Deep Learning Classification of Canine Behavior Using a Single Collar-Mounted Accelerometer: Real-World Validation

Collar-mounted canine activity monitors can use accelerometer data to estimate dog activity levels, step counts, and distance traveled. With recent advances in machine learning and embedded computing, much more nuanced and accurate behavior classification has become possible, giving these affordable consumer devices the potential to improve the efficiency and effectiveness of pet healthcare. Here, we describe a novel deep learning algorithm that classifies dog behavior at sub-second resolution using commercial pet activity monitors. We built machine learning training databases from more than 5000 videos of more than 2500 dogs and ran the algorithms in production on more than 11 million days of device data. We then surveyed project participants representing 10,550 dogs, which provided 163,110 event responses to validate real-world detection of eating and drinking behavior. The resultant algorithm displayed a sensitivity and specificity for detecting drinking behavior (0.949 and 0.999, respectively) and eating behavior (0.988, 0.983). We also demonstrated detection of licking (0.772, 0.990), petting (0.305, 0.991), rubbing (0.729, 0.996), scratching (0.870, 0.997), and sniffing (0.610, 0.968). We show that the devices’ position on the collar had no measurable impact on performance. In production, users reported a true positive rate of 95.3% for eating (among 1514 users), and of 94.9% for drinking (among 1491 users). The study demonstrates the accurate detection of important health-related canine behaviors using a collar-mounted accelerometer. We trained and validated our algorithms on a large and realistic training dataset, and we assessed and confirmed accuracy in production via user validation.

Download Full-text

Deep learning classification of canine behavior using a single collar-mounted accelerometer: Real-world validation

10.1101/2020.12.14.422660 ◽

2020 ◽

Author(s):

Robert D. Chambers ◽

Nathanael C. Yoder ◽

Aletha B. Carson ◽

Christian Junge ◽

David E. Allen ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Real World ◽

Learning Algorithm ◽

Drinking Behavior ◽

True Positive Rate ◽

Training Dataset ◽

Activity Levels ◽

Accelerometer Data ◽

Activity Monitors

AbstractCollar-mounted canine activity monitors can use accelerometer data to estimate dog activity levels, step counts, and distance traveled. With recent advances in machine learning and embedded computing, much more nuanced and accurate behavior classification has become possible, giving these affordable consumer devices the potential to improve the efficiency and effectiveness of pet healthcare. Here we describe a novel deep learning algorithm that classifies dog behavior at sub-second resolution using commercial pet activity monitors. We built machine learning training databases from over 5,000 videos of over 2,500 dogs and ran the algorithms in production on over 11 million days of device data. We then surveyed project participants representing 10,550 dogs, they provided us 163,110 event responses to validate real-world detection of eating and drinking behavior. The resultant algorithm displayed a sensitivity and specificity for detecting drinking behavior (0.949 and 0.999, respectively) and eating behavior (0.988, 0.983). We also demonstrated detection of licking, petting, rubbing, scratching, and sniffing. We show that the devices’ position on the collar has no measurable impact on performance. In production, users reported a true positive rate of 95.3% for eating (among 1,514 users), and of 94.9% (among 1,491 users) for drinking. The study demonstrates the accurate detection of important health-related canine behaviors using a collar-mounted accelerometer. We trained and validated our algorithms on a large and realistic training dataset, and we assessed and confirmed accuracy in production via user validation.

Download Full-text

Deep Neural Networks for Hierarchical Taxonomic Fossil Classification of Carbonate Skeletal Grains

10.5194/egusphere-egu21-16394 ◽

2021 ◽

Author(s):

Sidhant Idgunji ◽

Madison Ho ◽

Jonathan L. Payne ◽

Daniel Lehrmann ◽

Michele Morsilli ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Learning Algorithm ◽

Training Dataset ◽

Single Class ◽

Deep Learning Algorithm ◽

Human Ability ◽

Wide Range ◽

Potential Applications ◽

Animal Phyla

<p>The growing digitization of fossil images has vastly improved and broadened the potential application of big data and machine learning, particularly computer vision, in paleontology. Recent studies show that machine learning is capable of approaching human abilities of classifying images, and with the increase in computational power and visual data, it stands to reason that it can match human ability but at much greater efficiency in the near future. Here we demonstrate this potential of using deep learning to identify skeletal grains at different levels of the Linnaean taxonomic hierarchy. Our approach was two-pronged. First, we built a database of skeletal grain images spanning a wide range of animal phyla and classes and used this database to train the model. We used a Python-based method to automate image recognition and extraction from published sources. Second, we developed a deep learning algorithm that can attach multiple labels to a single image. Conventionally, deep learning is used to predict a single class from an image; here, we adopted a Branch Convolutional Neural Network (B-CNN) technique to classify multiple taxonomic levels for a single skeletal grain image. Using this method, we achieved over 90% accuracy for both the coarse, phylum-level recognition and the fine, class-level recognition across diverse skeletal grains (6 phyla and 15 classes). Furthermore, we found that image augmentation improves the overall accuracy. This tool has potential applications in geology ranging from biostratigraphy to paleo-bathymetry, paleoecology, and microfacies analysis. Further improvement of the algorithm and expansion of the training dataset will continue to narrow the efficiency gap between human expertise and machine learning.</p>

