Search

Binarization is an extreme quantization technique that is attracting research in the Internet of Things (IoT) field, as it radically reduces the memory footprint of deep neural networks without a correspondingly significant accuracy drop. To support the effective deployment of Binarized Neural Networks (BNNs), we propose CBin-NN, a library of layer operators that allows the building of simple yet flexible convolutional neural networks (CNNs) with binary weights and activations. CBin-NN is platform-independent and is thus portable to virtually any software-programmable device. Experimental analysis on the CIFAR-10 dataset shows that our library, compared to a set of state-of-the-art inference engines, speeds up inference by 3.6 times and reduces the memory required to store model weights and activations by 7.5 times and 28 times, respectively, at the cost of slightly lower accuracy (2.5%). An ablation study stresses the importance of a Quantized Input Quantized Kernel Convolution layer to improve accuracy and reduce latency at the cost of a slight increase in model size. [ABSTRACT FROM AUTHOR]

Datasets are key to developing new machine learning-based applications but are very costly to prepare, which hinders research and development in the field. We propose an edge-to-cloud end-to-end system architecture optimized for sport activity recognition dataset collection and application deployment. Tests in authentic contexts of use in four different sports have revealed the system's ability to effectively collect machine learning-usable data, with an energy consumption compatible with the timeframe of most of the sport types. The proposed architecture relies on a key feature of the Measurify internet of things framework for the management of measurement data (i.e.,.csv dataset management) and supports a workflow designed for efficient data labeling of signal timeseries. The architecture is independent of any specific sport, and a new dataset generation application can be set up in a few days, even by novice developers. With a view to concretely supporting the R&D community, our work is released open-source. [ABSTRACT FROM AUTHOR]

A realistic representation of the traffic participants is a key feature of serious games for driving. We propose a novel method for improving the behavioral planning of non-player vehicles (NPVs) by supporting implementation of (i) “human-like”, high-level decision making and (ii) different driving styles. The method relies on the deep reinforcement learning (DRL) technology, which is gaining ever more interest in the real-world automated driving research. We designed a system architecture including advanced driving assistance systems (ADAS) and trained the agent in the highway-env DRL environment. Compared to a low-level decision making system, our system performs better both in terms of safety and speed. Moreover, the proposed approach allows reducing the number of training steps by more than one order of magnitude. This makes the development of new models much more efficient. As a second main contribution, we demonstrate that it is possible to train agents characterized by different driving behaviors, by tweaking the weights of the factors of a general DRL reward function. This approach avoids heuristic coding of the driving styles, saving development and maintenance time. The developed agent models can then be seamlessly deployed as NPVs in any target SG in the same development environment (i.e., highway-env). Furthermore, the information and lessons learned presented in this article can be useful to effectively and efficiently train similar agents in their target SG environment. [ABSTRACT FROM AUTHOR]

As timely information about a project's state is key for management, we developed a data toolchain to support the monitoring of a project's progress. By extending the Measurify framework, which is dedicated to efficiently building measurement-rich applications on MongoDB, we were able to make the process of setting up the reporting tool just a matter of editing a couple of.json configuration files that specify the names and data format of the project's progress/performance indicators. Since the quantity of data to be provided at each reporting period is potentially overwhelming, some level of automation in the extraction of the indicator values is essential. To this end, it is important to make sure that most, if not all, of the quantities to be reported can be automatically extracted from the experiment data files actually used in the project. The originating use case for the toolchain is a collaborative research project on driving automation. As data representing the project's state, 330+ numerical indicators were identified. According to the project's pre-test experience, the tool is effective in supporting the preparation of periodic progress reports that extensively exploit the actual project data (i.e., obtained from the sensors—real or virtual—deployed for the project). While the presented use case concerns the automotive industry, we have taken care that the design choices (particularly, the definition of the resources exposed by the Application Programming Interfaces, APIs) abstract the requirements, with an aim to guarantee effectiveness in virtually any application context. [ABSTRACT FROM AUTHOR]

