Spyros Sioutas

Ionian University | IONIO · Department of Informatics

In the context of the Internet of Things (IoT), Tiny Machine Learning (TinyML) and Big Data, enhanced by Edge Artificial Intelligence, are essential for effectively managing the extensive data produced by numerous connected devices. Our study introduces a set of TinyML algorithms designed and developed to improve Big Data management in large-scale...

In the current era, where data is expanding due to the unforeseen volume, velocity, and variety of data types produced by IoT devices, there is an imperative need to manage such data in remote IoT environments. However, these complexities have been inadequately addressed by conventional data management methods. In such scenarios, Distributed Hash T...

This paper presents an innovative approach to overcoming the limitations of traditional cloud-centric architectures in the evolving Internet of Things (IoT) landscape. We introduce a set of novel decentralized algorithms boosting Mobile Edge Computing (MEC), a paradigm shift towards placing computational resources near data sources, thus boosting r...

The Internet of Things (IoT) has seen remarkable growth in recent years, but the data volatility and limited energy resources in these networks pose significant challenges. In addition, traditional quality of service metrics like throughput, latency, packet delay variation, and error rate remain important benchmarks. In this work, we explore the ap...

In this work, we present a Distributed Bayesian Inference Classifier for Large-Scale Systems, where we assess its performance and scalability on distributed environments such as PySpark. The presented classifier consistently showcases efficient inference time, irrespective of the variations in the size of the test set, implying a robust ability to...

In the evolving landscape of Industry 4.0, the convergence of peer-to-peer (P2P) systems, LoRa-enabled wireless sensor networks (WSNs), and distributed hash tables (DHTs) represents a major advancement that enhances sustainability in the modern agriculture framework and its applications. In this study, we propose a P2P Chord-based ecosystem for sus...

In this study, we introduce FLIBD, a novel strategy for managing Internet of Things (IoT) Big Data, intricately designed to ensure privacy preservation across extensive system networks. By utilising Federated Learning (FL), Apache Spark, and Federated AI Technology Enabler (FATE), we skilfully investigated the complicated area of IoT data managemen...

As the Internet of Things (IoT) landscape grows, with estimates exceeding 75 billion devices by 2025, effective data management and processing become primary challenges. Traditional cloud-centric models may struggle under this large data volume. This research presents Edge AI as an innovative solution, integrating artificial intelligence directly a...

In modern agriculture, the capability to promptly detect and respond to specific events is crucial. This study centres on the transformative potential of TinyML for enhancing event detection in Smart Agriculture, particularly when integrated with LoRa-based Wireless Sensor Networks (WSNs). In this work, we underscore the unique advantages of utiliz...

This study explores the design and capabilities of a Geographic Information System (GIS) incorporated with an expert knowledge system, tailored for tracking and monitoring the spread of dangerous diseases across a collection of fish farms. Specifically targeting the aquacultural regions of Greece, the system captures geographical and climatic data...

In this work, we introduce an innovative Markov Chain Monte Carlo (MCMC) classifier, a synergistic combination of Bayesian machine learning and Apache Spark, highlighting the novel use of this methodology in the spectrum of big data management and environmental analysis. By employing a large dataset of air pollutant concentrations in Madrid from 20...

Federated learning (FL) has emerged as a promising technique for preserving user privacy and ensuring data security in distributed machine learning contexts, particularly in edge intelligence and edge caching applications. Recognizing the prevalent challenges of imbalanced and noisy data impacting scalability and resilience, our study introduces tw...

Mobile Edge Computing (MEC) is a promising computing paradigm that provides computing and storage services for mobile and big data applications. MEC servers are deployed at base stations to establish a mobile edge network (MEN) where mobile users can offload tasks to nearby servers to speed up their mobile applications. However, challenges such as...

A method for query optimization is presented by utilizing Spark SQL, a module of Apache Spark that integrates relational data processing. The goal of this paper is to explore NoSQL databases and their effective usage in conjunction with distributed environments to optimize query execution time, in order to accommodate the user complex demands in a...

In the context of big-data analysis, the clustering technique holds significant importance for the effective categorization and organization of extensive datasets. However, pinpointing the ideal number of clusters and handling high-dimensional data can be challenging. To tackle these issues, several strategies have been suggested, such as a consens...

