Path planning is a critical problem that entails calculating a wide range of ideal paths for each drone in a swarm. If this challenge could be solved, it would be possible to control a large number of drones without the need for human involvement while preserving optimal trajectories. The fewer people needed to operate UAVs and the shorter the path, the lower the costs. The primary goal is to create Artificial Intelligence based systems that can calculate the best flying path for a swarm of drones. Regardless of the maps or the amount of drones in the swarm, the goal of these result paths is to accomplish comprehensive coverage of a flight area for tasks like agricultural prospection.

In the field of computer security, the possibility of knowing which specific version of an operating system is running behind a machine can be useful in order to assist in a penetration test or to monitor the devices connected to a specific network. This task can be done interacting directly with the systems you want to fingerprint, performing an active scan, or just sniffing the normal traffic produced by the targets and analyze it, following a passive approach. One of the most widespread tools that better provides the first functionality is Nmap, which follows a rule-based approach for its active scan.

In this context, applying Machine Learning techniques seems to be a good option for representing the knowledge kept in the Nmap database and extract the main features which identify an operating system family. The first research line on this topic would be the exploration of the strengths of different Machine Learning algorithms to perform operating system fingerprinting. Furthermore, some clustering analysis could be interesting in order to understand which of the tests performed by Nmap are more decisive when carrying on this task.

Authentication is the process of validating the user identity in a system for them to be authorized accordingly. Nowadays, passwords are the most used authentication method in information systems, including critical ones such as those holding medical data. However, passwords entail many security problems and are threatened by attacks like phishing and the installation of keyloggers, which allow an attacker to obtain the secret password that authenticates a user and, therefore, eventually getting access to the system.

For this reason, there is a need for new advanced authentication protocols that complement or even replace passwords. During the last years from 2014, the FIDO Alliance and the W3C have developed FIDO CTAP and W3C WebAuthn API that constitute a new authentication method that makes use of hardware devices known as security keys or authenticators. These devices allow a user to benefit from public-key cryptography to authenticate in a system only by pressing a button.

In this context, we have developed a debugging tool for the protocol, and we have designed two scenarios in the Network Access Control field: using WebAuthn API together with a Captive Portal and using FIDO CTAP together with the Extensible Authentication Protocol framework to allow users to use security keys to connect to an IEEE 802.11 or IEEE 802.3 Local Area Networks.

Information security is increasingly becoming an important matter in nowadays society. Regarding the medical and biomedical data, it is an especially critical aspect due to the implications that a security violation on them would cause (for example, the lost, modification or the non-authorized disclosure). In this work some of the current main threats are analyzed: Ransomware: a malware that ransoms the data (usually, by ciphering them) and that requests a ransom (usually, the payment by cryptocurrencies) to regain access to it. There are a vast number of reported cases in important hospital centers all around the world, whose information systems have been halted during hours or even days, with major economical and health consequences. Medical data steal: organized groups of cybercriminals make use of several techniques to gain access to medical data, with the objective of selling them in the black market. Several studies indicate that the value of a medical record is greater than the credit card details. Medical devices security: devices like MRI, PET or CT, have software components that make them vulnerable to attacks, in the same way that to any other IT system. The same occurs with implantable devices, like pacemakers. There are studies that demonstrate that images from a MRI can be altered by a malware, so that it is not noticeable by the medical expert.

Albert Szent-Györgyi defined a creative act as ‘seeing what everyone else has seen and thinking as no one else has thought’. Would a machine be able to perform a creative act? Ada Lovelace, considered the first woman programmer, proposed almost 200 years ago the use of computers for artistic creative tasks, specifically musical ones. In recent years, our research group has been working on the creation of artificial artists and critics, as well as on classifiers and predictors of complexity and aesthetics. Automatic prediction of the aesthetic value of images has received increasing attention in recent years. This has come about, in part, because of the potential impact that aesthetic value has on practical applications. An aesthetic image evaluation system has been developed in recent years by our research group and has recently been tested for its potential and effectiveness in practical applications for commercial tasks. The results suggest an increase in the impact of advertisements using aesthetic criteria.

