Autonomous Machine Learning Research Articles

Mechanisms for Securing Autonomous Shipping Services and Machine Learning Algorithms for Misbehaviour Detection

Technological developments within the maritime sector are resulting in rapid progress that will see the commercial use of autonomous vessels, known as Maritime Autonomous Surface Ships (MASSs). Such ships are equipped with a range of advanced technologies, such as IoT devices, artificial intelligence (AI) systems, machine learning (ML)-based algorithms, and augmented reality (AR) tools. Through such technologies, the autonomous vessels can be remotely controlled from Shore Control Centres (SCCs) by using real-time data to optimise their operations, enhance safety, and reduce the possibility of human error. Apart from the regulatory aspects, which are under definition by the International Maritime Organisation (IMO), cybersecurity vulnerabilities must be considered and properly addressed to prevent such complex systems from being tampered with. This paper proposes an approach that operates on two different levels to address cybersecurity. On one side, our solution is intended to secure communication channels between the SCCs and the vessels using Secure Exchange and COMmunication (SECOM) standard; on the other side, it aims to secure the underlying digital infrastructure in charge of data collection, storage and processing by relying on a set of machine learning (ML) algorithms for anomaly and intrusion detection. The proposed approach is validated against a real implementation of the SCC deployed in the Livorno seaport premises. Finally, the experimental results and the performance evaluation are provided to assess its effectiveness accordingly.

IoT-based framework for optimizing energy efficiency and reliability in acoustic sensor networks using mobile sinks

In today’s world, there is an increasing demand for environmental monitoring, surveillance, and oceanographic research, which poses challenges in improving energy efficiency and data transfer reliability in Acoustic Sensor Networks. Existing methods face hurdles due to limited energy resources and unreliable data transmission. We propose a Reliable and Energy-Efficient Framework with Sink Mobility (REEFSM) to address these issues. This framework optimizes energy consumption and enhances data reliability by incorporating advanced energy management strategies such as adaptive duty cycling and efficient data transmission mechanisms by minimizing forwarding nodes. Simulation results demonstrate that REEFSM reduces energy consumption by up to 43% and increases data reliability by 35% compared to protocols like EERBCR and DEADS. REEFSM ensures zero dead nodes, minimizes packet drops, and maintains high data accuracy throughout the simulation. This research outcome provides a sustainable and reliable solution for energy-efficient data collection in underwater environments. The future research directions, including integrating autonomous path planning, energy harvesting, and machine learning techniques, hold great potential for further advancements in the field.

Redefining Spectral Data Analysis with Immersive Analytics: Exploring Domain-Shifted Model Spaces for Optimal Model Selection.

Modern developments in autonomous chemometric machine learning technology strive to relinquish the need for human intervention. However, such algorithms developed and used in chemometric multivariate calibration and classification applications exclude crucial expert insight when difficult and safety-critical analysis situations arise, e.g., spectral-based medical decisions such as noninvasively determining if a biopsy is cancerous. The prediction accuracy and interpolation capabilities of autonomous methods for new samples depend on the quality and scope of their training (calibration) data. Specifically, analysis patterns within target data not captured by the training data will produce undesirable outcomes. Alternatively, using an immersive analytic approach allows insertion of human expert judgment at key machine learning algorithm junctures forming a sensemaking process performed in cooperation with a computer. The capacity of immersive virtual reality (IVR) environments to render human comprehensible three-dimensional space simulating real-world encounters, suggests its suitability as a hybrid immersive human-computer interface for data analysis tasks. Using IVR maximizes human senses to capitalize on our instinctual perception of the physical environment, thereby leveraging our innate ability to recognize patterns and visualize thresholds crucial to reducing erroneous outcomes. In this first use of IVR as an immersive analytic tool for spectral data, we examine an integrated IVR real-time model selection algorithm for a recent model updating method that adapts a model from the original calibration domain to predict samples from shifted target domains. Using near-infrared data, analyte prediction errors from IVR-selected models are reduced compared to errors using an established autonomous model selection approach. Results demonstrate the viability of IVR as a human data analysis interface for spectral data analysis including classification problems.