There is a growing body of research in the literature that investigates the relationship between emotions and decision-making in socio-economic contexts. Previous research has used Serious Games (SGs) based on game theory paradigms with socio-economic contexts to explore this relationship in controlled settings, but it is unclear whether such SGs can be applied in the wild, which would improve their usability in natural settings. The emergence and widespread availability of mobile computing technologies have enabled the creation of diverse SG implementations. We developed a mobile SG that combines four socio-economic interactions (trust game, ultimatum game, dictator game, prisoner's dilemma game) into one narrative and conducted an initial experiment with eight participants. This study discusses the challenges of deploying SGs in the wild and proposes solutions to overcome them. The results from the preliminary user experience experiment indicate that the SG is a suitable tool for emotion elicitation in the wild and that the results are similar to those observed in previous studies under controlled environments. We argue that these findings suggest that mobile SGs have potential for studying the relationship between emotions and decision-making in socio-economic contexts in the wild, improving the reach of these methods beyond laboratory settings. [ABSTRACT FROM AUTHOR]

The International Journal of Serious Games has published its latest issue, which includes seven articles covering a range of topics. One article explores the use of gamification to disseminate oral narratives and cultural expressions associated with tribal fabrics in Northeast India. Another article investigates the use of a web-based serious game called BehaviourCoach for health promotion, with positive feedback from participants. A third article presents a gamified shopping system using location-based technologies, showing a positive correlation between gamification strategies and customer experience. Other articles discuss the integration of AI in role-playing activities, the validity of ChatGPT as a tool for serious game design, and the implementation of knowledge tracing algorithms in a telecommunications serious game. Lastly, a free online game called Zarmelo Game is presented, which promotes collaborative and reflective processes in educational activities related to sets and quantifiers. [Extracted from the article]

Affective disorders can greatly influence the everyday lives of neurotypical and autistic individuals. As platforms that promote engagement, computer-based serious games (CSGs) have been previously proposed as therapies to treat affective disorders for both populations. However, these CSGs were assessed on a wide variety of experimental conditions, and there is a lack of comparative studies on their effectiveness. In this study, we identified and analyzed 37 interventions of CSGs for affective disorders in autistic and neurotypical individuals from 507 initial search results from four databases (Embase, Scopus, Web Of Science and IEEE Xplore), using concepts such as 'serious-games', 'affective-disorders', 'autism' and 'neurotypical'. A total of 21 different CSGs were identified that were evaluated with 30 different outcome measures in the reviewed interventions. A positive impact was reported in 22 of them; specifically, all instances of depression interventions reported a positive impact of CSG therapies. Our comparative analysis indicates that CSG applications could be effective in treating affective disorders in autistic and neurotypical individuals. Additionally, our analysis identifies CSG design characteristics that might be useful in applications involving depression, anxiety and phobias. Based on these characteristics, we provide a set of recommendations for CSG interventions for affective disorder therapies. [ABSTRACT FROM AUTHOR]

Serious virtual worlds (SVWs) represent a great opportunity for learning and should embed a lot of high-quality contextualised information so that the player can take the most from his or her exploration of the environment. This requires defining new methodologies and tools for effective production. We have investigated this issue in implementing a couple of SVWs and abstracted a conceptual framework relying on the task-based learning pedagogical theory. The model defines games set in realistic SVWs enriched with embedded educational tasks. Tasks are simple trial activities that embody units of knowledge. The player can discover them in his or her SVW exploration and interact with them in order to construct meaning, build lasting memories and deepen understanding of the featured item(s). The model involves pedagogical task annotation--which allows decoupling the tasks, which can be reused in different VWs from the definition of their delivery strategy in the context of a specific VW, which is specified by the VW designer and automatically managed by the run-time engine. This approach simplifies the authoring work. The visual Creative Toolkit (CT) we have developed is being used for producing contents for the 15 reconstructed cultural cities that will be featured in the first version of the Travel in Europe VW. The paper described the overall framework and the details of the CT. It also presented an implemented example, briefly discussing the methodology we have followed for developing cultural heritage content.

