Vasileios Tsoukas

ORCID: 0000-0003-0081-2052
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • IoT and Edge/Fog Computing
  • Fire Detection and Safety Systems
  • Vehicle Routing Optimization Methods
  • Advanced Neural Network Applications
  • Cryptography and Data Security
  • Privacy, Security, and Data Protection
  • Food Supply Chain Traceability
  • Blockchain Technology Applications and Security
  • Food Waste Reduction and Sustainability
  • Advanced Memory and Neural Computing
  • User Authentication and Security Systems
  • Advanced Manufacturing and Logistics Optimization
  • IoT-based Smart Home Systems
  • Transportation and Mobility Innovations
  • Data Stream Mining Techniques
  • Urban and Freight Transport Logistics
  • Smart Parking Systems Research
  • Privacy-Preserving Technologies in Data
  • Neural Networks and Reservoir Computing
  • Reinforcement Learning in Robotics
  • Algorithms and Data Compression
  • Innovative Human-Technology Interaction
  • Advanced Malware Detection Techniques
  • Complexity and Algorithms in Graphs
  • Customer churn and segmentation

University of Thessaly
2019-2025

University of Western Macedonia
2022

Food safety is a fundamental right in modern societies. One of the most pressing problems nowadays provenance food and food-related products that citizens consume, mainly due to several scares globalization markets, which has resulted supply chains extend beyond nations or even continent boundaries. networks are characterized by high complexity lack openness. There critical requirement for applying novel techniques verify authenticate origin, quality parameters, transfer/storage details...

10.3390/info13050213 article EN cc-by Information 2022-04-20

Internet of Things devices are commonly utilized in smart homes to provide services such as lighting, entertainment, and easy access, but they also employed warn occupants the event an emergency. Due computationally intensive nature existing Neural Network implementations, data must be transmitted cloud for analysis produce intelligent machines. TinyML is a promising approach that scientific community has proposed method constructing autonomous secure can collect, analyze, output without...

10.1109/mocast54814.2022.9837510 article EN 2022-06-08

Internet of Things devices are frequently used as consumer to provide digital solutions, such smart lighting and voice-activated assistants, but they also employed alert residents in the instance an emergency. Given increasingly costly nature present neural network systems, it is necessary transport information cloud for intelligent machine analysis. TinyML a potential technology that has been presented by research world building fully independent safe can gather, analyze, produce data,...

10.3390/technologies11020045 article EN cc-by Technologies 2023-03-22

Background: Epilepsy is one of the most common and devastating neurological disorders, manifesting with seizures affecting approximately 1–2% world’s population. The criticality seizure occurrence associated risks, combined overwhelming need for more precise innovative treatment methods, has led to development invasive neurostimulation devices programmed detect apply electrical stimulation therapy suppress reduce burden. Tiny Machine Learning (TinyML) a rapidly growing branch machine...

10.3390/biomedinformatics5010014 article EN cc-by BioMedInformatics 2025-03-10

This work proposes an effective solution to the Vehicle Routing Problem, taking into account all phases of delivery process. When compared real-world data, findings are encouraging and demonstrate value Machine Learning algorithms incorporated Several were combined along with a modified Hopfield network deliver optimal multiobjective issue on platform capable monitoring various Additionally, system providing viable insights analytics in regard orders was developed. The results reveal maximum...

10.3390/analytics2020018 article EN cc-by Analytics 2023-04-13

Agriculture is a high-priority sector since it creates economic opportunities and generates the majority of world's food. In 2050, agricultural products will be in exceptionally high demand due to 30% increase population. Human resources for agriculture development are disappearing as young people migrate major cities, while land being abused rapid expansion. To satisfy food demand, portion tasks must automated. Agricultural research has revealed that Internet Things (IoT) technology might...

10.1145/3575879.3575994 article EN 2022-11-25

The food industry is highly dependent upon supply chains. It critical for the quality of product that reaches consumer, all actors interact with corresponding chains act responsibly and according to appropriate regulations. Because that, monitoring a necessity nowadays. main problem current chain systems lack transparency, traceability, sustainability as those are required operate in complex ecosystem, involving multiple stakeholders across different countries. Blockchain technology has been...

