Audio signal classification plays a significant role in various real-world applications such as speech recognition, environmental sound analysis, and music genre identification. Traditional approaches often depend on manually extracted features, which may not capture the full complexity of audio data. This paper presents a deep learning-based method for automatic classification of audio signals using a One-Dimensional Convolutional Neural Network (1D-CNN) and a Recurrent Neural Network (RNN). The CNN model is utilized to extract spatial feature...s from spectrogram representations, while the RNN model effectively captures temporal dependencies within the audio sequences. Both models were trained and evaluated on a labelled dataset, and their performance was compared using metrics such as accuracy, precision, probability of detection (POD), and F1-score. The experimental results demonstrate that CNN has achieved high classification accuracy compared to RNN, with CNN excelling at spatial feature extraction and RNN providing temporal feature learning. The proposed approach confirms that deep learning models can significantly enhance the performance and reliability of audio signal classification systems.Read more

Objective: We compared the prevalence of abnormal glucose status between Senegalese migrants and their relatives staying in their villages in Fuuta (a rural region in the Northern part of Senegal).Design and methods: We led an exhaustive study on all the Senegalese migrants present in Saint-Die (Vosges, France) (SD) at a 1-year interval. We led a similar study at the same period on their relatives in their villages of Fuuta (F). Study parameters were Weight (W), height, Body Mass Index (BMI), Waist/Hip Ratio (WHR), and Fasting Capillary Glycaem...ia (FCG) expressed in total blood glucose. We classified patients into normal (N: FCG ≤ 1.00 g/l), Impaired Fasting Glycaemia (IFG: FCG between 1.00 g/l and 1.09 g/l), diabetic (D: FCG > 1.10 g/l when fasting or ≥ 1.80 g/l when not fasting), or abnormal glucose status (IFG + D). SD sample included 74 subjects (58.1% female) of mean age 41.7+/-12.7 years. The sample included 847 subjects (66.9% female) of mean age 37.3+/-17.8 years.Results: In the SD group, W was 76.8+/-11.4 kg (BMI = 26.80+/-4.30 kg/m2); 57 (77.03%) had normal blood glucose, and 17 (22.97%) had IFG+D, among whom 12 (70.6%) were diabetic. In the F group, W was 60.8+/-10.9 kg (BMI = 21.37+/-3.70 kg/m2); 791 (93.39%) had normal blood glucose, and only 56 (6.61%) had IFG+D, among whom 35 (62.5%) were diabetic. Prevalence of IFG+D between SD and F was significantly different (p < 0.01%). There are still significant differences after standardization on age.Conclusion: As described in other countries, Senegalese migrants have a much higher risk of developing diabetes mellitus than their relatives remaining in their birth country. The main reason seems to be the nutritional transition (diet and sedentary lifestyle).Read more

This research reveals the previously unexplored pharmacognostic potential of antidepressants found in nutrients derived from both legume and animal sources. Through preclinical investigations involving mouse models, the study focused into antidepressant and antioxidant activities of non-denatured and denatured protein extracts from beans and eggs. Non-denatured protein extracts from beans and eggs, at saturation levels of 40% and 80%, were examined as macronutrients, while denatured protein extracts at equivalent saturation levels were consider...ed micronutrients. The study employed the DPPH and hydrogen peroxide tests to assess antioxidant activity, and the forced swimming test and sucrose preference test to evaluate acute and chronic mild antidepressant effects, respectively. The acute toxicity study revealed that macronutrients from eggs at 40% and 80% saturation displayed non-toxic effects (LD50 >5 g/kg), while those from beans, specifically at saturation of 80%, exhibited a relatively low level of toxicity (LD50 = 2.5 g/kg). Evaluation of antioxidant activity using the DPPH test yielded inconclusive results due to the influence of ethanol precipitation. In contrast, the H2O2 test demonstrated significant antioxidant potential in both macronutrients and micronutrients extracted from beans and eggs at all saturation levels. In investigating antidepressant properties, both macronutrients and micronutrients of bean and egg protein extracts at 40% and 80% saturation exhibited notable antidepressant effects, particularly the micronutrients at saturation of 80%. This antidepressant effect was characterized by a reduction in immobility time and an increase in sucrose preference.In conclusion, this study uncovers the multifaceted potential of protein extracts sourced from natural products, plant and animal origins, as agents for treating depression. It opens up new avenues for research, with implications ranging from neuroprotection to the management of depression, inspiring optimism for innovative approaches to mental health treatment.Read more