The International Journal of Serious Games has released its eleventh volume, featuring five articles on various topics. One article explores the use of videogames and open feedback systems to enhance probabilistic reasoning skills. Another article discusses a multiplayer online role-playing game developed for student teachers. A third article presents a catalogue designed to help teachers find educational serious games. The fourth article introduces a framework for designing a virtual reality game that promotes the cultural heritage of a city. The final article reviews the gamification of cybersecurity awareness for non-IT professionals. These articles offer valuable insights into the use of serious games for educational and cultural purposes. [Extracted from the article]

The ever more extensive data collection from Internet of Thing (IoT) devices stresses the need for efficient application development tools. State-of-the-art IoT cloud services are powerful, but the best solutions are proprietary, and there is a growing demand for interoperability and standardization. We have investigated how to develop a nonvendor-locked framework, which exploits state of the art data management technologies, and targets effective and efficient development in this article. Focusing on the concept of measurement, we abstracted an architecture that could be applied in a variety of domains and contexts. We tested the framework and its workflow in four use cases analyzing data and enabling new services in health, automotive, and instruction. Our experience showed the benefits of the development tool, which is not tied to a commercial platform, nor requires the huge set-up times needed to start a project from scratch. The tool is released open-source, particularly supporting collaborative research. [ABSTRACT FROM AUTHOR]

As dynamic inductive power transfer for electric vehicles is growing in relevance, it is important to analyze solutions towards its deployment and integration in the cloud-based services for electric mobility. In this paper we present an Internet-enabling platform for Electric Vehicle Supply Equipment, which features a high-level Charging Station Control Unit and a Power Electronics Controller. The platform is a middleware that controls the charging process taking into account outside world information. Tests were performed in a safe driving track, in Italy, to verify the effectiveness and robustness of the installation, for one year, for a total of 120 drive hours, under various weather conditions. Tests showed the suitability of the platform in terms of ability to authenticate and authorize a vehicle even through a remote service, sequentially control each coil in a lane, monitor the charging process, assist the driver in keeping the vehicle aligned so as to maximize the energy exchange and deliver charging session information to the cloud (e.g. for billing). [ABSTRACT FROM AUTHOR]

The tomorrow's elastic adaptive mobility industrial research project developed eleven collaborative mobility apps addressing various traffic issues and scenarios. The apps, involving different aspects and degrees of collaboration (e.g., direct user participation, shared objectives, coordination, etc.), aim at increasing the driver/traveler awareness and support a better behavior. This paper describes the apps and the underlying system architecture shared by the participating car manufacturers. Then, it provides a user acceptance analysis grouping the apps according to the three main types of users and stakeholders: drivers, travelers, and administrators/operators. Data, collected in five European countries, shows that acceptance and expected impact are positive. The actual road-test experience did not diminish the high expectations raised by an initial presentation on paper, showing a good maturity of the prototypes. The Administrator app cluster shows a slightly better assessment, highlighting the importance of considering collaborative mobility as a system, including road, infrastructure, and traffic management. [ABSTRACT FROM AUTHOR]

Reality-enhanced gaming is an emerging serious game genre, that could contextualize a game within its real instruction-target environment. A key module for such games is the evaluator, that senses a user performance and provides consequent input to the game. In this project, we have explored an application in the automotive field, estimating driver performance in terms of fuel consumption, based on three key vehicular signals, that are directly controllable by the driver: throttle position sensor (TPS), engine rotation speed (RPM) and car speed. We focused on Fuzzy Logic, given its ability to embody expert knowledge and deal with incomplete information availability. The fuzzy models - that we iteratively defined based on literature expertise and data analysis - can be easily plugged into a reality-enhanced gaming architecture. We studied four models with all the possible combinations of the chosen variables (TPS and RPM; RPM and speed; TPS and speed; TPS, speed and RPM). Input data were taken from the enviroCar database, and our fuel consumption predictions compared with their estimated values. Results indicate that the model with the three inputs outperforms the other models giving a higher coefficient of determination (R2), and lower error. Our study also shows that RPM is the most important fuel consumption predictor, followed by TPS and speed. [ABSTRACT FROM AUTHOR]