Search

As the COVID-19 pandemic continues to affect the world, a new variant of concern, B.1.1.529 (Omicron), has been recently identified by the World Health Organization. At the time of writing, there are still no available primer sets specific to the Omicron variant, and its identification is only possible by using multiple targets, checking for specific failures, amplifying the suspect samples, and sequencing the results. This procedure is considerably time-consuming, in a situation where time might be of the essence. In this paper we use an Artificial Intelligence (AI) technique to identify a candidate primer set for the Omicron variant. The technique, based on Evolutionary Algorithms (EAs), has been already exploited in the recent past to develop primers for the B.1.1.7/Alpha variant, that have later been successfully tested in the lab. Starting from available virus samples, the technique explores the space of all possible subsequences of viral RNA, evaluating them as candidate primers. The criteria used to establish the suitability of a sequence as primer includes its frequency of appearance in samples labeled as Omicron, its absence from samples labeled as other variants, a specific range of melting temperature, and its CG content. The resulting primer set has been validated in silico and proves successful in preliminary laboratory tests. Thus, these results prove further that our technique could be established as a working template for a quick response to the appearance of new SARS-CoV-2 variants.

Digital Collectible Cards Games such as Hearthstone have become a very proli c test-bed for Arti cial Intelligence algorithms. The main researches have focused on the implementation of autonomous agents (bots) able to effectively play the game. However, this environment is also very attractive for the use of Data Mining (DM) and Machine Learning (ML) techniques, for analysing and extracting useful knowledge from game data. The objective of this work is to apply existing Game Mining techniques in order to study more than 600,000 real decks (groups of cards) created by players with many di erent skill levels. Data visualisation and analysis tools have been applied, namely, Graph representations and Clustering techniques. Then, an expert player has conducted a deep analysis of the results yielded by these methods, aiming to identify the use of standard - and well-known - archetypes de ned by the players. The used methods will also make it possible for the expert to discover hidden relationships between cards that could lead to nding better combinations of them, enhancing players' decks or, otherwise, identify unbalanced cards that could lead to a disappointing game experience. Moreover, although this work is mostly focused on data analysis and visualization, the obtained results can be applied to improve Hearthstone Bots' behaviour, e.g. predicting opponent's actions after identifying a speci c archetype in his/her deck., Spanish Government PID2020-113462RB-I00 PID2020-115570 GB-C22, Junta de Andalucia B-TIC-402-UGR18 P18-RT-4830 A-TIC-608-UGR20

The backlash is a lost motion in a mechanism created by gaps between its parts. It causes vibrations that increase over time and negatively affect accuracy and performance. The quickest and most precise way to measure the backlash is to use specific sensors, that have to be added to the standard equipment of the robot. However, this solution is little used in practice because raises the manufacturing costs. An alternative solution can be to exploit a virtual sensor, i.e., the information about phenomena that are not directly measured is reconstructed by signals from sensors used for other measurements.This work evaluates the use of bio-inspired swarm algorithms as the processing core of a virtual sensor for the backlash of a robotic joint. Swarm-based approaches, with their relatively modest occupation of memory and low computational load, could be ideal candidates to solve the problem. In this paper, we exploit four state-of-the-art swarm-based optimization algorithms: the Dragonfly Algorithm, the Ant Lion Optimizer, the Grasshopper Optimization Algorithm, and the Grey Wolf Optimizer. The four candidate algorithms are compared on 20 different datasets covering a range of backlash values that reflect an industrial case scenario. Numerical results indicate that, unfortunately, none of the algorithms considered provides satisfactory solutions for the problem analyzed. Therefore, even if promising, these algorithms cannot represent the final choice for the problem of interest.

