Abstract AdamZ is an advanced variant of the Adam optimiser, developed to enhance convergence efficiency in neural network training. This optimiser dynamically adjusts the learning rate by incorporating mechanisms to address overshooting and stagnation, which are common challenges in optimisation. Specifically, AdamZ reduces the learning rate when overshooting is detected and increases it during periods of stagnation, utilising hyperparameters such as overshoot and stagnation factors, thresholds, and patience levels to guide these adjustments. While AdamZ may lead to slightly longer training times compared to some other optimisers, it consistently excels in minimising the loss function, making it particularly advantageous for applications where precision is critical. Benchmarking results demonstrate the effectiveness of AdamZ in maintaining optimal learning rates, leading to improved model performance across diverse tasks.

Several architecture frameworks for software, systems, and enterprises have been proposed in the literature. They have identified various stakeholders and defined architecture viewpoints and views to frame and address stakeholder concerns. However, the Machine Learning (ML) and data science-related concerns of data scientists and data engineers are yet to be included in existing architecture frameworks. We interviewed 65 experts from around 25 organizations in over ten countries to devise and validate the proposed framework that addresses the mentioned shortcoming.

Software engineering of network-centric Artificial Intelligence (AI) and Internet of Things (IoT) enabled Cyber-Physical Systems (CPS) and services, involves complex design and validation challenges. In this paper, we propose a novel approach, based on the model-driven software engineering paradigm, in particular the domain-specific modeling methodology. We focus on a sub-discipline of AI, namely Machine Learning (ML) and propose the delegation of data analytics and ML to the IoT edge. This way, we may increase the service quality of ML, for example, its availability and performance, regardless of the network conditions, as well as maintaining the privacy, security and sustainability. We let practitioners assign ML tasks to heterogeneous edge devices, including highly resource-constrained embedded microcontrollers with main memories in the order of Kilobytes, and energy consumption in the order of milliwatts. This is known as Tiny ML. Furthermore, we show how software models with different levels of abstraction, namely platform-independent and platform-specific models can be used in the software development process. Finally, we validate the proposed approach using a case study addressing the predictive maintenance of a hydraulics system with various networked sensors and actuators.

Structured Query Language (SQL) Injection constitutes a most challenging type of cyber-attack on the security of databases. SQLI attacks provide opportunities by malicious actors to exploit the data, particularly client personal data. To counter these attacks security measures need to be deployed at all layers, namely application layer, network layer, and database layer; otherwise, the database remains vulnerable to attacks at all levels. Research studies have demonstrated that lack of input validation, incorrect use of dynamic SQL, and inconsistent error handling have continued to expose databased to SQ LI attacks. The security measures commonly deployed presently, being mostly focused on the network layer only, still leave the program code and the database at risk despite well-established approaches such as web server requests filtering, network firewalls and database access control. To overcome this deficiency, a Multi-Phase algorithmic framework is proposed with improved parameterised machine learning and deep learning to enhance database security in real-time at the database layer. The proposed method has been tested within a university and also in one of the branches of a commercial bank. The results show that the proposed method is able to i) prevent SQLi; ii) classify the type of attack during the detection process, and therefore iii) secure the database.

Abstract Models are used in both Software Engineering (SE) and Artificial Intelligence (AI). SE models may specify the architecture at different levels of abstraction and for addressing different concerns at various stages of the software development life-cycle, from early conceptualization and design, to verification, implementation, testing and evolution. However, AI models may provide smart capabilities, such as prediction and decision-making support. For instance, in Machine Learning (ML), which is currently the most popular sub-discipline of AI, mathematical models may learn useful patterns in the observed data and can become capable of making predictions. The goal of this work is to create synergy by bringing models in the said communities together and proposing a holistic approach to model-driven software development for intelligent systems that require ML. We illustrate how software models can become capable of creating and dealing with ML models in a seamless manner. The main focus is on the domain of the Internet of Things (IoT), where both ML and model-driven SE play a key role. In the context of the need to take a Cyber-Physical System-of-Systems perspective of the targeted architecture, an integrated design environment for both SE and ML sub-systems would best support the optimization and overall efficiency of the implementation of the resulting system. In particular, we implement the proposed approach, called ML-Quadrat, based on ThingML, and validate it using a case study from the IoT domain, as well as through an empirical user evaluation. It transpires that the proposed approach is not only feasible, but may also contribute to the performance leap of software development for smart Cyber-Physical Systems (CPS) which are connected to the IoT, as well as an enhanced user experience of the practitioners who use the proposed modeling solution.

