudHealth, a model-based health monitoring approach that can be used by operators to watch specific quality attributes. The CloudHealth Monitoring Model describes how to operationalize high level monitoring goals by dividing them into subgoals, deriving metrics for the subgoals, and using probes to collect the metrics. We use the CloudHealth Monitoring Model to control the probes that must be deployed on the target system, the KPIs that are dynamically collected, and the visualization of the data in dashboards.

Daniela Micucci, Marco Mobilio, Paolo Napoletano

Smartphones, smartwatches, fitness trackers, and ad-hoc wearable devices are being increasingly used to monitor human activities. Data acquired by the hosted sensors are usually processed by machine-learning-based algorithms to classify human activities. The success of those algorithms mostly depends on the availability of training (labeled) data that, if made publicly available, would allow researchers to make objective comparisons between techniques. Nowadays, publicly available data sets are few, often contain samples from subjects with too similar characteristics, and very often lack of specific information so that is not possible to select subsets of samples according to specific criteria. In this article, we present a new dataset of acceleration samples acquired with an Android smartphone designed for human activity recognition and fall detection. The dataset includes 11,771 samples of both human activities and falls performed by 30 subjects of ages ranging from 18 to 60 years. Samples are divided in 17 fine grained classes grouped in two coarse grained classes: one containing samples of 9 types of activities of daily living (ADL) and the other containing samples of 8 types of falls. The dataset has been stored to include all the information useful to select samples according to different criteria, such as the type of ADL, the age, the gender, and so on. Finally, the dataset has been benchmarked with four different classifiers and with two different feature vectors. We evaluated four different classification tasks: fall vs no fall, 9 activities, 8 falls, 17 activities and falls. For each classification task we performed a subject-dependent and independent evaluation. The major findings of the evaluation are the following: i) it is more difficult to distinguish between types of falls than types of activities; ii) subject-dependent evaluation outperforms the subject-independent one

Daniela Micucci, Marco Mobilio, Paolo Napoletano et al.

Life expectancy keeps growing and, among elderly people, accidental falls occur frequently. A system able to promptly detect falls would help in reducing the injuries that a fall could cause. Such a system should meet the needs of the people to which is designed, so that it is actually used. In particular, the system should be minimally invasive and inexpensive. Thanks to the fact that most of the smartphones embed accelerometers and powerful processing unit, they are good candidates both as data acquisition devices and as platforms to host fall detection systems. For this reason, in the last years several fall detection methods have been experimented on smartphone accelerometer data. Most of them have been tuned with simulated falls because, to date, datasets of real-world falls are not available. This article evaluates the effectiveness of methods that detect falls as anomalies. To this end, we compared traditional approaches with anomaly detectors. In particular, we experienced the kNN and the SVM methods using both the one-class and two-classes configurations. The comparison involved three different collections of accelerometer data, and four different data representations. Empirical results demonstrated that, in most of the cases, falls are not required to design an effective fall detector.