Search

This paper discusses the design and development of cyber-physical, social systems using a set of guidelines that capture the conceptual and technical characteristics of such systems. These guidelines are packaged into a framework that resorts to the concept of artifact. Because of these characteristics, the framework’s artifacts are specialized into 3 types referred to as data, thing, and social, all connected together through a set of situational relations referred to as work-withme, work-for-me, back-me, and avoid-me. To mitigate conflicts blue that could arise because of artifacts’ respective time availabilities when they jointly participate in situational relations, policies are put in place defining who does what, when, where, and why. To demonstrate the technical doability of the multi-type artifact framework, a system capturing cyber, physical, and social interactions in a healthcare case-study is developed, deployed, and evaluated.

The cutting-edge research of materials enables the discovery of novel energy harvesting materials. In this project the structural, electronic, magnetic, thermodynamic, thermoelectric, and optical properties of different energy harvesting materials are studied. The main objective of this work is primarily to study thermoelectrically efficient half-heuslers and photovoltaically active perovskites. Variant schematics of innovative compounds with defect introduction are investigated. The compositionally altered compounds designed by introducing crystallographic defects in terms of substitutional or interstitial dopants, offer new trends of material properties. To accomplish the task, Density Functional theory based computational packages (VASP and Wein2K) are used. Using defect and strain engineering, this study explores thermoelectric and photovoltaic properties. We have explored state-of-the-art features of defect tolerance, quantum and dielectric confinement, low effective masses, and high mobility in perovskites with halfmetallic and thermally stable half-heuslers exhibiting high figure of merit. Our goal is to computationally design and study half-Heuslers and perovskites for thermoelectric, solar applications, and green energy productions. The computational simulations and associated results are consistent with the previous studies to give a better understanding of the perovskites and half-heuslers.

The present work aimed to study the feasibility of photo-Fenton oxidation for the degradation of chlortetracycline chlorhydrate (CTC) in aqueous solutions, as well as the modelling of system behaviour by artificial neural networks. The removal performance of CTC oxidation by the Photo-Fenton process was studied under solar radiation. Different parameters were studied, such as pH (3 to 5), and initial concentrations of CTC (0.1 to 10 mg l–1), hydrogen peroxide (1.701 to 190.478 mg l–1), and ferrous ions (2.8 to 103.6 mg l–1). Results showed that a high removal efficiency of 92 % was achieved at pH 3 under optimised conditions, such as 10 mg l–1 of CTC, 127.552 mg l–1 of H2O2, and 36.4 mg l–1 of Fe2+. The transformation of CTC molecules was proved by UV-visible and HPLC analyses, which showed that almost no CTC molecules were remaining in the treated solution. A multi-layer perceptron artificial neural network has been developed to predict the experimental removal efficiency of CTC based on four dimensionless inputs: molecular weight, and initial concentrations of CTC, hydrogen peroxide and ferrous ions. The best network has been found with a high determination coefficient of 0.9960, and with a very acceptable root mean square error 0.0108. In addition, the global sensitivity analysis confirms that the most influential parameter for the CTC removal by photo-Fenton oxidation is the initial concentration of ferrous cations with a relative importance of 33 %., Cilj ovog rada bio je ispitati razgradnju klortetraciklin klorhidrata (CTC) u vodenoj otopini foto-Fentonovim procesom, kao i modelirati ponašanje sustava primjenom umjetnih neuronskih mreža. Učinkovitost uklanjanja CTC-a foto-Fentonovim procesom ispitana je pod sunčevom svjetlošću. Proučavani su različiti parametri poput pH (3 do 5) te početnih koncentracija CTC-a (0,1 do 10 mg l–1), vodikova peroksida (1,701 do 190,478 mg l–1) i željeznih iona (2,8 do 103,6 mg l–1). Dobivena je učinkovitost uklanjanja od 92 % pri pH 3, uz 10 mg l–1 CTC, 127,552 mg l–1 H2O2 i 36,4 mg l–1 Fe2+. Koncentracija CTC-a praćena je spektrofotometrijski i tekućinskom kormatografijom, te su utvrđene neznatne koncentracije CTC-a u vodenoj otopini nakon obrade. Umjetna neuronska mreža višeslojni perceptron razvijena je za predviđanje eksperimentalne učinkovitosti uklanjanja CTC-a na temelju četiri bezdimenzionalna ulaza: molekulske mase, te početnih koncentracija CTC-a, vodikova peroksida i željeznih iona. Pronađena je najbolja mreža s visokim koeficijentom determinacije od 0,9960 i vrlo prihvatljivom srednjom kvadratnom pogreškom od 0,0108. Globalna analiza osjetljivosti potvrdila je da je najutjecajniji parametar kod uklanjanja CTC-a foto-Fentonovim procesom početna koncentracija kationa željeza s relativnom važnošću od 33 %.

The predictability of the adsorption capacity of the multicomponent adsorption system was modelled using Support Vector Machine (SVM). Two SVM models were built and compared. In the first model, the SVM method was used with an already built-in optimisation algorithm. However, in the second model, the SVM method was used by means of a very recent and efficient optimisation algorithm: the Dragonfly Algorithm (DA). The models’ accuracy was evaluated by three well-established statistical metrics (root mean squared error RMSE, determination coefficient R2, and correlation coefficient R). The used data were collected from previous experimental papers published in literature containing all kinds of pollutants, such as heavy metal ions, dyes, and organic compounds, and different natural/synthetic adsorbents. The dataset contained five important variables with 1023 points; the variables were divided into four inputs (molecular weight, equilibrium concentrations of adsorbate, specific area of adsorbent, and temperature), and one output (adsorption capacity at equilibrium). The data were divided using the holdout function into two subsets (80 % for training set, and 20 % for test set). The programming stage was carried out using MATLAB software. The results showed that the optimised DA-SVM model with RBF-Gaussian kernel function had good ability for global search combined with high prediction accuracy, with R2 = 0.997, R = 0.998, and RMSE = 2.539. The obtained model can be used to predict the efficiency of the adsorption system, and provides a tool for process optimisation responding to changes in operating conditions. A new graphical user interface (GUI) was developed with MATLAB GUI to estimate accurately the desired responses by using the best DA-SVM model., Višekomponentni adsorpcijski kapacitet modelirana je metodom potpornih vektora (SVM). Razvijena su i uspoređena dva SVM modela. U prvom modelu primijenjena je metoda SVM s već ugrađenim optimizacijskim algoritmom. U drugom modelu primijenjena je SVM metoda s Dragonfly algoritmom (DA) optimizacije. Točnost modela procijenjena je pomoću tri uvriježene statističke mjere: korijena srednje kvadratne pogreške RMSE, koeficijenta determinacije R2 i koeficijenta korelacije R. Korišteni podatci o raznim onečišćivalima, poput iona teških metala, boja i organskih spojeva te različitim prirodnim/sintetskim adsorbensima prikupljeni su iz literaturno dostupnih znanstvenih radova. Skup podataka sadržavao je pet važnih varijabli s 1023 točke; 4 varijable bile su ulazne varijable (molekulska masa, ravnotežne koncentracije adsorbata, specifično područje adsorbensa i temperatura), a jedna izlazna (ravnotežni adsorpcijski kapacitet). Podatci su podijeljeni u dva podskupa: 80 % podataka uzeto je za treniranje, a 20 % za testiranje. Programiranje je provedeno u softveru MATLAB. Rezultati su pokazali da optimiran DA-SVM model s RBF-Gaussovom kernel funkcijom ima dobru sposobnost globalnog pretraživanja uz visoku točnost predviđanja, s R2 = 0,997, R = 0,998 i RMSE = 2,539. Dobiveni model može se primjenjivati za predviđanje učinkovitosti adsorpcijskog sustava te pruža alat za optimizaciju procesa u skladu s promjenama radnih uvjeta. Razvijeno je novo grafičko korisničko sučelje (GUI) za točnu procjenu željenih odziva koje primjenjuje najbolji DA-SVM model.