Technology has a fundamental role in the world of medicine. The appearance of new technologies has opened a wide range of possibilities in several fields. In this paper we describe current innovative techniques and methodologies for university training and for research and continuous training in Medicine: Virtual libraries to improve communication and encouraging interactive and personalized learning, critical analysis, individual and team work through the Internet. Interactive Anatomy Atlas based on multi-touch screen to easily explore and examine real bodies in great detail. 3d printing to accurately reproduce parts or the entire body of a patient to easily plan a complex surgical procedure. Augmented reality to offer new ways of displaying elements and providing much more facilities for professionals to carry out their work. Other technologies analysed are Simulators and Models, Interactive Display tables, Mobile apps, MOOCs, Flipped Classroom, Bring Your Own Device, Blended Learning or Design Thinking.

This paper presents how two apparently distinct branches, neuroscience and artificial intelligence, can collaborate in a symbiosis that allows them to join forces for new discoveries. Researchers specialising in the field of neuroscience can put forward conjectures and hypotheses that they have not been able to test for various reasons (high cost of testing, highly specialised simulations that programmes such as Neuron do not allow, etc.). All these questions posed by neuroscientists can be implemented by artificial intelligence experts within the connectionist branch. This allows new paradigms to appear in the artificial intelligence branch, and in the neuroscience branch to have a clearer idea of which hypothesis makes more sense in information processing. An example of this symbiosis has been the study of the tripartite synapse between neuron and astrocytes.

In this project, we show a new neuroscientific approach to information transmission and modulation in which networks of neurons and astrocytes mediate, thanks to the action of which, the processing of the received information is improved. The prefrontal cortex is in charge of cognitive control, and the information that arrives is processed from the beginning in that area to make decisions based on it. With the elapse of seconds after the information is processed by the brain, certain neuromodulators, such as dopamine in the hippocampus, are released and connect with the prefrontal cortex to modulate attention, impulse inhibition, memory or cognitive flexibility from how it was being done up to that moment. It is from this idea that a new computational model, composed of a Deep Learning network (representing the prefrontal cortex), a network of artificial neurons (representing the dopaminergic network) and the presence of an intermediate mediating component which would be the astrocyte, will be carried out. This new computational system shows improvements in the resolution of the AA problems it has faced, from the model with the DL network working in isolation, and even, improvement of the networks working together is observed if the astrocyte is in operation. Improvement also observed in biological brain processing.

An introduction to the different types of Artificial Intelligence (AI) systems is made and the best characteristics of each type are discussed for use in the medical environment. A brief historical introduction to the development of AI systems in medicine is made commenting on the successes and failures that occurred. Next, the most active fields of application in medicine of AI are studied in depth. We first speak of prioritization systems for radiologists' work lists, calculating scores for each patient so that the most serious patients are reported as a priority. It is discussed later on Image Enhancement systems in two senses. Those systems that are placed between the medical modalities and the storage systems (PACS) to increase the quality of the images by reducing the radiation doses received by the patient. Also on the systems that highlight and indicate pathologies in the images for the radiologist to review and validate the indication, also learning from the doctor's feedback. Finally, there is talk about automatic medical reporting systems that examine images to identify pathologies and are capable of writing reports and selecting key images. These systems also work by reinforcement using Feedback from the radiologist.

Predicting the activities of the chemical compounds by using in silico methods has been shown to be a cost- and time-effective way of aiding chemists in synthesizing new biological active compounds. MCF-7 is a commonly used breast cancer cell line, that has been propagated for many years by multiple groups. In this study a quantitative structure–activity relationship (QSAR) model [1-4] was developed to predict the anticancer activity for a diverse set of organic compounds. A number of models were developed, where a seventeen-variable model showed the best predictive performance with r² = 0.887 and q²_LOO = 0.828. The robustness and predictability of the best model was validated using the leave-one-out technique, external set and y-scrambling methods. The predictive ability of the model was confirmed with the external set, showing the r²_ext = 0.817. The developed model can be used in the prediction of the anticancer activity of new and untested organic compounds.

Materials and methods

The dataset of the compounds for the present research work was collected from several published experimental data [5-7] with anticancer activity (AA). All original activity data has been converted into molar 1/log(AA) response variables.