Download Full-text

Study on Radar Echo-Filling in an Occlusion Area by a Deep Learning Algorithm

Remote Sensing ◽

10.3390/rs13091779 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1779

Author(s):

Xiaoyan Yin ◽

Zhiqun Hu ◽

Jiafeng Zheng ◽

Boyong Li ◽

Yuanyuan Zuo

Keyword(s):

Deep Learning ◽

Loss Function ◽

Learning Algorithm ◽

Weather Radar ◽

Loss Functions ◽

Training Dataset ◽

Echo Intensity ◽

Common Mean ◽

Deep Learning Algorithm ◽

Radar Beam

Radar beam blockage is an important error source that affects the quality of weather radar data. An echo-filling network (EFnet) is proposed based on a deep learning algorithm to correct the echo intensity under the occlusion area in the Nanjing S-band new-generation weather radar (CINRAD/SA). The training dataset is constructed by the labels, which are the echo intensity at the 0.5° elevation in the unblocked area, and by the input features, which are the intensity in the cube including multiple elevations and gates corresponding to the location of bottom labels. Two loss functions are applied to compile the network: one is the common mean square error (MSE), and the other is a self-defined loss function that increases the weight of strong echoes. Considering that the radar beam broadens with distance and height, the 0.5° elevation scan is divided into six range bands every 25 km to train different models. The models are evaluated by three indicators: explained variance (EVar), mean absolute error (MAE), and correlation coefficient (CC). Two cases are demonstrated to compare the effect of the echo-filling model by different loss functions. The results suggest that EFnet can effectively correct the echo reflectivity and improve the data quality in the occlusion area, and there are better results for strong echoes when the self-defined loss function is used.

Download Full-text

Study on Influence of Range of Data in Concrete Compressive Strength with Respect to the Accuracy of Machine Learning with Linear Regression

Applied Sciences ◽

10.3390/app11093866 ◽

2021 ◽

Vol 11 (9) ◽

pp. 3866

Author(s):

Jun-Ryeol Park ◽

Hye-Jin Lee ◽

Keun-Hyeok Yang ◽

Jung-Keun Kook ◽

Sanghee Kim

Keyword(s):

Machine Learning ◽

Compressive Strength ◽

Linear Regression ◽

Coarse Aggregate ◽

Learning Algorithm ◽

Linear Regression Analysis ◽

Aggregate Size ◽

Training Dataset ◽

Machine Learning Algorithm ◽

Concrete Compressive Strength

This study aims to predict the compressive strength of concrete using a machine-learning algorithm with linear regression analysis and to evaluate its accuracy. The open-source software library TensorFlow was used to develop the machine-learning algorithm. In the machine-earning algorithm, a total of seven variables were set: water, cement, fly ash, blast furnace slag, sand, coarse aggregate, and coarse aggregate size. A total of 4297 concrete mixtures with measured compressive strengths were employed to train and testing the machine-learning algorithm. Of these, 70% were used for training, and 30% were utilized for verification. For verification, the research was conducted by classifying the mixtures into three cases: the case where the machine-learning algorithm was trained using all the data (Case-1), the case where the machine-learning algorithm was trained while maintaining the same number of training dataset for each strength range (Case-2), and the case where the machine-learning algorithm was trained after making the subcase of each strength range (Case-3). The results indicated that the error percentages of Case-1 and Case-2 did not differ significantly. The error percentage of Case-3 was far smaller than those of Case-1 and Case-2. Therefore, it was concluded that the range of training dataset of the concrete compressive strength is as important as the amount of training dataset for accurately predicting the concrete compressive strength using the machine-learning algorithm.

