Hybrid optimization model for conjunctive use of surface and groundwater resources in water deficit irrigation system.

The increasing demand for food production with limited available water resources poses a threat to agricultural activities. Conventional optimization algorithms increase the processing stage and perform in the space allocated from user. Therefore, the proposed work was used to design better performance results. The conjunctive allocation of water resources maximizes the net benefit of farmers. In this study, the novel hybrid optimization model developed is the first of its kind and was designed to resolve the sharing of water resource conflict among different reaches based on a genetic algorithm (GA), bacterial foraging optimization (BFO) and ant colony optimization (ACO) to maximize the net benefit of the water deficit in Sathanur reservoir command. The GA-based optimization model considered crop-related physical and economic parameters to derive optimal cropping patterns for three different conjunctive use policies and further allocation of surface and groundwater for different crops are enhanced with the BFO. The allocation of surface and groundwater for the head, middle and tail reaches obtained from the BFO is considered as an input to the ACO as a guiding mechanism to attain an optimal cropping pattern. Comparing the average productivity values, policy 3 (3.665 Rs/m3) has better values relating to policy 1 (3.662 Rs/m3) and policy 2 (3.440 Rs/m3). Thus, the developed novel hybrid optimization model (GA-BFO-ACO) is very promising for enhancing farmer's net income and can be replicated in other irrigated regions to overcome chronic water problems. The productivity value of policy 3 was 6.54% greater than that of policy 2, whereas that of policy 1 was 6.45% greater. Overall, the comparison shows that the better performance analysis of various optimization was done successfully.

Acoustic classification of multiple simultaneous bird species: a multi-instance multi-label approach.

Although field-collected recordings typically contain multiple simultaneously vocalizing birds of different species, acoustic species classification in this setting has received little study so far. This work formulates the problem of classifying the set of species present in an audio recording using the multi-instance multi-label (MIML) framework for machine learning, and proposes a MIML bag generator for audio, i.e., an algorithm which transforms an input audio signal into a bag-of-instances representation suitable for use with MIML classifiers. The proposed representation uses a 2D time-frequency segmentation of the audio signal, which can separate bird sounds that overlap in time. Experiments using audio data containing 13 species collected with unattended omnidirectional microphones in the H. J. Andrews Experimental Forest demonstrate that the proposed methods achieve high accuracy (96.1% true positives/negatives). Automated detection of bird species occurrence using MIML has many potential applications, particularly in long-term monitoring of remote sites, species distribution modeling, and conservation planning.

New DRASTIC framework for groundwater vulnerability assessment: bivariate and multi-criteria decision-making approach coupled with metaheuristic algorithm.

Unplanned anthropogenic activities and erratic climate events pose serious threats to groundwater contamination. Therefore, the vulnerability assessment model becomes an essential tool for proper planning and protection of this precious resource. DRASTIC is an extensively adopted groundwater vulnerability assessment model that suffers from several shortcomings in its assessment due to the subjectivity of its rates and weights. In this paper, a new framework was developed to address the subjectivity of DRASTIC model using a bivariate, multi-criteria decision-making approach coupled with a metaheuristic algorithm. Shannon entropy (SE) and stepwise weight assessment ratio analysis (SWARA) methods were coupled with biogeography-based optimization (BBO) to modify rates and weights. The performance of developed models was assessed using area under the receiver operating characteristic (AU-ROC) curve and weighted F1 score. The Shannon-MH model yields better results with an AUC value of 0.8249, whereas other models resulted in an AUC value of 0.8186, 0.7714, 0.7672, and 0.7378 for SWARA-MH, SWARA, SE, and original DRASTIC models, respectively. It is also evident from weighted F1 score that Shannon-MH model produced maximum accuracy with a value of 0.452 followed by 0.437, 0.419, 0.370, and 0.234 for SWARA-MH, SWARA, SE, and original DRASTIC models, respectively. The results indicated that Shannon model coupled with metaheuristic algorithm outperforms other developed models in groundwater vulnerability assessment.

Does your dermatology classifier know what it doesn't know? Detecting the long-tail of unseen conditions.

Supervised deep learning models have proven to be highly effective in classification of dermatological conditions. These models rely on the availability of abundant labeled training examples. However, in the real-world, many dermatological conditions are individually too infrequent for per-condition classification with supervised learning. Although individually infrequent, these conditions may collectively be common and therefore are clinically significant in aggregate. To prevent models from generating erroneous outputs on such examples, there remains a considerable unmet need for deep learning systems that can better detect such infrequent conditions. These infrequent 'outlier' conditions are seen very rarely (or not at all) during training. In this paper, we frame this task as an out-of-distribution (OOD) detection problem. We set up a benchmark ensuring that outlier conditions are disjoint between the model training, validation, and test sets. Unlike traditional OOD detection benchmarks where the task is to detect dataset distribution shift, we aim at the more challenging task of detecting subtle differences resulting from a different pathology or condition. We propose a novel hierarchical outlier detection (HOD) loss, which assigns multiple abstention classes corresponding to each training outlier class and jointly performs a coarse classification of inliers vs. outliers, along with fine-grained classification of the individual classes. We demonstrate that the proposed HOD loss based approach outperforms leading methods that leverage outlier data during training. Further, performance is significantly boosted by using recent representation learning methods (BiT, SimCLR, MICLe). Further, we explore ensembling strategies for OOD detection and propose a diverse ensemble selection process for the best result. We also perform a subgroup analysis over conditions of varying risk levels and different skin types to investigate how OOD performance changes over each subgroup and demonstrate the gains of our framework in comparison to baseline. Furthermore, we go beyond traditional performance metrics and introduce a cost matrix for model trust analysis to approximate downstream clinical impact. We use this cost matrix to compare the proposed method against the baseline, thereby making a stronger case for its effectiveness in real-world scenarios.

Clinically applicable deep learning for diagnosis and referral in retinal disease.

The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.

Latent IBP Compound Dirichlet Allocation.

We introduce the four-parameter IBP compound Dirichlet process (ICDP), a stochastic process that generates sparse non-negative vectors with potentially an unbounded number of entries. If we repeatedly sample from the ICDP we can generate sparse matrices with an infinite number of columns and power-law characteristics. We apply the four-parameter ICDP to sparse nonparametric topic modelling to account for the very large number of topics present in large text corpora and the power-law distribution of the vocabulary of natural languages. The model, which we call latent IBP compound Dirichlet allocation (LIDA), allows for power-law distributions, both, in the number of topics summarising the documents and in the number of words defining each topic. It can be interpreted as a sparse variant of the hierarchical Pitman-Yor process when applied to topic modelling. We derive an efficient and simple collapsed Gibbs sampler closely related to the collapsed Gibbs sampler of latent Dirichlet allocation (LDA), making the model applicable in a wide range of domains. Our nonparametric Bayesian topic model compares favourably to the widely used hierarchical Dirichlet process and its heavy tailed version, the hierarchical Pitman-Yor process, on benchmark corpora. Experiments demonstrate that accounting for the power-distribution of real data is beneficial and that sparsity provides more interpretable results.