The field of automated machine learning (AutoML) has gained significant attention in recent years due to its ability to automate the process of building and optimizing machine learning models. However, the increasing amount of big data being generated has presented new challenges for AutoML systems in terms of big data management. In this paper, we...

In the modern era where data is produced from multivariate sources, there is an urge to handle such data in an efficient yet effective manner. Therefore, applications that necessitate such capabilities shall make use of data structures and indexing mechanisms that can perform fast index operations along with low complexity as per insertion, deletio...

Visualization is a critical component across every software as it enables users to familiarize themselves with the environment and perform certain tasks with ease. Therefore, straightforward yet interactive and easy-to-understand tools let users’ complex demands be satisfied within minutes. The objective of this work is to give an optimized graphic...

Human resource management has a significant influence on the performance of any public body. Employee classification and ranking are definitely time-consuming processes, which in many cases lead to controversial results. In addition, assessing employee efficiency through a variety of skills could lead to never-ending calculations and error-prone st...

Mobile health applications are steadily gaining momentum in the modern world given the omnipresence of various mobile or WiFi connections. Given that the bandwidth of these connections increases over time, especially in conjunction with advanced modulation and error-correction codes, whereas the latency drops, the cooperation between mobile applica...

Blockchain is a linearly linked, distributed, and very robust data structure. Originally proposed as part of the Bitcoin distributed stack, it found a number of applications in a number of fields, most notably in smart contracts, social media, secure IoT, and cryptocurrency mining. It ensures data integrity by distributing strongly encrypted data i...

The rapid emergence of low-power embedded devices and modern machine learning (ML) algorithms has created a new Internet of Things (IoT) era where lightweight ML frameworks such as TinyML have created new opportunities for ML algorithms running within edge devices. In particular, the TinyML framework in such devices aims to deliver reduced latency,...

Social media have become the main platforms for expressing and supplementing nuanced human activity such as engaging in public and private conversations, creating and sharing multimedia content, participating to digital culture events, and recently describing emotions about events, places, or even products. In this survey, we provide a comprehensiv...

Speech processing, the field of analysing input speech signals and methods of processing them has emerged in the recent days. Additionally, the development of a speech processing system involves several components in the design phase with probabilistic approximations for enhanced audio sampling and de-noising. In this work, we focus into the use of...

Drones are intelligent devices that offer solutions for a continuously expanding variety of applications. Therefore, there would be a significant improvement if these systems could explore space automatically and without human-supervision. This work integrates cutting-edge artificial intelligence techniques that allow drones to travel independently...

Query optimization is a crucial process across data mining and big data analytics. As the size of the data in the modern applications is increasing due to various sources, types and multi-modal records across databases, there is an urge to optimize lookup and search operations. Therefore, indexes can be utilized to solve the matter of rapid data gr...

Emotion detection is crucial in many IoT deployments from an operational perspective with examples ranging from digital health to smart cities. This is particularly true in smart homes where the interaction between the local IoT ecosystem and the inhabitants are continuous, pervasive, and nuanced. More specifically, emotion estimation from human sp...

One of the biggest problems the public sector faces is the proper utilization of human resources. Within a particular combination of practices, dynamic resource allocation management aims to increase employee productivity. The question that arises is how to match the abilities of employees on a measurable scale through their connection with the log...

In distributed interactive application ecosystems, service provision and availability are key factors for the end user's perceived quality. Therefore, the location of any server facility is important from the provider's standpoint for efficient capital expenditure. Given the dynamicity of such environments (e.g., due to traffic load variance over t...

In this paper, the concepts and techniques for global graph clustering are examined, or the process of locating related clusters of vertices within a graph. We introduce the construction of a graph clustering technique based on an eigenvector embedding and a local graph clustering method based on stochastic exploration of the graph. Then, the devel...

In the modern era of Internet of Things (IoT) and Industry 4.0 there is a growing need for intelligent microcontrollers that can collect, sense and analyse data effectively and efficiently. Such devices can be installed in large scale IoT deployments ranging from smart homes to smart cities and smart buildings. The aim of these devices shall be not...

Federated Learning (FL) is an emerging technique that assures user privacy and data integrity in distributed machine learning environments. To perform so, chunks of data are trained across edge devices and a high performance cluster server maintains a local copy without exchanging it with other parties. In this work, we investigate a FL scenario in...