Download Full-text

A Survey on Bias and Fairness in Machine Learning

ACM Computing Surveys ◽

10.1145/3457607 ◽

2021 ◽

Vol 54 (6) ◽

pp. 1-35

Author(s):

Ninareh Mehrabi ◽

Fred Morstatter ◽

Nripsuta Saxena ◽

Kristina Lerman ◽

Aram Galstyan

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Deep Learning ◽

Real World ◽

State Of The Art ◽

Future Directions ◽

Discriminatory Behavior ◽

Real World Applications ◽

Near Future ◽

Different Sources

With the widespread use of artificial intelligence (AI) systems and applications in our everyday lives, accounting for fairness has gained significant importance in designing and engineering of such systems. AI systems can be used in many sensitive environments to make important and life-changing decisions; thus, it is crucial to ensure that these decisions do not reflect discriminatory behavior toward certain groups or populations. More recently some work has been developed in traditional machine learning and deep learning that address such challenges in different subdomains. With the commercialization of these systems, researchers are becoming more aware of the biases that these applications can contain and are attempting to address them. In this survey, we investigated different real-world applications that have shown biases in various ways, and we listed different sources of biases that can affect AI applications. We then created a taxonomy for fairness definitions that machine learning researchers have defined to avoid the existing bias in AI systems. In addition to that, we examined different domains and subdomains in AI showing what researchers have observed with regard to unfair outcomes in the state-of-the-art methods and ways they have tried to address them. There are still many future directions and solutions that can be taken to mitigate the problem of bias in AI systems. We are hoping that this survey will motivate researchers to tackle these issues in the near future by observing existing work in their respective fields.

Download Full-text

On the Unfounded Enthusiasm for Soft Selective Sweeps III: The Supervised Machine Learning Algorithm That Isn’t

Genes ◽

10.3390/genes12040527 ◽

2021 ◽

Vol 12 (4) ◽

pp. 527

Author(s):

Eran Elhaik ◽

Dan Graur

Keyword(s):

Machine Learning ◽

Learning Algorithm ◽

A Priori ◽

Neutral Theory ◽

Dominant Mode ◽

Supervised Machine Learning ◽

Training Dataset ◽

Selective Sweeps ◽

Two Factors ◽

Negative Controls

In the last 15 years or so, soft selective sweep mechanisms have been catapulted from a curiosity of little evolutionary importance to a ubiquitous mechanism claimed to explain most adaptive evolution and, in some cases, most evolution. This transformation was aided by a series of articles by Daniel Schrider and Andrew Kern. Within this series, a paper entitled “Soft sweeps are the dominant mode of adaptation in the human genome” (Schrider and Kern, Mol. Biol. Evolut. 2017, 34(8), 1863–1877) attracted a great deal of attention, in particular in conjunction with another paper (Kern and Hahn, Mol. Biol. Evolut. 2018, 35(6), 1366–1371), for purporting to discredit the Neutral Theory of Molecular Evolution (Kimura 1968). Here, we address an alleged novelty in Schrider and Kern’s paper, i.e., the claim that their study involved an artificial intelligence technique called supervised machine learning (SML). SML is predicated upon the existence of a training dataset in which the correspondence between the input and output is known empirically to be true. Curiously, Schrider and Kern did not possess a training dataset of genomic segments known a priori to have evolved either neutrally or through soft or hard selective sweeps. Thus, their claim of using SML is thoroughly and utterly misleading. In the absence of legitimate training datasets, Schrider and Kern used: (1) simulations that employ many manipulatable variables and (2) a system of data cherry-picking rivaling the worst excesses in the literature. These two factors, in addition to the lack of negative controls and the irreproducibility of their results due to incomplete methodological detail, lead us to conclude that all evolutionary inferences derived from so-called SML algorithms (e.g., S/HIC) should be taken with a huge shovel of salt.

Download Full-text

Segmentation of Affected Crops using Deep Learning

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.e1052.0785s319 ◽

2019 ◽

Vol 8 (5S3) ◽

pp. 232-234

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Monitoring System ◽

Learning Algorithm ◽

Target Area ◽

Learning Technology ◽

Machine Learning Algorithm ◽

Normal Human ◽

Human Monitoring ◽

Disease Attack

Deep Learning technology can accurately predict the presence of diseases and pests in the agricultural farms. Upon this Machine learning algorithm, we can even predict accurately the chance of any disease and pest attacks in future For spraying the correct amount of fertilizer/pesticide to elimate host, the normal human monitoring system unable to predict accurately the total amount and ardent of pest and disease attack in farm. At the specified target area the artificial percepton tells the value accurately and give corrective measure and amount of fertilizers/ pesticides to be sprayed.

