Search

Computational cost in metaheuristics such as Evolutionary Algorithm (EAs) is often a major concern, particularly with their ability to scale. In data-based training, traditional EAs typically use a significant portion, if not all, of the dataset for model training and fitness evaluation in each generation. This makes EA suffer from high computational costs incurred during the fitness evaluation of the population, particularly when working with large datasets. To mitigate this issue, we propose a Machine Learning (ML)-driven Distance-based Selection (DBS) algorithm that reduces the fitness evaluation time by optimizing test cases. We test our algorithm by applying it to 24 benchmark problems from Symbolic Regression (SR) and digital circuit domains and then using Grammatical Evolution (GE) to train models using the reduced dataset. We use GE to test DBS on SR and produce a system flexible enough to test it on digital circuit problems further. The quality of the solutions is tested and compared against state-of-the-art and conventional training methods to measure the coverage of training data selected using DBS, i.e., how well the subset matches the statistical properties of the entire dataset. Moreover, the effect of optimized training data on run time and the effective size of the evolved solutions is analyzed. Experimental and statistical evaluations of the results show our method empowered GE to yield superior or comparable solutions to the baseline (using the full datasets) with smaller sizes and demonstrates computational efficiency in terms of speed.

Acoustic surveys for sperm whales (Physeter macrocephalus) were conducted in the Mediterranean Sea in summer 2018 as part of the vessel-based component of the ACCOBAMS Survey Initiative (ASI). Equal-spaced zigzag transects provided uniform coverage of key sperm whale habitats and were surveyed using a towed hydrophone array deployed from a research vessel at speeds of 5-8 knots. A total of 14,039 km of tracklines were surveyed in the western basin, Hellenic Trench and Libyan waters, with an acoustic coverage of 10% realised for sperm whales. During these surveys, 254 individual sperm whales were detected on the trackline, with an additional 66 individuals off-track. Sperm whales were only seen ten times on-track, with an additional 16 off-track sightings. Estimates of slant range to echolocating whales were used to derive density estimates through both design- and model-based distance sampling methodologies. An acoustic availability of 0.912 (sd = 0.036) was derived from via published models. When correcting for availability bias, a design-based abundance estimates of 2,673 individuals (95% CI 1,739-4,105; CV = 0.21) was derived for the surveyed blocks, which incorporated most known sperm whale habitat in the Mediterranean Sea. The equivalent model-based estimate was 2,825 whales (2,053-3,888; CV = 0.16). Over 97% of detected whales were in the western basin, with highest densities in the Algerian and Liguro-Provencal Basins between Algeria and Spain/France. In the eastern basin, detections were sparse and concentrated along the Hellenic Trench. A density surface modelling (DSM) exercise identified location and benthic aspect as being the most instructive covariates for predicting whale abundance. Distance sampling results were used in a power analysis to quantify the survey effort required to identify population trends. In the most extreme scenario modelled (10% per annum decline with decennial surveys), the population could have dropped by 90% before the decline was identified with high statistical power. Increasing the regularity of surveys would allow population trends to be detected more expediently. Mediterranean sperm whales are listed as Endangered on the IUCN’s Red List and the need for urgent conservation measures to reduce injury and mortality remains paramount for this unique sub-population.

This work studies enhancing the capabilities of compact laser spectroscopes integrated into space-exploration rovers by adding 3D topography measurement techniques. Laser spectroscopy enables the in situ analysis of sample composition, aiding in the understanding of the geological history of extraterrestrial bodies. To complement spectroscopic data, the inclusion of 3D imaging is proposed to provide unprecedented contextual information. The morphological information aids material characterization and hence the constraining of rock and mineral histories. Assigning height information to lateral pixels creates topographies, which offer a more complete spatial dataset than contextual 2D imaging. To aid the integration of 3D measurement into future proposals for rover-based laser spectrometers, the relevant scientific, rover, and sample constraints are outlined. The candidate 3D technologies are discussed, and estimates of performance, weight, and power consumptions guide the down-selection process in three application examples. Technology choice is discussed from different perspectives. Inline microscopic fringe-projection profilometry, incoherent digital holography, and multiwavelength digital holography are found to be promising candidates for further development.