This paper aims to assess and improve the sustainability performance at a higher educational institute (HEI) in UAE using DMAIC methodology, considering five sustainability aspects (knowledge, behaviour, concern, awareness and attitude). One primary and six secondary research questions were defined in the define phase. In the measure phase, a questionnaire was designed to measure the current sustainability level based on the five sustainability aspects. A questionnaire was distributed among campus populations and statistically analysed in the analysis phase. Participation in UI GreenMetric was used in the control phase to monitor the performance from 2018 to 2020. It was found that the communication college has the lowest sustainability level at 25% marginal error compared with other colleges. Also, students have the lowest sustainability level compared with faculty and staff at a 15% marginal error. The proposed framework can help HEI decision‐makers assess their sustainability levels and suggest plans to enhance sustainability performance.

Bacteria of the genus Brucella are facultative intracellular parasites that cause brucellosis, a severe animal and human disease. Recently, a group of taxonomists merged the brucellae with the primarily free-living, phylogenetically related Ochrobactrum spp. in the genus Brucella. This change, founded only on global genomic analysis and the fortuitous isolation of some opportunistic Ochrobactrum spp. from medically compromised patients, has been automatically included in culture collections and databases. We argue that clinical and environmental microbiologists should not accept this nomenclature, and we advise against its use because (i) it was presented without in-depth phylogenetic analyses and did not consider alternative taxonomic solutions; (ii) it was launched without the input of experts in brucellosis or Ochrobactrum; (iii) it applies a non-consensus genus concept that disregards taxonomically relevant differences in structure, physiology, population structure, core-pangenome assemblies, genome structure, genomic traits, clinical features, treatment, prevention, diagnosis, genus description rules, and, above all, pathogenicity; and (iv) placing these two bacterial groups in the same genus creates risks for veterinarians, medical doctors, clinical laboratories, health authorities, and legislators who deal with brucellosis, a disease that is particularly relevant in low- and middle-income countries. Based on all this information, we urge microbiologists, bacterial collections, genomic databases, journals, and public health boards to keep the Brucella and Ochrobactrum genera separate to avoid further bewilderment and harm.

The aim of this work is to study the existence of solutions to a class of fractional differential equations with a mixed of fractional integral boundary conditions involving the Hilfer fractional derivative. The proof is based on Monch's fixed point theorem and the technique of measures of noncompactness. Two examples illustrating the main results are also constructed.

Despite various planning efforts, airspace capacity can sometimes be exceeded, typically because of disruptive events. Air traffic flow management (ATFM) is the process of managing flights in this situation. In this paper, we present an ATFM model that accounts for different rerouting options (path rerouting and diversion) and preexisting en route flights. The model proposes having a central authority to control all decisions, which is then compared with current practice. We also consider interflight and interairline fairness measures in the network. We use an exact approach to solve small- to medium-sized instances, and we propose a modified fix-and-relax heuristic to solve large-sized instances. Allowing a central authority to control all decisions increases network efficiency compared with the case where the ATFM authority and airlines control decisions independently. Our experiments show that including different rerouting options in ATFM can help reduce delays by up to 8% and cancellations by up to 23%. Moreover, ground delay cost has much more impact on network decisions than air delay cost, and network decisions are insensitive to changes in diversion cost. Furthermore, the analysis of the tradeoff between total network cost and overtaking cost shows that adding costs for overtaking can significantly improve fairness at only a small increase in total system cost. A balanced total cost per flight among airlines can be achieved at a small increase in the network cost (0.2%-3.0%) when imposing airline fairness. In conclusion, the comprehensiveness of the model makes it useful for analyzing a wide range of alternatives for efficient ATFM., Funding Agencies|University of Sharjah, Sharjah, United Arab Emirates [1702040585]; VINNOVA, the Swedish innovation agencyVinnova [2018-02998]

In this paper, six novel mathematical models based on semi-empirical calculus are proposed and applied to characterise the oven-drying process of cement mortar composites reinforced with cellulosic fibres (CMCRCFs). The drying experiments were carried out on four levels of oven-drying temperatures (70, 85, 105, and 120 °C), with four different cellulosic fibres content (0, 5, 10, and 20 %). Obtained results were compared to those derived by regression analysis of six most typically used mathematical drying models (Newton, Page, Page modified1, Page modified2, Handerson Pabis, and Logarithmic) in addition to six proposed models. The regression accuracy of the drying process was evaluated by the coefficient of determination (R2), low mean square error (MSE), low root mean squared error (RMSE), and mean absolute error (MAE). Additional criteria were used to ensure more validity of the selected models. The obtained values indicate a highly accurate fit of the proposed model MR9, meaning that the proposed model can clearly interpret the experimental drying data and predict the dry state of CMCRCFs., U ovom radu predloženo je i primijenjeno šest novih matematičkih modela temeljenih na poluempirijskom proračunu za karakterizaciju procesa sušenja u pećnici kompozita cementne žbuke ojačane celuloznim vlaknima (CMCRCF). Pokusi sušenja provedeni su pri četiri razine temperature sušenja u pećnici (70, 85, 105 i 120 °C) s četiri različita udjela celuloznih vlakana (0, 5, 10 i 20 %). Dobiveni rezultati uspoređeni su s onima dobivenim regresijskom analizom šest najčešće primjenjivanih matematičkih modela sušenja (Newton, Page, Page modified1, Page modified2, Handerson Pabis i Logarithmic) uz šest predloženih modela. Regresijska točnost procesa sušenja procijenjena je koeficijentom determinacije (R2), srednjom kvadratnom pogreškom (MSE), korijenom srednje kvadratne pogreške (RMSE) i srednjom apsolutnom pogreškom (MAE). Primijenjeni su i dodatni kriteriji da bi se osigurala veća valjanost odabranih modela. Dobivene vrijednosti pokazuju dobro slaganje predloženog modela MR9 s eksperimentalnim vrijednostima, što znači da predloženi model može jasno interpretirati eksperimentalne podatke o sušenju i predvidjeti suho stanje CMCRCF-a.

The aim of this work was to model the deep bed and cake filtration process using an alternative approach based on a fractional calculus (FC). The considered experimental data in this study were extracted from published studies. The data used in FC models contained two inputs - initial concentration and time, and volume of filtrate as an output. The FC kinetic constants were tuned by fitting the experimental and predicted data through Dragonfly algorithm implemented in MATLAB programming software. The performance of the developed models was assessed using different metrics by comparing the experimental against the predicted data. The developed fractional model with nth order presented very acceptable metrics in comparison to the pseudo-nth order and displayed strong potential for estimating the volume of filtrate. This work is licensed under a Creative Commons Attribution 4.0 International License., Cilj ovog rada bio je modelirati proces dubinske filtracije i filtracije kroz filtarski kolač primjenom alternativnog pristupa temeljenog na frakcijskom računu (FC). Eksperimentalni podatci koji su korišteni u ovom radu preuzeti su iz dostupnih objavljenih radova. Podatci za FC modele sadržavali su dva ulaza: početnu koncentraciju i vrijeme, te volumen filtrata kao jedini izlaz. Kinetičke konstante FC-a podešene su ugađanjem predviđenih i eksperimentalnih podataka primjenom Dragonfly algoritma implementiranog u računalnom programu MATLAB. Karakteristike razvijenih modela procijenjene su uspoređivanjem predviđenih s eksperimentalnim podatcima kroz više statističkih pokazatelja. Razvijeni frakcijski model n-tog reda pokazao je vrlo dobre karakteristike u usporedbi s modelom pseudo-n-tog reda čime je iskazao visok potencijal za primjenu u procjeni volumena filtrata. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