Download Full-text

Encoding Health Records into Pathway Representations for Deep Learning

10.3233/shti210800 ◽

2021 ◽

Author(s):

Marco Luca Sbodio ◽

Natasha Mulligan ◽

Stefanie Speichert ◽

Vanessa Lopez ◽

Joao Bettencourt-Silva

Keyword(s):

Neural Network ◽

Machine Learning ◽

Deep Learning ◽

Source Code ◽

Training Dataset ◽

Health Records ◽

Learning Tasks ◽

Patient Pathways ◽

Computational Resources ◽

The Impact

There is a growing trend in building deep learning patient representations from health records to obtain a comprehensive view of a patient’s data for machine learning tasks. This paper proposes a reproducible approach to generate patient pathways from health records and to transform them into a machine-processable image-like structure useful for deep learning tasks. Based on this approach, we generated over a million pathways from FAIR synthetic health records and used them to train a convolutional neural network. Our initial experiments show the accuracy of the CNN on a prediction task is comparable or better than other autoencoders trained on the same data, while requiring significantly less computational resources for training. We also assess the impact of the size of the training dataset on autoencoders performances. The source code for generating pathways from health records is provided as open source.

Download Full-text

ViraMiner: Deep Learning on Raw DNA Sequences for Identifying Viral Genomes in Human Samples

10.1101/602656 ◽

2019 ◽

Cited By ~ 4

Author(s):

Ardi Tampuu ◽

Zurab Bzhalava ◽

Joakim Dillner ◽

Raul Vicente

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Dna Sequences ◽

Recommendation System ◽

Clinical Importance ◽

Training Dataset ◽

Viral Genomes ◽

Human Samples ◽

Types Of Information ◽

Improved Accuracy

ABSTRACTDespite its clinical importance, detection of highly divergent or yet unknown viruses is a major challenge. When human samples are sequenced, conventional alignments classify many assembled contigs as “unknown” since many of the sequences are not similar to known genomes. In this work, we developed ViraMiner, a deep learning-based method to identify viruses in various human biospecimens. ViraMiner contains two branches of Convolutional Neural Networks designed to detect both patterns and pattern-frequencies on raw metagenomics contigs. The training dataset included sequences obtained from 19 metagenomic experiments which were analyzed and labeled by BLAST. The model achieves significantly improved accuracy compared to other machine learning methods for viral genome classification. Using 300 bp contigs ViraMiner achieves 0.923 area under the ROC curve. To our knowledge, this is the first machine learning methodology that can detect the presence of viral sequences among raw metagenomic contigs from diverse human samples. We suggest that the proposed model captures different types of information of genome composition, and can be used as a recommendation system to further investigate sequences labeled as “unknown” by conventional alignment methods. Exploring these highly-divergent viruses, in turn, can enhance our knowledge of infectious causes of diseases.

Download Full-text

Research on Feature Extracted Method for Flutter Test Based on EMD and CNN

International Journal of Aerospace Engineering ◽

10.1155/2021/6620368 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Hua Zheng ◽

Zhenglong Wu ◽

Shiqiang Duan ◽

Jiangtao Zhou

Keyword(s):

Feature Extraction ◽

Deep Learning ◽

Wind Tunnel ◽

Signal Analysis ◽

Learning Algorithm ◽

Structural Information ◽

Structural Response ◽

Training Dataset ◽

Measured Signal ◽

Test Dataset

Due to the inevitable deviations between the results of theoretical calculations and physical experiments, flutter tests and flutter signal analysis often play significant roles in designing the aeroelasticity of a new aircraft. The measured structural response from aeroelastic models in both wind tunnel tests and real fight flutter tests contain an abundance of structural information, but traditional methods tend to have limited ability to extract features of concern. Inspired by deep learning concepts, a novel feature extraction method for flutter signal analysis was established in this study by combining the convolutional neural network (CNN) with empirical mode decomposition (EMD). It is widely hypothesized that when flutter occurs, the measured structural signals are harmonic or divergent in the time domain, and that the flutter modal (1) is singular and (2) its energy increases significantly in the frequency domain. A measured-signal feature extraction and flutter criterion framework was constructed accordingly. The measured signals from a wind tunnel test were manually labeled “flutter” and “no-flutter” as the foundational dataset for the deep learning algorithm. After the normalized preprocessing, the intrinsic mode functions (IMFs) of the flutter test signals are obtained by the EMD method. The IMFs are then reshaped to make them the suitable size to be input to the CNN. The CNN parameters are optimized though the training dataset, and the trained model is validated through the test dataset (i.e., cross-validation). The accuracy rate of the proposed method reached 100% on the test dataset. The training model appears to effectively distinguish whether or not the structural response signal contains flutter. The combination of EMD and CNN provides effective feature extraction of time series signals in flutter test data. This research explores the connection between structural response signals and flutter from the perspective of artificial intelligence. The method allows for real-time, online prediction with low computational complexity.

Download Full-text