A5086102761- Advanced Neural Network Applications
- Digital Imaging for Blood Diseases
- COVID-19 diagnosis using AI
- Advanced Memory and Neural Computing
- Smart Agriculture and AI
- AI in cancer detection
- Anomaly Detection Techniques and Applications
- Machine Learning and ELM
- Retinal Imaging and Analysis
- Brain Tumor Detection and Classification
- Advanced Malware Detection Techniques
- Imbalanced Data Classification Techniques
- Network Security and Intrusion Detection
- Neural Networks Stability and Synchronization
- stochastic dynamics and bifurcation
- Retinal and Optic Conditions
- Spectroscopy and Chemometric Analyses
- Currency Recognition and Detection
- Sugarcane Cultivation and Processing
- Music Technology and Sound Studies
- Misinformation and Its Impacts
- Artificial Intelligence in Healthcare
- Optical Coherence Tomography Applications
- Sentiment Analysis and Opinion Mining
- Vehicle License Plate Recognition
University of Energy and Natural Resources
2022-2024
University of Electronic Science and Technology of China
2019-2023
China University of Petroleum, East China
2021
Activation functions facilitate deep neural networks by introducing non-linearity to the learning process. The feature gives network ability learn complex patterns. Recently, most widely used activation function is Rectified Linear Unit (ReLU). Though, other various existing including hand-designed alternatives ReLU have been proposed. However, none has succeeded in replacing due their inconsistencies. In this work, called ReLUMemristor-like Function (RMAF) proposed leverage benefits of...
Artificial Intelligence (AI) has been evident in the agricultural sector recently. The objective of AI agriculture is to control crop pests/diseases, reduce cost, and improve yield. In developing countries, faces numerous challenges form knowledge gap between farmers technology, disease pest infestation, lack storage facilities, among others. order resolve some these challenges, this paper presents pests/disease datasets sourced from local farms Ghana. dataset presented two folds; raw images...
Abstract This paper proposes a new dual horizontal squash capsule network (DHS‐CapsNet) to classify the lung and colon cancers on histopathological images. DHS‐CapsNet is made up of encoder feature fusion (EFF) novel (HSquash) function. The EFF aggregates extracted from 2‐lane convolutional layers, which provides rich information for better accuracy. HSquash proposed as function ensure that vectors are effectively squashed produces sparsity high discriminative extract important images with...
Brain tumor recently is considered among the deadliest cancers according to research statistics and have several categories, based on different characteristics of tumor. Early detection types help devise treatment plans achieve high survival rate. Human inspection noted be cost effective, error prone time-consuming, which led interest in Convolutional Neural Networks (CNNs) automatize problem. However, CNNs fail consider precise location features as beneficial, harmful, because its...
This article is concerned with the exponential synchronization of coupled memristive neural networks (CMNNs) multiple mismatched parameters and topology-based probability impulsive mechanism (TPIM) on time scales. To begin with, a novel model designed by taking into account three types parameters, including: 1) dimensions; 2) connection weights; 3) time-varying delays. Then, method auxiliary-state variables adopted to deal model, which implies that presented can not only use any isolated...
The work of the Ophthalmologist in manually detecting specific eye related disease is challenging especially screening through large volume dataset. Deep learning models can leverage on medical imaging like retina Optical Coherence Tomography (OCT) image dataset to help with classification task. As a result, many solutions have been proposed based deep learning-based convolutional neural networks (CNNs). However, limitations such as inability recognize pose, pooling operations which affect...
Abstract Capsule network's hierarchical framework (CapsNets) consists of an initial standard convolution layer that uses activation function at its core. The rectified linear unit (ReLU) is widely used in CapsNet and brain tumor classification tasks among several existing functions. However, ReLU has some shortcomings where the zero derivatives cause failure neuron activation. Furthermore, performance accuracy obtained by with on unsatisfactory. We proposed a new called parametric scaled...
This article investigates the problem of relaxed exponential stabilization for coupled memristive neural networks (CMNNs) with connection fault and multiple delays via an optimized elastic event-triggered mechanism (OEEM). The two or some nodes can result in other cause iterative faults CMNNs. Therefore, method backup resources is considered to improve fault-tolerant capability survivability In order robustness enhance ability process noise signals, time-varying bounded threshold matrices,...
Convolutional neural networks (CNNs) for automatic classification and medical image diagnosis have recently displayed a remarkable performance. However, the CNNs fail to recognize original images rotated oriented differently, limiting their This paper presents new capsule network (CapsNet) based framework known as multi-lane atrous feature fusion (MLAF-CapsNet) brain tumor type classification. The MLAF-CapsNet consists of CLAHE, where increases receptive fields maintains spatial...
Availability of massive amounts data is a key contributing factor that influences the performance deep learning models. Convolutional Neural Networks for instance, require large in different variations to enable them generalize well viewpoints. However, health and other application domains, generation processing tasks are time-consuming requires annotation by experts. Capsule Network (CapsNet) have been proposed curtail limitations (CNNs). Due problem crowding, capsule perform badly on...
Government policies face challenges whenever it is implemented or proposed. The ordinary Ghanaian always feels the down side of government policies. This paper ponders on Ghana proposed electronic levy mobile money transactions which was announced in 2022 budget November 17, 2021. Using concept sentiment analysis and Twitter data, we have carefully studied this policy from perspective citizen. Aside conducting a non-bias examination, full data has also been performed to further expound...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Hyperspectral imaging, combined with deep learning techniques, has been employed to classify maize. However, the implementation of these automated methods often requires substantial processing and computing resources, presenting a significant challenge for deployment on embedded devices due high GPU power consumption. Access Ghanaian local maize data such classification tasks is also extremely difficult in Ghana. To address challenges, this research aims create simple dataset comprising...
Capsule Networks have shown great promise in image recognition due to their ability recognize the pose, texture, and deformation of objects object parts. However, majority existing capsule networks are deterministic with limited express uncertainty. Many them tend be overconfident on out-of-distribution data, making less trustworthy hence reducing suitability for practical adoption safety-critical areas such as health self-driving cars. In this work, we propose a network based variational...
The squash function in capsule networks (CapsNets) dynamic routing is less capable of performing discrimination non-informative capsules which leads to abnormal activation value distribution capsules. In this paper, we propose vertical (VSquash) improve the original by preventing values primary layer shrink capsules, promote discriminative and avoid high information sensitivity. Furthermore, a new neural network, (i) skip-connected convolutional (S-CCCapsule), (ii) Integrated (ISCC) (iii)...
This paper highlights a hybrid static classifier based on CNN and bi-directional LSTM for malware classification tasks in the IoT. Our approach learns takes note of nature complex patterns Byte Assemble files represented one-dimensional images better feature extraction. is employed automatic selection Furthermore, extracted features are forwarded to classification. Extensive experiments were performed using Microsoft datasets. Experimental results show that our HCL-Classifier achieves...