2D materials attracted considerable interest in the research community following the first report in 2004 on the preparation of graphene by simple micromechanical exfoliation of highly oriented pyrolytic graphite. For example, single-layer Molybdenum Di selenide (MoSe2) and Tungsten Di selenide (WSe2) transistors with on/off ratios of 108 and ultra-low standby power dissipation were demonstrated. Graphene electrodes have been used to develop fully transparent resistive memories to suppress unwanted surface effects that occur in oxide memory devices. Photodetectors based on MoSe2 with few layers have shown excellent photodetection properties. Phototransistors based on WSe2 monolayers exhibit photosensitivity up to 2200 AW, demonstrating the emerging applications of 2D materials for highefficiency optoelectronic devices. In particular, the 2D monolayers of semiconducting transition metal dichalcogenides (TMDs) exhibit direct bandgaps and have intriguing optical properties suitable for optoelectronic applications in light-emitting diodes and photovoltaics. To realize highly efficient optoelectronic devices based on TMD monolayers, it is also essential to develop a strategy for tuning the bandgaps of TMD monolayers. A significant drawback of graphene is that it does not have a bandgap and is therefore not considered the best material for light-emitting devices. This drawback of graphene has severely limited its application in the electronics industry, where semiconductor materials are widely used. In contrast, single-layer TMDs such as WSe2 and WSe2 are direct bandgap semiconductors and show good light emission properties. In this work, density functional theory is used to perform systematic studies of layered MoSe2 and WSe2. Theoretically, we transition metals Rh and Ru to perform planned studies of layered MoSe2 and WSe2 via substitutional doping and vacanc

This article aims to perform the logistic viability analysis of PAC for West Africa using the AHP multicriteria method. This port contributes largely in the country's economy through customs and tax revenues, the formation of the Gross Domestic Product (GDP) and also in international trade. Four criteria (quality of infrastructure and services, equipment productivity, and logistics cost of cargo) were modeled. With the result, the port infrastructure criterion is most important, followed by the port equipment criterion. Showing the importance of each port logistics viability criterion (infrastructure, service, equipment, cost), the alternative long-term logistics viability is preferable to the medium-term and short-term. The application of the AHP shows in its result that for long-term port logistics viability, it is preferable to invest more in modern and quality infrastructure and equipment.

The Autonomous Port of Cotonou (PAC) located in West Africa has an access channel 15m deep, 11 berths, and an internal draft of 15m (maximum), and is connected with a road to serve continental countries such as Burkina-Faso, Chad , Mali, Niger and Nigeria. The PAC presents low productivity (average of 10,000,000 tons / year, 24.40% of the movement from the port of Lagos / Nigeria) in West Africa. This article aims to evaluate the application of fuzzy logic in the Autonomous Port of Cotonou (Benin) in the analysis of logistic viability. The methodology followed the fuzzy logic that is a support method for logistic decision-making, based on fuzzy rules (SBRF). It was used characteristic of Mamdani Matlab Toolbox with three membership functions (triangular, trapezoidal and Gaussian) to model the quality variables of infrastructures and services, equipment productivity, seeking a long-term way out of logistic viability. The result of logistic viability was medium term, equivalent to 13 years / 25 years; as far as the outcome of the future PAC is concerned. The logistic viability of the PAC depends on its input variables. The projection of this application was long term, at least 19 years / 25 years when the infrastructures are of good quality and the equipment is more modern and consistent with the current realities to satisfy the expectations of the customers. &nbsp

In this novel article, a comparative study has been conducted between analytical and fractional solution of Fick’s first- and second-order of diffusion to model the solar drying process of different products and dryers under different operating parameters. Laplace and Laplace’s inverse transform have been used to obtain the solution in function with two parameters: the order index n and the fractional time index α of the above Fick’s laws, and their parameters have been non-linearly optimised using a grey wolf optimisation (GWO) algorithm. The results showed that the anomalous diffusion phenomenon during the drying process is best described by the fractional‐order model. Values obtained using the model MR12 were in better agreement with the experimental data than the values obtained using the other selected models with very acceptable statistical parameters. This work is licensed under a Creative Commons Attribution 4.0 International License., U ovom novom članku provedena je usporedna studija između analitičkog i frakcijskog rješenja Fickove difuzije prvog i drugog reda kako bi se modelirao solarni postupak sušenja različitih proizvoda i sušila pod različitim radnim parametrima. Laplaceova transformacija i Laplaceova inverzna transformacija primijenjene su za dobivanje rješenja u funkciji s dva parametra: indeksom reda n i razlomljenim vremenskim indeksom α gore navedenih Fickovih zakona, a njihovi parametri nelinearno su optimirani pomoću “algoritma sivog vuka” (engl. Gray Wolf Optimizer, GWO). Rezultati su pokazali da fenomen anomalne difuzije tijekom postupka sušenja najbolje opisuje model frakcijskog reda. Vrijednosti dobivene primjenom modela MR12 bolje su se slagale s eksperimentalnim podatcima od vrijednosti dobivenih primjenom ostalih odabranih modela s vrlo prihvatljivim statističkim parametrima. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

Item does not contain fulltext, BACKGROUND: Chimeric antigen receptor (CAR) T-cell therapy can induce side-effects such as cytokine release syndrome and immune effector cell-associated neurotoxicity syndrome (ICANS), which often require intensive care unit admission. The aim of this study was to describe management of critically ill CAR T-cell recipients in intensive care. METHODS: This international, multicentre, observational cohort study was done in 21 intensive care units in France, Spain, the USA, the UK, Russia, Canada, Germany, and Austria. Eligible patients were aged 18 years or older; had received CAR T-cell therapy in the past 30 days; and had been admitted to intensive care for any reason. Investigators retrospectively included patients admitted between Feb 1, 2018, and Feb 1, 2019, and prospectively included patients admitted between March 1, 2019, and Feb 1, 2020. Demographic, clinical, laboratory, treatment, and outcome data were extracted from medical records. The primary endpoint was 90-day mortality. Factors associated with mortality were identified using a Cox proportional hazard model. FINDINGS: 942 patients received CAR T-cell therapy, of whom 258 (27%) required admission to intensive care and 241 (26%) were included in the analysis. Admission to intensive care was needed within median 4·5 days (IQR 2·0-7·0) of CAR T-cell infusion. 90-day mortality was 22·4% (95% CI 17·1-27·7; 54 deaths). At initial evaluation on admission, isolated cytokine release syndrome was identified in 101 patients (42%), cytokine release syndrome and ICANS in 93 (39%), and isolated ICANS in seven (3%) patients. Grade 3-4 cytokine release syndrome within 1 day of admission to intensive care was found in 50 (25%) of 200 patients and grade 3-4 ICANS in 38 (35%) of 108 patients. Bacterial infection developed in 30 (12%) patients. Life-saving treatments were used in 75 (31%) patients within 24 h of admission to intensive care, primarily vasoactive drugs in 65 (27%) patients. Factors independently associated

Identifying anomalous documents in a text corpus is an important problem that has wide applications. Due to the high dimensional and sparse nature of text data, traditional outlier detection methods fail to identify features that distinguish outliers. Inspired by the capability of Nonnegative Matrix Factorization (NMF) for text clustering, we explore it for text outlier detection. In this paper, a novel NMF-based method called Nonnegative Orthogonal Constraint Outlier Learning (NOCOL) is introduced that learns the outliers effectively during the factorization process. Experimental results show the higher accuracy of NOCOL in identifying text outliers in comparison to the state-of-the-art methods.

