•Design of sensor using the colorimetric principle.•Development of an IoT system for soil fertility.•Fuzzy rule-based analysis at edge level.•Periodic automated fertilizer alert to the farmers based ...on soil nutrients level.
This paper presents an Internet of Things (IoT) based system by designing a novel Nitrogen-Phosphorus-Potassium (NPK) sensor with Light Dependent Resistor (LDR) and Light Emitting Diodes (LED). The principle of colorimetric is used to monitor and analyze the nutrients present in the soil. The data sensed by the designed NPK sensor from the selected agricultural fields are sent to Google cloud database to support fast retrieval of data. The concept of fuzzy logic is applied to detect the deficiency of nutrients from the sensed data. The crisp value of each sensed data is discriminated into five fuzzy values namely very low, low, medium, high and very high during fuzzification. A set of If-then rules are framed based on individual chemical solutions of Nitrogen (N), Phosphorous (P) and Potassium (K). Mamdani inference procedure is used to derive the conclusion about the deficiency of N, P and K available in soil chosen for testing and accordingly an alert message is sent to the farmer about the quantity of fertilizer to be used at regular intervals. The proposed hardware prototype and the software embedded in the microcontroller are developed in Raspberry pi 3 using Python. The developed model is tested in three different soil samples like red soil, mountain soil and desert soil. It is observed that the developed system results in linear variation with respect to the concentration of the soil solution. A sensor network scenario is created using Qualnet simulator to analyze the performance of designed NPK sensor in terms of throughput, end to end delay and jitter. From the different variety of experiments conducted, it is noticed that the developed IoT system is found to be helpful to the farmers for high yielding of crops.
Exploring novel computational methods in making sense of biological data has not only been a necessity, but also productive. A part of this trend is the search for more efficient in silico ...methods/tools for analysis of promoters, which are parts of DNA sequences that are involved in regulation of expression of genes into other functional molecules. Promoter regions vary greatly in their function based on the sequence of nucleotides and the arrangement of protein-binding short-regions called motifs. In fact, the regulatory nature of the promoters seems to be largely driven by the selective presence and/or the arrangement of these motifs. Here, we explore computational classification of promoter sequences based on the pattern of motif distributions, as such classification can pave a new way of functional analysis of promoters and to discover the functionally crucial motifs. We make use of Position Specific Motif Matrix (PSMM) features for exploring the possibility of accurately classifying promoter sequences using some of the popular classification techniques. The classification results on the complete feature set are low, perhaps due to the huge number of features. We propose two ways of reducing features. Our test results show improvement in the classification output after the reduction of features. The results also show that decision trees outperform SVM (Support Vector Machine), KNN (K Nearest Neighbor) and ensemble classifier LibD3C, particularly with reduced features. The proposed feature selection methods outperform some of the popular feature transformation methods such as PCA and SVD. Also, the methods proposed are as accurate as MRMR (feature selection method) but much faster than MRMR. Such methods could be useful to categorize new promoters and explore regulatory mechanisms of gene expressions in complex eukaryotic species.
Histopathological image classification is one of the important application areas of medical imaging. However, an accurate and efficient classification is still an open-ended research due to the ...complexity in histopathological images. For the same, this paper presents an efficient architecture of convolutional neural network for the classification of histopathological images. The proposed method consists of five subsequent blocks of layers, each having convolutional, drop-out, and max-pooling layers. The performance of the introduced classification system is validated on colorectal cancer histology image dataset which consists of RGB-colored images belonging to eight different classes. The experimental results confirm the higher performance of the proposed convolutional neural network against existing different machine learning models with the lowest error rate of 22.7%.