AI Unleashed: Pioneering Trends and Future Directions in Artificial Intelligence

Artificial Intelligence (AI) expeditiously transmutes from a specialized area of study to a key component of contemporary technology, propelling breakthroughs in a wide range of industries. AI Unleashed, Pioneering Trends and Future Directions in Artificial Intelligence is a study examining the current developments influencing the field's progress and future course. This study explores essential fields, including autonomous systems, machine learning, and natural language processing, showcasing new developments and present uses. It also considers AI's ethical and societal ramifications, including issues with prejudice, privacy, and the necessity of robust governance systems. Exploring the confluence of artificial intelligence (AI) with other cutting-edge technologies, such as quantum computing and the Internet of Things (IoT), highlights the potential for unparalleled capabilities. With a perspective beyond the future, this overview highlights the significant obstacles and possibilities that will shape artificial intelligence (AI), from improving human-machine interaction to expanding general intelligence. This assessment offers insights into the cutting-edge trends propelling AI forward and the future paths that will mold the next wave of AI innovation through an extensive examination.

Active Gait System for Real-Time Surveillance Against Cyber-Physical Attacks

Cyberterrorism, espionage, and warfare are serious threats to national security. These attacks can harm people or destroy critical infrastructures like the data centres, computer networks, and systems. Surveillance systems currently used in monitoring critical infrastructures, national key points, and military exclusion zones (MEZ) are ineffective in detecting unauthorised intrusions. These issues compromise the stability of the countries, and the safety of the citizens and result in the loss of important assets. This experimental research study developed a Cyber Physical Security (CPS) defense gait-recognition monitoring system. Autonomous Machine Learning (ML) technology was employed to enhance the precision and reliability of the system against CPA, in tracking access, managing security clearances, and triggering alerts in the event of unauthorized entries to restricted areas.

Impact of artificial intelligence on aeronautics: An industry-wide review

Curiously, there are few contributions in the scientific literature on the subject of artificial intelligence (AI) and its impact on aeronautics. However, many communications and reports have been published by aeronautic companies about their applications of AI technologies. This article makes an industry-wide review of AI in aeronautics using a three-step sequential approach: (i) a review of AI and its concepts to define and develop a conceptual map; (ii) a selection of 100 use cases from aeronautics companies that use AI technologies (e.g., Airbus, Boeing, Air France, Safran, EasyJet, Dassault Aviation, Altair); and (iii) an analysis of the use cases using the topics defined in the conceptual map. The main results describe a rising interest in the integration of AI technologies by entities in the aeronautic sector. Moreover, the results from the use cases show that the most recurrent technologies are big data analytics, autonomous intelligent systems, predictive analytics, machine learning, and robotics. Another finding is related to the several benefits that motivate companies to integrate AI technologies into their industrial and operational processes. The most frequent benefits include customer satisfaction, saving time, safety and security, cost reduction, better decision making, solving complex problems, and ensuring optimisation and efficiency. It also appears that the performance of companies is positively impacted by using these AI technologies. Such impacts span all operational departments including marketing, where these technologies help satisfy customer needs; the industrial and operational area, which is provided with quality products; and where productivity and economic performance are optimised for more efficiency.

A proposed HAZOP based upgradation model for improvement in existing industrial practices: a geothermal energy industry case study

Purpose This paper aims to conduct a detailed analysis of the industrial practices currently being used in the geothermal energy industry and to determine whether they are contributing to any limitations. A HAZOP-based upgradation model for improvement in existing industrial practices is proposed to ensure the removal of inefficient conventional practices. The HAZOP-based upgradation model examines the setbacks, identifies its causes and consequences and suggests improvement methods comprising of modern-day technology. Design/methodology/approach This paper proposed a HAZOP-based upgradation model for improvement in existing industrial practices. The proposed HAZOP model identifies the drawbacks brought on by conventional practices and suggests improvements. Findings The study reviewed the challenges geothermal power plants currently face due to conventional practices and suggested a total of 22 upgradation recommendations. From those, a total of 11 upgradation modules comprising modern digital technology and Industry 4.0 elements were proposed to improve the existing practices in the geothermal energy industry. Autonomous robots, augmented reality, machine learning and Internet of Things were identified as useful methods for the upgradation of the existing geothermal energy system. Research limitations/implications If proposed recommendations are incorporated, the efficiency of geothermal energy generation will increase as cumulating setbacks will no longer degrade the work output. Practical implications The proposed recommendation by the study will make way for Industry 4.0 integration with the geothermal energy sector. Originality/value The paper uses a proposed HAZOP-based upgradation model to review issues in existing industrial practices of the geothermal energy sector and recommends solutions to overcome operability issues using Industry 4.0 technologies.

