Image-based Quality Identification of Black Soybean (Glycine soja) Using Convolutional Neural Network

Indonesia is home to over 30,000 types of herbal plants, with approximately 1,200 species utilized as raw materials for alternative and traditional medicine. Leaves play a crucial role in herbal medicine preparation. However, many people struggle to identify different herbal leaves due to their similar appearances, making classification difficult. Each leaf possesses unique characteristics such as shape, size, midrib, stalk, blade, and type, which can be used for differentiation. To assist in identifying herbal leaves, a classification system based on image recognition is essential. Convolutional Neural Networks (CNN) are deep learning algorithms designed for processing two-dimensional image data. Model performance can be enhanced through transfer learning, with MobileNetV2 and ResNet50V2 being widely used architectures. These pretrained models have been trained to recognize images with high accuracy. This study focuses on classifying herbal plants based on leaf shape using CNN architectures from MobileNetV2 and ResNet50V2. The evaluation results show that the MobileNetV2 architecture, with a 90%:10% data split, achieved an accuracy of 98.51%, precision of 98.92%, recall of 98.51%, and an F1-score of 98.56%. These findings indicate that CNN with transfer learning can effectively classify herbal leaves with high accuracy.

Sign Language is the main communication medium for deaf people, in Indonesia itself there are several types of sign language, one of which is SIBI or Indonesian Sign Language System. This type of SIBI sign language is one type of sign language used in special school (SLB) environments. Deaf children are not yet able to use sign language and others have difficulty communicating with people around them. This research aims to help deaf children learn sign language, as well as help them communicate through sign language interpreters. The methodology applied to the application is by using a Convolutional Neural Network with the MobileNetV2 architecture. CNN is an algorithm that is included in the artificial neural network category which has the advantage of having a very high level of accuracy in classification, and MobileNetV2 is a form of Convolutional Neural Network (CNN) architecture that is able to overcome the need for excess computing resources created by Google researchers. so that it can be used on mobile devices or cell phones. The model training stage obtained an accuracy value of 98.99% with a total of 100 epochs. The model trained did not experience overfitting or underfitting so the model can be used. The testing stage uses black box testing to ensure the application is running correctly. The final stage is conducting research using TAM (Technology Acceptance Model) to measure the level of approval of the application using a Likert scale. Testing using black box testing was successful and met expectations, and the implementation of the application received an approval rate of 78.4% on average.

In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (RF) of CNNs is crucial to their generalization. An insufficient RF limits the CNN's ability to fit the training data. In contrast, CNNs with an excessive RF tend to over-fit the training data and fail to generalize to unseen testing data. As state-of-the-art CNN architectures - in computer vision and other domains - tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks. We study well-known CNN architectures and how their building blocks affect their receptive field. We propose several systematic approaches to control the RF of CNNs and systematically test the resulting architectures on different audio classification and tagging tasks and datasets. The experiments show that regularizing the RF of CNNs using our proposed approaches can drastically improve the generalization of models, out-performing complex architectures and pre-trained models on larger datasets. The proposed CNNs achieve state-of-the-art results in multiple tasks, from acoustic scene classification to emotion and theme detection in music to instrument recognition, as demonstrated by top ranks in several pertinent challenges (DCASE, MediaEval).

Recognition of human activity based on convolutional neural network has received the interest of researchers in recent years due to its significant improvement in accuracy. A large number of algorithms based on the deep learning approach have been proposed for activity recognition purpose. However, with the increasing advancements in technologies having limited computational resources, it needs to design an efficient deep learning-based approaches with improved utilization of computational resources. This paper presents a simple and efficient 2-Dimensional convolutional neural network (2-D CNN) architecture with very small size convolutional kernel for human activity recognition. The merit of the proposed CNN architecture over standard deep learning architectures is fewer trainable parameters and lesser memory requirement which enables it to train the proposed CNN architecture on low GPU memory-based devices and also works well with smaller as well as larger size datasets. The proposed approach consists of mainly four stages: namely (1) creation of dataset and data augmentation, (2) designing 2-D convolutional neural network (CNN) architecture, (3) the proposed 2-D CNN architecture trained from scratch up to optimum stage, and (4) evaluation of the trained 2-D CNN architecture. To illustrate the effectiveness of the proposed architecture several extensive experiments are conducted on three publicly available datasets, namely IXMAS, YouTube, and UCF101 dataset. The results of the proposed method and its comparison with other state-of-the-art methods [8-12,14,18-26,29-33] demonstrate the usefulness of the proposed method.