Despite various planning efforts, airspace capacity can sometimes be exceeded, typically because of disruptive events. Air traffic flow management (ATFM) is the process of managing flights in this situation. In this paper, we present an ATFM model that accounts for different rerouting options (path rerouting and diversion) and preexisting en route flights. The model proposes having a central authority to control all decisions, which is then compared with current practice. We also consider interflight and interairline fairness measures in the network. We use an exact approach to solve small- to medium-sized instances, and we propose a modified fix-and-relax heuristic to solve large-sized instances. Allowing a central authority to control all decisions increases network efficiency compared with the case where the ATFM authority and airlines control decisions independently. Our experiments show that including different rerouting options in ATFM can help reduce delays by up to 8% and cancellations by up to 23%. Moreover, ground delay cost has much more impact on network decisions than air delay cost, and network decisions are insensitive to changes in diversion cost. Furthermore, the analysis of the tradeoff between total network cost and overtaking cost shows that adding costs for overtaking can significantly improve fairness at only a small increase in total system cost. A balanced total cost per flight among airlines can be achieved at a small increase in the network cost (0.2%-3.0%) when imposing airline fairness. In conclusion, the comprehensiveness of the model makes it useful for analyzing a wide range of alternatives for efficient ATFM., Funding Agencies|University of Sharjah, Sharjah, United Arab Emirates [1702040585]; VINNOVA, the Swedish innovation agencyVinnova [2018-02998]

In this paper, we study the existence of solutions for hybrid fractional integro-differential equations involving \(\psi\)-Caputo derivative. We use an hybrid fixed point theorem for a sum of three operators due to Dhage for proving the main results. An example is provided to illustrate main results.

The aim of this study was to predict the fouling resistance (FR) using the artificial neural networks (ANN) approach. An experimental database collected from the literature regarding the fouling of condenser tubes cooling seawater of a nuclear power plant was used to build the ANN model. All models contained 7 inputs: dimensionless condenser cooling seawater temperature, dimensionless inside overall heat transfer coefficient, dimensionless outside overall heat transfer coefficient, dimensionless condenser temperature, dimensionless condenser pressure, dimensionless output power, and dimensionless overall thermal efficiency. Dimensionless fouling resistance was the output. The accuracy of the model was confirmed by comparing the predicted and experimental data. The results showed that ANN with a configuration of 7 input neurons, 7 hidden neurons, and 1 output neuron presented an excellent agreement, with the root mean squared error RMSE = 3.6588 ∙ 10–7, average absolute percentage error MAPE = 0.1295 %, and high determination coefficient of R2 = 0.99996. After conducting the sensitivity analysis (all input variables had strong effect on the estimation of the fouling resistance), in order to control the fouling, an inverse artificial neural network (ANNi) model was established, and showed good agreement in the case of different values of dimensionless condenser cooling seawater temperature. This work is licensed under a Creative Commons Attribution 4.0 International License., Cilj ovog istraživanja bio je predvidjeti otpor prljanja primjenom umjetnih neuronskih mreža (ANN). Baza podataka za ANN modeliranje preuzeta je iz dostupne literature i sadrži podatke vezane uz prljanje kondenzacijskih cijevi u sustavu hlađenja morskom vodom u nuklearnoj elektrani. Sedam parametara korišteno je kao ulaz u neuronske mreže: bezdimenzijska temperatura morske vode, bezdimenzijski unutarnji ukupni koeficijent prijenosa topline, bezdimenzijski vanjski ukupni koeficijent prijenosa topline, bezdimenzijska temperatura kondenzatora, bezdimenzijski tlak u kondenzatoru, bezdimenzijska izlazna snaga i bezdimenzijska ukupna toplinska efikasnost. Kao izlaz uzet je bezdimenzijski otpor prljanja. Točnost modela potvrđena je statističkom analizom podudarnosti predviđenih i eksperimentalno dobivenih podataka. Rezultati su pokazali izvrsno slaganje u slučaju neuronske mreže sa 7 ulaza, 7 neurona u skrivenom sloju i 1 izlazom, uz korijen srednje kvadratne pogreške (RMSE) od 3,6588 ∙ 10–7, srednju apsolutnu postotnu pogrešku (MAPE) od 0,1295 % te visoki koeficijent determinacije (R2 = 0,99996). Nakon provedene analize osjetljivosti (sve ulazne varijable imale su snažan utjecaj na procjenu otpora prljanja), s ciljem kontrole prljanja, uspostavljen je model inverzne umjetne neuronske mreže (ANNi); model je pokazao dobro slaganje za različite vrijednosti bezdimenzijske temperature morske vode. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

The aim of this work was to develop three artificial intelligence-based methods to model the ternary adsorption of heavy metal ions {Pb2+, Hg2+, Cd2+, Cu2+, Zn2+, Ni2+, Cr4+} on different adsorbates {activated carbon, chitosan, Danish peat, Heilongjiang peat, carbon sunflower head, and carbon sunflower stem). Results show that support vector regression (SVR) performed slightly better, more accurate, stable, and more rapid than least-square support vector regression (LS-SVR) and artificial neural networks (ANN). The SVR model is highly recommended for estimating the ternary adsorption kinetics of a multicomponent system. This work is licensed under a Creative Commons Attribution 4.0 International License., Cilj ovog rada bio je razviti tri metode temeljene na umjetnoj inteligenciji za modeliranje trostruke adsorpcije iona teških metala {Pb2+, Hg2+, Cd2+, Cu2+, Zn2+, Ni2+, Cr4+} na različitim adsorbatima {aktivni ugljen, kitozan, danski treset, treset Heilongjiang, ugljik glave suncokreta i ugljik stabljike suncokreta). Rezultati pokazuju da se regresija potpornih vektora (SVR) pokazala nešto boljom, preciznijom, stabilnijom i bržom od regresije potpornih vektora najmanjih kvadrata (LS-SVR) i umjetnih neuronskih mreža (ANN). Za procjenu kinetike trostrukog adsorpcijskog sustava višekomponentnog sustava preporučuje se model SVR. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

The objective of this study was to model the removal efficiency of ternary adsorption system using feed-forward back propagation artificial neural network (FFBP-ANN). The ANN model was trained with Levenberg–Marquardt back propagation algorithm and the best model was found with the architecture of {9-11-4-3} neurons for the input layer, first and second hidden layers, and the output layer, respectively, based on two metrics, namely, mean squared error (MSE) = (0.2717–0.5445) and determination coefficient (R2) = (0.9997–0.9999). Results confirmed the robustness and the efficiency of the developed ANN model to model the adsorption process. This work is licensed under a Creative Commons Attribution 4.0 International License., Cilj ove studije bio je modelirati učinkovitost uklanjanja ternarnog adsorpcijskog sustava pomoću višeslojne unaprijedne neuronske mreže s povratnim rasprostiranjem pogreške (FFBP-ANN). Model ANN-a učen je algoritmom Levenberg–Marquardt, a najbolji model bio je s arhitekturom {9-11-4-3} neurona za ulazni, prvi i drugi skriveni sloj te izlazni sloj, na temelju dvaju metričkih pokazatelja: srednje kvadratne pogreške (MSE) = (0,2717 – 0,5445) i koeficijenta određivanja (R2) = (0,9997 – 0,9999). Rezultati su potvrdili robusnost i učinkovitost razvijenog ANN modela za modeliranje procesa adsorpcije. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

This paper discusses the design of a business model dedicated for IoT applications that would be deployed on top of cloud and fog resources. This business model features 2 constructs, flow (specialized into data and collaboration) and placement (specialized into processing and storage). On the one hand, the flow construct is about who sends what and to whom, who collaborates with whom, and what restrictions exist on what to send, to whom to send, and with whom to collaborate. On the other hand, the placement construct is about what and how to fragment, where to store, and what restrictions exist on what and how to fragment, and where to store. The paper also discusses the development of a system built-upon a deep learning model that recommends how the different flows and placements should be formed. These recommendations consider the technical capabilities of cloud and fog resources as well as the networking topology connecting these resources to things.

