various concentrated work on detection of defects printed circuit boards (PCBs) have been done, but it is also crucial to classify these in order analyze and identify the root causes defects. This project aimed detecting classifying bare single layer PCBs by introducing a hybrid algorithm combining research done Heriansyah et al [1] Khalid [2]. proposes PCB defect classification system using morphological image segmentation simple processing theories Based initial studies, some can only...

Fruit recognition is useful for automatic fruit harvesting. application can reduce or minimize human intervention during harvesting operation. However, in computer vision, very challenging because of similar shapes, colors and textures among various fruits. Illuminations changes due to weather condition also leads a task recognition. Thus, this paper tends investigate the performance basic Convolutional Neural Network (CNN), Alexnet Googlenet recognizing nine different types fruits from...

This research investigates the application of texture features for leaf recognition herbal plant identification. Malaysia is rich with plants but not many people can identify them and know about their uses. Preservation knowledge these herb important since it enables general public to gain useful which they apply whenever necessary. Leaf image chosen available visible all time. Unlike flowers that are always or roots easy obtain, most abundant type data in botanical reference collections. A...

<span lang="EN-GB">Skin disease has lower impact on mortality compared to others but instead it greater effect quality of life because involves symptoms such as pain, stinging and itchiness. Psoriasis is one the ordinary skin diseases which are relapsing, chronic immune-mediated inflammatory disease. It estimated about 125 million people worldwide being infected with various types infection. </span><span lang="EN-GB">Challenges arise when patients only predict type they had...

Diabetic Retinopathy (DR) is a disease that causes visual impairment and blindness in patients with it. appears characterized by condition of swelling leakage the blood vessels located at back retina eye. Early detection through retinal fundus image eye could take time requires an experienced ophthalmologist. This study proposed deep learning method, Efficientnet-b7 model to identify diabetic retinopathy automatically. applies three preprocessing techniques be implemented dataset "APTOS 2019...

Magnetic Resonance Imaging (MRI) is a body sensing technique that can produce detailed images of the condition organs and tissues. Specifically related to brain tumors, resulting be analyzed using image detection techniques so tumor stages classified automatically. Detection tumors requires high level accuracy because it effectiveness medical actions patient safety. So far, Convolutional Neural Network (CNN) or its combination with GA has given good results. For this reason, in study, we...

The advantage of deep learning is that the analysis and massive amounts unsupervised data make it a beneficial tool for Big Data analysis. Convolution Neural Network (CNN) method can be used to classify image, cluster them by similarity, perform image recognition in scene. This paper conducts comparative study between three models, which are simple-CNN, AlexNet GoogLeNet Roman handwritten character using Chars74K dataset. produced results indicate GooleNet achieves best accuracy but requires...

<span lang="EN-US">Maize is one of the world's leading food supplies. Therefore, crop's production must continue to reproduce fulfill market demand. Maize an active feeder, therefore, it need be adequately supplied with nutrients. The healthy plants will in deep green color indicate consist adequate nutrient. Current practice identify nutrient deficiency on maize leaf throught a laboratory test. It time consuming and required agriculture knowledge. image processing approach has been...

This paper investigates the application of deep Convolutional Neural Network (CNN) for herbal plant recognition through leaf identification. Traditional identification is often time-consuming due to varieties as well similarities possessed within species. study shows that a CNN model can be created and enhanced using multiple parameters boost accuracy performance. also significant effects multi-layer on small sample sizes achieve reasonable Furthermore, data augmentation provides more...

Betta fish sellers and breeders often face challenges in accurately identifying species due to variations colors, patterns, shapes, leading potential financial losses deceptive transactions. To address this issue, we developed a mobile application that employs MobileNet, deep learning (DL) technique, classify species. The dataset, acquired from online stores, comprises 400 images, with 100 images representing each of the four studied species: comb tail, delta spade veil tail. Prior model...

Face recognition is one of the well studied problems by researchers in computer visions. Among challenges this task are occurrence different facial expressions like happy or sad, and views images such as front side views. This paper experiments a publicly available dataset that consists 200,000 celebrity faces. Deep Learning technique gaining its popularity vision applies for face problem. One techniques under deep learning Convolutional Neural Network (CNN). There also pre-trained CNN...