Every year, new Convolutional Neural Network (CNN) architectures appear to deal with different problems in the activity of image and video recognition. These architectures usually work along the ImageNet dataset for looking for the best performance of the CNNs without taking into account the video task where they are used. This can represent a problem if the task is Human Action Recognition (HAR) in video, since the CNN architectures are pre-trained with an image dataset that can practically contain any object, while HAR problem requires consecutive frames of people doing actions. To prove the idea that using CNNs pre-trained on an image dataset does not always achieve the best performance on a video dataset and that, therefore, it is worth comparing the performance of different CNNs under similar circumstances for the HAR problem, this work proposes an analysis between eight different CNN architectures. Each one of the CNN was exclusively trained with RGB images, which were extracted from the frames of the different classes of videos of HMDB51 dataset. To make the classification of an activity in video, we average the predictions taking into account the successes. We also made some ensembles with the best performance CNNs to measure the improvement in accuracy. Our results suggest that Xception is a strong baseline model that could be used by the community to make their comparisons of their proposals more robust.

The identification and classification of white blood cells have become important in medical image analysis for disease diagnosis and health monitoring. Traditional classification methods often consume time and are less reliable. Based on these issues, this study aims to implement a Convolutional Neural Network (CNN) with the MobileNetV2 architecture in the classification of white blood cells to improve efficiency and accuracy. This research method emphasizes the use of the MobileNetV2 architecture in CNN. The training process is conducted using Google Colaboratory with the aid of TensorFlow. Model evaluation is carried out using various standard metrics, including accuracy, precision, recall, and F1-score. The results of the study show that the implementation of CNN with the MobileNetV2 architecture produces an efficient and accurate white blood cell classification model. Through a training process with 15 epochs, the model achieved a high accuracy rate and a low error rate. The accuracy rate in this study indicated an accuracy result of 94.8%. The model evaluation demonstrated good performance in classifying different types of white blood cells, as shown by the evaluation metrics and the confusion matrix. This model implementation has great potential to be used in medical image analysis for efficient and accurate disease diagnosis and health monitoring. Implementasi model ini memiliki potensi besar untuk digunakan dalam analisis citra medis untuk diagnosis penyakit dan pemantauan kesehatan yang efisien dan akurat.

In this paper, the Convolutional Neural Network (CNN) architecture, which is one of the deep learning architectures, is used to classify the basic circuit components drawn by hand. During the training and testing stages of the model, a new dataset containing images of 863 circuit components manually drawn by different people is created. The data set contains images of four different classes of circuit components such as resistor, inductor, capacitor and voltage source. All images have been fixed to the same size and converted to grayscale to increase recognition performance and reduce process complexity. In the study, training for four classes is performed with CNN architecture. Based on the CNN architecture, four new CNN models are employed with different the number of layers. The training and validation results of these models are compared separately, the model with the highest training and validation performance is observed with four layer CNN model (CNN-4). This model obtained 84.41% accuracy rate at classification task.

Classification performance based on ImageNet is the de-facto standard metric for CNN development. In this work we challenge the notion that CNN architecture design solely based on ImageNet leads to generally effective convolutional neural network (CNN) architectures that perform well on a diverse set of datasets and application domains. To this end, we investigate and ultimately improve ImageNet as a basis for deriving such architectures. We conduct an extensive empirical study for which we train 500 CNN architectures, sampled from the broad AnyNetX design space, on ImageNet as well as 8 additional well-known image classification benchmark datasets from a diverse array of application domains. We observe that the performances of the architectures are highlydataset dependent. Some datasets even exhibit a negative error correlation with ImageNet across all architectures. We show how to significantly increase these correlations byutilizing ImageNet subsets restricted to fewer classes. These contributions can have a profound impact on the way we design future CNN architectures and help alleviate the tilt we see currently in our community with respect to over-reliance on one dataset.