In this paper, we propose a multi-perspective model for smart products as a basis to implement advanced web-based services in the smart factory production chain. The model relies on three perspectives that are: the product, the production process and the work centers involved in the production chain. For each perspective, the physical world is connected with the cyber world, where collected sensor data is properly organised to enable data analysis and exploration according to the three perspectives in an interleaved way. A portfolio of web-based services at production chain level is also described according to the model. Among them, a data access dashboard has been designed in order to enable controlled exploration of production chain data for different actors involved in the production activities, ranging from the suppliers to the producer of the final product. The approach is devoted to the production of costly and complex products, where the conceptualisation of a Smart Product as the integration of product, process and infrastructure sensor data aims at ensuring high product quality levels, long lasting operativity, less frequent and efficient maintenance activities and constant performances over time.

Artificial Intelligence has been a growth catalyst to our society and is cosidered across all idustries as a fundamental technology. However, its development has been limited to the signal processing domain that relies on the generated and collected data from other sensors. In recent research, concepts of Digital Artificial Intelligence and Physicial Artifical Intelligence have emerged and this can be considered a big step in the theoretical development of Artifical Intelligence. In this paper we explore the concept of Physicial Artifical Intelligence and propose two subdomains: Integrated Physicial Artifical Intelligence and Distributed Physicial Artifical Intelligence. The paper will also examine the trend and governance of Physicial Artifical Intelligence.

In this study, an artificial neural network (ANN) was developed to obtain a generalized model for predicting the direct and open sun drying process for some medicinal plants. Since the quality of the experimental dataset can lead to a very performant model, in this study the dataset was collected from previously published papers and divided randomly into three subsets, namely 70 %, 15 %, and 15 % for training, testing, and validation. Based on the complex solar drying behaviour, ten parameters were considered as inputs: time, global solar radiation (GSR), outside temperature, inclination, emissivity, altitude, longitude, latitude, inside temperature, and nutritional value, to predict moisture content (MC), and drying rate (DR). Based on a trial and error method, the best ANN model was found with a topology of 10-28-14-2, with regression coefficient and root mean square error of (R = 97.044 %. RMSE = 4.589 %) and (R = 99.968 %, RMSE = 1.185 %) for MC and DR, respectively. It can be concluded that the obtained ANN model provides the best method for solar dryer modelling which can be generalized for any location in the world. This work is licensed under a Creative Commons Attribution 4.0 International License., U ovom istraživanju razvijena je umjetna neuronska mreža (ANN) za dobivanje uopćenog modela za predviđanje izravnog i otvorenog postupka solarnog sušenja za određene ljekovite biljke. Budući da kvaliteta eksperimentalnog skupa podataka može dovesti do modela visoke izvedbe, u ovoj je studiji skup podataka prikupljen iz prethodno objavljenih radova i nasumce podijeljen u tri podskupine – 70 % za trening, 15 % za testiranje i 15 % za validaciju. Na temelju složenog postupka solarnog sušenja, za predviđanje sadržaja vlage (SV) i brzine sušenja (BS) uzima se deset ulaznih parametara: vrijeme, globalno sunčevo zračenje (GSZ), vanjska temperatura, nagib, emisivnost, nadmorska visina, zemljopisna dužina, zemljopisna širina, unutarnja temperatura i hranjiva vrijednost. Na temelju metode pokušaja i pogreške, pronađen je najbolji model ANN s topologijom 10-28-14-2 te koeficijentom regresije i srednjom kvadratnom pogreškom od (R = 97,044 %, RMSE = 4,589 %) za SV i (R = 99,968 %, RMSE = 1,185 %) za BS. Može se zaključiti da je dobiveni ANN najbolji model za modeliranje solarnih sušilica koji se može generalizirati za bilo koje mjesto na svijetu. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

This work aimed to model the critical pressure, temperature, volume properties, and acentric factors of 6700 pure compounds based on five relevant descriptors and two thermodynamic properties. To that end, four methods were used, namely, multi-linear regression (MLR), artificial neural networks (ANNs), support vector machines (SVMs) using sequential minimal optimisation (SMO), and hybrid SVM with Dragonfly optimisation algorithm (SVM-DA) to model each property. The results suggested that hybrid SVM-DA had better prediction performance compared to the other models in terms of average absolute relative deviation (AARD%) of {0.7551, 1.962, 1.929, and 2.173} and R2 of {0.9699, 0.9673, 0.9856, and 0.9766} for critical temperature, critical pressure, critical volume, and acentric factor, respectively. The developed models can be used to estimate the property of newly designed compounds only from their molecular structure., Cilj ovog rada bio je modeliranje kritičnog tlaka, temperature, volumnih svojstava i acentričnih čimbenika 6700 čistih spojeva na temelju pet relevantnih deskriptora i dva termodinamička svojstva. U tu svrhu primijenjene su četiri metode: višestruka linearna regresija (MLR), umjetna neuronska mreža (ANN), metoda potpornih vektora (SVM) i algoritam optimizacije Dragonfly (SVM-DA), koji se za modeliranje svakog svojstva koriste sekvencijalnom minimalnom optimizacijom (SMO) i hibridnim SVM-om. Rezultati su pokazali da hibridni SVM-DA daje bolje predviđanje u odnosu na ostale modele u smislu postotka prosječnog apsolutnog relativnog odstupanja (AARD%) od {0,7551, 1,962, 1,929 i 2,173} i R2 od {0,9699, 0,9673, 0,9856, i 0,9766} za kritičnu temperaturu, kritični tlak, kritični volumen i acentrični faktor. Razvijeni modeli mogu se primjenjivati za procjenu svojstava novodizajniranih spojeva samo iz njihove molekularne strukture.

In this work, two novel models have been proposed based on semi-empirical and factional calculus incorporating non-integer time derivatives in the Fick’s first law of anomalous diffusion. The experimental data has been collected from literature of 15 kinetics investigated in a convective dryer under the effect of temperatures ranging from 40 to 80 °C at 10 °C interval, and thickness of the slices of 2 to 6 mm at 2 mm interval. The collected experimental dataset was of apple slices (Golab variety). Results from this study were compared with a set of 64 thin-layer drying models previously published in the literature. The fitting capability of the models was compared using the mean of root mean square error MRMSE (%) of all kinetics and the global determination coefficient R2. All models’ constants and coefficients were optimised by dragonfly algorithm programmed in MATLAB software. Results show that the fractional model is highly capable of describing the drying curve of the apple slices with a determination coefficient (R2) of 0.99981, and average root mean square error (MRMSE) of 0.43 % in comparison to the best empirical models with R2 of 0.99968 and MRMSE of 0.61 %. This work is licensed under a Creative Commons Attribution 4.0 International License., U ovom radu predložena su dva nova modela temeljena na poluempirijskom i frakcijskom računu koji uključuje necjelobrojne vremenske derivate u Fickovom prvom zakonu anomalne difuzije. Eksperimentalni podatci o 15 kinetika istraženih u konvektivnom sušioniku pod utjecajem temperatura u rasponu od 40 do 80 °C u razmaku od 10 °C i debljine kriški od 2 do 6 mm u razmaku od 2 mm prikupljeni su iz literature. Prikupljeni eksperimentalni skup podataka bio je na kriškama jabuke (sorta Golab). Rezultati ove studije uspoređivani su s nizom od 64 modela tankoslojnog sušenja koji su prethodno objavljeni u literaturi. Sposobnost uklapanja modela uspoređena je koristeći srednju vrijednost srednje kvadratne pogreške MRMSE (%) svih kinetika i globalni koeficijent određivanja R2. Konstante i koeficijenti svih modela optimizirani su algoritmom dragonfly programiranim u softveru MATLAB. Rezultati pokazuju da je frakcijski model visoko sposoban opisati krivulju sušenja kriški jabuke s koeficijentom utvrđivanja (R2) 0,99981 i prosječnom srednjom kvadratnom pogreškom (MRMSE) 0,43 % u usporedbi s najboljim empirijskim modelima s R2 0,99968 i MRMSE 0,61 %. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