As the COVID-19 pandemic continues, new SARS-CoV-2 variants with potentially dangerous features have been identified by the scientific community. Variant B.1.1.7 lineage clade GR from Global Initiative on Sharing All Influenza Data (GISAID) was first detected in the UK, and it appears to possess an increased transmissibility. At the same time, South African authorities reported variant B.1.351, that shares several mutations with B.1.1.7, and might also present high transmissibility. Earlier this year, a variant labelled P.1 with 17 non-synonymous mutations was detected in Brazil. Recently the World Health Organization has raised concern for the variants B.1.617.2 mainly detected in India but now exported worldwide. It is paramount to rapidly develop specific molecular tests to uniquely identify new variants. Using a completely automated pipeline built around deep learning and evolutionary algorithms techniques, we designed primer sets specific to variants B.1.1.7, B.1.351, P.1 and respectively. Starting from sequences openly available in the GISAID repository, our pipeline was able to deliver the primer sets for each variant. In-silico tests show that the sequences in the primer sets present high accuracy and are based on 2 mutations or more. In addition, we present an analysis of key mutations for SARS-CoV-2 variants. Finally, we tested the designed primers for B.1.1.7 using RT-PCR. The presented methodology can be exploited to swiftly obtain primer sets for each new variant, that can later be a part of a multiplexed approach for the initial diagnosis of COVID-19 patients.

The SARS-CoV-2 variant B.1.1.7 lineage, also known as clade GR from Global Initiative on Sharing All Influenza Data (GISAID), Nextstrain clade 20B, or Variant Under Investigation in December 2020 (VUI – 202012/01), appears to have an increased transmissability in comparison to other variants. Thus, to contain and study this variant of the SARS-CoV-2 virus, it is necessary to develop a specific molecular test to uniquely identify it. Using a completely automated pipeline involving deep learning techniques, we designed a primer set which is specific to SARS-CoV-2 variant B.1.1.7 with >99% accuracy, starting from 8,923 sequences from GISAID. The resulting primer set is in the region of the synonymous mutation C16176T in the ORF1ab gene, using the canonical sequence of the variant B.1.1.7 as a reference. Furtherin-silicotesting shows that the primer set’s sequences do not appear in different viruses, using 20,571 virus samples from the National Center for Biotechnology Information (NCBI), nor in other coronaviruses, using 487 samples from National Genomics Data Center (NGDC). In conclusion, the presented primer set can be exploited as part of a multiplexed approach in the initial diagnosis of Covid-19 patients, or used as a second step of diagnosis in cases already positive to Covid-19, to identify individuals carrying the B.1.1.7 variant.

[EN] In recent years, modelling techniques have become more frequently adopted in the field of food processing, especially for cereal-based products, which are among the most consumed foods in the world. Predictive models and simulations make it possible to explore new approaches and optimize proceedings, potentially helping companies reduce costs and limit carbon emissions. Nevertheless, as the different phases of the food processing chain are highly specialized, advances in modelling are often unknown outside of a single domain, and models rarely take into account more than one step. This paper introduces the first high-level overview of modelling techniques employed in different parts of the cereal supply chain, from farming to storage, from drying to milling, from processing to consumption. This review, issued from a networking project including researchers from over 30 different countries, aims at presenting the current state of the art in each domain, showing common trends and synergies, to finally suggest promising future venues for research., The authors would like to acknowledge networking and article processing charge support by COST Action CA15118 (Mathematical and Computer Science Methods for Food Science and Industry).

Machine learning agents learn to take decisions extracting information from training data. When similar inferences can be obtained using a small subset of the same training set of samples, the subset is called coreset. Coresets discovery is an active line of research as it may be used to reduce the training speed as well as to allow human experts to gain a better understanding of both the phenomenon and the decisions, by reducing the number of samples to be examined. For classification problems, the state-of-the-art in coreset discovery is EvoCore, a multi-objective evolutionary algorithm. In this work EvoCore is exploited both on synthetic and on real data sets, showing how coresets may be useful in explaining decisions taken by machine learning classifiers.

Industrial manipulators are robots used to replace humans in dangerous or repetitive tasks. Also, these devices are often used for applications where high precision and accuracy is required. The increase of backlash caused by wear, that is, the increase of the amount by which teeth space exceeds the thickness of gear teeth, might be a significant problem, that could lead to impaired performances or even abrupt failures. However, maintenance is difficult to schedule because backlash cannot be directly measured and its effects only appear in closed loops. This paper proposes a novel technique, based on an Evolutionary Algorithm, to estimate the increase of backlash in a robot joint transmission. The peculiarity of this method is that it only requires measurements from the motor encoder. Experimental evaluation on a real-world test case demonstrates the effectiveness of the approach.

