Stuttering can make everyday conversations challenging, especially in situations that involve unfamiliar people or social pressure. While traditional therapy provides structured support, many individuals struggle to apply those techniques in real-world scenarios. Digital speech tools exist, but most focus on repetitive drills and rarely provide realistic, contextdriven speaking practice. We present EaseTalk, an AI-driven mobile application that allows users to practice real-life conversational scenarios in a supportive, self-paced environment. The app uses speech recognition and prompt-engineered large language models (LLMs) to detect speech disfluencies such as repetitions, prolongations and blocks. EaseTalk aims to empower users through independent, scenario-based speech practice with potential applications extending beyond stuttering into areas like social anxiety, interview preparation and language learning.
The explosive growth of the Internet of Things (IoT) demands security mechanisms that adapt to emerging threats. Telemetry meets this need by fusing federated learning, explainable AI, and privacy-preserving analytics into a multi-layer monitoring framework. Lightweight agents such as r-Monitoring impose only 0.27 % CPU overhead at device level, while the BACON federated anomaly detector safeguards system traffic. On a 21-sensor industrial robot, TELEMETRY's Nokia pipeline flagged subtle speed anomalies with 73% accuracy; within the NF-ToN-IoT corpus, BACON differentiated benign from malicious flows with 96% accuracy and markedly fewer false positives than signature baselines. The Misuse Detection Toolkit ensemble further achieved 97.7% validation accuracy across 50 training epochs, underscoring the framework's adaptability. Together, these layers cut detection latency and reduce on-device resource use, illustrating how ML-driven, federated monitoring can harden next-generation IoT deployments. Ongoing work explores graph-based analytics, adaptive models, and more scalable federation schemes.
Autonomous vehicles (AVs) are becoming integral to on-demand micro transit, offering the potential for safer, efficient, and sustainable transportation. However, AV deployment faces several challenges, including the lack of suitable roadways, varying travel conditions. Traditional routers prioritize speed and not reliability, leading to unpredictable operations and complications in planning. To address these, we introduce AVATAR, an autonomy-aware routing framework that prioritizes dependable, low-variance routes. Our approach encodes multiple objectives including road speed, speed variability, zoning areas, pedestrian encounters, and operator preferred roadways into edge-level routing engines. Objective optimized routes are generated, then scored using a multi-criteria decision-making process. User-configurable preference profiles, allow operators to define a balance between reliability and speed. AVATAR is a data-driven framework that supports both real-time AV operations and offline analysis, enabling transit operators to assess and refine routing strategies. Our experiments using real-world data from Silicon Valley, California, and Yokohama, Japan show that our approach significantly improves AV reliability and performance and advances the sustainable and scalable integration of AVs into future transportation networks.
With the growing adoption of location-based services, ensuring user privacy without compromising data utility has become a critical research focus. In this paper, we investigate the impact of different statistical noise distributions-Laplace, Gaussian, Exponential, Cauchy, and Uniform, on trajectory anonymization across different transportation modes using Differential Privacy. We propose a modality-wise anonymization approach and assess its effectiveness through two down-stream tasks utility metric: (i) counting the number of unique users within a predefined area, and (ii) predicting modes of transport. Experimental results on the two public datasets Geolife and Roma taxi reveal that our modality based anonymization retains high utility, achieving up to 5% improvement in micro-F1 scores compared to single-noise based anonymization and preserves user counts (deviates by 4 users) closely as of original data. These findings emphasize that downstream tasks play a pivotal role in designing privacy-preserving mechanisms while maintaining the practical usability of mobility data.
The authors of the article examined the modern challenges involved in developing an access control system for smart factories, focusing on the creation of an integrated solution for monitoring and managing the information security of the Internet of Things (IoT) through the integration of diverse tools and methods within a single system. In this paper, the information system is examined through the lens of system analysis, focusing on the interactions between the subjects and objects within the system. This perspective allows for an accurate assessment of the current state of objects, taking into account the system's architecture and its vulnerabilities, as well as the evolution of the system state over time. The approach proposed incorporates modern tools and software solutions, including intrusion detection systems (IDS), fuzzy testing, Software Bill of Materials (SBOM), and various machine learning (ML) techniques.
