Semi-ProtoPNet Deep Neural Network for the Classification of Defective Power Grid Distribution Structures.

Power distribution grids are typically installed outdoors and are exposed to environmental conditions. When contamination accumulates in the structures of the network, there may be shutdowns caused by electrical arcs. To improve the reliability of the network, visual inspections of the electrical power system can be carried out; these inspections can be automated using computer vision techniques based on deep neural networks. Based on this need, this paper proposes the Semi-ProtoPNet deep learning model to classify defective structures in the power distribution networks. The Semi-ProtoPNet deep neural network does not perform convex optimization of its last dense layer to maintain the impact of the negative reasoning process on image classification. The negative reasoning process rejects the incorrect classes of an input image; for this reason, it is possible to carry out an analysis with a low number of images that have different backgrounds, which is one of the challenges of this type of analysis. Semi-ProtoPNet achieves an accuracy of 97.22%, being superior to VGG-13, VGG-16, VGG-19, ResNet-34, ResNet-50, ResNet-152, DenseNet-121, DenseNet-161, DenseNet-201, and also models of the same class such as ProtoPNet, NP-ProtoPNet, Gen-ProtoPNet, and Ps-ProtoPNet.

Residual behavior of quizalofop ethyl on onion (Allium cepa L.).

Quizalofop ethyl, a phenoxy propionate herbicide, is used for postemergence control of annual and perennial grass weeds in broad-leaved crops in India. The experiments were designed to study the dissipation kinetics of quizalofop ethyl on onion for two seasons. A simple, rapid, and sensitive method for estimation of quizalofop ethyl residues in onion and soil was developed and validated. The recoveries of quizalofop ethyl residues from onion and soil at different spiking level range from 84.81 to 92.68 %. The limit of quantification of this method was found to be 0.01 µg g(-1). The risk assessment through consumption of the onion in comparison to its acceptable daily intake which is an important parameter for the safety of the consumer was also evaluated. Standardized methodology supported by recovery studies was adopted to estimate residues of quizalofop ethyl on onion and soil. The average initial deposits of quizalofop ethyl on onion were observed to be 0.25 and 0.33 mg kg(-1), following single application of the herbicide at 50 g active ingredient (a.i.) ha(-1) during 2009 and 2010, respectively. The half-life values (T (1/2)) of quizalofop ethyl on onion crop were worked out to be 0.85 and 0.79 days, respectively, during 2009 and 2010. At harvest time, the residues of quizalofop ethyl on onion and soil were found to be below the determination limit of 0.01 mg kg(-1) following single application of the herbicide at 50 and 100 g a.i. ha(-1) for both the periods.

Degradation dynamics of emamectin benzoate on cabbage under subtropical conditions of Punjab, India.

Emamectin benzoate (Proclaim 5 SG) was applied to cabbage at 8.5 and 17 g a.i. ha⁻¹, during the head initiation stage. A high performance liquid chromatography (HPLC) analytical method, for the determination of emamectin benzoate in cabbage, was developed. Average recoveries of emamectin benzoate ranged from 92 % to 96 % at different fortification levels (0.05, 0.25 and 0.50 mg kg⁻¹). The initial deposits, 0.11 and 0.21 mg kg⁻¹ of emamectin benzoate at 8.5 and 17 g a.i. ha⁻¹, dissipated below the determination limit of 0.05 mg kg⁻¹ in 3 and 5 days, respectively.

Dissipation pattern of flubendiamide in/on brinjal (Solanum melongena L.).

Residues of flubendiamide and desiodo flubendiamide were studied following three applications of flubendiamide 480 SC at 7 days interval at 90 and 180 g a.i. ha(-1) in/on brinjal fruits. An average initial deposit of 0.33 and 0.61 mg kg(-1) of flubendiamide was observed respectively after application at single and double dosages. The residues of flubendiamide dissipated quickly at both the dosages, and after 3 days, the extent of dissipation was found to be about 76% and 79% at the single and double dosages, respectively. Brinjal fruit samples analysed at different time intervals did not show the presence of desiodo flubendiamide. The half-life of flubendiamide was observed to be 0.62 and 0.54 days at single and double dosages, respectively. The limit of determination of flubendiamide and desiodo flubendiamide was observed to be 0.05 mg kg(-1). Soil samples analysed after 15 days of the last application did not reveal the presence of flubendiamide and desiodo flubendiamide at their determination limit of 0.05 mg kg(-1). An assessment of the total intake of flubendiamide resulting through the consumption of brinjal fruits and its comparison with acceptable daily intake seems to be quite safe from consumer point of view.

