Search results

The advancements of deep learning (DL) models demonstrate significant performance on accurate pancreatic tumor segmentation and classification.

The presented model involves different stages of operations, namely preprocessing, image segmentation, feature extraction and image classification. Primarily, bilateral filtering (BF) technique is applied for image preprocessing to eradicate the noise present in the CT pancreatic image. Besides, noninteractive GrabCut (NIGC) algorithm is applied for the image segmentation process. Subsequently, residual network 152 (ResNet152) model is utilized as a feature extractor to originate a valuable set of feature vectors. At last, the red deer optimization algorithm (RDA) tuned backpropagation neural network (BPNN), called RDA-BPNN model, is employed as a classification model to determine the existence of pancreatic tumor.

The experimental results are validated in terms of different performance measures and a detailed comparative results analysis ensured the betterment of the RDA-BPNN model with the sensitivity of 98.54%, specificity of 98.46%, accuracy of 98.51% and F-score of 98.23%.

The study also identifies several novel automated deep learning based approaches used by researchers to assess the performance of the RDA-BPNN model on benchmark dataset and analyze the results in terms of several measures.

One of the objectives of smart village is the efficient use of regional resources by local people to improve economic, social and environment conditions. Small-scale dairy farm (SDFs) exist in every village of India, contributing significantly to local economy and welfare of few families. The purpose of this work is to develop a mechanism to make SDF not only efficient but effective in operations.

A systems thinking approach is used to identify the variables influencing a SDF and develop a general framework – RAMHI (resources, alternate revenue, manpower, herd and infrastructure) comprising endogenous and exogenous variables. A representative SDF as a case study was chosen to implement RAMHI and assess its implementation feasibility and economic benefits.

Implementation of RAMHI gradually improves the economic benefits of a SDF. The key performing indicators like average milk produced/day; milk revenue/fodder cost; number of successful artificial insemination (AI) of herd/number of AI of herd; milking cow/dry cow; and milking cow/total cow, increased substantially in two successive years.

The literature reported and discussed individual variables influencing functioning of SDF while there are few conceptual frameworks proposed, comprising not more than three variables. This paper not only presents a comprehensive generalized framework – RAMHI, which comprises five variables like resources, alternate revenue, manpower, herd and infrastructure but also explains the implementation strategy and its benefits using a case study.