Vigna
is a large, pan-tropic and highly variable group of the legumes family which is known for its > 10 cultivated species having significant commercial value for their nutritious grains and ...multifarious uses. The wild
vignas
are considered a reservoir of numerous useful traits which can be deployed for introgression of resistance to biotic and abiotic stresses, seed quality and enhanced survival capability in extreme environments. Nonetheless, for their effective utilization through introgression breeding information on their genetic diversity, population structure and crossability is imperative. Keeping this in view, the present experiment was undertaken with 119 accessions including 99 wild
Vigna
accessions belonging to 19 species and 18 cultivated genotypes of
Vigna
and 2 of
Phaseolus
. Total 102 polymorphic SSRs were deployed to characterize the material at molecular level which produced 1758 alleles. The genotypes were grouped into four major clusters which were further sub-divided in nine sub-clusters. Interestingly, all cultivated species shared a single cluster while no such similarities were observed for the wild accessions as these were distributed in different groups of sub-clusters. The co-dominant allelic data of 114 accessions were then utilized for obtaining status of the accessions and their hybrid forms. The model-based population structure analysis categorized 114 accessions of
Vigna
into 6 genetically distinct sub-populations (
K
= 6) following admixture-model based simulation with varying levels of admixture. 91 (79.82%) accessions resembled their hierarchy and 23 (20.18%) accessions were observed as the admixture forms. Maximum number of accessions (25) were grouped in sub-population (SP) 6 and the least accessions were grouped in SP3 and SP5 (11 each). The population genetic structure, therefore, supported genetic diversity analysis and provided an insight into the genetic lineage of these species which will help in effective use of germplasm for development of cultivars following selective prebreeding activities.
Purpose: To assess patient experience of intravitreal injections using vital-signs, visual-experience, pain-rating and emotional response during intravitreal anti-VEGF injections. Methods: A ...prospective observational study of patient experience of intravitreal anti-VEGF injections done following metrics were collected pre-injection, during injection, and post-injection: pain assessment using visual analog score, fear-response rating, visual-experience questionnaire, and vital-signs. Results: A total of one-hundred-and-seventy-four patients undergoing intravitreal anti-VEGF injections for retinal pathologies were included in the study. Mean age was 58.8 ± 10.4 years in <5 injection group (n = 133) and 59.02 ± 9.0 years in ≥5 injection group (n = 41) (P = 0.90).During injection, 90.2% of patients in <5 injection group reported moderate or severe pain compared to 78% of patients in ≥5 injection group. In pre and post-injection phases, mild-to-moderate pain was reported in both groups (P = <0.001). Ninety-two (52.9%) patients reported having a mild frightening experience. There was no statistical significance in patients assessment of fear with respect to age, sex, or number of injections. The Systolic Blood Pressure (SBP) during and following injection ((SBP 171.7 ± 21.1,150.8 ± 16.2) procedures was significantly higher in cases with <5 injections when comparing to cases with >5 injections (SBP 159.7 ± 26.4, 143.2 ± 17.0) (P = 0.003), (P = 0.011). DBP, heart rate, pulse rate measurements were similar among patients in all phases of the study. Conclusion: We report a large sample size with comprehensive assessments of the patient experience. Higher pain ratings in the <5 injection group, the increase in the SBP in the pre-and during injection phases, and the overall rating of mild-to-moderate fear during the procedure.
To describe pediatric mental health emergency department (ED) visit rates and visit characteristics before and during the COVID-19 pandemic.
We conducted a cross-sectional study of ED visits by ...children 5–17 years old with a primary mental health diagnosis from March 2018 to February 2021 at a 10-hospital health system and a children's hospital in the Chicago area. We compared demographic and clinical characteristics of children with mental health ED visits before and during the pandemic. We conducted an interrupted time series analysis to determine changes in visit rates.
We identified 8,127 pediatric mental health ED visits (58.5% female, 54.3% White, Not Hispanic/Latino and 42.4% age 13–15). During the pandemic, visits for suicide or self-injury increased 6.69% (95% CI 4.73, 8.65), and visits for disruptive, impulse control, conduct disorders increased 1.94% (95% CI 0.85, 3.03). Mental health ED visits by children with existing mental health diagnoses increased 2.29% (95% CI 0.34, 4.25). Mental health ED visits that resulted in medical admission increased 4.32% (95% CI 3.11, 5.53). The proportion of mental health ED visits at community hospitals increased by 5.49% (95% CI 3.31, 7.67). Mental health ED visit rates increased at the onset of the pandemic (adjusted incidence rate ratio aIRR 1.27, 95% CI 1.06, 1.50), followed by a monthly increase thereafter (aIRR 1.04, 95% CI 1.02, 1.06).
Mental health ED visit rates by children increased during the COVID-19 pandemic. Changes in mental health ED visit characteristics during the pandemic may inform interventions to improve children's mental health.
