The paper proposes an approach for estimating the rectal temperature of dairy cows based on the non-invasive real-time monitoring of their respiration rates and the temperature-humidity index (THI) of the environment, combined with the analysis of infrared images. We use multimodal machine learning for the joint processing (fusion) of these different types of data. The implementation is performed using a new open source AutoML Python module named AutoGluon. After training and optimizing three different regression models (a neural network and two powerful boosting algorithms), it reduces the variance of the result using level 2 stacking. The evaluation metrics we work with are the mean absolute error, MAE, and the coefficient of determination, $R^2$. For a sample of 295 studied animals, a weighted ensemble provides quite decent results: $R^2=0.73$ and MAE $\approx 0.1$ °C. For another sample of 118 cows, we additionally use the pulse rate as a predictor and we achieve $R^2=0.65$, MAE $\approx 0.2$ °C. The maximal error is almost $1$ °C due to outliers, but the median absolute error in both cases is significantly lower: MedAE $<0.1$ °C, with the standard deviations respectively being $0.{118}^{°}$ and $0.{137}^{°}$. These encouraging results give us confidence that tabular and visual data fusion in ML models has great potential for the advancement of non-invasive real-time monitoring and early diagnostics methods.

Noise is defined as unwanted sound, whether chronic or periodic, and can be described in a variety of terms, including its frequency, intensity, frequency spectrum, and sound pressure shape over time. The sources of noise can be technical devices, various hydraulic systems, the engines of various machines, routine work (opening and closing doors, repairing stalls, talking of workers, feeding), mechanical ventilators, animal activities, including climbing barriers, chewing barriers, vocalizations of cows. Good farms in terms of noise level are considered to be those with a noise level up to 70 dB, while farms with a noise level above 70 dB are problematic. Noise levels above 70 dB also have a detrimental effect on cow welfare, and this is associated with a high number of somatic cells in milk. When milking dairy cows, the noise level should not exceed 65–70 dB, or if it exceeds this value, it should be for a short time, as this can lead to health disorders in humans and animals in the medium term.

The aim of the present research was to study the influence of the calving season in conditions of the upcoming climate changes on the productive traits of dairy cows in Bulgaria. The study was conducted on a cattle farm with a capacity of 500 dairy cows, which were loose-housed in open free-stall barns (shed-type). In the research, 286 lactations of 199 Holstein cattle from the studied farm were included. The cows with the highest average milk yield for lactation—8522.2 kg—calved in the spring, while the cows with the lowest milk yield—8082.7 kg—calved in the summer. Cows that calved in the spring had the highest maximum daily milk yield (lactation peak)—38 kg—whereas cows that calved in the summer had the lowest—35.7 kg. Regarding the composition indicators of milk, fat, and protein content, no significant effect of the calving season was found, but there was a tendency for the lowest values for the percentage of fat in milk to be reported for cows that calved in the summer—3.68%—and the highest for those calved in the spring—3.71%. Regarding the percentage of protein in the milk, the lowest values were observed for cows that calved in autumn—3.19%—and the highest for cows that calved in summer—3.27%.

Chronic obstructive pulmonary disease (COPD) is characterized by irreversible airflow obstruction and is associated with chronic local and systemic inflammation and oxidative stress. The enhanced oxidative stress and inflammation have been reported to affect telomere length (TL). Furthermore, a number of SNPs at loci encoding the main components of the telomerase genes, TERT and TERC have been shown to correlate with TL. We aimed to explore the leukocyte TL and genotypes for single nucleotide polymorphisms, rs12696304 (C > G) and rs10936599 (C > T) near TERC in COPD cases and matched healthy controls using q-PCR technologies. Successful assessment of TL was performed for 91 patients and 88 controls. The patients had shorter TL (17919.36 ± 1203.01 bp) compared to controls (21 271.48 ± 1891.36 bp) although not significant (p = 0.137). The TL did not associate with the gender, age, spirometric indexes, smoking habits but tended to correlate negatively with BMI (Rho = − 0.215, p = 0.076) in the controls, but not in COPD patients. The genotype frequencies of the SNPs rs12696304 and rs10936599 were compared between patients and controls and the odds ratios (OR) for developing COPD were calculated. The carriers of the common homozygous (CC) genotypes of the SNPs had higher risk for COPD, compared to carriers of the variants alleles (rs12696304 CG+GG vs. CC; OR: 0.615, 95% CI [0.424–0.894], p = 0.011 and for rs10936599 CT+TT vs. CC OR = 0.668, 95% CI [0.457–0.976], p = 0.044). Analysis on the combined effects of the TERC rs12696304 (C > G) and rs10936599 (C > T) genotypes, CC/CC genotype combination was associated with higher risk for COPD (p < 0.0001) and marginally lower FEV1% pr. in patients with GOLD II (p = 0.052). There was no association between the SNP genotypes and TL. In summary, our results suggest that COPD patients may have shorter TL, and rs12696304 and rs10936599 near TERC may affect the risk of COPD independently of TL.

Background and Aim: Rising global temperatures and increasing humidity levels are intensifying the risk of heat stress (HS) in high-yielding dairy cattle. The temperature–humidity index (THI) is a standard metric for evaluating thermal stress in livestock. This study aimed to assess seasonal and diurnal variations in temperature, relative humidity, and THI within a milking parlor and determine their compliance with established thermal comfort thresholds for dairy cows. Materials and Methods: The study was conducted in a glass-roofed, windowless milking parlor housing 400 Holstein–Friesian cows in Bulgaria. Microclimatic parameters (temperature, relative humidity, and THI) were measured during three daily milking sessions (morning, noon, and evening) at 3 time points (start, middle, and end) over a 12-month period. Measurements were taken inside the parlor and 10 m outside. Statistical analysis involved one-way analysis of variance and post hoc tests using STATISTICA version 10. Results: Summer and spring exhibited the highest mean and peak temperatures (up to 31.4 °C), while winter showed the highest relative humidity (82.39%). THI values peaked in summer, reaching levels classified as “danger” for dairy cows. Morning milking generally recorded lower temperatures and THI. Seasonal variation significantly influenced all microclimatic indicators (p < 0.001), while milking sequence significantly affected temperature and THI (p < 0.05). Conclusion: In-parlor thermal conditions, especially during summer, exceeded comfort thresholds and posed a risk for HS. The study underscores the urgent need to revise livestock housing regulations to include THI-specific standards for milking parlors. Incorporating real-time microclimatic monitoring can enhance animal welfare and productivity in dairy systems. Keywords: dairy cows, heat stress, microclimate, milking parlor, seasonal variation, temperature–humidity index, thermal comfort.

The study was carried out in the milking parlor of a dairy cattle farm consisting 500 animals from Holstein-Friesian breed in Bulgaria. The animals were housed in a freestall dairy barn and milked in double-8 milking parlor “herringbone” type. The level of noise was measured three times in every milking (at the beginning, in the middle and at the finishing of the milking) in the morning, midday and evening milking every month for one year. The noise level in the working environment was recorded by noise meter„ Lutron SL-4023SD. The highest noise levels were reported in summer and winter, with maximum values up to 78.3 dB. It was found that regardless of the season during the morning milking the lowest noise levels in the milking parlor were reported (from 70.37 to 70.46 dB). The average values for noise level for an 8-hour working day by seasons varied from 69.87 dB to 74.36 dB, with the highest reported value for the winter season.