- IoT Networks and Protocols
- Energy Harvesting in Wireless Networks
- User Authentication and Security Systems
- Bluetooth and Wireless Communication Technologies
- Smart Parking Systems Research
- Indoor and Outdoor Localization Technologies
- IoT and Edge/Fog Computing
- Soil Moisture and Remote Sensing
- Wireless Body Area Networks
- Context-Aware Activity Recognition Systems
- RFID technology advancements
- Water Quality Monitoring Technologies
- IoT-based Smart Home Systems
- Security in Wireless Sensor Networks
- Advanced Malware Detection Techniques
- Smart Agriculture and AI
- Smart Cities and Technologies
- Opportunistic and Delay-Tolerant Networks
- Building Energy and Comfort Optimization
- Optical Wireless Communication Technologies
- Wireless Networks and Protocols
- Antenna Design and Analysis
- Obstructive Sleep Apnea Research
- Infection Control and Ventilation
- QR Code Applications and Technologies
University of Split
2015-2025
Ministry of Health
2022
Ghent University
2020
University of Salento
2020
Universidade Federal do Piauí
2020
Ericsson (Croatia)
2018
University of Zadar
2018
The growth of the Internet Things (IoT) continues to be rapid, making it an essential part information technology. As a result, IoT devices must able handle data collection, machine-to-machine (M2M) communication, and preprocessing data, while also considering cost, processing power, energy consumption. This paper introduces system for device indoor localization that uses variations in strength wireless signal. proposed addresses logistics use cases which is imperative achieve reliable...
The Internet-of-Things vision of ubiquitous and pervasive computing gives rise to future smart irrigation systems comprising the physical digital worlds. A ecosystem combined with Machine Learning can provide solutions that successfully solve soil humidity sensing task in order ensure optimal water usage. Existing are based on data received from power hungry/expensive sensors transmitting sensed over wireless channel. Over time, become difficult maintain, especially remote areas due battery...
Finding a free parking lot contributes largely to total traffic congestion and increases gas emissions in urban overpopulated cities. Recent advances smart systems adopt Internet of Things (IoT) concepts which tend improve bottlenecks by providing information about available lots. The detection vehicle presence at the usually means adopting solutions comprised power-hungry battery-operated sensor devices. In this article hardware-based approach is introduced aims building self-powered...
The Internet of Things (IoT) has a lot to offer and contribute the retail industry, from innovations in store experience increased efficiency management supply chain optimization. On its way real-world applications, Radio Frequency IDentification (RFID) became main enabler for final IoT deployment. However, improve technology performance even further, it is important overcome fundamental limitations physical layer and, consequently, better understand how use an optimal way. analysis provided...
Obstructive Sleep Apnea (OSA) is a prevalent condition that disrupts sleep quality and contributes to significant health risks, necessitating accurate efficient diagnostic methods. This study introduces machine learning-based framework aimed at detecting apnea events through analysis of polysomnographic (PSG) oximetry data. The core component Long Short-Term Memory (LSTM) network, which particularly suited processing sequential time-series data, capturing complex temporal relationships...
LoRaWAN networks are increasingly recognized for their vulnerability to various jamming attacks, which can significantly disrupt communication between end nodes and gateways. This paper explores the feasibility of executing reactive jammers upon detecting packet transmission using commercially available equipment based on Software-Defined Radios (SDRs). The proposed approach demonstrates how attackers exploit detection initiate targeted interference, effectively compromising message...
LoRaWANs are increasingly recognized for their vulnerability to various jamming attacks, which can significantly disrupt communication between end nodes and gateways. This paper explores the feasibility of executing reactive jammers upon detecting packet transmission using commercially available equipment based on software-defined radios (SDRs). The proposed approach demonstrates how attackers exploit detection initiate targeted interference, effectively compromising message integrity. Two...
HASH(0x3b6160c)
Classical password/PIN-based authentication methods have proven to be vulnerable a broad range of observation attacks (such as key-logging, video-recording or shoulder surfing attacks). In order mitigate these attacks, number solutions been proposed, most them being cognitive schemes (challenge-response protocols that require users perform some kind operations). this paper, we show successful passive side-channel timing on two schemes, well-known Hopper-Blum (HB) protocol and U.S. patent...
The detection of vehicle presence in parking slots is a fundamental part smart systems. problem commonly approached with devices composed specific sensors, which usually are either magnetic or infrared. sensor continuously sampled by an onboard microcontroller capable determining the slot status (available occupied) and sending information to central collection gathering system means wireless technology. Nevertheless, cost power consumption still issue. Based on consideration that only...
The Low-Power Wide-Area Network (LPWA) has already started to gain a notorious adoption in the Internet of Things (IoT) landscape due its enormous potential. It is employed wide variety scenarios involving parking lot occupancy, package delivery, smart irrigation, lightning, fire detection, etc. If messages from LPWA devices can be manipulated or blocked, this will violate integrity collected information and lead unobserved events (e.g., fire, leakage). This paper explores possibility that...
The Internet of Things (IoT) framework has transformed sensor data utilization, ushering in a new era sensors integrated into various aspects modern environment. A pressing concern the realm wearable technology is efficient power management, encompassing low consumption and reducing battery recharging times. This study introduces an electronic device equipped with Bluetooth 5.1 Low Energy (BLE) module, capable detecting, collecting, aggregating transmitting Root Sum Squares Method (RSS)...
Classical PIN-entry methods are vulnerable to a broad class of observation attacks (shoulder surfing, key-logging).A number alternative that based on human cognitive skills have been proposed. These can be classified into two classes regarding information available passive adversary: (i) the adversary fully observes entire input and output procedure, (ii) only partially observe and/or output. In this paper we propose novel scheme - Shoulder Surfing Safe Login (SSSL). SSSL is challenge...
This paper reports two attacks on Undercover, a human authentication scheme against passive observers proposed at CHI 2008. The first attack exploits nonuniform behavior in responding to challenges and the second one is based information leaked from or responses visible attacker. can be generalized break alternative Undercover designs presented Pervasive 2009. All exploit design flaws of implementations.
On the way from Internet of things (IoT) to underground (IoUT) main challenge is antenna design. The enabling technologies still rely on simple design and low cost, but systems are more complex. LoRa-based system combined with a machine learning approach can be used for estimation soil moisture by using signal strength data, improvement performance we propose optimization use. properties frequency-dependent varying in time, which may cause variations wavelength input impedance underground....
This study presents the design and evaluation of a plush smart toy prototype for teaching geometry shapes to young children. The hardware involves integration sensors, microcontrollers, an LCD screen, machine learning algorithm enable gesture recognition by toy. detects whether child’s outline matches shape displayed on screen. A pilot was conducted with 14 preschool children assess usability performance results indicate that is easy use, engages in learning, has potential be effective...