A novel autonomous machine learning technique for recognizing control chart patterns

A number of strategies have been developed for controlling and monitoring the production process since the quality of the product has emerged as one of the key concerns in today's manufacturing sector. Control charts are the best tools for monitoring and adjusting products and processes. This research proposes a novel automatic method for the recognition of nine control chart patterns (CCPs) based on novel autonomous machine learning. The classification portion and the tuning portion make up the two main components of this procedure. Support Vector Machine (SVM) have demonstrated outstanding performance over the past few years on a variety of applications, including signal dispensation, speech detection, and image processing. SVM is consequently employed as the intelligent classifier for the recognition of CCPs in the classification phase. One key challenge with SVM is that it requires a high level of expertise to choose appropriate parameters, such as the quantity of kernel and their spatial diameters, knowledge rate, etc. It is difficult to fine-tune the SVM parameters because of their domestic dependence. These problems led to the employment of the Harmony Search (HS) Algorithm for the best tuning of SVM parameters in the tuning section of the proposed technique. Instead of depending on any feature engineering procedures, the suggested method, in contrast to the popular CCPs recognition methods, takes raw data and runs it through many hidden layers to obtain the best feature representation. The quantitative and simulation results demonstrate the suggested method's performance advantage over the earlier methods.

자율 기계 학습을 위한 효과적인 스마트 온실 데이터 전처리 시스템

Recently, research on a smart farm that creates new values by combining information and communication technology(ICT) with agriculture has been actively done. In order for domestic smart farm technology to have productivity at the same level of advanced agricultural countries, automated decision-making using machine learning is necessary. However, current smart greenhouse data collection technologies in our country are not enough to perform big data analysis or machine learning. In this paper, we design and implement a smart greenhouse data preprocessing system for autonomous machine learning. The proposed system applies target data to various preprocessing techniques. And the proposed system evaluate the performance of each preprocessing technique and store optimal preprocessing technique for each data. Stored optimal preprocessing techniques are used to perform preprocessing on newly collected data

Evaluation of Machine Learning Algorithms for Malware Detection

This research study mainly focused on the dynamic malware detection. Malware progressively changes, leading to the use of dynamic malware detection techniques in this research study. Each day brings a new influx of malicious software programmes that pose a threat to online safety by exploiting vulnerabilities in the Internet. The proliferation of harmful software has rendered manual heuristic examination of malware analysis ineffective. Automatic behaviour-based malware detection using machine learning algorithms is thus considered a game-changing innovation. Threats are automatically evaluated based on their behaviours in a simulated environment, and reports are created. These records are converted into sparse vector models for use in further machine learning efforts. Classifiers used to synthesise the results of this study included kNN, DT, RF, AdaBoost, SGD, extra trees and the Gaussian NB classifier. After reviewing the test and experimental data for all five classifiers, we found that the RF, SGD, extra trees and Gaussian NB Classifier all achieved a 100% accuracy in the test, as well as a perfect precision (1.00), a good recall (1.00), and a good f1-score (1.00). Therefore, it is reasonable to assume that the proof-of-concept employing autonomous behaviour-based malware analysis and machine learning methodologies might identify malware effectively and rapidly.

Autonomous and sustainable machine learning: pursuing new horizons of intelligent systems

The paradigm of Artificial Intelligence and Machine Learning has resulted in an amazingly diverse plethora of models operating in various environments and quite often exhibiting numerous successes. There is a growing spectrum of challenging application areas of high criticality where one has to meet a number of fundamental requirements. Those manifest evidently when Machine Learning constructs have to function autonomously and any decisions being rendered entail far reaching implications. The carefully crafted learning process has to result with advanced models. Along with the developed models, they have to come hand-in-hand with credibility measures that are crucial to assess an extent to which the results generated by such measures are meaningful, trustworthy and credible. The credibility of the Machine Learning models becomes of paramount importance given the nature of application domains. Autonomous systems including autonomous vehicles, user identification (both using audio and video channels), financial systems (calling for sound mechanisms to quantify risk levels) require the ML system making classification or prediction decisions some level of self-awareness. Among others, this translates to forming sound answers to the following crucial questions emerging within the design process: How much confidence could be associated with the result? Could any action /decision be taken on a basis of obtained result? Given the reported level of credibility, is there any other experimental evidence one could acquire to validate the decision? In this study, we advocate that a general way to achieve such goals is to engage the mechanism of Granular Computing; subsequently, the granularity endowing the results are sought as a vehicle use to quantify the credibility level. Sustainable (or green) Machine Learning gives rise to the agenda of knowledge reuse, namely exploring possibilities of potential reuse of the already designed models in a spectrum of current environments where computing overhead as one of the ways to contribute to the agenda of sustainable Machine Learning and discuss a crucial role of information granularity in this context.