Conducting marine mammal research can raise several important ethical issues. For example, the continuation of whaling for commercial purposes despite the international moratorium provides opportunities for scientists to obtain data and tissue samples. In 2021 we analysed 35 peer-reviewed papers reporting research based on collaborations with Icelandic whalers. Results highlighted little consideration or understanding of the legal and ethical issues associated with the deliberate killing of whales amongst those researchers, funding bodies, universities and journals involved. Ethical statements were rarely provided. Those that were written were incomplete. Whilst research using whaling data may seem acceptable to some, it often becomes hard to justify when subject to scrutiny by the media and the public. Thus, there is a particular danger of reputational harm for early career researchers who may become unwittingly involved in such activities. Here we also consider the broader variety of ethical issues raised by non-lethal research (both historical and recent) on marine mammals including tagging and biopsy. We discuss instances where study animals were harmed or even killed and where the public mistook tags for harpoons. Without clear guidelines, reviewers and journal editors are put in an impossible position when considering whether to reject papers on ethical grounds. We propose that for such studies, universities, funders, journals, and permit issuers must require ethical assessments and that journals more effectively implement their existing policies on publishing ethical statements. The professional marine mammal societies need to work together to produce modern ethical guidance. Such guidance should require transparency in the provenance of data and samples while including advice on law, welfare issues, involvement of local scientists, and offshoring. Furthermore, it should require appraisal of and justification for the absolute necessity of invasive procedures. As is already the case in biomedical disciplines, ethical statements should be required in marine mammal science.

Abstract Health care interoperability unfolds the way for personalized health care services at a reduced cost. Furthermore, a decentralized system holds the promise to prevent compromises such as cyber‐attacks due to data breaches. Hence, there is a need for a framework that seamlessly integrates and shares data across the system stakeholders. We propose SEquestered aNd SynergIstic BLockchain Ecosystem (SENSIBLE), a blockchain‐powered, knowledge‐driven data‐sharing framework that gives patients complete control of their medical history and can extract rich information hidden in it using knowledge graphs (KGs). By incorporating both blockchain and KGs, we can provide a platform for secure data sharing among stakeholders by maintaining data privacy and integrity through data authentication and robust data integration. We present a Proof‐of‐Concept of the SENSIBLE network with Ethereum to share dynamic knowledge across stakeholders. Dynamic knowledge generation on the blockchain provides a two‐fold advantage of cooperation and communication amongst the stakeholders in the health care ecosystem. This leads to operational ease through sharing relevant portions of complex information while also ensuring the isolation of sensitive medical data.

GRAPE is an implementation of Grammatical Evolution (GE) in DEAP, an Evolutionary Computation framework in Python, which consists of the necessary classes and functions to evolve a population of grammar-based solutions, while reporting essential measures. This tool was developed at the Bio-computing and Developmental Systems (BDS) Research Group, the birthplace of GE, as an easy to use (compared to the canonical C++ implementation, libGE) tool that inherits all the advantages of DEAP, such as selection methods, parallelism and multiple search techniques, all of which can be used with GRAPE. In this paper, we address some problems to exemplify the use of GRAPE and to perform a comparison with PonyGE2, an existing implementation of GE in Python. The results show that GRAPE has a similar performance, but is able to avail of all the extra facilities and functionality found in the DEAP framework. We further show that GRAPE enables GE to be applied to systems identification problems and we demonstrate this on two benchmark problems.