Think positive: An interpretable neural network for image recognition.

The COVID-19 pandemic is an ongoing pandemic and is placing additional burden on healthcare systems around the world. Timely and effectively detecting the virus can help to reduce the spread of the disease. Although, RT-PCR is still a gold standard for COVID-19 testing, deep learning models to identify the virus from medical images can also be helpful in certain circumstances. In particular, in situations when patients undergo routine X-rays and/or CT-scans tests but within a few days of such tests they develop respiratory complications. Deep learning models can also be used for pre-screening prior to RT-PCR testing. However, the transparency/interpretability of the reasoning process of predictions made by such deep learning models is essential. In this paper, we propose an interpretable deep learning model that uses positive reasoning process to make predictions. We trained and tested our model over the dataset of chest CT-scan images of COVID-19 patients, normal people and pneumonia patients. Our model gives the accuracy, precision, recall and F-score equal to 99.48%, 0.99, 0.99 and 0.99, respectively.

Object or Background: An Interpretable Deep Learning Model for COVID-19 Detection from CT-Scan Images.

The new strains of the pandemic COVID-19 are still looming. It is important to develop multiple approaches for timely and accurate detection of COVID-19 and its variants. Deep learning techniques are well proved for their efficiency in providing solutions to many social and economic problems. However, the transparency of the reasoning process of a deep learning model related to a high stake decision is a necessity. In this work, we propose an interpretable deep learning model Ps-ProtoPNet to detect COVID-19 from the medical images. Ps-ProtoPNet classifies the images by recognizing the objects rather than their background in the images. We demonstrate our model on the dataset of the chest CT-scan images. The highest accuracy that our model achieves is 99.29%.

An Interpretable Deep Learning Model for Covid-19 Detection With Chest X-Ray Images.

Timely and accurate detection of an epidemic/pandemic is always desired to prevent its spread. For the detection of any disease, there can be more than one approach including deep learning models. However, transparency/interpretability of the reasoning process of a deep learning model related to health science is a necessity. Thus, we introduce an interpretable deep learning model: Gen-ProtoPNet. Gen-ProtoPNet is closely related to two interpretable deep learning models: ProtoPNet and NP-ProtoPNet The latter two models use prototypes of spacial dimension [Formula: see text] and the distance function [Formula: see text]. In our model, we use a generalized version of the distance function [Formula: see text] that enables us to use prototypes of any type of spacial dimensions, that is, square spacial dimensions and rectangular spacial dimensions to classify an input image. The accuracy and precision that our model receives is on par with the best performing non-interpretable deep learning models when we tested the models on the dataset of [Formula: see text]-ray images. Our model attains the highest accuracy of 87.27% on classification of three classes of images, that is close to the accuracy of 88.42% attained by a non-interpretable model on the classification of the given dataset.

Residual behaviour and risk assessment of flubendiamide on chickpea (Cicer arietinum L.).

The study was undertaken to determine the disappearance trends of flubendiamide residues on chickpea under field conditions and thereby, ensure consumer safety. Average initial deposits of flubendiamide on chickpea pods were found to be 0.68 and 1.17 mg kg(-1), respectively, following three applications of flubendiamide 480SC @ 48 and 96 g a.i. ha(-1) at 7d intervals. Half-life of flubendiamide on chickpea pods was observed to be 1.39 and 1.44 d, respectively, at single and double dosages whereas with respect to chickpea leaves, these values were found to be 0.77 and 0.86 d. Desiodo flubendiamide was not detected at 0.05 mg kg(-1) level on chickpea samples collected at different intervals. Theoretical maximum residue contribution (TMRC) for flubendiamide was calculated and found to be well below the maximum permissible intake (MPI) on chickpea pods and leaves at 0-day (1 h after spraying) for the both dosages. Thus, the application of flubendiamide at the recommended dose on chickpea presents no human health risks and is safe to the consumers.