National Institute of Applied Science and Technology

Mrabet H., Belguith S., Alhomoud A., Jemai A.

The Internet of Things (IoT) is leading today’s digital transformation. Relying on a combination of technologies, protocols, and devices such as wireless sensors and newly developed wearable and implanted sensors, IoT is changing every aspect of daily life, especially recent applications in digital healthcare. IoT incorporates various kinds of hardware, communication protocols, and services. This IoT diversity can be viewed as a double-edged sword that provides comfort to users but can lead also to a large number of security threats and attacks. In this survey paper, a new compacted and optimized architecture for IoT is proposed based on five layers. Likewise, we propose a new classification of security threats and attacks based on new IoT architecture. The IoT architecture involves a physical perception layer, a network and protocol layer, a transport layer, an application layer, and a data and cloud services layer. First, the physical sensing layer incorporates the basic hardware used by IoT. Second, we highlight the various network and protocol technologies employed by IoT, and review the security threats and solutions. Transport protocols are exhibited and the security threats against them are discussed while providing common solutions. Then, the application layer involves application protocols and lightweight encryption algorithms for IoT. Finally, in the data and cloud services layer, the main important security features of IoT cloud platforms are addressed, involving confidentiality, integrity, authorization, authentication, and encryption protocols. The paper is concluded by presenting the open research issues and future directions towards securing IoT, including the lack of standardized lightweight encryption algorithms, the use of machine-learning algorithms to enhance security and the related challenges, the use of Blockchain to address security challenges in IoT, and the implications of IoT deployment in 5G and beyond.

Rejaibi E., Komaty A., Meriaudeau F., Agrebi S., Othmani A.

• A deep Recurrent Neural Network based framework for depression recognition from speech. • A robust approach that outperforms the state-of-art approaches on DAIC-WOZ dataset. • Fast, non-invasive and non-intruded approach, convenient for real-world applications. • Expanding training labels and transferred features to overcome data scarcity. • Evaluation of the proposed approach under multi-modal and a multi-features experiments. Clinical depression or Major Depressive Disorder (MDD) is a common and serious medical illness. In this paper, a deep Recurrent Neural Network-based framework is presented to detect depression and to predict its severity level from speech. Low-level and high-level audio features are extracted from audio recordings to predict the 24 scores of the Patient Health Questionnaire and the binary class of depression diagnosis. To overcome the problem of the small size of Speech Depression Recognition (SDR) datasets, expanding training labels and transferred features are considered. The proposed approach outperforms the state-of-art approaches on the DAIC-WOZ database with an overall accuracy of 76.27% and a root mean square error of 0.4 in assessing depression, while a root mean square error of 0.168 is achieved in predicting the depression severity levels. The proposed framework has several advantages (fastness, non-invasiveness, and non-intrusion), which makes it convenient for real-time applications. The performances of the proposed approach are evaluated under a multi-modal and a multi-features experiments. MFCC based high-level features hold relevant information related to depression. Yet, adding visual action units and different other acoustic features further boosts the classification results by 20% and 10% to reach an accuracy of 95.6% and 86%, respectively. Considering visual-facial modality needs to be carefully studied as it sparks patient privacy concerns while adding more acoustic features increases the computation time.

Rathod N.B., Elabed N., Punia S., Ozogul F., Kim S., Rocha J.M.

Polyphenol has been used in treatment for some health disorders due to their diverse health promoting properties. These compounds can reduce the impacts of oxidation on the human body, prevent the organs and cell structure against deterioration and protect their functional integrity. The health promoting abilities are attributed to their high bioactivity imparting them high antioxidative, antihypertensive, immunomodulatory, antimicrobial, and antiviral activity, as well as anticancer properties. The application of polyphenols such as flavonoids, catechin, tannins, and phenolic acids in the food industry as bio-preservative substances for foods and beverages can exert a superb activity on the inhibition of oxidative stress via different types of mechanisms. In this review, the detailed classification of polyphenolic compunds and their important bioactivity with special focus on human health are addressed. Additionally, their ability to inhibit SARS-CoV-2 could be used as alternative therapy to treat COVID patients. Inclusions of polyphenolic compounds in various foods have demonstrated their ability to extend shelf life and they positive impacts on human health (antioxidative, antihypertensive, immunomodulatory, antimicrobial, anticancer). Additionally, their ability to inhibit the SARS-CoV-2 virus has been reported. Considering their natural occurrence and GRAS status they are highly recommended in food.