Big data management methods are paramount in the modern era as applications tend to create massive amounts of data that comes from various sources. Therefore, there is an urge to create adaptive, speedy and robust frameworks that can effectively handle massive datasets. Distributed environments such as Apache Spark are of note, as they can handle s...

Data streams are becoming increasingly important across a wide array of fields and are generally expected to be the preferred form of big data as aggregators and smart stream analytics in general can efficiently yield stream descriptions in various levels. Among them, event detection analytics are paramount since they typically allow the identifica...

Social media are widely considered as reflecting to a great extent human behavior including thoughts, emotions, as well as reactions to events. Consequently social media analysis relies heavily on examining the interaction between accounts. This work departs from this established viewpoint by treating the online activity as a result of the diffusio...

Pure peer-to-peer networks serve to secure information in a decentralized, distributed topology. The multi-armed bandit (MAB) problem formulation proves to be a useful tool for analyzing the problem of optimizing new peer connections. In this paper, we outline the new peer scenario described as a reinforcement learning problem with MABs in order to...

The employment of various language modelling techniques in the area of information retrieval is gaining wide adoption in the state of the art methods. The precision of the language model enables the solution of the issue of information retrieval in a huge corpus of texts. To accomplish this, these techniques begin by estimating a probabilistic ling...

In the dairy industry farming as well as transportation conditions are paramount to product quality and to the overall supply chain resiliency. However, modern farms are complex installations with a broad spectrum of factors such as atmospheric conditions, including rain and humidity, ground composition, and highly irregular animal motion making di...

Markov Chain Monte Carlo techniques are used to generate samples that closely approximate a given multivariate probability distribution, with the function not having to be normalised in the case of certain algorithms such as Metropolis-Hastings. As with other Monte Carlo techniques, MCMC employs repeated random sampling to exploit the law of large...

Monte Carlo simulations using Markov chains as the Gibbs sampler and Metropolis algorithm are widely used techniques for modelling stochastic problems for decision making. Like all other Monte Carlo approaches, MCMC exploits the law of large numbers via repeated random sampling. Samples are formed by running a Markov Chain that is constructed in su...

Domestic appliance power consumption measurement was, until recently, a problem without a satisfying solution. It required the use of a measuring device for each appliance to be studied, and thus the spending of a considerable amount of both money and time. The technological advancements made in the past few decades have enabled the engineering of...

Non-Intrusive Load Monitoring (NILM) or Energy disaggregation may be the holy grail of energy efficiency. The impact of energy disaggregation at the commercial level of home customers is the increased utility customer engagement and the reduced energy usage. The goal at this level is to itemize the consumer’s energy bill, analyze the energy usage a...

Consensus protocols constitute an important part in virtually any blockchain stack as they safeguard transaction validity and uniqueness. This task is achieved in a distributed manner by delegating it to certain nodes which, depending on the protocol, may further utilize the computational resources of other nodes. As a tangible incentive for nodes...

Tailored analytics play a key role in the successful delivery of cultural content to huge and diverse groups. Primarily the latter depends on a number of information retrieval factors determining user experience quality, most prominently precision, recall, and timing. These imply that cultural analytics should be designed with strong predictive pow...

Consensus protocols constitute an important part in virtually any blockchain stack as they safeguard transaction validity and uniqueness. This task is achieved in a distributed manner by delegating it to certain nodes which, depending on the protocol, may further utilize the computational resources of other nodes. As a tangible incentive for nodes...

In this work, we propose D3-Tree, a dynamic distributed deterministic structure for data management in decentralized networks, by engineering and extending an existing decentralized structure. Conducting an extensive experimental study, we verify that the implemented structure outperforms other well-known hierarchical tree-based structures since it...

Big data streams are possibly one of the most essential underlying notions. However, data streams are often challenging to handle owing to their rapid pace and limited information lifetime. It is difficult to collect and communicate stream samples while storing, transmitting and computing a function across the whole stream or even a large segment o...

At the dawn of the Internet era graph analytics play an important role in high-and low-level network policymaking across a wide array of fields so diverse as transportation network design, supply chain engineering and logistics, social media analysis, and computer communication networks, to name just a few. This can be attributed not only to the si...

Social graphs abound with information which can be harnessed for numerous behavioral purposes including online political campaigns, digital marketing operations such as brand loyalty assessment and opinion mining, and determining public sentiment regarding an event. In such scenarios the efficiency of the deployed methods depends critically on thre...