Social networks are one the main sources of information transmission nowadays. However, not all nodes in social networks are equal: in fact, some nodes are more influential than others, i.e., their information tends to spread more. Finding the most influential nodes in a network – the so-called Influence Maximization problem – is an NP-hard problem with great social and economical implications. Here, we introduce a framework based on Evolutionary Algorithms that includes various graph-aware techniques (spread approximations, domain-specific operators, and node filtering) that facilitate the optimization process. The framework can be applied straightforwardly to various social network datasets, e.g., those in the SNAP repository.

A better understanding of protein fouling during the thermal treatment of whey protein concentrate (WPC) solutions is critical for better fouling control. In order to understand the impact of various parameters on the total whey protein fouling mass, a dimensional analysis was applied to the experimental data obtained from a pilot scale plate heat exchanger, setting total fouling mass as the target variable. A model was developed to predict the total fouling mass, covering a series of variables including whey protein solution concentration (2.5–25 g/L), calcium concentration (70-120 ppm), running time (90-330 min), fouling solution flow rate (200-500 L/h), total fouling surface area, outlet temperature (82-97 °C) and differences in whey protein concentrate powders. In addition to temperature dimensionless parameters, the main parameters involved in the model are the Reynolds number (2000-5000) and the calcium to β-lactoglobulin molar ratio (2.7–34.7). The model developed concerns only pure whey proteins solutions since all the testing solutions were casein free. This model has allowed us to provide guidelines as to how the above parameters influence fouling within the plate heat exchanger, as well as empirical correlations for predicting such fouling development.

The two volumes LNCS 10199 and 10200 constitute the refereed conference proceedings of the 20th European Conference on the Applications of Evolutionary Computation, EvoApplications 2017, held in Amsterdam, The Netherlands, in April 2017, collocated with the Evo* 2016 events EuroGP, EvoCOP, and EvoMUSART. The 46 revised full papers presented together with 26 poster papers were carefully reviewed and selected from 108 submissions. EvoApplications 2016 consisted of the following 13 tracks: EvoBAFIN (natural computing methods in business analytics and finance), EvoBIO (evolutionary computation, machine learning and data mining in computational biology), EvoCOMNET (nature-inspired techniques for telecommunication networks and other parallel and distributed systems), EvoCOMPLEX (evolutionary algorithms and complex systems), EvoENERGY (evolutionary computation in energy applications), EvoGAMES (bio-inspired algorithms in games), EvoIASP (evolutionary computation in image analysis, signal processing, and pattern recognition), EvoINDUSTRY (nature-inspired techniques in industrial settings), EvoKNOW (knowledge incorporation in evolutionary computation), EvoNUM (bio-inspired algorithms for continuous parameter optimization), EvoPAR (parallel implementation of evolutionary algorithms), EvoROBOT (evolutionary robotics), EvoSET (nature-inspired algorithms in software engineering and testing), and EvoSTOC (evolutionary algorithms in stochastic and dynamic environments).

International audience; The complexity of cell phones is continually increasing, with regards to both hardware and software parts. As many complex devices, their components are usually designed and verified separately by specialized teams of engineers and programmers. However, even if each isolated part is working flawlessly, it often happens that bugs in one software application arise due to the interaction with other modules. Those software misbehaviors become particularly critical when they affect the residual battery life, causing power dissipation. An automatic approach to detect power-affecting software defects is proposed. The approach is intended to be part of a qualifying verification plan and complete human expertise. Motorola, always at the forefront of researching innovations in the product development chain, experimented the approach on a mobile phone prototype during a partnership with Politecnico di Torino. Software errors unrevealed by all human-designed tests have been detected by the proposed framework, two out of three critical from the power consumption point of view, thus enabling Motorola to further improve its verification plans. Details of the tests and experimental results are presented.