Abid F.B., Sallem M., Braham A.

In modern manufacturing processes, motivations for automatic fault diagnosis (FD) are increasingly growing as a result of the great trends toward achieving zero breakdowns. Induction motors (IMs) represent a critical part in most of the applications. Due to its high potential of automatic feature extraction, the deep learning (DL)-based FD of IM has recently been introduced and has essentially emphasized on the diagnosis using the vibration analysis. However, this approach has not received considerable attention when using the current analysis, although it represents a cost-effective alternative. Moreover, the already implemented DL architectures are still suffering from lack of physical interpretability. In this article, a new DL architecture called deep-SincNet is implemented for a multi-FD task. The proposed end-to-end scheme automatically learns the fault features from the raw motor current and accordingly finalizes the FD process. A high accuracy for several separated and combined faults, a more physical interpretability, a high robustness against noisy environments, and a significant gain in implementation cost prove the competitive performance of the proposed approach.

Kadri A., Marzougui H., Aouiti A., Bacha F.

This paper deals with a modeling and control of a hybrid power system based on fuel cell and wind turbine (WT) system based a Doubly Fed Induction Generator (DFIG). To improve the performance of the hybrid energy system, a super-capacitor storage system is associated with a fuel cell which is not able to compensate the fast variation of the load power demand. In this case, rule based energy management algorithm should be applied to share energy between three source elements in order to satisfy load power demand. The main originality of this work lies in the new topology of the WT-DFIG/Full cell/super capacitor hybrid power system which presents an easier accessibility of DC and AC grid. For the wind energy conversion system, the proposed control is the Maximum Power Point Tracking algorithm based a torque control loop (OTC). The wind turbine is equipped with a DFIG operated at variable speed which the control is based on direct power control. Simulation results show the effectiveness of the proposed control strategy and the energy management algorithm. A dSpace 1104 real-time board is used for management algorithm implementation. The obtained experimental results prove the efficiency of the proposed control strategy.

Bensid A., El Abed N., Houicher A., Regenstein J.M., Özogul F.

In the food industry, there is a need to use the properties of antioxidants and antimicrobials effectively to prevent microbial growth in foods, as well as to retard the oxidation of fats to delay rancidity. Nevertheless, the emerging concern about the negative effects of synthetic antioxidants and antimicrobials on consumers' health along with the advantages of natural substances have led to more fundamental research to investigate the mechanism of action and toxicity of natural antioxidants and antimicrobials. There is also a need to establish in each country an appropriate regulatory scheme to assure consumers of the safety and efficacy of these materials. Thus, this present review provides a detailed overview of the different antioxidant and antimicrobial groups, focusing on their properties, mechanism of action, and applicability in the food industry to be a guide for students and researchers.

Inanli A.G., Tümerkan E.T., Abed N.E., Regenstein J.M., Özogul F.

Background Seafood is highly susceptible to spoilage due to microbiological, chemical and enzymatic reactions, which are the principal causes of their quality deterioration. Therefore, greater consumer demand for high quality seafood along with a concern for the safety of the artificial preservatives currently used to prevent quality losses creates a challenge. Natural preservatives, such as chitosan biopolymer, are potential alternatives to maintain seafood quality by reducing microbial growth, increasing oxidative stability and protecting sensorial properties. Scope and approach This review focuses on the use of chitosan as a food preservative, and its functional properties in food, such as antioxidant and antimicrobial activities, its importance as a dietary fibre and its use for enzymes-immobilization. The applications of this biopolymer on seafood and seafood products as a functional biomaterial and its health benefits are discussed. Key finding and conclusions Chitosan is a functional biomaterial for the preservation of foods, mainly due to its natural origin and its excellent biological properties. It has antimicrobial activities against spoilage microorganisms and food-borne pathogens, and a strong antioxidant activity that can protect against lipid oxidation in seafood. Chitosan can also be characterized by its wide range of benefits for health promotion and disease prevention.

