The study focused on a method of detection for bee colony infestation with the Varroa destructor mite, based on the measurements of the chemical properties of beehive air. The efficient detection of varroosis was demonstrated. This method of detection is based on a semiconductor gas sensor array and classification module. The efficiency of detection was characterized by the true positive rate (TPR) and true negative rate (TNR). Several factors influencing the performance of the method were determined. They were: (1) the number and kind of sensors, (2) the classifier, (3) the group of bee colonies, and (4) the balance of the classification data set. Gas sensor array outperformed single sensors. It should include at least four sensors. Better results of detection were attained with a support vector machine (SVM) as compared with the k-nearest neighbors (k-NN) algorithm. The selection of bee colonies was important. TPR and TNR differed by several percent for the two examined groups of colonies. The balance of the classification data was crucial. The average classification results were, for the balanced data set: TPR = 0.93 and TNR = 0.95, and for the imbalanced data set: TP = 0.95 and FP = 0.53. The selection of bee colonies and the balance of classification data set have to be controlled in order to attain high performance of the proposed detection method.

Honey bees are subject to a number of stressors. In recent years, there has been a worldwide decline in the population of these insects. Losses raise a serious concern, because bees have an indispensable role in the food supply of humankind. This work is focused on the method of assessment of honey bee colony infestation by Varroa destructor. The approach allows to detect several categories of infestation: “Low”, “Medium” and “High”. The method of detection consists of two components: (1) the measurements of beehive air using a gas sensor array and (2) classification, which is based on the measurement data. In this work, we indicate the sensitivity of the bee colony infestation assessment to the timing of measurement data collection. It was observed that the semiconductor gas sensor responses to the atmosphere of a defined beehive, collected during 24 h, displayed temporal variation. We demonstrated that the success rate of the bee colony infestation assessment also altered depending on the time of day when the gas sensor array measurement was done. Moreover, it was found that different times of day were the most favorable to detect the particular infestation category. This result could indicate that the representation of the disease in the beehive air may be confounded during the day, due to some interferences. More studies are needed to explain this fact and determine the best measurement periods. The problem addressed in this work is very important for scheduling the beekeeping practices aimed at Varroa destructor infestation assessment, using the proposed method.

Varroosis is a dangerous and difficult to diagnose disease decimating bee colonies. The studies conducted sought answers on whether the electronic nose could become an effective tool for the efficient detection of this disease by examining sealed brood samples. The prototype of a multi-sensor recorder of gaseous sensor signals with a matrix of six semiconductor gas sensors TGS 823, TGS 826, TGS 832, TGS 2600, TGS 2602, and TGS 2603 from FIGARO was tested in this area. There were 42 objects belonging to 3 classes tested: 1st class—empty chamber (13 objects), 2nd class—fragments of combs containing brood sick with varroosis (19 objects), and 3rd class—fragments of combs containing healthy sealed brood (10 objects). The examination of a single object lasted 20 min, consisting of the exposure phase (10 min) and the sensor regeneration phase (10 min). The k-th nearest neighbors algorithm (kNN)—with default settings in RSES tool—was successfully used as the basic classifier. The basis of the analysis was the sensor reading value in 270 s with baseline correction. The multi-sensor MCA-8 gas sensor signal recorder has proved to be an effective tool in distinguishing between brood suffering from varroosis and healthy brood. The five-time cross-validation 2 test (5 × CV2 test) showed a global accuracy of 0.832 and a balanced accuracy of 0.834. Positive rate of the sick brood class was 0.92. In order to check the overall effectiveness of baseline correction in the examined context, we have carried out additional series of experiments—in multiple Monte Carlo Cross Validation model—using a set of classifiers with different metrics. We have tested a few variants of the kNN method, the Naïve Bayes classifier, and the weighted voting classifier. We have verified with statistical tests the thesis that the baseline correction significantly improves the level of classification. We also confirmed that it is enough to use the TGS2603 sensor in the examined context.

