Explore the vast range of titles available.

This paper introduces SmartBarrel, an innovative IoT-based sensory system that monitors and forecasts wine fermentation processes. At the core of SmartBarrel are two compact, attachable devices—the probing nose (E-nose) and the probing tongue (E-tongue), which mount directly onto stainless steel wine tanks. These devices periodically measure key fermentation parameters: the nose monitors gas emissions, while the tongue captures acidity, residual sugar, and color changes. Both utilize low-cost, low-power sensors validated through small-scale fermentation experiments. Beyond the sensory hardware, SmartBarrel includes a robust cloud infrastructure built on open-source Industry 4.0 tools. The system leverages the ThingsBoard platform, supported by a NoSQL Cassandra database, to provide real-time data storage, visualization, and mobile application access. The system also supports adaptive breakpoint alerts and real-time adjustment to the nonlinear dynamics of wine fermentation. The authors developed a novel deep learning model called V-LSTM (Variable-length Long Short-Term Memory) to introduce intelligence to enable predictive analytics. This auto-calibrating architecture supports variable layer depths and cell configurations, enabling accurate forecasting of fermentation metrics. Moreover, the system includes two fuzzy logic modules: a device-level fuzzy controller to estimate alcohol content based on sensor data and a fuzzy encoder that synthetically generates fermentation profiles using a limited set of experimental curves. SmartBarrel experimental results validate the SmartBarrel’s ability to monitor fermentation parameters. Additionally, the implemented models show that the V-LSTM model outperforms existing neural network classifiers and regression models, reducing RMSE loss by at least 45%. Furthermore, the fuzzy alcohol predictor achieved a coefficient of determination (R2) of 0.87, enabling reliable alcohol content estimation without direct alcohol sensing.

This paper presents a new deep learning model called the stranded Long Short-Term Memory. The model utilizes arbitrary LSTM recurrent neural networks of variable cell depths organized in classes. The proposed model can adapt to classifying emergencies at different intervals or provide measurement predictions using class-annotated or time-shifted series of sensory data inputs. In order to outperform the ordinary LSTM model’s classifications or forecasts by minimizing losses, stranded LSTM maintains three different weight-based strategies that can be arbitrarily selected prior to model training, as follows: least loss, weighted least loss, and fuzzy least loss in the LSTM model selection and inference process. The model has been tested against LSTM models for forecasting and classification, using a time series of temperature and humidity measurements taken from meteorological stations and class-annotated temperature measurements from Industrial compressors accordingly. From the experimental classification results, the stranded LSTM model outperformed 0.9–2.3% of the LSTM models carrying dual-stacked LSTM cells in terms of accuracy. Regarding the forecasting experimental results, the forecast aggregation weighted and fuzzy least loss strategies performed 5–7% better, with less loss, using the selected LSTM model strands supported by the model’s least loss strategy.

This paper presents FireVision, an innovative platform and model for real-time fire detection and monitoring. The platform utilizes automated drone flights to collect high-resolution imagery in both suburban and forested settings. Ensemble deep learning inference, based on Mask R-CNN weak learners, is employed to trigger alerts. Detection performance is further enhanced by integrating ResNet-50, ResNet-101, and ResNet-152 classifiers, which can be deployed in the cloud or on the drone’s edge co-processing units. Additionally, a fire criticality index is introduced, leveraging detection bounds and masks to assess the severity of fire events, alongside an automated drone path-planning algorithm for identifying critical fire incidents. Experiments were conducted using a supervised, mask-annotated dataset to evaluate model accuracy and inference speed across various cloud and edge computing configurations. Results indicate that ResNet-101 surpasses ResNet-50 by 5 to 12.5 percent in mAP@0.5 mask accuracy, with an 18 percent increase in inference time on the cloud and a 27 percent increase on the drone edge device GPU. In comparison, ResNet-152 achieves a 0.5 to 1.2 percent improvement in mAP@0.5 over ResNet-101, but its inference time is nine times slower in the cloud and 1.3 times slower on the GPU.

Blindness and low vision are increasing serious public health issues that affect a significant percentage of the population worldwide. Vision plays a crucial role in spatial navigation and daily activities. Its reduction or loss creates numerous challenges for an individual. Assistive technology can enhance mobility and navigation in outdoor environments. In the field of orientation and mobility training, technologies with haptic interaction can assist individuals with visual impairments in learning how to navigate safely and effectively using the sense of touch. This paper presents a virtual reality platform designed to support the development of navigation techniques within a safe yet realistic environment, expanding upon existing research in the field. Following extensive optimization, we present a visual representation that accurately simulates various 3D tile textures using graphics replicating real tactile surfaces. We conducted a user interaction study in a virtual environment consisting of 3D navigation tiles enhanced with tactile textures, placed appropriately for a real-world scenario, to assess user performance and experience. This study also assess the usability and user experience of the platform. We hope that the findings will contribute to the development of new universal navigation techniques for people with visual impairments.