Results and discussion

The whole set of 105 compounds was divided into the training set consisted of 84 compounds and a test set (predicting set) of 21 compounds. GA-MLRA technique has identified several models. Statistical characteristics with seventeen descriptors variables models are obtained.

The following equation represent the developed model towards the AA:

1/Log(AA)= 0.001(±0.0005)T(N..F)+6.858(±9.022)X2A+ 9.937(±3.472)BELm1+1.955(±1.510)BELv3+0.029(±0.018)RDF080m+ 0.264(±0.211)Mor18u-0.343(±0.211)Mor21u-0.030(±0.097)Mor07m-0.155(±0.055)Mor09m+21.201(±18.218)G2e-10.253(±7.711)ISH-3.915(±2.455)HATS3m-57.537(±31.154)R7u+-3.630(±1.665)R1e-0.081(±0.054)n=CR2-0.099(±0.126)nCOOR+0.087(±0.261)nNHR-8.969(±12.499)

This model shows the best r² and q² values for the training set, and the best predictive potential for the test set for AA.

Conclusion. A QSAR study has been performed on the set of 105 organic compounds to analyze and predict IC₅₀ values of a series of compounds related to anticancer activity. QSAR analysis was performed using a combination of machine learning methods, such as GA for variable selection and MLRA.

As a result, a transparent, mechanistic model to predict IC₅₀ values related to anticancer activity is proposed. The best overall performance is achieved by seventeen-variable QSAR model, where r² values for the training and test sets are 0.887 and 0.817, respectively. The significant molecular descriptors related to the compounds with anticancer activity are: T(N..F), X2A, BELm1, BELv3, RDF080m, Mor18u, Mor21u, Mor07m, Mor09m, G2e, ISH, HATS3m, R7u+, R1e, n=CR2, nCOOR, and nNHR. Obtained model can be used to estimate the anticancer activities.

REFERENCES

[1] Puzyn T., Rasulev B., Gajewicz A., Hu X., Dasari T.P., Michalkova A., Hwang H.M., Toropov A., Leszczynska D., Leszczynski J. Using Nano-QSAR to predict the cytotoxicity of metal oxide nanoparticles, Nature Nanotechnology, 2011, 6, 175-178

[2] Turabekova, M.A., Rasulev, B., Dzhakhangirov, F.N., Leszczynska, D., Leszczynski, J., Aconitum and Delphinium alkaloids of curare-like activity. QSAR analysis and molecular docking of alkaloids into AChBP, European Journal of Medicinal Chemistry, 2010, 45 (9), 3885-3894

[3] Gajewicz A., Rasulev B., Dinadayalane T., Urbaszek P., Puzyn T., Leszczynska D., Leszczynski J. Advancing risk assessment of engineered nanomaterials: Application of computational approaches, Advanced Drug Delivery Reviews, 2012, 64 (15), 1663-1693

[4] Patnode K., Demchuk Z., Johnson S., Voronov A., Rasulev B. Combined Computational Protein-ligand Docking and Experimental Study of Bioplastic Films from Soybean Protein, Zein and Natural Modifiers, ACS Sustainable Chemistry and Engineering, 2021, 9, 10740-10748,

[5] Abdulrahman, H.L., Uzairu, A. & Uba, S. QSAR, Ligand Based Design and Pharmacokinetic Studies of Parviflorons Derivatives as Anti-Breast Cancer Drug Compounds Against MCF-7 Cell Line. Chemistry Africa, 2021, 4, 175–187. doi.org/10.1007/s42250-020-00207-7

[6] Bohari, M. H., Srivastava, H. K., & Sastry, G. N. Analogue-based approaches in anti-cancer compound modelling: the relevance of QSAR models. Organic and Medicinal Chemistry Letters, 2011, 1(1), 3. doi.org/10.1186/2191-2858-1-3

[7] Xu-Yan Wang, Chuang-Jun Li, Jie Ma, Chuan Li, Fang-You Chen, Nan Wang, Cang-Jie Shen, Dong-Ming Zhang. Cytotoxic 9,19-cycloartane type triterpenoid glycosides from the roots of Actaea Dahurica. Phytochemistry, 2019, 160, 48-55, doi.org/10.1016/j.phytochem.2019.01.004.