Optimizing traffic routing, specifically minimizing network travel time, has remained a long-standing concern since the development and adoption of ground vehicles. While several approaches have been proposed to guide drivers of ground vehicles towards traversing network paths that mitigate network congestion, or travel time, these approaches have consistently made simplifying assumptions regarding driver rationality preventing them from being implemented effectively in real-world settings. Modeling routing interactions as Stackelberg games between ground vehicle drivers and an intelligent traffic system offers a promising approach to developing network-wide routing solutions, but the role and impact of trust between network drivers and the system aiming to route traffic has been overlooked in existing literature. The work that I have conducted throughout my Ph.D. studies so far aims to address this gap in the literature by incorporating the human bias of trust into Stackelberg games between drivers and an intelligent traffic system. This is achieved by modeling drivers' trust towards the system, as well as system trust towards each driver, as stochastic variables. Algorithmic solutions that leverage trust to improve route recommendations, estimate evolving driver trust, and dynamically trade control among multiple potential vehicle drivers to mitigate traffic network travel time have been proposed as part of my ongoing Ph.D. research. Each of the proposed models and solutions contributes to a more realistic framework for ground vehicle traffic routing by explicitly accounting for trust from the perspective of drivers and intelligent transportation systems, ultimately enabling more effective, trust-aware routing strategies that can better adapt to real-world driver behavior.
Data Confidence Fabrics (DCFs) are emerging as a mechanism to obtain measurable trust in decentralized smart computing environments, while remote attestation (RA) is being established as a key mechanism for verifying security in distributed systems. However, both of these approaches remain underutilized in container orchestration platforms, resulting in inadequate trust guarantees, increased attack surface areas, and insufficient mechanisms for verifying the integrity of devices and applications. In this paper, we propose leveraging DCFs to integrate RA with software security practices, and utilizing this integration to securely onboard devices and containerized applications by tracing their provenance and analyzing vulner-abilities. This dual-level protection bridges device attestation measurements with measurements of application security to provide measurable and transparent confidence scores for both. The proposed approach brings trustworthiness into a distributed environment where devices are continuously monitored for malicious tampering, and applications are assessed before being run. We verified this approach on a setup representing real environments. Additionally, a machine learning model was put under test and trained on data weighted with confidence scores produced by our proposed approach. The model saw improved performance and accuracy, showing that this approach can increase the reliability of systems.
Induction motors are the primary way to convert electrical current into mechanical power. They are a fundamental component of industrial processes and equipment. Early fault detection and preventive maintenance are of great concern. In the last few years, many deep learning data-driven approaches have been used to detect faults in electric motors. This problem comes with two significant challenges: some faults are easier to detect using a specific sensor (e.g., vibration or current); in industrial applications, it is hard to obtain fault measurements. In most cases, only measurements of normal behaviour are available. This paper presents a multi-signal unsupervised anomaly detection system based on deep convolutional variational autoencoders (VAE). We use three sensors to sample from operating industrial motors: vibration, current, and magnetic flux. We divide the dataset into a training set, in which the network fits the nominal working condition of the motor. The system is then deployed in detection mode, analyzing the stream of data provided by the sensors. The experimental results show that the system accurately detects anomalies and has sufficient sensitivity to recognize changes in the motor load and behavior in practice.
This paper presents an enhanced edge-cloud service-continuity platform that integrates advanced Transport Layer Security (TLS) 1.3 features to address performance and security challenges in dynamic smart environments such as smart cities and logistics. Building on a previously proposed proxy-based architecture, we incorporate two key TLS mechanisms: hybrid post-quantum key exchange using X25519MLKEM768 to mitigate Store Now Decrypt Later (SNDL) attacks, and stateless session resumption for fast handover across edge proxies. Our open-source implementation relies on Envoy proxies and BoringSSL library. We evaluate the cryptographic, data, and latency overheads across multiple network conditions. Results show that hybrid post-quantum TLS introduces manageable overheads while significantly enhancing security, and that session resumption reduces connection costs by up to 73%. These findings confirm the viability of strong cryptographic protections without sacrificing service performance, making the solution suitable for secure, seamless continuity in smart city edge computing scenarios.
In today's digital economy, data represents a critical strategic resource, necessitating innovative approaches to its monetization and value realization. This study evaluates various methodologies for data monetization through customized demand representations. By examining diverse consumer demand models, we capture the intricate behaviors of digital market consumers. Our contribution includes improving existing modeling techniques by incorporating nuanced dependencies of data value, such as price sensitivity, quality perception, and trustworthiness of services. Moreover, we address non-discrete service consumption scenarios relevant to contemporary offerings like Information-as-a-Service (IaaS) and Answers-as-a-Service (AaaS). This work contributes to the linkage between theoretical models and practical strategies specific to data markets, expanding current understanding and providing actionable insights for effective data monetization strategies. Additionally, the study highlights potential areas for future research, particularly regarding the integration of emerging technological advancements and evolving regulatory landscapes. These insights can guide firms in adapting their data monetization frameworks to maintain a competitive advantage in rapidly changing markets.
