Neuromorphic computing spiking neural network edge detection model for content based image retrieval.

In contemporary times, content-based image retrieval (CBIR) techniques have gained widespread acceptance as a means for end-users to discern and extract specific image content from vast repositories. However, it is noteworthy that a substantial majority of CBIR studies continue to rely on linear methodologies such as gradient-based and derivative-based edge detection techniques. This research explores the integration of bioinspired Spiking Neural Network (SNN) based edge detection within CBIR. We introduce an innovative, computationally efficient SNN-based approach designed explicitly for CBIR applications, outperforming existing SNN models by reducing computational overhead by 2.5 times. The proposed SNN-based edge detection approach is seamlessly incorporated into three distinct CBIR techniques, each employing conventional edge detection methodologies including Sobel, Canny, and image derivatives. Rigorous experimentation and evaluations are carried out utilizing the Corel-10k dataset and crop weed dataset, a widely recognized and frequently adopted benchmark dataset in the realm of image analysis. Importantly, our findings underscore the enhanced performance of CBIR methodologies integrating the proposed SNN-based edge detection approach, with an average increase in mean precision values exceeding 3%. This study conclusively demonstrated the utility of our proposed methodology in optimizing feature extraction, thereby establishing its pivotal role in advancing edge centric CBIR approaches.

Investigating the performance of a perforated pooled circular stepped cascade aeration system for intensive aquaculture.

Aeration plays a crucial role in aquaculture to maintain adequate dissolved oxygen (DO) levels in water, which is essential for supporting aquatic life. However, traditional aeration systems such as paddlewheel aerators or diffused air aerators often come with high energy consumption, frequent maintenance, and greater operational costs. To address these challenges, this research paper presents the development and evaluation of a more sustainable and cost-effective aerator, named the perforated pooled circular stepped cascade aerator (PPCSC), for intensive aquaculture. Laboratory experiments were conducted in a masonry tank to assess the performance of the PPCSC aerator with different bottom radii (Rb) and discharges (Q). The results showed that the highest standard aeration efficiency (SAE) of 4.564 ± 0.6662 kg O2/kWh was achieved with a bottom radii (Rb) of 0.75 m and a discharge (Q) of 0.016 m3/s. A developed regression model was found to effectively evaluate the standard oxygen transfer rate (SOTR) and SAE for different Rb and Q values used in the PPCSC system. Both Rb and Q were found to significantly impact the SOTR and SAE of the PPCSC aerator. Overall, the PPCSC aerator is a promising option for small-scale tank-based intensive aquaculture due to its high performance and lower operational costs.

Prediction of viscoelastic properties of peanut-based 3D printable food ink.

Viscoelastic properties of 3D printable peanut-based food ink were investigated using frequency sweep and relaxation test. The incorporation of xanthan gum (XG) improved the shear thinning behavior (n value ranging from 0.139 to 0.261) and lowered the η*, G', and G'' values, thus making food ink 3D printable. The addition of XG also caused a downward shift in the relaxation curve. This study evaluates the possibility of an artificial neural network (ANN) approach as a substitute for the Maxwell three-element and Peleg model for predicting the viscoelastic behavior of food ink. The results revealed that all three models accurately predicted the decay forces. The inclusion of XG decreased the hardness and enhanced the cohesiveness, so enabling the 3D printing of food ink. The hardness was highly positively correlated with Maxwell model parameters Fe , F1 , F2 , F3, and Peleg constant k2 (0.57) and negatively correlated with k1 (-0.76).

Detection of Coconut Clusters Based on Occlusion Condition Using Attention-Guided Faster R-CNN for Robotic Harvesting.

Manual harvesting of coconuts is a highly risky and skill-demanding operation, and the population of people involved in coconut tree climbing has been steadily decreasing. Hence, with the evolution of tree-climbing robots and robotic end-effectors, the development of autonomous coconut harvesters with the help of machine vision technologies is of great interest to farmers. However, coconuts are very hard and experience high occlusions on the tree. Hence, accurate detection of coconut clusters based on their occlusion condition is necessary to plan the motion of the robotic end-effector. This study proposes a deep learning-based object detection Faster Regional-Convolutional Neural Network (Faster R-CNN) model to detect coconut clusters as non-occluded and leaf-occluded bunches. To improve identification accuracy, an attention mechanism was introduced into the Faster R-CNN model. The image dataset was acquired from a commercial coconut plantation during daylight under natural lighting conditions using a handheld digital single-lens reflex camera. The proposed model was trained, validated, and tested on 900 manually acquired and augmented images of tree crowns under different illumination conditions, backgrounds, and coconut varieties. On the test dataset, the overall mean average precision (mAP) and weighted mean intersection over union (wmIoU) attained by the model were 0.886 and 0.827, respectively, with average precision for detecting non-occluded and leaf-occluded coconut clusters as 0.912 and 0.883, respectively. The encouraging results provide the base to develop a complete vision system to determine the harvesting strategy and locate the cutting position on the coconut cluster.

Economic feasibility study of aerators in aquaculture using life cycle costing (LCC) approach.

Selection of aerator is a very important aspect in aquaculture operations. The selected aerator must be economically efficient and should be able to fulfil the requirement of oxygen supply in the pond water. In the present study, economic feasibility of nine different types of aerators, namely, perforated pooled circular stepped cascade (PPCSC), pooled circular stepped cascade (PCSC), circular stepped cascade (CSC), paddle wheel (PWA), spiral aerator (SA), propeller-aspirator-pump (PAA), submersible (SUBA), impeller aerator (IA) and air-jet aerator (AJA) was assessed based on capitalization method, a life cycle costing (LCC) approach. The results revealed that the PPCSC aerator can be considered as the most suitable aerator when dissolved oxygen (DO) content in the pond water is less than equal to 3 mg/L, and pond water volume (V) is less than 2100 m3. In other situations, mostly when pond water volume is more, IA proves to be the most suitable aerator, followed by PWA, PPCSC, and other available aerators. The sensitivity analysis conducted by using varying stocking density and capital cost also showed the same trend with regard to selection of aerators. This life cycle costing approach for selection of aerator can be implemented for any types of cultured species at any prevailing environmental conditions.