The problem of energy disaggregation is the separation of an aggregate energy signal into the consumption of individual appliances in a household. This is useful, since the goal of energy efficiency at the household level can be achieved through energy-saving policies towards changing the behavior of the consumers. This requires as a prerequisite t...

Process mining is the art and science of (semi)automatically generating business processes from a large number of logs coming from potentially heterogeneous systems. With the recent advent of Industry 4.0 analog enterprise environments such as floor shops and long supply chains are bound to full digitization. In this context interest in process min...

Digital repositories and cultural content delivery systems built on top of them are integral parts in the current form of cultural landscape. In these systems netizen engagement is paramount and it can take many forms ranging from participation to digital fora to custom multimedia creation. One important engagement manifestation is the annotation o...

Database deployment is a complex task depending on a multitude of operational parameters such as anticipated data scaling trends, expected type and volume of queries, uptime requirements, replication policies, available budget, and personnel training and experience. Thus, enterprise database administrators eventually rely on various performance met...

Does a tweet with specific emotional content posted by an influential account have the capability to shape or even completely alter the opinions of its readers? Moreover, can other influential accounts further enhance its original emotional potential by retweeting it and, thus, letting their followers read it? Real Twitter conversations seem to imp...

Graph neural networks (GNNs) is an emerging class of iterative connectionist models taking full advantage of the interaction patterns in an underlying domain. Depending on their configuration GNNs aggregate local state information to obtain robust estimates of global properties. Since graphs inherently represent high dimensional data, GNNs can effe...

Substantial empirical evidence, including the success of synthetic graph generation models as well as of analytical methodologies, suggests that large, real graphs have a recursive community structure. The latter results, in part at least, in other important properties of these graphs such as low diameter, high clustering coefficient values, heavy...

Technologies such as cloud computing and big datamanagement, have lately made significant progress creating anurgent need for specific databases that can safely store extensivedata along with high availability. Specifically, an evergrowingamount of companies have put to use a multitude of non-relational databases, typically known as NoSQL databases...

Self organizing maps (SOMs) are neural networks designed to be in an unsupervised way to create connections, learned through a modified Hebbian rule, between a high- (the input vector space) and a low-dimensional space (the cognitive map) based solely on distances in the input vector space. Moreover, the cognitive map is segmentwise continuous and...

Recommender systems are mechanisms that filter information in order to predict the preference of a user for an item drawn from a finite collection. Prime examples include recommendation platforms for movies, games, travel destinations, and books. Such systems rely on identifying users with similar preferences, as indicated by an appropriately selec...

In this work, we survey state of the art hierarchical distributed data structures for the efficient handling of big data, in scenarios where the dominant operation is range queries which have to be answered in real-time. Our main focus is on structures that exhibit stable scalability.

Privacy Preserving and Anonymity have gained significant concern from the big data perspective. We have the view that the forthcoming frameworks and theories will establish several solutions for privacy protection. The k-anonymity is considered a key solution that has been widely employed to prevent data re-identifcation and concerns us in the cont...

We present efficient fully persistent B-trees in the I/O model with block size B that support range searches on t reported elements at any accessed version of size n in O(logB⁡n+t/B) I/Os and updates at any accessed version in O(logB⁡n+log2⁡B) amortized I/Os, using O(m/B) disk blocks after m updates. This improves both the query and update I/O-effi...

Self organizing maps (SOMs) are neural networks designed to be in an unsupervised way to create connections, learned through a modified Hebbian rule, between a high-(the input vector space) and a low-dimensional space (the cognitive map) based solely on distances in the input vector space. Moreover, the cognitive map is segmentwise continuous and p...

The skyline of a set P of points consists of the “best” points with respect to minimization or maximization of the attribute values. A point p dominates another point q if p is as good as q in all dimensions and it is strictly better than q in at least one dimension. In this work, we focus on the 2-d space and provide expected performance guarantee...

Mobile health applications are steadily gaining momentum in the modern world given the omnipresence of various mobile or Wi-Fi connections. Given that the bandwidth of these connections increases over time, especially in conjunction with advanced modulation and error-correction codes, whereas the latency drops, the cooperation between mobile applic...

How online cultural content is chosen based on conscious or subconscious criteria is an central question across a broad spectrum of sciences and for the entertainment industry, including content providers and distributors. To this end, a number of tailored analytics forming the backbone of recommendation engines specialized for retrieving cultural...