A malicious botnet is a collection of compromised hosts coordinated by an external entity. The malicious software, or malware, that infect the systems are its basic units and they are responsible for its global behavior. Anti Virus software and Intrusion Detection Systems detect botnets by analyzing network and files, looking for signature and known behavioral patterns. Thus, the malware hiding capability is a crucial aspect. This paper describes a new obfuscation mechanism based on evolutionary algorithms: an evolutionary core is embedded in the malware to generate a different, optimized hiding strategy for every single infection. Such always-changing, hard-to-detect malware can be used by security industries to stress the analysis methodologies and to test the ability to react to malware mutations. This research is the first step in a more ambitious research project, where a whole botnet, composed of different malware and Anti Virus software, is analyzed as a prey-predator ecosystem.

Global Sensitivity Analysis (GSA) studies how uncertainty in the inputs of a system influences uncertainty in its outputs. GSA is extensively used by experts to gather information about the behavior of models, through computationally-intensive stochastic sampling of parameters' space. Some studies propose to make use of the considerable quantity of data acquired in this way to optimize the model parameters, often resorting to Evolutionary Algorithms (EAs). Nevertheless, efficiently exploiting information gathered from GSA might not be so straightforward. In this paper, we present a counterexample followed by experimental results to prove how naively combining GSA and EA can bring about negative outcomes.

Wireless sensor network (WSN) routing protocols, e.g., the Collection Tree Protocol (CTP), are designed to adapt in an ad-hoc fashion to the quality of the environment. WSNs thus have high internal dynamics and complex global behavior. Classical techniques for performance evaluation (such as testing or verification) fail to uncover the cases of extreme behavior which are most interesting to designers. We contribute a practical framework for performance evaluation of WSN protocols. The framework is based on multi-objective optimization, coupled with protocol simulation and evaluation of performance factors. For evaluation, we consider the two crucial functional and non-functional performance factors of a WSN, respectively: the ratio of data delivery from the network (DDR), and the total energy expenditure of the network (COST). We are able to discover network topological configurations over which CTP has unexpectedly low DDR and/or high COST performance, and expose full Pareto fronts which show what the possible performance tradeoffs for CTP are in terms of these two performance factors. Eventually, Pareto fronts allow us to bound the state space of the WSN, a fact which provides essential knowledge to WSN protocol designers.

This short paper proposes two different ways for exploiting an evolutionary algorithm to devise malware: the former targeting heuristic-based anti-virus scanner; the latter optimizing a Trojan attack. An extended internal on the same the subject can be downloaded from http://www.cad.polito.it/downloads/

The complexity of cell phones is continually increasing, with regards to both hardware and software parts. As many complex devices, their components are usually designed and verified separately by specialized teams of engineers and programmers. However, even if each isolated part is working flawlessly, it often happens that bugs in one software application arise due to the interaction with other modules. Those software misbehaviors become particularly critical when they affect the residual battery life, causing power dissipation. An automatic approach to detect power-affecting software defects is proposed. The approach is intended to be part of a qualifying verification plan and complete human expertise. Motorola, always at the forefront of researching innovations in the product development chain, experimented the approach on a mobile phone prototype during a partnership with Politecnico di Torino. Software errors unrevealed by all human-designed tests have been detected by the proposed framework, two out of three critical from the power consumption point of view, thus enabling Motorola to further improve its verification plans. Details of the tests and experimental results are reported.

In software-based self-test (SBST) a microprocessor executes a set of test programs devised for detecting the highest possible percentage of faults. The main advantages of this approach are its high defect fault coverage (being performed at-speed) and the reduced cost (since it does not require any change in the processor hardware). SBST can also be used for on-line test of a microprocessor-based system. However, some additional constraints exist in this case (e.g. in terms of test length and duration, as well as intrusiveness). This paper faces the issue of automatically transforming a test set devised for manufacturing test in a test set suitable for on-line test. Experimental results are reported on an Intel 8051 microcontroller. Preliminary results have been published in [133].