Abstract This work investigates the potential for using Grammatical Evolution (GE) to generate an initial seed for the construction of a pseudo-random number generator (PRNG) and cryptographically secure (CS) PRNG. We demonstrate the suitability of GE as an entropy source and show that the initial seeds exhibit an average entropy value of 7.940560934 for 8-bit entropy, which is close to the ideal value of 8. We then construct two random number generators, GE-PRNG and GE-CSPRNG, both of which employ these initial seeds. We use Monte Carlo simulations to establish the efficacy of the GE-PRNG using an experimental setup designed to estimate the value for pi, in which 100,000,000 random numbers were generated by our system. This returned the value of pi of 3.146564000, which is precise up to six decimal digits for the actual value of pi. We propose a new approach called control_flow_incrementor to generate cryptographically secure random numbers. The random numbers generated with CSPRNG meet the prescribed National Institute of Standards and Technology SP800-22 and the Diehard statistical test requirements. We also present a computational performance analysis of GE-CSPRNG demonstrating its potential to be used in industrial applications.

The advent of cloud-based super-computing platforms has given rise to a Data Science (DS) boom. Many types of technological problems that were once considered prohibitively expensive to tackle are now candidates for exploration. Machine Learning (ML) tools that were valued only in academic environments are quickly being embraced by industrial giants and tiny startups alike. Coupled with modern-day computing power, ML tools can be looked at as hammers that can deal with even the most stubborn nails. ML tools have become so ubiquitous that the current industrial expectation is that they should not only deliver accurate and intelligent solutions but also do so rapidly. In order to keep pace with these requirements, a new enterprise, referred to as MLOps has blossomed in recent years. MLOps combines the process of ML and DS with an agile software engineering technique to develop and deliver solutions in a fast and iterative way. One of the key challenges to this is that ML and DS tools should be efficient and have better usability characteristics than were traditionally offered. In this paper, we present a novel software for Grammatical Evolution (GE) that meets both of these expectations. Our tool, GELAB, is a toolbox for GE in Matlab which has numerous features that distinguish it from existing contemporary GE software. Firstly, it is user-friendly and its development was aimed for use by non-specialists. Secondly, it is capable of hybrid optimization, in which standard numerical optimization techniques can be added to GE. We have shown experimentally that when hybridized with meta-heuristics GELAB has an overall better performance as compared with standard GE.

Abstract Mineralogy is the key to understanding the origin of Phobos and its position in the evolution of the Solar System. In situ Raman spectroscopy on Phobos is an important tool to achieve the scientific objectives of the Martian Moons eXploration (MMX) mission, and maximize the scientific merit of the sample return by characterizing the mineral composition and heterogeneity of the surface of Phobos. Conducting in situ Raman spectroscopy in the harsh environment of Phobos requires a very sensitive, compact, lightweight, and robust instrument that can be carried by the compact MMX rover. In this context, the Raman spectrometer for MMX (i.e., RAX) is currently under development via international collaboration between teams from Japan, Germany, and Spain. To demonstrate the capability of a compact Raman system such as RAX, we built an instrument that reproduces the optical performance of the flight model using commercial off-the-shelf parts. Using this performance model, we measured mineral samples relevant to Phobos and Mars, such as anhydrous silicates, carbonates, and hydrous minerals. Our measurements indicate that such minerals can be accurately identified using a RAX-like Raman spectrometer. We demonstrated a spectral resolution of approximately 10 cm−1, high enough to resolve the strongest olivine Raman bands at ~ 820 and ~ 850 cm−1, with highly sensitive Raman peak measurements (e.g., signal-to-noise ratios up to 100). These results strongly suggest that the RAX instrument will be capable of determining the minerals expected on the surface of Phobos, adding valuable information to address the question of the moon’s origin, heterogeneity, and circum-Mars material transport. Graphical Abstract