Khemiri S., Khelifi N., Nunes M.C., Ferreira A., Gouveia L., Smaali I., Raymundo A.

Microalgae have been widely used as a source of functional ingredients such as pigments, antioxidants, vitamins, and omega-3 polyunsaturated fatty acids. They also represent a promising alternative source of protein. The objective of this study was to evaluate the impact of the addition of two green microalgae species ( Nannochloropsis gaditana L2 and Chlamydomonas sp. EL5) on the techno-functional and nutritional properties of gluten-free bread. Microalgae biomass was added in the amounts of 1.0 and 3.0 g/100 g of flour. The behavior of the dough during the mixing as well as the physicochemical properties of the prepared breads were investigated. Gluten-free bread with N. gaditana L2 and Chlamydomonas sp. EL5 presented significantly higher protein and higher levels of lipids and ash, compared with the control bread. The incorporation of 3% microalgae biomass revealed a 100% increase in iron and calcium contents. The fatty acid profile of supplemented bread changed in a species-specific manner with a particular increase in linolenic acid (18:3 ω3) and a decrease in ω3/ω6 ratio. Besides, due to its original biochemical composition, mainly the highly protein content, microalgae incorporation was found to bring an overall structuring effect on the gluten-free bread texture. However, the dough mixing properties were not affected significantly by microalgae addition. A significant change in color was recorded in doughs, breads, crusts and crumbs. This was caused by the presence of pigment in microalgae biomass, which turned into more intense green-yellow tonalities. A sensory analysis revealed that the supplemented breads scored highest for nearly all the sensory parameters with the 3% N. gaditana L2 bread as the preferred one in terms of global appreciation. This innovative approach gives new insights of the possibility of improving gluten-free products, structurally and nutritionally, using only microalgae as a natural and a sustainable food ingredient. • 1% and 3% microalgae biomass were successfully used in gluten-free bread recipe. • Dough mixing properties were slightly affected by microalgae supplementation. • Microalgae incorporation significantly influence the breads textural properties. • Enriched breads had greater nutritional properties. • Microalgae addition enhanced the sensory properties of gluten free breads.

Šimat V., Elabed N., Kulawik P., Ceylan Z., Jamroz E., Yazgan H., Čagalj M., Regenstein J.M., Özogul F.

The oceans have been the Earth’s most valuable source of food. They have now also become a valuable and versatile source of bioactive compounds. The significance of marine organisms as a natural source of new substances that may contribute to the food sector and the overall health of humans are expanding. This review is an update on the recent studies of functional seafood compounds (chitin and chitosan, pigments from algae, fish lipids and omega-3 fatty acids, essential amino acids and bioactive proteins/peptides, polysaccharides, phenolic compounds, and minerals) focusing on their potential use as nutraceuticals and health benefits.

Bouazizi S., Montevecchi G., Antonelli A., Hamdi M.

The peels of prickly pears represent around half of the fruit and are generally discarded, thus becoming an environmental problem. Due to the high content of bioactive compounds, prickly pear peels could be conveniently used as a nutraceutical and functional ingredient in some food preparations, such as bakery products. This study was aimed at assessing the aptitude of prickly pear peel flour to be mixed (10 g, 20 g, and 30 g/100 g) with wheat flour for biscuits preparation through the analysis of the physical and chemical properties of doughs and biscuits and through sensory evaluation. The composition of prickly pear flour showed a significantly higher concentration of fibre (20.70 g/100 g d.w.), ash (14.57 g/100 g d.w.), and phenolic compounds (2776 mg/100 g d.w.) compared to the control wheat flour, thus improving technological properties such as the aptitude to kneading, the flavour retention, and the antioxidant capacity. The acceptance sensory test showed that biscuits prepared with 20 g/100 g and 30 g/100 g of prickly pear flour were more appreciated for smell, taste, colour, and overall acceptability.