Although font recognition is a fundamental issue in the field of document analysis and recognition, it was usually ignored in the past. With the development of optical character recognition (OCR), font recognition becomes more and more important. This paper proposed a well-designed convolutional neural network (CNN) architecture for traditional Mongolian font recognition by means of a single word. To be specific, the whole word image is regarded as input of CNN. Hence, the word images should be normalized into the same size before being inputted into CNN. By comparison, an appropriate aspect ratio for the traditional Mongolian word images has been determined. Experimental results demonstrate that the proposed CNN architecture outperforms three classic CNN architectures, including LeNet-5, AlexNet and GoogLeNet. Therefore, the proposed CNN is much more suitable for the task of the traditional Mongolian font recognition in the way of a single word.

Bangla handwritten character recognition is a popular research topic as its difficulty is higher than the recognition of other languages because of multiple formats of compound characters. State of the art Convolutional neural network (CNN) architectures are very much useful in computer vision applications. Some works have been carried out in Bangla handwritten character recognition but most of them either not very efficient or they can not classify a lot of characters. In this work, state of art pre-trained CNN architectures is used to classify 231 different Bangla handwritten characters using CMATERdb dataset. The images were first converted to B&W form with white as the foreground color. The size of the images is reduced to 28 × 28 form. These images are used as input to the CNN architectures. The weights of the state-of-the-art CNN models are kept as it was. The training learning rate was set to 0.001 and categorical cross-entropy as the error function. After 50 epochs, InceptionResNetV2 achieved the best accuracy (96.99%). DenseNet121 and InceptionNetV3 also provided remarkable recognition accuracy (96.55 and 96.20%, respectively). We also considered combination of trained InceptionResNetV2, InceptionNetV3 and DenseNet121 architectures which provided better recognition accuracy (97.69%) than other single CNN architectures but it is not feasible for using as it requires a lot of computation power and memory. The models were tested in the cases where characters look confusing to humans, but all the architectures showed equal capability in recognizing these images. Considering computational complexity, memory and capability of recognizing confused characters, InceptionResNetV2 can be said as the best performing model.

The convolutional neural network (CNN) architecture has shown remarkable success in image classification and segmentation. Its popularity has increased promptly due to various factors such as exponential growth in computational resources, availability of benchmark datasets, supporting libraries, and open-source software. The efficiency of CNN architecture majorly depends on the complexity of the architecture, availability of datasets, and hyperparameter selection. But, due to the huge number of parameters in CNN architecture, its selection has completely remained ad hoc in the past works. In this article, a novel encoding technique has been proposed that can represent complex CNN architecture effectively. The article defines basic building blocks to represent CNN architecture such as the genesis block, transit block, agile block, and output block. This encoding structure is used to generate dynamic length chromosome structure and initialized using evolutionary algorithms. A comparative analysis is also presented that shows compared its effectiveness with existing encoding representations on the basis of the number of encoding parameters, training cost, and efficiency.

Ultrasound (US) is the preferred modality for fatty liver disease diagnosis due to its noninvasive, real-time, and cost-effective imaging capabilities. However, traditional B-mode US is qualitative, and therefore, the assessment is very subjective. Computer-aided diagnostic tools can improve the specificity and sensitivity of US and help clinicians to perform uniform diagnoses. In this work, we propose a novel deep learning model for nonalcoholic fatty liver disease classification from US data. We design a multi-feature guided multi-scale residual convolutional neural network (CNN) architecture to capture features of different receptive fields. B-mode US images are combined with their corresponding local phase filtered images and radial symmetry transformed images as multi-feature inputs for the network. Various fusion strategies are studied to improve prediction accuracy. We evaluate the designed network architectures on B-mode in vivo liver US images collected from 55 subjects. We also provide quantitative results by comparing our proposed multi-feature CNN architecture against traditional CNN designs and machine learning methods. Quantitative results show an average classification accuracy above 90% over tenfold cross-validation. Our proposed method achieves a 97.8% area under the ROC curve (AUC) for the patient-specific leave-one-out cross-validation (LOOCV) evaluation. Comprehensive validation results further demonstrate that our proposed approaches achieve significant improvements compared to training mono-feature CNN architectures ([Formula: see text]). Feature combination is valuable for the traditional classification methods, and the use of multi-scale CNN can improve liver classification accuracy. Based on the promising performance, the proposed method has the potential in practical applications to help radiologists diagnose nonalcoholic fatty liver disease.