The deep sea is the largest ecosystem on Earth, yet little is known about the processes driving patterns of genetic diversity in its inhabitants. Here, we investigated the macro- and microevolutionary processes shaping genomic population structure and diversity in two poorly understood, globally distributed, deep-sea predators: Cuvier’s beaked whale (Ziphius cavirostris) and Blainville’s beaked whale (Mesoplodon densirostris). We used double-digest restriction associated DNA (ddRAD) and whole mitochondrial genome (mitogenome) sequencing to characterise genetic patterns using phylogenetic trees, cluster analysis, isolation-by-distance, genetic diversity and differentiation statistics. Single nucleotide polymorphisms (SNPs; Blainville’s n = 43 samples, SNPs=13988; Cuvier’s n = 123, SNPs= 30479) and mitogenomes (Blainville’s n = 27; Cuvier’s n = 35) revealed substantial hierarchical structure at a global scale. Both species display significant genetic structure between the Atlantic, Indo-Pacific and in Cuvier’s, the Mediterranean Sea. Within major ocean basins, clear differentiation is found between genetic clusters on the east and west sides of the North Atlantic, and some distinct patterns of structure in the Indo-Pacific and Southern Hemisphere. We infer that macroevolutionary processes shaping patterns of genetic diversity include biogeographical barriers, highlighting the importance of such barriers even to highly mobile, deep-diving taxa. The barriers likely differ between the species due to their thermal tolerances and evolutionary histories. On a microevolutionary scale, it seems likely that the balance between resident populations displaying site fidelity, and transient individuals facilitating gene flow, shapes patterns of connectivity and genetic drift in beaked whales. Based on these results, we propose management units to facilitate improved conservation measures for these elusive species.

Grammatical Evolution is a Genetic Programming variant which evolves problems in any arbitrary language that is BNF compliant. Since its inception, Grammatical Evolution has been used to solve real-world problems in different domains such as bio-informatics, architecture design, financial modelling, music, software testing, game artificial intelligence and parallel programming. Multi-output problems deal with predicting numerous output variables simultaneously, a notoriously difficult problem. We present a Multi-Genome Grammatical Evolution better suited for tackling multi-output problems, specifically digital circuits. The Multi-Genome consists of multiple genomes, each evolving a solution to a single unique output variable. Each genome is mapped to create its executable object. The mapping mechanism, genetic, selection, and replacement operators have been adapted to make them well-suited for the Multi-Genome representation and the implementation of a new wrapping operator. Additionally, custom grammar syntax rules and a cyclic dependency-checking algorithm have been presented to facilitate the evolution of inter-output dependencies which may exist in multi-output problems. Multi-Genome Grammatical Evolution is tested on combinational digital circuit benchmark problems. Results show Multi-Genome Grammatical Evolution performs significantly better than standard Grammatical Evolution on these benchmark problems.

Neural networks have revolutionised the way we approach problem solving across multiple domains; however, their effective design and efficient use of computational resources is still a challenging task. One of the most important factors influencing this process is model hyperparameters which vary significantly with models and datasets. Recently, there has been an increased focus on automatically tuning these hyperparameters to reduce complexity and to optimise resource utilisation. From traditional human-intuitive tuning methods to random search, grid search, Bayesian optimisation, and evolutionary algorithms, significant advancements have been made in this direction that promise improved performance while using fewer resources. In this article, we propose HyperGE, a two-stage model for automatically tuning hyperparameters driven by grammatical evolution (GE), a bioinspired population-based machine learning algorithm. GE provides an advantage in that it allows users to define their own grammar for generating solutions, making it ideal for defining search spaces across datasets and models. We test HyperGE to fine-tune VGG-19 and ResNet-50 pre-trained networks using three benchmark datasets. We demonstrate that the search space is significantly reduced by a factor of ~90% in Stage 2 with fewer number of trials. HyperGE could become an invaluable tool within the deep learning community, allowing practitioners greater freedom when exploring complex problem domains for hyperparameter fine-tuning.