The aim of this work was to model the moisture content (MC) and drying rate (DR) using artificial neural network (ANN) methodology. Many architectures have been tested and the best topology was selected based on a trial and error method. The dataset was randomly divided into 60, 20, and 20 % for training, test, and validation stage of the ANN model, respectively. The best topology was 10-{29-13}-2 obtained with high correlation coefficient R (%) of {99.98, 98.41} and low root mean square error RMSE (%) (0.36, 6.29) for MC and DR, respectively. The obtained ANN can be used to interpolate the MC and DR with high accuracy. This work is licensed under a Creative Commons Attribution 4.0 International License., Cilj ovog rada bio je modelirati sadržaj vlage (MC) i brzinu sušenja (DR) primjenom metodologije umjetne neuronske mreže (ANN). Testirane su mnoge arhitekture, a najbolja topologija odabrana je na temelju metode pokušaja i pogrešaka. Skup podataka podijeljen je nasumično na 60, 20 i 20 % za fazu treninga, testa i validacije ANN modela. Najbolja topologija bila je 10-{29-13}-2 dobivena visokim koeficijentom korelacije R (%) od {99,98, 98,41} i niskom srednjom kvadratnom pogreškom RMSE (%) (0,36, 6,29) za MC, odnosno DR. Dobiveni ANN model može se s velikom točnošću primijeniti za interpolaciju MC-a i DR-a. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

The aim of this work was to model multi-system dynamic adsorption using an artificial intelligence technique. A set of data points, collected from scientific papers containing the dynamic adsorption kinetics on activated carbon, was used to build the artificial neural network (ANN). The studied parameters were molar mass, initial concentration, flow rate, bed height, particle diameter, BET surface area, average pore diameter, time, and concentration of dimensionless effluents. Results showed that the optimized ANN was obtained with a high correlation coefficient, R = 0.997, a root mean square error of RMSE = 0.029, and a mean absolute deviation of AAD (%) = 1.810 during the generalisation phase. Furthermore, a sensitivity analysis was also conducted using the inverse artificial neural network method to study the effect of all the inputs on the dynamic adsorption. Also in this work, the traceability of the estimated results was conducted by developing a graphical user interface. This work is licensed under a Creative Commons Attribution 4.0 International License., Cilj ovog rada bio je modelirati višesustavnu dinamičku adsorpciju tehnikom umjetne inteligencije. Za izradu umjetne neuronske mreže (ANN) upotrijebljen je skup podataka prikupljen iz znanstvenih radova koji sadrže kinetiku dinamičke adsorpcije na aktivnom ugljenu. Ispitivani parametri bili su: molarna masa, početna koncentracija, brzina protoka, visina sloja, promjer čestica, površina BET, prosječni promjer pora, vrijeme i koncentracija bezdimenzijskih otpadnih voda. Rezultati su pokazali da je tijekom faze generalizacije dobiven optimiran ANN s visokim koeficijentom korelacije, R = 0,997, korijenom srednje kvadratne pogreške RMSE = 0,029 i srednjim apsolutnim odstupanjem AAD (%) = 1,810. Dodatno, provedena je i analiza osjetljivosti primjenom metode inverzne umjetne neuronske mreže kako bi se proučio učinak svih ulaza na dinamičku adsorpciju. U radu je provedena i sljedivost procijenjenih rezultata razvojem grafičkog korisničkog sučelja. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

To operate under normal conditions and depending on the technology used, the electronic components must be at a temperature below 80 to 85 degrees C. Several cooling systems were investigated with the aim of improving the heat transfer process in this kind of applications. Single-phase liquid cooling systems, which mainly consist of a hot watercooled micro-heat exchanger, provide an efficient approach to dissipate heat flows. In the present study, numerical and experimental investigations were carried out to study the characteristics of laminar flow and forced convective heat transfer in micro-channels. The inlet temperature of cooling water ranged from 25 to 65 degrees C, the Reynolds number of water flow varied from 250 to 2000, and the electronic power supply component was set at 50, 80 and 120 W. The results showed that the micro heat exchanger was able to dissipate around 70 to 78% of the heat released by the electronic component. As regards the numerical results, it was observed that the inlet water temperature of 55 degrees C kept a heat source up to 80 W for a temperature source below the critical value of 80 degrees C.

In the present article, two models based on the artificial neural network methodology (ANN) have been optimised to predict the density (ρ) and kinematic viscosity (μ) of different systems of biofuels and their blends with diesel fuel. An experimental database of 1025 points, including 34 systems (15 pure systems, 14 binary systems, and 5 ternary systems) was used for the development of these models. These models use six inputs, which are temperature (T) in the range of −10 – 200 °C, volume fractions (X1, X2, X3) in the range of 0–1, and to distinguish these systems, we used kinematic viscosity at 20 °C in the range of 0.67–74.19 mm2 s–1 and density at 20 °C in the range of 0.7560–0.9188 g cm–3. The best results were obtained with the architecture of {6-26-2: 6 neurons in the input layer – 26 neurons in the hidden layer – 2 neurons in the output layer}. Results of comparison between experimental and simulated values in terms of the correlation coefficients were: R2 = 0.9965 for density, and R2 = 0.9938 for kinematic viscosity. A 238 new database experimental of 4 systems (2 pure systems, 1 binary system, and 1 ternary system) was used to check the accuracy of the two ANN models previously developed. Results of prediction performances in terms of the correlation coefficients were: R2 = 0.9980 for density, and R2 = 0.9653 for kinematic viscosity. Comparison of validation results with those of the other studies shows that the neural network models gave far better results. This work is licensed under a Creative Commons Attribution 4.0 International License., U ovom članku dva modela zasnovana na metodologiji umjetne neuronske mreže (ANN) optimizirana su za predviđanje gustoće (ρ) i kinematičke viskoznosti (μ) različitih sustava biogoriva i njihovih mješavina s dizelskim gorivom. Za razvoj tih modela upotrijebljena je eksperimentalna baza podataka od 1025 točaka, uključujući 34 sustava (15 čistih sustava, 14 binarnih sustava i 5 ternarnih sustava). Ti modeli koriste šest ulaza: temperatura (T) u rasponu od −10 do 200 °C, volumni udjeli (X1, X2, X3) u rasponu 0 – 1, a za razlikovanje tih sustava korištena je kinematička viskoznost pri 20 °C u rasponu 0,67 – 74,19 mm2 s–1 i gustoća pri 20 °C u rasponu 0,7560 – 0,9188 g cm–3. Najbolji rezultati dobiveni su arhitekturom {6-26-2: 6 neurona u ulaznom sloju – 26 neurona u skrivenom sloju – 2 neurona u izlaznom sloju}. Rezultati usporedbe eksperimentalnih i simuliranih vrijednosti u smislu korelacijskih koeficijenata bili su: R2 = 0,9965 za gustoću i R2 = 0,9938 za kinematičku viskoznost. Za provjeru točnosti dva prethodno razvijena modela ANN upotrijebljeno je 238 novih eksperimentalnih baza podataka s 4 sustava (2 čista sustava, 1 binarni sustav i 1 ternarni sustav). Rezultati performansi predviđanja s obzirom na korelacijske koeficijente bili su: R2 = 0,9980 za gustoću i R2 = 0,9653 za kinematičku viskoznost. Usporedba rezultata validacije s rezultatima drugih studija pokazuje da su modeli neuronske mreže dali znatno bolje rezultate. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