Autonomous machine learning for early bot detection in the internet of things

The high costs incurred due to attacks and the increasing number of different devices in the Internet of Things (IoT) highlight the necessity of the early detection of botnets (i.e., a network of infected devices) to gain an advantage against attacks. However, early botnet detection is challenging because of continuous malware mutations, the adoption of sophisticated obfuscation techniques, and the massive volume of data. The literature addresses botnet detection by modeling the behavior of malware spread, the classification of malicious traffic, and the analysis of traffic anomalies. This article details ANTE, a system for ANTicipating botnEt signals based on machine learning algorithms. The system adapts itself to different scenarios and detects different types of botnets. It autonomously selects the most appropriate Machine Learning (ML) pipeline for each botnet and improves the classification before an attack effectively begins. The system evaluation follows trace-driven experiments and compares ANTE results to other relevant results from the literature over four representative datasets: ISOT HTTP Botnet, CTU-13, CICDDoS2019, and BoT-IoT. Results show an average detection accuracy of 99.06% and an average bot detection precision of 100%.

Data-driven and autonomous manufacturing control in cyber-physical production systems

Modern manufacturing networks consist of cyber-physical systems (CPS) which offer an array of interesting capabilities, ranging from local computation over data generation to communication capabilities. As traditional control approaches fail to fully leverage these capabilities, the last decade has seen a renewed interest in distributed control approaches based on autonomous entities. In this article, we study the synergistic potentials of autonomous control and machine learning in a job-shop setting, addressing challenges of modern manufacturing such as market fluctuation and process time variance, thus leveraging the potentials of CPS in order to flexibly configure manufacturing networks and achieve cost-minimal production. We utilize a multi-agent based discrete-event simulation to compare this novel approach to a traditional heuristic, underlining the potentials and advantages of data-driven control approaches.

With Clear Intention—An Ethical Responsibility Model for Robot Governance

There is much discussion about super artificial intelligence (AI) and autonomous machine learning (ML) systems, or learning machines (LM). Yet, the reality of thinking robotics still seems far on the horizon. It is one thing to define AI in light of human intelligence, citing the remoteness between ML and human intelligence, but another to understand issues of ethics, responsibility, and accountability in relation to the behavior of autonomous robotic systems within a human society. Due to the apparent gap between a society in which autonomous robots are a reality and present-day reality, many of the efforts placed on establishing robotic governance, and indeed, robot law fall outside the fields of valid scientific research. Work within this area has concentrated on manifestos, special interest groups and popular culture. This article takes a cognitive scientific perspective toward characterizing the nature of what true LMs would entail—i.e., intentionality and consciousness. It then proposes the Ethical Responsibility Model for Robot Governance (ER-RoboGov) as an initial platform or first iteration of a model for robot governance that takes the standpoint of LMs being conscious entities. The article utilizes past AI governance model research to map out the key factors of governance from the perspective of autonomous machine learning systems.

FTAP: Feature transferring autonomous machine learning pipeline

An effective method in machine learning often involves considerable experience with algorithms and domain expertise. Many existing machine learning methods highly rely on feature selection which are always domain-specific. However, the intervention by data scientists is time-consuming and labor-intensive. To meet this challenge, we propose a Feature Transferring Autonomous machine learning Pipeline (FTAP) to improve efficiency and performance. The proposed FTAP has been extensively evaluated on different modalities of data covering audios, images, and texts. Experimental results demonstrate that the proposed FTAP not only outperforms state-of-the-art methods on ESC-50 dataset with multi-class audio classification but also has good performance in distant domain transfer learning. Furthermore, FTAP outperforms TPOT, a state-of-the-art autonomous machine learning tool, on learning tasks. The quantitative and qualitative analysis proves the feasibility and robustness of the proposed FTAP.

An overview of machine learning applications for smart buildings

The efficiency, flexibility, and resilience of building-integrated energy systems are challenged by unpredicted changes in operational environments due to climate change and its consequences. On the other hand, the rapid evolution of artificial intelligence (AI) and machine learning (ML) has equipped buildings with an ability to learn. A lot of research has been dedicated to specific machine learning applications for specific phases of a building's life-cycle. The reviews commonly take a specific, technological perspective without a vision for the integration of smart technologies at the level of the whole system. Especially, there is a lack of discussion on the roles of autonomous AI agents and training environments for boosting the learning process in complex and abruptly changing operational environments. This review article discusses the learning ability of buildings with a system-level perspective and presents an overview of autonomous machine learning applications that make independent decisions for building energy management. We conclude that the buildings’ adaptability to unpredicted changes can be enhanced at the system level through AI-initiated learning processes and by using digital twins as training environments. The greatest potential for energy efficiency improvement is achieved by integrating adaptability solutions at the timescales of HVAC control and electricity market participation.

