The health of poultry flock is crucial in sustainable farming. Recent advances in machine learning and speech analysis have opened up opportunities for real-time monitoring of the behavior and health of flock. However, there has been little research on using Tiny Machine Learning (Tiny ML) for continuous vocalization monitoring in poultry. This study addresses this gap by developing and deploying Tiny ML models on low-power edge devices to monitor chicken vocalizations. The focus is on overcoming challenges such as memory limitations, processing power, and battery life to ensure practical implementation in agricultural settings. In collaboration with avian researchers, a diverse dataset of poultry vocalizations representing a range of health and environmental conditions was created to train and validate the algorithms. Digital Signal Processing (DSP) blocks of the Edge Impulse platform were used to generate spectral features for studying fowl vocalization. A one-dimensional Convolutional Neural Network (CNN) model was employed for classification. The study emphasizes accurately identifying and categorizing different chicken noises associated with emotional states such as discomfort, hunger, and satisfaction. To improve accuracy and reduce background noise, noise-robust Tiny ML algorithms were developed. Before the removal of background noise, our average accuracy and F1 scores were 91.6% and 0.92, respectively. After the removal, they improved to 96.6% and 0.95.

Infections with Mycoplasma gallisepticum (MG) in poultry are associated with a wide range of disease conditions, including those affecting the respiratory and reproductive systems. The purpose of this study was to endorse the more sensitive diagnostic scheme for MG infection and identify the best molecular marker for MG phylogenetic analysis using six housekeeping genes: mgc2, mraW, atpG, ugpA, DUF31196, and lgT. For these purposes, 55 poultry flocks of different species were screened using either qRT-PCR or PCR techniques analogous to conventional culturing from non-cultured and cultured swabs on PPLO broth. The rate of MG positivity was the highest when using qRT-PCR from cultured broth (89.0%) and the lowest when using conventional culturing (34.5%). Compared to qRT-PCR from broth, statistical analysis using the Roc curve in MedCalc statistical software showed that the PCR schemes (qRT-PCR from swabs and PCR from swabs and broth) performed better than conventional culturing in terms of sensitivity, accuracy, and area under the curve (AUC), suggesting that they may be more reliable schemes. Further support was added by Cohen’s kappa test, showing moderate agreement between the molecular approaches. Among the six screened genes, mgc2 and mraW had the highest detection rates (69% and 65.4%, respectively). The comparative phylogenetic analysis revealed that mgc2 or atpG gene sequences distinguished MG isolates into different clades with high discriminatory power.

Background: Coleus forskolii, green coffee and green tea have been shown to effect on body functions and health. Methods: Twenty males and thirty female albino mice of 33.86 ±0.27g BW were classified into two groups; control group fed basal control diet versus treated group fed basal control diet containing multi-ingredient supplement (Coleus forskohlii, green coffee bean and green tea; 1.5% per supplement)for ten weeks. Initial and final body weights were recorded of control and supplemented groups. Germinal vesicle oocytes were harvested from ovaries after 48:0h of PMSG injection for investigating oocyte quality. Furthermore, female mice were mated with fertile males and pregnancy rate and offspring numbers were recorded. In addition, the male mice of both groups were sedated using 26.6 mg/kg BW xylazine for recording rectal temperature, pulse rate and SPO2. Besides, blood samples were collected for complete blood picture and plasma biochemistry analyses. Result: The results showed that multi-ingredient supplement caused significant decrease in body weight gain versus increase (P less than 0.05) of rectal temperature. Reproductive performances represented by oocyte quality and pregnancy rate were significantly decreased in multi-ingredient supplement group. Furthermore, blood cells and plasma profiles (urea, creatinine, glucose, aspartate aminotransferase, alanine aminotransferase and lactate dehydrogenase) were decreased in multi-ingredient supplement groups except total protein if compared to control group. It could be concluded that multi-ingredient supplement resulted in significant decrease of body weight gain, reproductive performances and blood cell profiles as well.

This review is a comprehensive investigation of avian candidiasis, mainly caused by Candida albicans, although the prevalence of non-albicans Candida species has increased in domestic and wild birds. Avian candidiasis causes significant economic losses in poultry production through increased mortality, cost of treatments, and reduced growth rates, particularly in young birds and intensive farming operations. The pathogenesis section provides a description of the molecular virulence factors such as adhesin-mediated attachment (ALS, Agglutinin-Like Sequence family; HWP1, Hyphal Wall Protein 1), yeast-to-hypha morphogenesis, tissue damage by Candidalysin, biofilm formation on mucosal and abiotic surfaces, and secreted hydrolytic enzymes including secreted aspartyl proteinases (SAPs) and phospholipases. The identified predisposing factors include immunosuppression, malnutrition, abuse of antibiotics, bad husbandry, and crop stasis. The diagnostic methods discussed encompass cytological analysis and fungal culture on selective media to more sophisticated methods of molecular analysis (PCR, MALDI-TOF MS, and NGS). Antifungal susceptibility investigations indicate that nystatin and amphotericin B are still very effective against most avian isolates and that resistance to the azoles is on the rise, especially with respect to the non-albicans Candida species. Nystatin is still the first-line treatment of localized infections; azoles are still used for resistant or systemic infections despite their hepatotoxicity. Sanitation, proper nutrition, and proper use of antimicrobials are essential to prevent diseases. The knowledge gaps comprise the absence of avian-specific pharmacokinetic information, poor knowledge of species-species virulence phenotypes, and the lack of point-of-care diagnostics. The need to have integrated One Health surveillance systems is emphasized by the zoonotic potential of the avian Candida reservoirs.