This work is the first to formulate distributed inference in deep neural networks (DNNs) when considering frequency selection of an edge/hub/cloud device as an additional knob of control which can impact the global latency and/or energy. Specifically, each device in the network may have a set of discrete operating frequencies which we utilize to formulate the problem of layer-wise partitioning of a DNN in a distributed execution environment. We first develop a procedure for profiling energy and latency of a device, based on its operating frequencies, to execute a subset of DNN layers. We then propose an Integer Linear Programming (ILP) formulation for distributed inference which incorporates frequency-dependent energy and latency profiles. In our experiments, we demonstrate variations of ILP including energy-, and latency-constrained, when aiming to find the transition layer from the edge to a cloud device. We consider NVIDIA Jetson Nano and LePotato as edge device options to explore frequency selection. We show better energy and/or latency of our ILP, compared to a recent work (JointDNN).
Efficient water management is a fundamental pillar of sustainable agriculture and one of the main goals of precise agriculture. Indeed, due to the worsening of environmental conditions, the reduction of water resources, the increased deser-tification of some areas of the world, and the huge water usage by agriculture activities, water management is critical to promote a more sustainable agriculture and to support the food production, especially in poorest and most populated areas of the world. This paper presents an extended smart irrigation system that enhances a sensor-based automation framework with real-time water flow monitoring to allow a prompt detection of leaks. The new system is based on a centralized monitoring of water use that allows its application even in extensive crops where the widespread distribution of a dense network of sensors over large areas is not possible, making it feasible also for developing countries thanks to its low cost. This proactive approach, that can be integrated with fine-tuned and distributed monitoring systems, ensures optimal water usage, minimizes waste, and contributes to the reduction of operational costs and to the environmental sustainability of agricultural activities. The paper details the implementation, integration, and benefits of this new system, demonstrating its value in sustainable crops management.
Brain tumours are abnormal and uncontrollable multiplication of cells in the brain. They can have significant implications for patients, ranging from headaches and nausea to more severe symptoms such as seizures and memory difficulties. An accurate diagnosis is vital to implement a successful treatment plan. Current deep learning approaches for classifying brain tumours rely on the availability of large amounts of labelled data. This can be challenging, as highly trained medical professionals need to manually label each image. To address these limitations, this work proposes a few-shot learning method that uses a varying number of shots, ranging from 1-shot to 10-shots. Three categories of brain tumours are classified: glioma, meningioma, and pituitary tumours. The proposed approach demonstrates 96.30 % and 96.96 % accuracies for the 1-shot and 10-shot models, respectively. The state-of-the-art CNN method achieved a 97.07% accuracy. However, this approach required significantly larger quantities of labelled data. This development could improve the classification of brain tumours, particularly for rare diseases or instances where there is a scarcity of labelled data.
Federated Learning (FL) is a distributed learning paradigm that leverages the computational strength of local devices to collaboratively train a model. The clients train the local model on their respective devices and submit the weight updates to the server for aggregation. This paradigm allows the clients to experience diverse data without sharing their local data with other participants or the server. However, FL is susceptible to backdoor attackers that deliberately train the model on altered data, essentially trying to get favor on a specific subtask separated from the main task. In this work, we focus on powerful backdoor attackers who play attacks in a distributed manner to strengthen their impact and to escape a strong detection method. We propose a novel defense algorithm against distributed backdoor attacks, which leverages dynamic model clipping and a reputation-based global model update by filtering adversarial update vectors. While requiring minimal changes to the standard FL framework, our algorithm can be used as a plug-in solution. By simulating various forms of backdoor attacks over three benchmark datasets, we find that with a negligible compromise on the overall performance of the model, our algorithm maintains a lower attack success rate and outperforms the prior solutions.
The proliferation of IoT devices and the growing demand for real-time applications have driven a shift in the computation paradigm, from Cloud computing to Edge computing, creating the Cloud-to-Things Continuum (C2TC). Many real-time IoT applications involve Mobile Nodes (MNs), which may dynamically join or leave. In addition, in future reconfigurable IoT systems, applications with different requirements will coexist, and will be dynamically introduced or removed. All this asks for dynamic management mechanisms to ensure the requirements of different real-time applications, even when the system configuration changes over time. In this paper, we propose DJ-NECORA, an online algorithm for the joint allocation of networking and computing resources in C2TC that is capable of guaranteeing the requirements of real-time applications and efficiently managing possible changes in the system configuration. We evaluated DJ-NECORA through simulation in a realistic scenario. The results show that DJ-NECORA effectively handles application dynamics and, in some scenarios, outperforms offline resource allocation solutions by supporting 14% more MNs.