Microprocessor testing is becoming a challenging task, due to the increasing complexity of modern architectures. Nowadays, most architectures are tackled with a combination of scan chains and Software-Based Self-Test (SBST) methodologies. Among SBST techniques, evolutionary feedback-based ones prove effective in microprocessor testing: their main disadvantage, however, is the considerable time required to generate suitable test programs. A novel evolutionary-based approach, able to appreciably reduce the generation time, is presented. The proposed method exploits a high-level representation of the architecture under test and a dynamically built Finite State Machine (FSM) model to assess fault coverage without resorting to time-expensive simulations on low-level models. Experimental results, performed on an OpenRISC processor, show that the resulting test obtains a nearly complete fault coverage against the targeted fault model.

This chapter presents an innovative approach for the generation of test programs detecting path-delay faults in microprocessors. The proposed method takes advantage of the multiobjective implementation of a previously devised evolutionary algorithm and exploits both gate- and RT-level descriptions of the processor: the former is used to build Binary Decision Diagrams (BDDs) for deriving fault excitation conditions; the latter is used for the automatic generation of test programs able to excite and propagate fault effects, based on a fast RTL simulation. Experiments on an 8-bit microcontroller show that the proposed method is able to generate suitable test programs more efficiently compared to existing approaches. Preliminary results have been published in [10].

The incessant progress in manufacturing technology is posing new challenges to microprocessor designers. Nowadays, comprehensive verification of a chip can only be performed after tape-out, when the first silicon prototypes are available. Several activities that were originally supposed to be part of the pre-silicon design phase are migrating to this post-silicon time as well. This chapter describes a post-silicon methodology that can be exploited to devise functional failing tests. Such tests are essential to analyze and debug speed paths during verification, speed-stepping, and other critical activities. The proposed methodology is based on the Genetic Programming paradigm, and exploits a versatile toolkit named μGP. The chapter describes how an evolutionary algorithm can successfully tackle a significant and still open industrial problem. Moreover, it shows how to take into account complex hardware characteristics and architectural details of such complex devices. The experimental evaluation clearly demonstrate the potential of this line of research. Results of this work have been accepted for publication in [137].

Artificial olfaction systems that try to mimic human olfaction by using arrays of gas chemical sensors combined with pattern recognition methods represent a potentially economic tool in many areas of industry such as: perfumery, food and drinks production, clinical diagnosis, health and safety, environmental monitoring and process control. However, successful applications of these systems are still largely limited to specialized laboratories. Among others, sensor drift, the lack of stability over time still limit real industrial setups. This chapter presents and discusses an evolutionary based adaptive drift-correction method designed to work with state-of-the-art classification algorithms. The proposed system exploits a leading-edge evolutionary strategy to iteratively tweak the coefficients of a linear transformation able to transparently transform raw sensors measures in order to mitigate negative effects of the drift. The optimal correction strategy is learned without a-priori models or other hypothesis on the behavior of physical-chemical sensors. Preliminary results have been published in [49].

Traditional test generation methodologies for peripheral cores are performed by a skilled test engineer, leading to long generation times. In this paper a test generation methodology based on an evolutionary tool which exploits high level metrics is presented. To strengthen the correlation between high-level coverage and the gate-level fault coverage, in the case of peripheral cores, the FSMs embedded in the system are identified and then dynamically extracted via simulation, while transition coverage is used as a measure of how much the system is exercised. The results obtained by the evolutionary tool outperform those obtained by a skilled engineer on the same benchmark. Preliminary results have been published in [127].

International audience; Gas chemical sensors are strongly affected by the so-called drift, i.e., changes in sensors' response caused by poisoning and aging that may significantly spoil the measures gathered. The paper presents a mechanism able to correct drift, that is: delivering a correct unbiased fingerprint to the end user. The proposed system exploits a state-of-the-art evolutionary strategy to iteratively tweak the coefficients of a linear transformation. The system operates continuously. The optimal correction strategy is learnt without a-priori models or other hypothesis on the behavior of physical-chemical sensors. Experimental results demonstrate the efficacy of the approach on a real problem.

In this paper we describe an improvement of an entropy-based diversity preservation approach for evolutionary algorithms. This approach exploits the information contained not only in the parts that compose an individual, but also in their position and relative order. We executed a set of preliminary experiments in order to test the new approach, using two different problems in which diversity preservation plays a major role in obtaining good solutions.