One of the main disadvantages of the use of synthetic or semi-synthetic polymeric materials is their degradation and aging. The purpose of this study was to use artificial neural networks (ANN) and multiple linear regressions (MLR) to predict the carbonyl, hydroxyl, and polyene indices (ICO, IOH, and IOP), and viscosity average molecular weight (MV) of poly(vinyl chloride), polystyrene, and poly(methyl methacrylate). These physicochemical properties are considered fundamental during the study of photostabilization of polymers. From the five repeating units of monomers, the structure of the polymer studied is shown. Quantitative structure-property relationship (QSPR) models obtained by using relevant descriptors showed good predictability. Internal validation {R2, RMSE, and Q2LOO}, external validation {R2, RMSE, Q2pred, rm2, Δrm2, k, and k’}, and applicability domain were used to validate these models. The comparison of the results shows that the ANN models are more efficient than those of the MLR models. Accordingly, the QSPR model developed in this study provides excellent predictions, and can be used to predict ICO, IOH, IOP, and MV of polymers, particularly for those that have not been tested. This work is licensed under a Creative Commons Attribution 4.0 International License., Jedan od glavnih nedostataka upotrebe sintetičkih ili polusintetičkih polimernih materijala je njihova razgradnja i starenje. Svrha ove studije je primjena umjetnih neuronskih mreža (ANN) i višestrukih linearnih regresija (MLR) za predviđanje karbonilnih, hidroksilnih i polienskih indeksa (ICO, IOH i IOP) i prosječne molekulske mase viskoznosti (MV) poli(vinil-klorida), polistirena i poli(metil metakrilata). Ta fizikalno-kemijska svojstva smatraju se važnim tijekom proučavanja fotostabilizacije polimera. Iz pet ponavljajućih jedinica monomera prikazana je struktura ispitivanog polimera. Kvantitativni modeli odnosa strukture-svojstava (QSPR) dobiveni primjenom relevantnih deskriptora pokazali su dobru predvidljivost. Za potvrdu tih modela provedene su: interna provjera {R2, RMSE i Q2LOO}, vanjska provjera {R2, RMSE, Q2pred, rm2, Δrm2, k i k’} i domena primjenjivosti. Usporedba rezultata pokazuje da su modeli ANN učinkovitiji od modela MLR. Prema tome, model QSPR razvijen u ovoj studiji pruža izvrsna predviđanja i može se primjenjivati za predviđanje ICO, IOH, IOP i MV polimera, posebno za one koji nisu testirani. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

The present work is devoted to the study of the physicochemical characteristics of soils taken from the matorrals of the mountains of Tiaret (Western Algeria). Through the 24 samples analyzed, the results show that the color of all the samples is yellow-red (YR) with a texture that varies between sandy-loam, loam-clay-sandy and loamy, low humidity (2.28 ± 0.28%), a low to very low organic matter content (0.71 ± 0.54%) and a pH varying between neutral, slightly alkaline and alkaline (7.49 ± 0.31). The analyzed soils are generally not salty and have a low electrical conductivity (0.30 ± 0.07mS / cm), the limestone loads are very low to low (0.72 ± 0.54%). Three soil classes were defined by the ascending hierarchical classification (AHC) with percentages of (33.34%, 45.83% and 20.83%) respectively. The Principal Component Analysis (PCA) reveals that the first axis has a higher inertia rate of information with 41.21% followed by the second axis with 24.74%, the latter are very well correlated with the majority of the variables measured to confirm the shaping of the vegetation by these parameters. These finding would systematically lead to the land degradation and by consequence the regression of vegetation cover in these mountains, where, protection measures are obligatory.

River flooding is a natural phenomenon that can have a devastating effect on human life and economic losses. There have been various approaches in studying river flooding; however, insufficient understanding and limited knowledge about flooding conditions hinder the development of prevention and control measures for this natural phenomenon. This paper entails a new approach for the prediction of water level in association with flood severity using the ensemble model. Our approach leverages the latest developments in the Internet of Things (IoT) and machine learning for the automated analysis of flood data that might be useful to prevent natural disasters. Research outcomes indicate that ensemble learning provides a more reliable tool to predict flood severity levels. The experimental results indicate that the ensemble learning using the Long-Short Term memory model and random forest outperformed individual models with a sensitivity, specificity and accuracy of 71.4%, 85.9%, 81.13%, respectively.

This paper presents a simulation and experimental validation of H-bridge inverter with the implementation of a Newton-Raphson algorithm for selective harmonics elimination. Contributions are made in interfacing and programming of Arduino ATmega328P microcontroller and use it to control of single-phase inverter by selective harmonic elimination technique. Through this work, we have given a general analytical description of the total harmonic distortion and present the method of application of the Newton-Raphson algorithm for selective harmonic elimination. MATLAB Simulink used for simulation and Arduino IDE software was used to program the Arduino board. The validity of the simulation model is verified by experimental results, the inverter was realized and the algorithm control is tested, results of the simulation and realization are compared, they show the efficiency of the system analysis and demonstrate the ability of Arduino to control the inverter and to generate complex signals for the electrical systems control., Comment: 08 pages,18 figures, Published with International Journal of Engineering Trends and Technology (IJETT)

The present work aims to show one of the advantages of using the property of closure under coupling in the DEVS specification. The advantage concerned in this paper attempts to address the need for memory resources during the simulation of systems by cellular-DEVS. This improvement of performance is based on the usage of the property closure under coupling in the DEVS formalism. With this property and taking account of the iterative behavior of each cellular-DEVS atomic model, we provide simulation of many models simultaneously. The method starts with the specification of the cellular-DEVS coupled model which is then converted into its equivalent DEVS atomic model. Thus, the goal of this conversion is to transform large quantities of atomic models coupled together, which require huge computational resources, into one DEVS atomic model. A case study is presented at the end of the work on modeling and simulation of forest fire propagation using DEVS and cellular-DEVS. A specification by cellular-DEVS of the forest fire model and its non-modular equivalent DEVS atomic model are presented. Finally, a comparison between both methods is presented in term of consumption of resources., Comment: This work was conducted between 2013 and 2015

The opinion expressed in various Web sites and social-media is an essential contributor to the decision making process of several organizations. Existing sentiment analysis tools aim to extract the polarity (i.e., positive, negative, neutral) from these opinionated contents. Despite the advance of the research in the field, sentiment analysis tools give \textit{inconsistent} polarities, which is harmful to business decisions. In this paper, we propose SentiQ, an unsupervised Markov logic Network-based approach that injects the semantic dimension in the tools through rules. It allows to detect and solve inconsistencies and then improves the overall accuracy of the tools. Preliminary experimental results demonstrate the usefulness of SentiQ., Comment: In Proceedings of the 9th KDD Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM 20). San Diego, CA, USA, 8 pages

Design patterns are well practices to share software development experiences. These patterns allow enhancing reusability, readability and maintainability of architecture and code of software applications. As simulation applies computerized models to produce traces in order to obtain results and conclusions, designers of simulation explored design patterns to make the simulation code more reusable, more readable and easy to maintain, in addition to design complex software oriented simulation modeling. In DEVS (Discrete Event System specification), the designers have successfully designed simulations, frameworks, tools, etc. However, some issues remain still open and should be explored like how a piece of code that implements a set of states, events and transitions may be reused to design a new DEVS model? How may a DEVS model be extended to a new formalism? Etc. In this paper, we address these issues and we propose a set of patterns that may serve as guidelines to designers of DEVS models and its extensions and may contribute to the design of an operational simulation framework. These patterns are inspired partly by the available designs of DEVS community and software engineering developers.