Early detection algorithm for alzheimer’s disease using autonomous learning

The current document describes the approach to a research problem that aims to generate an algorithm that allows detecting the probable appearance of Alzheimer’s disease in its first phase, using autonomous learning techniques or Machine Learning, more specifically KNN (K- nearest Neighbor) with which the best result was obtained. This development will be based on a complete information bank taken from ADNI (Alz- heimer’s Disease NeuroImaging Initiative), with all the necessary parameters to direct the inves- tigation to an algorithm that is as efficient as pos- sible, since it has biological, sociodemographic and medical history data, biological specimens, neural images, etc., and in this way the early de- tection of the aforementioned disease was con- figured. A complete guide to the process will be carried out to finally obtain the KNN algorithm whose efficiency is 99%, and then discuss the obtained results.

Classification of Lathe’s Cutting Tool Wear Based on an Autonomous Machine Learning Model

Classification of Lathe’s Cutting Tool Wear Based on an Autonomous Machine Learning Model

RAI: Rapid, Autonomous and Intelligent machine learning approach to identify fire-vulnerable bridges

Recent surveys have noted that the majority of bridges continue to serve for a prolonged period of time (+40 years) that far exceeds its intended operational lifespan. Given our limited resources to maintain and upkeep bridges, these structures become notoriously vulnerable to extreme events. Building upon the fact that bridges continue not to be specifically designed to withstand the adverse effects of fire, this study presents the development of a rapid, automated, and intelligent (RAI) approach that leverages machine learning to identify vulnerable bridges to fire hazard. This work also presents details on a comprehensive database comprising actual observations collected from 135 notable and international bridge fire incidents. This database was developed to train two machine learning techniques, deep learning and genetic algorithms, to quantify hidden patterns that govern the propensity of existing/new/historical bridges to undergo fire damage and/or fire-induced collapse via a multi-classification analysis. The proposed RAI approach also has the capability to pinpoint fire-vulnerable bridge components and to display its level of confidence in its predictions. As such, our approach can be of aid to bridge engineers and government officials (who may not be well-versed in fire design) with accuracy reaching 89.6%. This approach is implemented into a software (App) with optimized architecture and reduced computational complexity and hence is easily scalable and integratable into a user-friendly framework and handheld devices. The outcome of this study shows that the RAI approach can be deployed to arrive at an instantaneous assessment of fire vulnerable bridges.

Assessing the new Natural Resources Conservation Service water supply forecast model for the American West: A challenging test of explainable, automated, ensemble artificial intelligence

Western US water management is underpinned by spring-summer water supply forecasts (WSFs) from hydrologic models forced primarily by winter mountain snowpack data. The US Department of Agriculture Natural Resources Conservation Service (NRCS) operates the largest such system regionally. NRCS recently developed a next-generation WSF prototype, the multi-model machine-learning metasystem (M4). Here, we test this ensemble artificial intelligence (AI)-based prototype against challenging theoretical and practical criteria for accepting a new operational WSF model. In 20 hindcasting test-cases spanning diverse environments across the western US and Alaska, on average out-of-sample R2 and RPSS improved over 50% and RMSE improved 13% relative to current benchmarks. The M4 ensemble mean forecast also performed more consistently than any of its diverse constituent models and in several cases outperformed all of them. Live operational testing at a subset of sites during the 2020 forecast season additionally demonstrated logistical feasibility of workflows, as well as geophysical explainability of results in terms of known hydrologic processes, belying the black-box reputation of machine learning and enabling relatable forecast storylines for clients. This was accomplished using WSF-focused pragmatic solutions, like “popular votes” for different candidate predictors among the constituent forecast systems, and graphical visualization of reduced-dimension, AI-extracted nonlinear feature-target relationships. We also found that certain M4 technical design elements, including autonomous machine learning (AutoML), hyperparameter pre-calibration, and theory-guided data science, collectively permitted automated (“over-the-loop”) training and operation. Overall, the analyses confirmed M4 meets requirements for NRCS operational adoption. This finding signals that, despite negligible operational-community uptake of machine learning so far, suitably purpose-designed novel AI systems have capacity to transition into large-scale practical applications with service-delivery organizations; it appears M4 will be the largest AI migration into operational river forecasting to date. It may ultimately provide a broader integration platform for harnessing multiple data and model types.