LPNet: A lightweight CNN with discrete wavelet pooling strategies for colon polyps classification

The traditional process of disease diagnosis from medical images follows a manual process, which is tedious and arduous. A computer-aided diagnosis (CADs) system can work as an assistive tool to improve the diagnosis process. In this pursuit, this article introduces a unique architecture LPNet for classifying colon polyps from the colonoscopy video frames. Colon polyps are abnormal growth of cells in the colon wall. Over time, untreated colon polyps may cause colorectal cancer. Different convolutional neural networks (CNNs) based systems have been developed in recent years. However, CNN uses pooling to reduce the number of parameters and expand the receptive field. On the other hand, pooling results in data loss and is deleterious to subsequent processes. Pooling strategies based on discrete wavelet operations have been proposed in our architecture as a solution to this problem, with the promise of achieving a better trade-off between receptive field size and computing efficiency. The overall performance of this model is superior to the others, according to experimental results on a colonoscopy dataset. LPNet with bio-orthogonal wavelet achieved the highest performance with an accuracy of 93.55%. It outperforms the other state-of-the-art (SOTA) CNN models for the polyps classification task, and it is lightweight in terms of the number of learnable parameters compared with them, making the model easily deployable in edge devices.     

Machinability and surface morphology investigations of multiwall carbon nanotube reinforced aluminium 7075 metal matrix composite during electrical discharge machining: A grey relational approach

Multiwall carbon nanotube buttressed aluminium 7075 metal matrix composite was synthesized through an amended liquid metallurgy method, which consisted semisolid stirring, ultrasonic treatment and squeeze casting. Aim was to investigate its machinability and surface morphology during electrical discharge machining. Variable machining factors were peak current, pulse-on time and gap voltage, whereas the responses under investigation were electrode wear rate, material removal rate and average surface roughness. Results revealed electrode wear rate, material wear rate and average surface roughness increased on increasing peak current and pulse-on time, but all these responses behaved inversely with the increase of gap voltage. Average surface roughness reduced by around 44 % on reducing the peak current from 10 A to 4 A and increasing gap voltage from 55 V to 80 V at constant pulse-on time of 300 μs; however, it increased by around 25 % on reducing the gap voltage from 80 V to 55 V and increasing the pulse-on time from 100 μs to 300 μs at constant peak current of 10 A. Significance of the process parameters were verified, regression models were developed and morphology of the machined surfaces was studied. Finally, multiple response optimization was conducted following grey relational approach.     

Early Skin Disease Identification Using eep Neural Network

Skin lesions detection and classification is a prominent issue and difficult even for extremely skilled dermatologists and pathologists. Skin disease is the most common disorder triggered by fungus, viruses, bacteria, allergies, etc. Skin diseases are most dangerous and may be the cause of serious damage. Therefore, it requires to diagnose it at an earlier stage, but the diagnosis therapy itself is complex and needs advanced laser and photonic therapy. This advance therapy involves financial burden and some other ill effects. Therefore, it must use artificial intelligence techniques to detect and diagnose it accurately at an earlier stage. Several techniques have been proposed to detect skin disease at an earlier stage but fail to get accuracy. Therefore, the primary goal of this paper is to classify, detect and provide accurate information about skin diseases. This paper deals with the same issue by proposing a high-performance Convolution neural network (CNN) to classify and detect skin disease at an earlier stage. The complete methodology is explained in different folds: firstly, the skin diseases images are pre-processed with processing techniques, and secondly, the important feature of the skin images are extracted. Thirdly, the pre-processed images are analyzed at different stages using a Deep Convolution Neural Network (DCNN). The approach proposed in this paper is simple, fast, and shows accurate results up to 98% and used to detect six different disease types.     

Position-only planar hexagonal array antenna pattern nulling with simultaneous side lobe reduction at multiple azimuth planes

This article presents a study on the placement of multiple nulls as well as minimization of side lobe level in the radiation pattern using a planar hexagonal antenna array structure in two different vertical planes. The desired null depth is achieved to suppress the interference signal by the position-only control of the uniformly excited isotropic antennas in the array structure. The immediate solution to the mentioned computational problem is reached by various meta-heuristic optimization algorithms such as teaching learning-based optimization (TLBO), symbiotic organism search (SOS), and moth fly optimization (MFO) within a considerably reduced processing time with a control over the design constrains. Various examples for diversified scenarios are demonstrated to place multiple deep nulls in the radiation pattern without compromising the pattern constraints and all other radiation pattern characteristics. This experiment sought to illustrate and quantify the unique benefits and limitations of proposed technique using three considered meta-heuristic optimization algorithm.