BackgroundHigh resolution and high throughput genotype to phenotype studies in plants are underway to accelerate breeding of climate ready crops. In the recent years, deep learning techniques and in particular Convolutional Neural Networks (CNNs), Recurrent Neural Networks and Long-Short Term Memories (LSTMs), have shown great success in visual data recognition, classification, and sequence learning tasks. More recently, CNNs have been used for plant classification and phenotyping, using individual static images of the plants. On the other hand, dynamic behavior of the plants as well as their growth has been an important phenotype for plant biologists, and this motivated us to study the potential of LSTMs in encoding these temporal information for the accession classification task, which is useful in automation of plant production and care.MethodsIn this paper, we propose a CNN-LSTM framework for plant classification of various genotypes. Here, we exploit the power of deep CNNs for automatic joint feature and classifier learning, compared to using hand-crafted features. In addition, we leverage the potential of LSTMs to study the growth of the plants and their dynamic behaviors as important discriminative phenotypes for accession classification. Moreover, we collected a dataset of time-series image sequences of four accessions of Arabidopsis, captured in similar imaging conditions, which could be used as a standard benchmark by researchers in the field. We made this dataset publicly available.ConclusionThe results provide evidence of the benefits of our accession classification approach over using traditional hand-crafted image analysis features and other accession classification frameworks. We also demonstrate that utilizing temporal information using LSTMs can further improve the performance of the system. The proposed framework can be used in other applications such as in plant classification given the environment conditions or in distinguishing diseased plants from healthy ones.

High resolution and high throughput, genotype to phenotype studies in plants are underway to accelerate breeding of climate ready crops. Complex developmental phenotypes are observed by imaging a variety of accessions in different environment conditions, however extracting the genetically heritable traits is challenging. In the recent years, deep learning techniques and in particular Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) and Long-Short Term Memories (LSTMs), have shown great success in visual data recognition, classification, and sequence learning tasks. In this paper, we proposed a CNN-LSTM framework for plant classification of various genotypes. Here, we exploit the power of deep CNNs for joint feature and classifier learning, within an automatic phenotyping scheme for genotype classification. Further, plant growth variation over time is also important in phenotyping their dynamic behavior. This was fed into the deep learning framework using LSTMs to model these temporal cues for different plant accessions. We generated a replicated dataset of four accessions of Arabidopsis and carried out automated phenotyping experiments. The results provide evidence of the benefits of our approach over using traditional hand-crafted image analysis features and other genotype classification frameworks. We also demonstrate that temporal information further improves the performance of the phenotype classification system.

This paper studies the problem of broadcasting layered video streams over heterogeneous single-hop wireless networks using feedback-free random linear network coding (RLNC). We combine RLNC with unequal error protection (UEP) and our main purpose is twofold. First, to systematically investigate the benefits of UEP+RLNC layered approach in servicing users with different reception capabilities. Second, to study the effect of not using feedback, by comparing feedbackfree schemes with idealistic full-feedback schemes. To these ends, we study 'expected percentage of decoded frames' as a key content-independent performance metric and propose a general framework for calculation of this metric, which can highlight the effect of key system, video and channel parameters. We study the effect of number of layers and propose a scheme that selects the optimum number of layers adaptively to achieve the highest performance. Assessing the proposed schemes with real H.264 test streams, the trade-offs among the users' performances are discussed and the gain of adaptive selection of number of layers to improve the trade-offs is shown. Furthermore, it is observed that the performance gap between the proposed feedback-free scheme and the idealistic scheme is very small and the adaptive selection of number of video layers further closes the gap.

No abstract

No abstract