This paper presents the development and evaluation of a smartphone application designed to improve accessibility for blind users. It uses the lightweight EfficientDet-lite2 model and the comprehensive COCO dataset in order to provide real-time object detection. The novelty of the application is in the integration of haptic feedback, which is activated when users touch objects that are detected on the screen, combined with audio notifications that announce the name of the detected object in multiple languages. This multimodal feedback mechanism helps blind users to recognize, explore, and move within their environment more effectively and safely. Extensive usability and user experience evaluation was conducted with blind and blindfolded users. The evaluation assessed the usability, effectiveness, accessibility, and user satisfaction and experience of the application. Additionally, a comparative analysis was performed between the use of haptic feedback and scenarios where haptic feedback was disabled. The results show a higher level of user satisfaction, greater ease of use, and significant potential for improving the independence of blind people when the haptic feedback is enabled. The findings also suggest that the inclusion of haptic feedback significantly enhances the user experience. This study underlines the importance of multimodal feedback systems in assistive technologies and the potential of mobile applications to provide accessible solutions for blind users.

Modern irrigation systems utilize sensors and actuators, interconnected together as a single entity. In such entities, A.I. algorithms are implemented, which are responsible for the irrigation process. In this paper, the authors present an irrigation Open Watering System (OWS) architecture that spatially clusters the irrigation process into autonomous irrigation sections. Authors’ OWS implementation includes a Neuro-Fuzzy decision algorithm called FITRA, which originates from the Greek word for seed. In this paper, the FITRA algorithm is described in detail, as are experimentation results that indicate significant water conservations from the use of the FITRA algorithm. Furthermore, the authors propose a new communication protocol over LoRa radio as an alternative low-energy and long-range OWS clusters communication mechanism. The experimental scenarios confirm that the FITRA algorithm provides more efficient irrigation on clustered areas than existing non-clustered, time scheduled or threshold adaptive algorithms. This is due to the FITRA algorithm’s frequent monitoring of environmental conditions, fuzzy and neural network adaptation as well as adherence to past irrigation preferences.

This article explores the MELOS project, a collaborative initiative dedicated to the documentation and digital management of historical Greek music recordings. Developed as part of the \"Research-Create-Innovate\" program, the project integrates collections from multiple institutions into a unified, open-source platform using the ReasonableGraph system. The study focuses on the Vassilis Tsitsanis Collection, highlighting the complexities of cataloguing and analyzing Greek urban folk-popular music. By structuring metadata based on a hierarchical ontology and employing interdisciplinary methodologies, the platform enhances access to discographic material while addressing longstanding gaps in research. The article underscores the significance of commercial recordings as musicological sources, advocating for an expanded, scientifically grounded approach to their study and preservation.

The rapid integration of generative AI in education often frames teachers as technology users who primarily need technical training. Existing prompt engineering frameworks offer technical guidance but have limited grounding in theories of teacher professional development or reflective practice. This misses a key feature of prompt engineering: prompting can externalize pedagogical thinking, making AI interaction a process of knowledge externalization. Through systematic conceptual analysis, this paper proposes a reconceptualization of prompt engineering from a technical competency to a reflective professional practice. The methodology integrates three theoretical traditions: Schön’s reflective practice theory (for externalizing tacit knowledge), Wiggins and McTighe’s backward design (for structuring instructional decisions), and Celik’s AI-TPACK framework (as integrated knowledge base). This synthesis suggests that effective prompting can be understood as an act of pedagogical externalization requiring integrated professional knowledge. The paper develops a seven-strategy framework (RPE framework) as an analytic lens for examining prompt engineering sophistication. This theoretical framework offers theory-derived hypotheses that require future empirical validation rather than presenting verified outcomes. Ultimately, the RPE framework offers a conceptual basis for potentially shifting the focus from technical training to teacher professional development by repositioning educators as AI-assisted instructional designers rather than mere AI users.

Sensory and haptic data transfers to critical real-time applications over the Internet require better than best effort transport, strict timely and reliable ordered deliveries. Multi-sensory applications usually include video and audio streams with real-time control and sensory data, which aggravate and compress within real-time flows. Such real-time are vulnerable to synchronization to synchronization problems, if combined with poor Internet links. Apart from the use of differentiated QoS and MPLS services, several haptic transport protocols have been proposed to confront such issues, focusing on minimizing flows rate disruption while maintaining a steady transmission rate at the sender. Nevertheless, these protocols fail to cope with network variations and queuing delays posed by the Internet routers. This paper proposes a new haptic protocol that tries to alleviate such inadequacies using three different metrics: mean frame delay, jitter and frame loss calculated at the receiver end and propagated to the sender. In order to dynamically adjust flow rate in a fuzzy controlled manners, the proposed protocol includes a fuzzy controller to its protocol structure. The proposed FRTPS protocol (Fuzzy Real-Time haPticS protocol), utilizes crisp inputs into a fuzzification process followed by fuzzy control rules in order to calculate a crisp level output service class, denoted as Service Rate Level (SRL). The experimental results of FRTPS over RTP show that FRTPS outperforms RTP in cases of congestion incidents, out of order deliveries and goodput.

This paper investigates the effect of tactile feedback on the power efficiency and timing of controlling a remote robotic arm using a custom-built haptic glove. The glove integrates flex sensors to monitor finger movements and vibration motors to provide tactile feedback to the user. Communication with the robotic arm is established via the ESP-NOW protocol using an Arduino Nano ESP32 microcontroller (Arduino, Turin, Italy). This study examines the impact of tactile feedback on task performance by comparing precision, completion time, and power efficiency in object manipulation tasks with and without feedback. Experimental results demonstrate that tactile feedback significantly enhances the user’s control accuracy, reduces task execution time, and enables the user to control hand movement during object grasping scenarios precisely. It also highlights its importance in teleoperation systems. These findings have implications for improving human–robot interaction in remote manipulation scenarios, such as assistive robotics, remote surgery, and hazardous environment operations.