Tunis University

About: Tunis University is a education organization based out in Tunis, Tunisia. It is known for research contribution in the topics: Population & Thin film. The organization has 11745 authors who have published 15400 publications receiving 154900 citations. The organization is also known as: University of Tunis & UT.

Effects of high-intensity interval training on body composition, aerobic and anaerobic performance and plasma lipids in overweight/obese and normal-weight young men.

Abstract: To examine the effects of short high-intensity interval training (HIIT) on body composition, physical performance and plasma lipids in overweight/obese compared to normal-weight young men. Nine overweight/obese and nine normal-weight men (control group) aged 17 to 20 years underwent a HIIT programme three times per week for eight weeks. Body composition, indices of aerobic [maximal aerobic velocity (MAV) and maximal oxygen uptake (VO2max)] and anaerobic [squat jump (SJ), counter-movement jump (CMJ), five-jump test (FJT), 10-m and 30-m sprint] performances, as well as fasting plasma lipids, were assessed in the two groups at PRE and POST HIIT. The HIIT programme resulted in significant reductions in body mass (-1.62%, P=0.016, ES=0.11) and fat mass (-1.59%, P=0.021, ES=0.23) in obese, but not in normal-weight subjects. MAV (+5.55%, P=0.005, ES=0.60 and +2.96%, P=0.009, ES=0.82), VO2max (+5.27%, P=0.006, ES=0.63 and +2.88%, P=0.009, ES=0.41), FJT (+3.63%, P=0.005, ES=0.28 and +2.94%, P=0.009, ES=0.52), SJ (+4.92%, P=0.009, ES=0.25 and +6.94%, P=0.009, ES=0.70) and CMJ (+6.84%, P=0.014, ES=0.30 and +6.69%, P=0.002, ES=0.64) significantly increased in overweight/obese and normal-weight groups, respectively. 30-m sprint time significantly decreased in both groups (-1.77%, P=0.038, ES=0.12 and -0.72%, P=0.030, ES=0.16). Plasma total cholesterol (-11.8%, P=0.026, ES=0.96), LDL cholesterol (-11.9%, P=0.050, ES=0.77) and triglycerides (-21.3%, P=0.023, ES=1.08) significantly decreased in the obese group, but not in the normal-weight group. The eight-week HIIT programme resulted in a slight improvement in physical fitness and a significant decrease in plasma lipids in the obese. Short duration HIIT may contribute to an improved cardiometabolic profile in the obese.

Nodes self-scheduling approach for maximising wireless sensor network lifetime based on remaining energy

Abstract: Coverage and energy conservation are two major issues in wireless sensor networks (WSNs), especially when sensors are randomly deployed in large areas. In such WSNs, sensors are equipped with limited lifetime batteries and redundantly cover the target area. To face the short lifetime of the WSN, the objective is to optimise energy consumption while maintaining the full sensing coverage. A major technique to save the energy is to use a wake-up scheduling protocol through which some nodes stay active whereas the others enter sleep state so as to conserve their energy. This study presents an original algorithm for node selfscheduling to decide which ones have to switch to the sleep state. The novelty is to take into account the remaining energy at every node in the decision of turning off redundant nodes. Hence, the node with a low remaining energy has priority over its neighbours to enter sleep state. The decision is based on a local neighbourhood knowledge that minimises the algorithm overhead. To verify and evaluate the proposed algorithm, simulations have been conducted and have shown that it can contribute to extend the network lifetime. A comparison with existing works is also presented and the performance gains are highlighted.

A Personalized Hybrid Tourism Recommender System

Abstract: This paper focuses on building personalized recommender system in the tourism field. The application recommends to a tourist the best attractions in a particular place according to his preferences, his profile and his appreciation to previous visited places. This paper proposes a hybrid recommender system that combines the three most known recommender methods which are: the collaborative filtering (CF), the content-based filtering (CB) and the demographic filtering (DF). In order to implement these recommender methods, we have applied different machine learning algorithms which are the K-nearest neighbors (K-NN) for both CB and CF and the decision tree for the DF. The hybridization is a good choice to make the best of their advantages and to overcome the cold start problem. To enhance the recommendation accuracy, we use two hybridization techniques: switching and weighted. For the weighted approach, a novel linear programming model is applied to obtain the optimal weights' values. An extensive experimental study is conducted based on different evaluation metrics using extracted data from TripAdvisor. Our results show that the hybrid method is more accurate than the other recommender approaches used separately.

Random forest-based approach for physiological functional variable selection for driver’s stress level classification

Abstract: This paper is devoted to a statistical physiological functional variable selection for driver's stress level classification using random forests. Indeed, this study focuses on humans physiological changes, produced when driving in different urban routes, captured using portable sensors. Specifically, the electrodermal activity measured on two different locations: hand and foot, electromyogram, heart rate and respiration of ten driving experiments in three types of routes: rest area, city, and highway driving issued from drivedb database, available online on the PhysioNet website. Several studies were achieved on driver's stress level recognition using physiological signals. Classically, researchers extract expert-based features from physiological signals and select the most relevant ones for stress level recognition. This work provides a random forest-based method for the selection of physiological functional variables in order to classify the driver's stress level. On the methodological side, the contributions of this work are to consider physiological signals as functional variables, decomposed on wavelet basis and to offer a procedure of variable selection. On the applied side, the proposed method provides a " blind " procedure of driver's stress level classification performing as the expert-based study in terms of misclassification rate. It offers moreover a ranking of physiological variables according to their importance in stress level classification. The obtained results suggest that electromyogram and heart rate signals are not very relevant when compared to the electro-dermal and the respiration signals.