Metadata-based similarity measurement is far from obsolete nowadays, despite research's focus on content and context based information. It allows for aggregating information from textual references, measuring similarity when content is not available, traditional keyword search in search engines, merging results in meta-search engines, etc. Existing...

Content Management Systems (CMSs) play an increasingly important role in the evolution of the World Wide Web, since almost half of the websites today use some form of CMS as their main development platform. CMSs provide development teams with standardized software platforms that significantly facilitate and speed up Web development, while maintaini...

The availability of numerical data grows from 1 day to another in a remarkable way. New technologies of high-throughput Next-Generation Sequencing (NGS) are producing DNA sequences. Next-Generation Sequencing describes a DNA sequencing technology which has revolutionized genomic research. In this paper, we perform some experiments using a cloud inf...

Blockchain is a linearly linked, distributed, and very robust data structure. Originally proposed as part of the Bitcoin distributed stack, it can be applied in a number of fields, most notably in smart contracts, social media, secure IoT, and cryptocurrency mining. It ensures data integrity by distributing strongly encrypted data in widely redunda...

The need to store massive volumes of spatio-temporal data has become a difficult task as GPS capabilities and wireless communication technologies have become prevalent to modern mobile devices. As a result, massive trajectory data are produced, incurring expensive costs for storage, transmission, as well as query processing. A number of algorithms...

A new dynamic Interpolation Search (IS) data structure is presented that achieves O(log⁡log⁡n) search time with high probability on unknown continuous or even discrete input distributions with measurable probability of element collisions, including power law and Binomial distributions. No such previous result holds for IS when the probability of el...

Imagine that we have a highly competing virus that is spreading over a (e.g., social) network where users have different sensitivity/interest against it. A virus may be anything that has a “spreading” behavior such as a rumor, a social media trend or even an infectious disease. Is it possible to predict the outcome in such a viral phenomenon and co...

In the original publication, part figures were incorrectly positioned in Figure 2. The correct figure is given below.

Non-linear system identification is a challenging problem with a plethora of engineering applications including digital telecommunications, adaptive control of biological systems , assessing integrity of mechanical constructs, and geological surveys. Various approaches have been proposed in the scientific literature, including Volterra and multivar...

The availability of numerical data grows from one day to another in a remarkable way. New technologies of high-throughput Next Generation Sequencing (NGS) are producing DNA sequences. Next Generation Sequencing describes a DNA sequencing technology which has revolutionised genomic research. In this paper, we perform some experiments using a cloud i...

Fibonacci numbers appear in numerous engineering and computing applications including population growth models, software engineering, task management, and data structure analysis. This mandates a computationally efficient way for generating a long sequence of successive Fibonacci integers. With the advent of GPU computing and the associated special...

In the context of this research work, we studied the problem of privacy preserving on spatiotemporal databases. In particular, we investigated the k-anonymity of mobile users based on real trajectory data. The k-anonymity set consists of the k nearest neighbors. We constructed a motion vector of the form (x,y,g,v) where x and y are the spatial coor...

Deep Learning has dramatically advanced the state of the art in vision, speech and many other areas. Recently, numerous deep learning algorithms have been proposed to solve traditional artificial intelligence problems. In this paper, in order to detect the version that can provide the best trade-off in terms of time and accuracy, convolutional netw...

Blockchain is a linearly linked, distributed, and very robust data structure. Originally proposed as part of the Bitcoin distributed stack, it found a number of applications in a number of fields, most notably in smart contracts, social media, secure IoT, and cryptocurrency mining. It ensures data integrity by distributing strongly en-crypted data...

Mobile health applications are steadily gaining momentum in the modern world given the omnipresence of various mobile or WiFi connections. Given that the bandwidth of these connections increases over time, especially in conjunction with advanced modulation and error-correction codes, whereas the latency drops, the cooperation between mobile applica...

Metadata-based similarity measurement is far from obsolete in our days, despite research's focus on content and context. It allows for aggregating information from textual references, measuring similarity when content is not available, traditional keyword search in search engines, merging results in meta-search engines and many more research and in...

Over the last decade, the vast explosion of Internet data has fueled the development of Big Data management systems and technologies. The huge amount of data in combination with the need for records linkage under privacy perspective, has led us to current study. To this direction, we describe Privacy Preserving Record Linkage problem based on Bloom...