10.1109/seeda-cecnsm53056.2021.9566256 article EN 2021-09-24

The rapid evolution of mobile phone devices resulted in the conversion a simple communication device to complicated small portable computer offering plethora features and services. Sensitive data are now stored that can be easily lost, stolen, or compromised. A user survey was conducted get better understanding what users think about their devices, authentication methods they use, willingness try new one. This paper presents results derived from 81 users. reveal still use text-based methods,...

10.1145/3437120.3437337 article EN 2020-11-20

The creation of a framework in which traditional Machine Learning and neuromorphic algorithms compete to solve shared Reinforcement environment is presented this work. In addition, configuration allows the exploitation modern widely-used libraries. PyTorch used investigate expanded capabilities potential training an action-critic network pair comprised specialised units using custom learning algorithm. policy value networks utilised context are fully interconnected MultiLayer Perceptrons....

10.1145/3635059.3635066 article EN cc-by 2023-11-24

Nowadays, one can observe massive amount of data production by numerous devices interacting with their environment and end users. [1] Such be the subject advanced processing usually through machine learning algorithms. Hence, we are able to provide intelligent applications analytics in many research domains like health informatics, information technology, environmental sciences, so on forth. However, choosing appropriate model for most difficult tasks. In this paper, try facilitate...

10.1109/seeda-cecnsm.2019.8908366 article EN 2019-09-01

Driving under the influence of alcohol is one most severe and critical problems in every country throughout world. a difficult endeavor that demands high degree concentration great visual processing. A system based on Internet Things can be utilized to measure drivers' level restrict their operation motor vehicles. This technology affordable but has number disadvantages, including requirement for an internet connection, transfer data other organizations, bandwidth latency constraints,...

10.1109/seeda-cecnsm57760.2022.9932962 article EN 2022-09-23

Cloud computing is a widely adopted technology that offers storage, collaboration tools, and processing power to users. In many cases, data are originated from portable devices, built improve our quality of life by sending sensitive personal data, e.g., health doctors or cloud platforms. However, saving transferring huge volumes contain information raises privacy concerns. Homomorphic Encryption form can perform computation on encrypted without the need decrypting it, giving an answer...

10.1109/icce56470.2023.10043586 article EN 2023 IEEE International Conference on Consumer Electronics (ICCE) 2023-01-06

The merger of Internet Things (IoT) and Machine Learning undoubtedly offers several benefits, but due to the nature IoT devices their underlying design, a number difficulties challenges exist. most fundamental these has do with security dangers posed by transmission voluminous amounts data, as well networking obstacles, such delay bandwidth constraints. Moving all processing close network's edge preventing data third parties, cloud or other devices, is potential solution. Embedded Learning,...

10.1109/dcoss-iot58021.2023.00082 article EN 2023-06-01

Multiple Sequence Alignment (MSA) is one of the most fundamental methodologies in Bioinformatics and method capable arranging DNA or protein sequences to detect regions similarity. Even on cutting-edge workstations, MSA procedure requires a significant amount time regarding its execution time. This paper demonstrates how utilize Extensa Explorer by Tensilica (Cadence) create an extended instruction set meet requirements some widely used algorithms for analysis. Kalign showed highest...

10.3390/electronics11162550 article EN Electronics 2022-08-15

A critical issue for a mobile device user is the protection of stored sensitive data and their access, via device. widely used technique protecting with display lock screen. Many security methods have been proposed but they suffer from technical vulnerabilities, algorithm weakness, issues due to using, or high complexity that prevents large groups adopting it everyday use. In this paper, an easy secure screen locking proposed. Comparison existing offered, highlighting strong points solution,...

10.1145/3368640.3368657 article EN 2019-11-28

This paper presents the work conducted on providing an efficient solution to Vehicle Routing Problem considering all stages of a delivery process. The results are promising when compared real-life data and depict benefits application ML algorithms in A platform capable monitor various process was developed, number models were incorporated provide best multiobjective problem. indicate average maximum 25% distance saving, 14% regarding total time.

10.1145/3575879.3576009 article EN 2022-11-25
Coming Soon ...