Deep Learning (DL) is a fastest growing and a broader part of machine learning family. Deep learning uses Convolutional Neural Networks (CNN) for image classification as it gives the most accurate results in solving real- world problem. CNN has various pre-trained architecture like AlexNet, GoogleNet, DenseNet, SqueezeNet, ResNet, VGGNet etc. In this study, we have used CNN and AlexNet architecture for detecting the disease in Mango and Potato leaf and compare the accuracy and efficiency between these architectures. The dataset containing 4004 images were used for this work. The images for potato were taken from plantvillage website, while images for mango were collected from GBPUAT field location. The results show that accuracy achieved from AlexNet is higher than CNN architecture.

Convolutional Neural Network (CNN) architectures for the classification of remote sensing images have been in use for the last 6 years. These CNN architectures are preferred over other standard classifiers, such as SVM and Multilayer perceptron, due to their ability to automatically extract features from image patches. Recently, attention-based models have been used for remote sensing classification because of their ability to concentrate on a few relevant features while ignoring others. To mimic the behavior of the human retina’s ganglia neuron, the concept of On-Off Center-Surround (OOCS) filters has recently been introduced with CNN. This study is an attempt to use both OOCS and attention based deep learning architecture with CNN using two remote sensing datasets. Results suggest that the use of both OOCS and the attention layer does not improve classification accuracy in comparison to the CNN model only.

Fresh bread is generally made from wheat flour but it cannot be consumed by people with coeliac or those with gluten sensitivity. Rice flour can be used as a substitute for wheat flour because it has physico-chemical characteristics in the form of amylose and amylopectin which are similar to wheat, as well as the role of rice and its processed foods in the consumption of Asian society, especially Indonesia. This study aims to determine the effect of hydrocolloid addition on the physical and sensory quality of gluten-free white bread and to determine the type of hydrocolloid that has the best effect on the physical and sensory quality of gluten-free white bread. The experiment used a completely randomized design with the treatment of hydrocolloid types consisting of 6 levels (Xanthan Gum, Konjac, Pectin, Carboxymethyl Celulose, Hydroxypropyl Methyl Celulose, and Psyllium Husk). Each treatment was repeated three times resulting in a total of 21 experimental units. Parameters observed were moisture content, hardness, volume development, and sensory tests on pore uniformity, texture, mouthfeel, and overall acceptance using a hedonic scale. Data were analyzed using Analysis of Variance and on treatments that showed a significant effect is then continued with DMRT (Duncan Multiple Range Test) test. The results showed that the addition of various hydrocolloids significantly affected the physical characteristics of fresh bread compared to those without hydrocolloids. Among the hydrocolloids tested, the addition of xanthan gum showed the best results in physical and sensory characteristics, namely with a moisture content value of 39.25 percent, a volume development value of 24.5 percent, with a sensory assessment of pore uniformity, texture, value, mouthfeel and overall acceptance rather like. However, xanthan gum has a texture analysis value of 12.58N. It can be concluded that the addition of hydrocolloids affects the physical characteristics (moisture content, hardness, and development volume) and sensory (pore uniformity, texture, mouthfeel, and overall acceptance) of gluten-free white bread for the better. Keywords: Gluten Free Bread, Hydrocolloids, Physical Characteristics, Sensory Characteristics.