American foulbrood is a dangerous bee disease that attacks the sealed brood. It quickly leads to the death of bee colonies. Efficient diagnosis of this disease is essential. As specific odours are produced when larvae rot, it was investigated whether an electronic nose can distinguish between colonies affected by American foulbrood and healthy ones. The experiment was conducted in an apiary with 18 bee families, 9 of which showed symptoms of the disease confirmed by laboratory diagnostics. Three units of the Beesensor V.2 device based on an array of six semiconductor TGS gas sensors, manufactured by Figaro, were tested. Each copy of the device was tested in all bee colonies: sick and healthy. The measurement session per bee colony lasted 40 min and yielded results from four 10 min measurements. One 10-min measurement consisted of a 5 min regeneration phase and a 5 min object-measurement phase. For the experiments, we used both classical classification methods such as k-nearest neighbour, Naive Bayes, Support Vector Machine, discretized logistic regression, random forests, and committee of classifiers, that is, methods based on extracted representative data fragments. We also used methods based on the entire 600 s series, in this study of sequential neural networks. We considered, in this study, six options for data preparation as part of the transformation of data series into representative results. Among others, we used single stabilised sensor readings as well as average values from stable areas. For verifying the quality of the classical classifiers, we used the 25-fold train-and-test method. The effectiveness of the tested methods reached a threshold of 75 per cent, with results stable between 65 and 70 per cent. As an element to confirm the possibility of class separation using an artificial nose, we used applied visualisations of classes. It is clear from the experiments conducted that the artificial nose tested has practical potential. Our experiments show that the approach to the problem under study by sequential network learning on a sequence of data is comparable to the best classical methods based on discrete data samples. The results of the experiment showed that the Beesensor V.2 along with properly selected classification techniques can become a tool to facilitate rapid diagnosis of American foulbrood under field conditions.

American foulbrood is a dangerous disease of bee broods found worldwide, caused by the Paenibacillus larvae larvae L. bacterium. In an experiment, the possibility of detecting colonies of this bacterium on MYPGP substrates (which contains yeast extract, Mueller-Hinton broth, glucose, K2HPO4, sodium pyruvate, and agar) was tested using a prototype of a multi-sensor recorder of the MCA-8 sensor signal with a matrix of six semiconductors: TGS 823, TGS 826, TGS 832, TGS 2600, TGS 2602, and TGS 2603 from Figaro. Two twin prototypes of the MCA-8 measurement device, M1 and M2, were used in the study. Each prototype was attached to two laboratory test chambers: a wooden one and a polystyrene one. For the experiment, the strain used was P. l. larvae ATCC 9545, ERIC I. On MYPGP medium, often used for laboratory diagnosis of American foulbrood, this bacterium produces small, transparent, smooth, and shiny colonies. Gas samples from over culture media of one- and two-day-old foulbrood P. l. larvae (with no colonies visible to the naked eye) and from over culture media older than 2 days (with visible bacterial colonies) were examined. In addition, the air from empty chambers was tested. The measurement time was 20 min, including a 10-min testing exposure phase and a 10-min sensor regeneration phase. The results were analyzed in two variants: without baseline correction and with baseline correction. We tested 14 classifiers and found that a prototype of a multi-sensor recorder of the MCA-8 sensor signal was capable of detecting colonies of P. l. larvae on MYPGP substrate with a 97% efficiency and could distinguish between MYPGP substrates with 1–2 days of culture, and substrates with older cultures. The efficacy of copies of the prototypes M1 and M2 was shown to differ slightly. The weighted method with Canberra metrics (Canberra.811) and kNN with Canberra and Manhattan metrics (Canberra. 1nn and manhattan.1nn) proved to be the most effective classifiers.

Beekeeping is an extremely difficult field of agriculture. It requires efficient management of the bee nest so that the bee colony can develop efficiently and produce as much honey and other bee products as possible. The beekeeper, therefore, must constantly monitor the contents of the bee comb. At the University of Warmia and Mazury in Olsztyn, research is being carried out to develop methods for efficient management of the apiary. One of our research goals was to test whether a gas detector (MCA-8) based on six semiconductor sensors—TGS823, TGS826, TGS832, TGS2600, TGS2602, and TGS2603 from the company FIGARO—is able to recognize the contents of bee comb cells. For this purpose, polystyrene and wooden test chambers were created, in which fragments of bee comb with different contents were placed. Gas samples were analyzed from an empty comb, a comb with sealed brood, a comb with open brood, a comb with carbohydrate food in the form of sugar syrup, and a comb with bee bread. In addition, a sample of gas from an empty chamber was tested. The results in two variants were analyzed: (1) Variant 1, the value of 270 s of sensor readings from the sample measurement (exposure phase), and (2) Variant 2, the value of 270 s of sensor readings from the sample measurement (measurement phase) with baseline correction by subtracting the last 600 s of surrounding air measurements (flushing phase). A five-time cross-validation 2 (5xCV2) test and the Monte Carlo cross-validation 25 (trained and tested 25 times) were performed. Fourteen classifiers were tested. The naive Bayes classifier (NB) proved to be the most effective method for distinguishing individual classes from others. The MCA-8 device brilliantly differentiates an empty comb from a comb with contents. It differentiates better between an empty comb and a comb with brood, with results of more than 83%. Lower class accuracy was obtained when distinguishing an empty comb from a comb with food and a comb with bee bread, with results of less than 73%. The matrix of six TGS sensors in the device shows promising versatility in distinguishing between various types of brood and food found in bee comb cells. This capability, though still developing, positions the MCA-8 device as a potentially invaluable tool for enhancing the efficiency and effectiveness of beekeepers in the future.