This paper investigates the application of eight color models for automatic palm oil Fresh Fruit Bunch (FFB) ripeness classification with multi-class Support Vector Machine (SVM). Ripeness is important during harvesting to ensure that they are harvested correct ripe stage optimum production. Since a significant indicator agriculturists determine FFB, it critical right model. Eight have been investigated namely, HSV, I1I2I3, LAB, XYZ, YCbCr, YIQ, YUV and RGB. Color moments were extracted from...

This paper presents a comparative study between Bag of Features (BoF), Conventional Convolutional Neural Network (CNN) and Alexnet for fruit recognition. Automatic recognition can minimize human intervention in their harvesting operations, operation time cost. On the other hand, this task is very challenging because similarities shapes, colours textures among various types fruits. Thus, robust technique that produce good result necessary. Due to outstanding performance deep learning like CNN...

Herbs are an important nutritional source for humans since they provide a variety of nutrients. Indigenous people have employed herbs, in particular, as traditional medicines ancient times. Malaysia has hundreds plant species; herb detection may be difficult due to the species and their shape color similarities. Furthermore, there is scarcity support datasets detecting these plants. The main objective this paper investigate performance convolutional neural network (CNN) on Malaysian...

Predicting students’ academic performance is critical for educational institutions because strategic programs can be planned in improving or maintaining during their period of studies the institutions. The this study measured by cumulative grade point average (CGPA) upon graduating. In study, demographic profile and CGPA first semester undergraduate are used as predictor variable under-graduate degree program. Three predictive models have been developed, namely, logistic regression,...

This paper presents flower and leaf recognition for plant identification using Convolutional Neural Network (CNN). In this study, the performance of CNN images leaves, flowers a combination both are investigated. Two publicly available datasets, namely Folio dataset Flower Recognition dataset, have been used training testing purposes. has proven to produce excellent results object but its can still be influenced by type number layers architecture. Experimental indicate that utilization only...

Course timetabling problem is common in schools and higher learning institutions. Courses must be allocated to teachers/lecturers, students, timeslots venues without violating a set of predefined constraints determined by the respective institution. The complex due different requirements institutions process finding solution can lengthy time-consuming. This paper presents our research findings on implementing bipartite graph edge coloring approach solving course problem. data used this study...

This paper aims to evaluate the accuracy performance of pre-trained Convolutional Neural Network (CNN) models, namely AlexNet and GoogLeNet accompanied by one custom CNN. have been proven for their good capabilities as these network models had entered ImageNet Large Scale Visual Recognition Challenge (ILSVRC) produce relatively results. The evaluation results in this research are based on accuracy, loss time taken training validation processes. dataset used is Caltech101 California Institute...

Due to the increasing crime rate in Malaysia, safety and security need be robust from intruders. Numerous biometric-based technologies are offered but they not friendly less accurate. Among available biometric technology, face recognition is friendliest among all technology. Hence, aim of this research identify best classifier for using facial geometry distance measure. A comparison between Support Vector Machine (SVM), Multi Linear Perceptron (MLP) Naive Bayes classifiers conducted...

This paper evaluates two deep learning techniques that are basic Convolutional Neural Network (CNN) and AlexNet along with a classical local descriptor is Bag of Features (BoF) Speeded-Up Robust Feature (SURF) Support Vector Machine (SVM) classifier for indoor object recognition.A publicly available dataset, MCIndoor20000, has been used in this experiment consists doors, signage, stairs images Marshfield Clinic.Experimental results indicate achieves the highest accuracy followed by CNN...

This paper discusses the performance of four popular machine learning techniques for predicting heart failure using a publicly available dataset from kaggle.com, which are Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB), and Logistic Regression (LR). They were selected due to their good in medical-related applications. Heart is common public health problem, there need improve management cases increase survival rate. The vast amount medical data related availability...

This research compares the recognition performance between pre-trained models, GoogLeNet and AlexNet, with basic Convolution Neural Network (CNN) for leaf recognition. Lately, CNN has gained a lot of interest in image processing applications. Numerous models have been introduced most popular are AlexNet. Each model its own layers convolution computational complexity. A great success achieved using these classification computer vision this investigates their performances MalayaKew (MK), an...