Universities around the world have an important role in sustainability which encourage them to conduct campus sustainability studies to measure their sustainability performance. This study aims to assess sustainability performance and compare the level of behavior between males and females at the University of Sharjah. We developed and distributed a questionnaire to all the university populations to measure sustainability behavior. We used a Likert scale and hypothesis testing to analyze the questionnaire. By the end of the questionnaire duration, we received 646 responses, where 238 were males, and 408 were females. To analyze the questionnaire, the sign test was applied to determine the level of sustainable behavior of the males’ and females’ respondents. The results of this test showed that both males’ and females’ behavior levels are high. This is a good sign that both males and females are practicing their daily activities in a sustainable manner. Furthermore, the Wilcoxon–Mann–Whitney test was applied to compare the males’ and females’ behavior levels. As a result, it was found that males have better sustainability behavior. It is recommended that the University of Sharjah organizes more events and activities to boost the behavior level of female respondents. Also, the university may define some rules and regulations to monitor the sustainability behavior at the campus by providing rewards, incentives, and penalties in case of violation. © Springer Nature Switzerland AG 2020.

In this study, the solubility of 145 solid solutes in supercritical CO2 (scCO2) was correlated using computational intelligence techniques based on Quantitative Structure-Property Relationship (QSPR) models. A database of 3637 solubility values has been collected from previously published papers. Dragon software was used to calculate molecular descriptors of 145 solid systems. The genetic algorithm (GA) was implemented to optimise the subset of the significantly contributed descriptors. The overall average absolute relative deviation MAARD of about 1.345 % between experimental and calculated values by support vector regress SVR-QSPR model was obtained to predict the solubility of 145 solid solutes in supercritical CO2, which is better than that obtained using ANN-QSPR model of 2.772 %. The results show that the developed SVR-QSPR model is more accurate and can be used as an alternative powerful modelling tool for QSAR studies of the solubility of solid solutes in supercritical carbon dioxide (scCO2). The accuracy of the proposed model was evaluated using statistical analysis by comparing the results with other models reported in the literature. This work is licensed under a Creative Commons Attribution 4.0 International License., U ovom je istraživanju korelirana topljivost 145 čvrstih otopljenih tvari u superkritičnom CO2 (scCO2) primjenom tehnika računalne inteligencije zasnovanim na modelima kvantitativne strukture i svojstva (QSPR). Baza podataka 3637 topljivosti prikupljena je iz prethodno objavljenih radova. Program Dragon primijenjen je za izračunavanje molekularnih deskriptora 145 čvrstih sustava. Genetski algoritam (GA) implementiran je kako bi se optimizirao podskup deskriptora sa značajnim doprinosom. Ukupno prosječno apsolutno relativno odstupanje MAARD od oko 1,345 % između eksperimentalnih i izračunatih vrijednosti pomoću regresije potpornih vektora modelom SVR-QSPR dobiveno je za predviđanje topljivosti 145 čvrstih otopljenih tvari u superkritičnom CO2, što je bolje od onog dobivenog primjenom modela ANN-QSPR (2,772 %). Rezultati pokazuju da je razvijeni model SVR-QSPR precizniji i da se može primijeniti kao alternativni alat za modeliranje QSAR studija topljivosti otopljenih čvrstih tvari u superkritičnom ugljikovu dioksidu (scCO2). Točnost predloženog modela procijenjena je statističkom analizom uspoređivanjem rezultata s ostalim modelima zabilježenim u literaturi. Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

QC 20220923Part of proceedings: ISBN 978-94-024-1731-9

Microbes in indoor environments are constantly being exposed to antimicrobial surface finishes. Many are rendered non-viable after spending extended periods of time under low-moisture, low-nutrient surface conditions, regardless of whether those surfaces have been amended with antimicrobial chemicals. However, some microorganisms remain viable even after prolonged exposure to these hostile conditions. Work with specific model pathogens makes it difficult to draw general conclusions about how chemical and physical properties of surfaces affect microbes. Here, we explore the survival of a synthetic community of non-model microorganisms isolated from built environments following exposure to three chemically and physically distinct surface finishes. Our findings demonstrated the differences in bacterial survival associated with three chemically and physically distinct materials. Alkaline clay surfaces select for an alkaliphilic bacterium, Kocuria rosea, whereas acidic mold-resistant paint favors Bacillus timonensis, a Gram-negative spore-forming bacterium that also survives on antimicrobial surfaces after 24 hours of exposure. Additionally, antibiotic-resistant Pantoea allii did not exhibit prolonged retention on antimicrobial surfaces. Our controlled microcosm experiment integrates measurement of indoor chemistry and microbiology to elucidate the complex biochemical interactions that influence the indoor microbiome.

Connection in today's world is no longer between people but also between people and things, and between things. TheWorld-of-Persons (WoP) and the World-of-Things (WoT) collide in ways that have never been imagined before. Nevertheless, there are obstacles in progressing both technically and socially. This paper proposes a modeling framework for bridging the gap between WoP and WoT which addresses some of the technical obstacles while also acknowledging the potential social obstacles.

Despite the growing interest in the Internet-of-Things, many organizations remain reluctant to integrating things into their business processes. Different reasons justify this reluctance including things’ limited capabilities to act upon the cyber-physical surrounding in which they operate. To address this specific limitation, this paper examines thing empowerment with cognitive capabilities that would make them for instance, selective of the next business processes in which they would participate. The selection is based on things’ restrictions like limitedness and goals to achieve like improved reputation. For demonstration purposes, water leaks are used as a case study. A BPEL-based business process driving the fixing of water leaks is implemented involving different cognitive things like moisture sensor., Corrigendum in: Cognitive Systems Research, Volume 58, December 2019, Page 54. doi:10.1016/j.cogsys.2019.05.006

In the current study, an artificial neural network (ANN) and multiple linear regressions (MLR) have been used to develop predictive models for the estimation of molecular diffusion coefficients of 1252 polar and non-polar binary gases at multiple pressures over a wide range of temperatures and substances. The quality and reliability of each method were estimated in terms of the correlation coefficient (R), mean squared errors (MSE), root mean squared error (RMSE), and in terms of external validation coefficients (Q2ext). The comparison between the artificial neural network (ANN) and the multiple linear regressions (MLR) revealed that the neural network models showed a good predicting ability with lower errors (the roots of the mean squared errors in the total database were 0.1400 for ANN1 and 0.1300 for ANN2), and (root mean squared errors in the total databases were 0.5172 for MLR1 and 0.5000 for MLR2). This work is licensed under a Creative Commons Attribution 4.0 International License., U ovoj studiji primijenjene su umjetna neuronska mreža (ANN) i model višestruke linearne regresije (MLR) za razvoj prediktivnih modela za procjenu koeficijenata molekularne difuzije 1252 polarnih i nepolarnih binarnih plinova pri višestrukim tlakovima u širokom rasponu temperatura i tvari. Kvaliteta i pouzdanost svake metode procijenjeni su pomoću korelacijskog koeficijenta (R), srednjih kvadratnih pogrešaka (MSE), korijena srednje kvadratne pogreške (RMSE) te koeficijenata vanjske validacije (Q2ext). Usporedba između umjetne neuronske mreže (ANN) i višestrukih linearnih regresija (MLR) otkrila je da modeli neuronske mreže pokazuju dobru sposobnost predviđanja s nižim pogreškama (korijeni srednjih kvadratnih pogrešaka u ukupnoj bazi podataka bili su 0,1400 za ANN1 i 0 (1300 za ANN2 a pogreške korijena srednje vrijednosti u ukupnim bazama podataka bile su 0,5172 za MLR1 i 0,5000 za MLR2). Ovo djelo je dano na korištenje pod licencom Creative Commons Imenovanje 4.0 međunarodna.

This paper discusses the blend of cognitive computing with the Internet-of-Things that should result into developing cognitive things. Today’s things are confined into a data-supplier role, which deprives them from being the technology of choice for smart applications development. Cognitive computing is about reasoning, learning, explaining, acting, etc. In this paper, cognitive things’ features include functional and non-functional restrictions along with a 3 stage operation cycle that takes into account these restrictions during reasoning, adaptation, and learning. Some implementation details about cognitive things are included in this paper based on a water pipe case-study.