As smart cities nowadays use many Internet of Things (IoT) devices, the need for service composition methods that are both efficient and flexible has become unavoidable. Methodologies should be designed to provide flexibility and sustain high quality of service (QoS) under dynamic urban conditions. Deterministic techniques often have poor scalability and require complete, accurate QoS information. In contrast, non-deterministic approaches can handle uncertainty but tend to be computationally expensive and less reliable under dynamic conditions. Service composition is considered an NP-hard problem due to the exponential complexity involved in selecting and combining optimal services under multiple QoS constraints. This paper proposes a novel hybrid framework called Bayesian Network–Grey Wolf Optimizer (BN-GWO), which integrates Bayesian Networks (BN) with the Grey Wolf Optimizer (GWO) algorithm. The BN captures conditional dependencies among QoS attributes and accurately estimates missing values, while the GWO algorithm efficiently explores the compositional space to optimize QoS metrics. Experimental evaluations conducted using QoS traces synthetically generated via the iFogSim2 simulation platform demonstrate that the proposed BN-GWO framework significantly outperforms state-of-the-art methods across multiple performance metrics.

The paper presents an overview of Call Detail Records (CDRs), important datasets within the telecommunications industry that capture detailed information about telephonic activities. CDRs encompass a vast array of metadata, including the date, time, duration, source, destination of calls, and more specific details like service type, call status, and location data. This paper highlights the significant potential of CDRs in various applications, ranging from telecom fraud detection, urban planning, disaster readiness, to novel methodologies for predicting socio-economic metrics like poverty. We discuss specific use cases, demonstrating the critical role of CDRs in identifying SIM box fraud, analyzing urban mobility, and enhancing emergency response strategies through sophisticated data analysis techniques. Furthermore, we introduce a novel CDR Generator solution developed within the RITHMS project (G.A. 101073932) aimed at detecting suspicious activities around archaeological sites. The tool leverages modern technologies such as Python, Streamlit, and Folium, to generate synthetic CDRs based on selected geographic areas, demonstrating the applicability of CDRs in safeguarding cultural heritage. We find that the generated dataset largely preserves the properties of the real dataset, thus being of real use for the research community suffering from the limited availability of datasets from either practical simulations or experimental testbeds that can be considered as reference or standard datasets

One particular example of a useful software application for Software Defined Networks (SDN) is represented by a traffic analysis mechanism, which provides a network administrator with a control panel from which he can collect traffic data. The data can then be used to fit Artificial Intelligence (AI) models, which will further classify the traffic of the network in real-time, enabling a network admin to monitor the network with ease. This paper presents an SDN classifier, aiming to achieve real-time multi-class traffic classification in a software-defined network. To enhance the classification accuracy, six artificial intelligence algorithms, including Logistic Regression, K-Nearest Neighbors (KNN), Naïve Bayes, Support Vector Machines (SVM), Decision Tree, and Artificial Neural Networks (ANN), are tested. Due to the possibility of training on unnormalized data, the data is preprocessed by rescaling values between 0 and 1. Additionally, the paper explores the supervised learning potential of the last three algorithms in traffic classification. The findings show that one of the top performing algorithms is ANN, along with SVM and KNN.

The paper proposes a Machine Learning methodology for Android malware detection and recognition, including crypto-mining applications using the blockchain. The design is based on a hierarchical classification method, with several decision stages. A combination of functional and statistical features is proposed to be applied for data classification in order to provide a high-performance malware recognition process. The specific contribution of this design methodology is the hierarchical classifier with detection and discrimination stages, respectively. Further works should be done for various features sets in order to achieve an optimized and high-accuracy modeling process supporting an innovative Machine Learning-based solution for Android malware detection.

Wi-Fi communication is becoming popular for offloading mobile networks. However, there are several radio communication problems, such as spectrum sharing and fading. The purpose of this paper is to define a communication scheme that implements a random fluctuation of the natural environment of communication channels. Only the transmitter and the receiver share the communication channel features. From mutuality among a transmitter and a receiver, it might be required for them to share one-time information of their fluctuating channel. This can deliver a secret key agreement scheme without key management and key distribution processes. In this article, we propose a new secret key generation and agreement scheme that utilizes the fluctuation of channel features with an electronically steerable parasitic array radiator (ESPAR) antenna. The antenna, which has been proposed and prototyped, is a smart antenna designed for users. Using the beamforming technique of the ESPAR antenna, one can intensify the fluctuation of the channel features. For the communication analysis we used Ekahau Heatmapper to create a propagation pattern and to highlight the effects of fading in a wireless distribution system (WDS) network built on Lancom Wi-Fi access points. From the experimental results, we conclude that the proposed scheme can generate secret keys from the received signal strength indicator (RSSI) profile with sufficient independence.

To respond to current consumer demands and lifestyle challenges with agility, agri-food practitioners have to evolve quickly and remain competitive. Unfortunately, in many situations, development and proliferation of innovative foods in the market act as a barrier to consumers instead of a driving force, because food manufacturers tend to proceed according to profit maximization and cost minimization approach. These foods generally do not promote health and even may contribute to the development of non-communicable diseases, leading to lack of consumer trust. To help modern consumers to make correct food choices on a daily basis with long-term beneficial effects on their body, this paper proposes a concept of a novel e-platform on healthy eating behavior. By accessing the platform, every consumer will have access not only to safe, high-quality, sufficient and affordable food in his own region, but will also be able to select the “healthiest” one in terms of his own preferences and physiological needs.

Customer price knowledge has been the object of considerable research in the past decades since the advent of online shopping. Furthermore, customers express online their personal opinions regarding the products or services they purchase, this activity becoming a habit for many people nowadays. However, due to the difficulty of analyzing such large datasets, extracting price knowledge from big data presents unique systems engineering and architectural challenges. The purpose of this paper is to analyze several existing solutions used for search and analysis of large volumes of data, with applicability in the retail field, and to present the results for price knowledge extraction from Big Data using Exalead Cloud View technology. The main contribution of this paper consists in the development of several connectors and a data model based on properties and patterns specific for price calculations.

Current M2M communication platforms are being integrated in cloud IoT applications for providing remote sensing and actuating. Nevertheless, requirements for energy efficiency and resilience in severe operating environments are driving the development of new algorithms and infrastructures. This paper presents a survey of the measurement results for the winegrowing season 2014, as it was seen by an M2M remote telemetry station in cooperation with a big data processing platform and several sensors. We demonstrate the use of recent technologies such as Cloud IoT systems and Big Data processing in order to implement disease prediction and alerting application for viticulture. Finally, the extension of the proposed system for other agriculture applications is discussed.