NAND flash memory – ubiquitous in today’s world of smart phones, SSDs (solid state drives), and cloud storage – has a number of well-known reliability problems. NAND data contains bit errors, which require the use of error correcting codes (ECCs). The raw bit error rate (RBER) increases with program-erase (P-E) cycling, and the number of P-E cycles the device can withstand before the RBER exceeds the ECC capability is called its endurance. ECC operates on data stored in a sector of NAND, and there is a large variation in the endurance of sectors within a device and across devices, resulting in excessively conservative endurance specifications. This research shows, for the first time, that a sector’s true endurance can be predicted with remarkable accuracy, using a combination of the sector’s location within the device, and measurements taken at the very beginning of life. Real-world data is gathered on millions of NAND sectors using a custom-built test platform. Optimised machine learning classification models are built from the raw data to predict if a sector will pass or fail to a fixed ECC threshold, after a target P-E cycling level has been reached. A novel technique is demonstrated that uses different ECC thresholds for model training and testing, which allows the models to be tuned so that they never misclassify samples that would fail. This eliminates ECC failures and data loss, allowing simpler, less expensive ECC schemes to be used for modern NAND devices. It also enables significant endurance extensions to be achieved.

Robotics technology has made significant advancements in various fields in industry and society. It is clear how robotics has transformed manufacturing processes and increased productivity. Additionally, navigation robotics has also been impacted by these advancements, with investors now investing in autonomous transportation for both public and private use. This research aims to explore how training scenarios affect the learning process for autonomous navigation tasks. The primary objective is to address whether the initial conditions (learning cases) have a positive or negative impact on the ability to develop general controllers. By examining this research question, the study seeks to provide insights into how to optimize the training process for autonomous navigation tasks, ultimately improving the quality of the controllers that are developed. Through this investigation, the study aims to contribute to the broader goal of advancing the field of autonomous navigation and developing more sophisticated and effective autonomous systems. Specifically, we conducted a comprehensive analysis of a particular navigation environment using evolutionary computing to develop controllers for a robot starting from different locations and aiming to reach a specific target. The final controller was then tested on a large number of unseen test cases. Experimental results provide strong evidence that the initial selection of the learning cases plays a role in evolving general controllers. This work includes a preliminary analysis of a specific set of small learning cases chosen manually, provides an in-depth analysis of learning cases in a particular navigation task, and develops a tool that shows the impact of the selected learning cases on the overall behavior of a robot’s controller.

In this article, we discuss a data sharing and knowledge integration framework through autonomous agents with blockchain for implementing Electronic Health Records (EHR). This will enable us to augment existing blockchain-based EHR Systems. We discuss how major concerns in the health industry, i.e., trust, security and scalability, can be addressed by transitioning from existing models to convergence of the three technologies – blockchain, agent-based modeling, and knowledge graph in a decentralized ecosystem. Each autonomous agent is responsible for instantiating key processes, such as user authentication and authorization, smart contracts, and knowledge graph generation through data integration among the participating stakeholders in the network. We discuss a layered approach for the design of the proposed system leading to an enhanced, safer clinical decision-making system. This can pave the way toward more informed and engaged patients and citizens by delivering personalized healthcare.

Abstract Graphene oxide (GO) is a graphene derivative that emits fluorescence, which makes GO an attractive material for optoelectronics and biotechnology. In this work, we utilize ozone treatment to controllably tune the band gap of GO, which can significantly enhance its applications. Ozone treatment in aqueous GO suspensions yields the addition/rearrangement of oxygen-containing functional groups suggested by the increase in vibrational transitions of C-O and C=O moieties. Concomitantly it leads to an initial increase in GO fluorescence intensity and significant (100 nm) blue shifts in emission maxima. Based on the model of GO fluorescence originating from sp2 graphitic islands confined by oxygenated addends, we propose that ozone-induced functionalization decreases the size of graphitic islands affecting the GO band gap and emission energies. TEM analyses of GO flakes confirm the size decrease of ordered sp2 domains with ozone treatment, whereas semi-empirical PM3 calculations on model addend-confined graphitic clusters predict the inverse dependence of the band gap energies on sp2 cluster size. This mod el explains ozone-induced increase in emission energies yielding fluorescence blue shifts and helps develop an understanding of the origins of GO fluorescence emission. Furthermore, ozone treatment provides a versatile approach to controllably alter GO band gap for optoelectronics and bio-sensing applications.