Water quality prediction using CNN Vijay Anand, M; Sohitha, Chennareddy; Saraswathi, Galla Neha ...
Journal of physics. Conference series,
05/2023, Letnik:
2484, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Abstract
The interaction of solar radiation with the water level concentration and the elements of the water cause the water to have its characteristic hue. The alteration of the color of the water ...is reflective of the alteration of the water’s properties and the degree to which it is suitable for use. Due to disasters like floods, tsunami in the last few years and water pollution has been an increasing problem. In world the intake of contaminated water causes 40% of deaths. Drinking unclean water is not safe and in order to reduce the issue to a level of extent, prediction of water quality can be done before consuming. The process used in water plants is based on the parameters pH, turbidity, temperature, hardness etc., of water using filtration and the water quality prediction can also be done using IOT by including both hardware and software. This project mainly comprises the primary level of water prediction using machine learning. Based on the color and quality of water the system predicts whether the given water sample is suitable for drinking or any further use. Tensorflow, Keras and CNN are used to train the model to forecast the water quality prediction. This project is cost-effective and works efficiently and can be used as immediate and initial level of water quality check since image processing tool is used. This model of water quality prediction can be checked using mobile captured and Google earth images of water samples.
Purpose: An undergraduate research conducted during the pre-covid times, to highlight the importance of screen time and its association with dry eye in medical students. The aim was to study the ...prevalence of dry eye among medical students using the ocular surface index (OSDI) questionnaire. Methods: This was a cross-sectional study. This study was conducted among medical students using an OSDI questionnaire in the pre-covid times. Based on the pilot study, the minimum sample size calculated was 245. A total of 310 medical students participated in the study. These medical students answered the OSDI questionnaire. The OSDI score was used to categorize students with dry eye as mild (13-22 points), moderate (23-32 points), and severe (33-100 points). In addition, the associations between the OSDI score and possible risk factors such as gender, contact lens/spectacle wear, laptop/mobile usage, and duration of exposure to air conditioners were also studied. Results: The analysis of the study revealed that out of 310 students, dry eye was seen in 143 (46.1%) and severe dry eyes were seen in 50 (16.1%). A high OSDI score (>13 points) was associated with the usage of a laptop/mobile for more than 6 h in 40 (52.6%) (P < 0.001). Conclusion: The prevalence of dry eye among medical students was 46.1% in the present study. Longer duration of usage of visual display units (laptop/mobile) was the only factor that showed a statistically significant association with dry eye in our study.
Metal cutting researchers attempt to develop technology for metal cutting and use of cutting fluids have been continuous due to increasing demands for high productivity. This work reports on the ...effect of coconut oil under minimum quantity lubrication (MQL) during end milling of AL7049. Dry, wet and MQL approaches are all used to conduct the experimental studies. In contrast to dry and wet machining, it is apparent that MQL generates surfaces with less roughness. A multilayer perceptron (MLP) prediction model was developed considering the real-time dataset with three inputs, and an output that led to prediction of surface roughness. It was analyzed to determine the appropriate activation function and observed that ReLU activation function outpaces sigmoid and tanh and adapted to the proposed solution. K fold cross-validation was done for the developed MLP model with backpropagation to substantiate high accuracy in predictions than KNN and linear regression. The MQL will be good alternative to wet machining and also environmentally friendly machining solution.
Cervical cancer is one of the most common cancers in developing nations. It has had a tremendous impact on the lifetime of millions of women over the last century and continues to do so. In this ...collaborative clinicians' review, we highlight the incidence, treatment and clinical outcomes of cervical cancer in low-income (LICs) and low- and middle-income countries (LMICs) across Asia, South America, South Africa and Eastern Europe. With the cervical cancer burden and locally advanced cancers being high, the majority of LICs/LMICs have been striving to adhere to optimal evaluation and treatment guidelines. However, the huge gap in resource availability, rural versus urban disparity and access to resources have led to poor compliance to evaluation, treatment and post-treatment rehabilitation. To mitigate the overwhelming numbers, various treatment strategies like neoadjuvant chemotherapy, hypofractionation radiation schedules (both external and brachytherapy) have been attempted with no major success. Also, the compliance to concurrent chemoradiation in various regions is a major challenge. With the burden of advanced cancers, the lack of palliative care services and their integration in cancer care is still a reality.