Open RAN (Open Radio Access Network) is a next-generation wireless network gaining significant research interest globally due to its potential to provide a cost-efficient and scalable solution for growing network demands. Energy efficiency is an important area of focus in Open RAN deployments, as reducing power consumption while maintaining network performance is essential for sustainable wireless communication. This paper demonstrates the impact of CPU (Central Processing Unit) scheduling process priorities on power consumption and network performance in an Open RAN NodeB deployed on a testbed in the USA. The experimental results are demonstrated using two scenarios: (1) CPU Priority-Based Scheduling, where specific CPU process priorities are assigned to improve throughput while maintaining power efficiency, highlighting the importance of priority selection for optimizing performance. (2) CPU Affinity-Based Scheduling, where CPU affinity is assigned to specific cores to enhance resource utilization, leading to improved performance and efficient power consumption in a virtualized Open RAN setup. This demonstration of CPU priority-based resource tuning in virtual Open RAN provides valuable insights into CPU optimization strategies that can contribute to the development of energy-efficient and sustainable next-generation wireless networks.
This paper introduces a novel approach for coordinated evacuation route planning during disasters, focusing on guiding groups of individuals-such as families or neigh-bors-who are spatially separated but socially connected. Recognizing the importance of group cohesion during evacuations, we designed and implemented a prototype system, which was validated through a real-world evacuation drill conducted in Kobe City during the 30th memorial year of the Great HanshinEarthquake. We introduce and formulate a new problem, termed the ‘Evacuation Routing Problem’ (ERP), using integer linear programming (ILP). Our system recommends that group members rendezvous at specific points along their evacuation routes. The core idea is to model each evacuation route as a tree on a predefined road network, where the leaves correspond to evacuees (group members) and the root corresponds to the shelter. This problem can be viewed as a variant of the Steiner Tree Problem, augmented with an additional constraint to ensure that members of a group meet at an optimal rendezvous node while en route to the shelter. To validate our method, we conducted a pilot experiment in Kobe City, Japan. We developed a prototype system featuring a web-based interface that generates high-quality evacuation routes derived from ILP solutions. The experiment involved two family groups, and the developed system navigated a real road network that included various points of interest such as parks, shopping malls, offices, and schools. The results showed that one family successfully gathered at the proposed rendezvous point and evacuated together, while the other group was unable to meet due to a suggested detour. Drawing from these experimental outcomes and user feedback, we analyze system limitations and discuss potential improvements from a user-centric perspective.
The increasing availability of smart devices in people's daily lives is constantly driving the design of novel services aimed to support the users by leveraging data provided by sensors embedded in their devices. In this paper, we present a scenario where data generated by wearable devices, such as smartphones and smartwatches, are analyzed to perform Human Activity Recognition (HAR). Given the different nature of the devices, using a single classifier may lead to inconsistent performance, especially for tasks that are semantically complex. Conversely, a distributed approach to activity recognition, where independent classifiers are used on each device, would be more computationally demanding and challenging to maintain. To address these issues, we present a probabilistic data fusion approach to integrate measurements from multiple devices while improving the overall system accuracy. Experiments performed on real data acquired from different devices show the effectiveness of our approach, especially in the recognition of complex activities.
This paper introduces novel quantitative metrics for evaluating the performance of occupant identification and tracking models in multi-building smart spaces. We evaluate two state transition system models: the Centralized State Transition System (CSTS) and the Distributed State Transition System (DSTS). Both are probabilistic models characterized by events, state transition functions, and states. Events abstract biometric recognition, transition functions capture state changes, and states provide the foundation for information retrieval. To systematically compare these models, we introduce two figures of merit, for comparing event-level and state-level behavior, respectively. Experimental results indicate that CSTS outperforms DSTS in their figures of merit, demonstrating greater accuracy, however, DSTS remains a viable alternative in scenarios where building-specific structure and reduced state update complexity offer advantages. Our findings emphasize that both models have their strengths, and also that different scenarios may require different metrics for a more nuanced understanding of system performance and comparison.
Food insecurity (FI) is a persistent public health issue in the United States, disproportionately affecting racially and ethnically marginalized populations while also contributing to a heightened risk for chronic health conditions such as obesity, type 2 diabetes, hypertension, and mental health disorders. Food-as-Medicine initiatives, including Food Prescription (FoodRx) programs, have emerged as promising interventions that connect individuals experiencing FI with access to nutritious foods and related resources. However, the conventional “one-size-fits-all” design of many FoodRx programs limits effectiveness by failing to consider individual-level factors such as demographics, health status, nutritional knowledge, cultural food practices, and lifestyle behaviors. This manuscript introduces My FoodRx, an innovative, personalized mobile Health application designed to enhance traditional FoodRx approaches by providing customized nutrition and educational support to food-insecure adults at risk for chronic diseases. The platform integrates real-time food pantry data with user health profiles to generate personalized dietary recommendations, including curated recipes and adaptive education. With an architecture that is modular, cloud-connected with secure backend infrastructure, and HIPAA-compliant data management, My FoodRx leverages a client-server framework to support scalability and future integration with broader healthcare and community systems. By aligning digital health technology with the promotion of food security and chronic disease management, My FoodRx offers a novel, application for delivering personalized dietary recommendations for improved health outcomes.