Battery-operated low-power portable computing devices are becoming an inseparable part of human daily life. One of the major goals is to achieve the longest battery life in such a device. Additionally, the need for performance in processing multimedia content is ever increasing. Processing image and video content consume more power than other applications. A widely used approach to improving energy efficiency is to implement the computationally intensive functions as digital hardware accelerators. Spatial filtering is one of the most commonly used methods of digital image processing. As per the Fourier theory, an image can be considered as a two-dimensional signal that is composed of spatially extended two-dimensional sinusoidal patterns called gratings. Spatial frequency theory states that sinusoidal gratings can be characterised by its spatial frequency, phase, amplitude, and orientation. This article presents results from our investigation into assessing the impact of these characteristics of a digital image on the energy efficiency of hardware-accelerated spatial filters employed to process the same image. Two greyscale images each of size 128 × 128 pixels comprising two-dimensional sinusoidal gratings at maximum spatial frequency of 64 cycles per image orientated at 0° and 90°, respectively, were processed in a hardware implemented Gaussian smoothing filter. The energy efficiency of the filter was compared with the baseline energy efficiency of processing a featureless plain black image. The results show that energy efficiency of the filter drops to 12.5% when the gratings are orientated at 0° whilst rises to 72.38% at 90°.

With increasing complexity of the social systems under surveillance, demand grows for automated tools which are able to support end users in making sense of situational context from the amount of available data and incoming data streams. This paper presents MOSAIC (Multi-Modal Situation Assessment and Analytics Platform), a semantically integrated system which aims at exploiting multi-modal data analysis comprising advanced tools for text and data mining, criminal network analysis, and decision support. The aim is to provide, from an enriched context, an understanding of behaviour of the system under surveillance thus supporting authorities in their decision making processes. Specific measures and algorithms have been developed to support analysts in retrieving, analysing, and disrupting criminal networks, identifying offenders that pose the greatest harm aligned with domain-specific strategies, as well as enabling the investigation of intervention strategies. A case study is provided in order to illustrate the system in practice.

This research presents a novel multifunctional platform focusing on the clinical diagnosis of kidneys and their pathology (tumors, stones and cysts), using a “templates”-based technique. As a first step, specialist clinicians train the system by accurately annotating the kidneys and their abnormalities creating “3-D golden standard models.” Then, medical technicians experimentally adjust rules and parameters (stored as “templates”) for the integrated “automatic recognition framework” to achieve results which are closest to those of the clinicians. These parameters can later be used by nonexperts to achieve increased automation in the identification process. The system's functionality was tested on 20 MRI datasets (552 images), while the “automatic 3-D models” created were validated against the “3-D golden standard models.” Results are promising as they yield an average accuracy of 97.2% in successfully identifying kidneys and 96.1% of their abnormalities thus outperforming existing methods both in accuracy and in processing time needed.

With the growing need for privacy-aware and privacy-respecting CCTV systems, it becomes crucial to develop workflows and architectures that can support and enhance privacy protection. Recent advances in image processing enable the automation of many surveillance tasks, increasing the risks of privacy infringements. Fortunately, image processing and pattern recognition techniques can also be used for automatically evaluating the context in which video surveillance takes place, and can therefore be employed for applying context-specific privacy rules. This paper describes how Bag-of-Visual-Words algorithms as well as human tracking and gait analysis cane used for recognizing specific sub-contexts that necessitate the application of particular privacy protection rules in usage contexts such as ambient assisted living, public or workspace surveillance We explain how the data of a multi-modal surveillance system should be handled in order to avoid unnecessary processing of sensitive information through Image Quality Descriptors that will support visual classifications by computing reliability measures relating to the image quality such as noise or problems with respect to ambient conditions.

The ext Generation etwork is a future based network providing next generation services such as IPTV, Online gaming, Video on demand etc, based on IP protocol in the presence of core network. This research based Paper discusses the architecture of ext Generation etwork, its challenges & solutions, its reliability and its pros & cons. The main objective is to investigate the effectiveness of G providing next generation services. This paper discusses the basic customers’ needs and future trends of technologies perspective. Different technologies and their uses providing different services were reviewed. The term ext Generation etwork ( G ) is used to support telecommunication network architecture and its technologies and services. Conventional Public Switched Telephone etwork (PST ) data, Voice Communication and Video Services are to be supported on the basis of G . The information carried through this network is based on packet switched form known as Internet network.