Custom Convolutional Neural Network with Data Augmentation and Bayesian Optimization for Gram-Negative Bacteria Classification

One of the newest methods used in image classification is the Convolutional Neural Network. This method uses a large number of hidden layers to process data so that the resulting accuracy is excellent. However, this affects the time of the training process used. The selection of suitable architecture also determines the results of the classification. In this research, the author tries to reduce computational time by reducing the number of layers and using optimization. Transfer learning helps in the preparation of models using pre-trained data before, while data augmentation increases data variation. Bayesian optimization helps to find out momentum values and initial learning rate. The data source of this research is the primary image of Gram-negative bacteria from pneumonia patients. Data was collected at Dr. Soetomo's Microbiology Laboratory in Surabaya, Indonesia. Data distribution includes training, validation, and testing divided by percentage and proportional distribution of the number of files. This research used four classes of Gram-negative bacteria with a total of 1,000 images. An experimental comparison was made with a comparison of the Convolutional Neural Network architecture. The test results show an increase in accuracy by using aiming layers 26-34, having an accuracy range of 99.5% to 99.8%. The computational time required for the training process is around 2 minutes 30 seconds, with a momentum value of 0.92813 and an initial learning level of 0,00022397. The best accuracy errors were obtained at MSE 0.0025, RMSE 0.05, and MAE 0.0025.

[1]  Saeid Nahavandi,et al.  Extreme learning machine based transfer learning algorithms: A survey , 2017, Neurocomputing.

[2]  Hao Chen,et al.  Deep Cascaded Networks for Sparsely Distributed Object Detection from Medical Images , 2017, Deep Learning for Medical Image Analysis.

[3]  Domenec Puig,et al.  An optimized convolutional neural network with bottleneck and spatial pyramid pooling layers for classification of foods , 2017, Pattern Recognit. Lett..

[4]  Anna Plichta,et al.  Deep learning approach to bacterial colony classification , 2017, PloS one.

[5]  Rasmus Bro,et al.  Using deep learning to evaluate peaks in chromatographic data. , 2019, Talanta.

[6]  Isabel Segura-Bedmar,et al.  Evaluation of pooling operations in convolutional architectures for drug-drug interaction extraction , 2018, BMC Bioinformatics.

[7]  Kenneth P Smith,et al.  Automated Interpretation of Blood Culture Gram Stains by Use of a Deep Convolutional Neural Network , 2017, Journal of Clinical Microbiology.

[8]  Dinh Van Tai,et al.  A fruits recognition system based on a modern deep learning technique , 2019, Journal of Physics: Conference Series.

[9]  J. Sykes.  Chapter 36 – Gram-negative Bacterial Infections , 2013 .

[10]  Ling Huang,et al.  Optimization of deep convolutional neural network for large scale image retrieval , 2018, Neurocomputing.

[11]  Rainer Goebel,et al.  Transfer learning of deep neural network representations for fMRI decoding , 2019, Journal of Neuroscience Methods.

[12]  A. Mechelli,et al.  Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications , 2017, Neuroscience & Biobehavioral Reviews.

[13]  Qiang Yang,et al.  Action-model acquisition for planning via transfer learning , 2014, Artif. Intell..

[14]  Jianhang Liu,et al.  MCSM-Wri: A Small-Scale Motion Recognition Method Using WiFi Based on Multi-Scale Convolutional Neural Network , 2019, Sensors.

[15]  Liu Boqin,et al.  Application of Transfer Learning in Task Recommendation System , 2017 .

[16]  Vijay Kotu.  Chapter 8 – Model Evaluation , 2015 .

[17]  Weiguo Fan,et al.  A new image classification method using CNN transfer learning and web data augmentation , 2018, Expert Syst. Appl..

[18]  Ashraf Darwish,et al.  An optimized model based on convolutional neural networks and orthogonal learning particle swarm optimization algorithm for plant diseases diagnosis , 2020, Swarm Evol. Comput..

[19]  Mirjam Kretzschmar,et al.  Tracking Pseudomonas aeruginosa transmissions due to environmental contamination after discharge in ICUs using mathematical models , 2019, PLoS Comput. Biol..

[20]  Tobias Meisen,et al.  Transfer-Learning: Bridging the Gap between Real and Simulation Data for Machine Learning in Injection Molding , 2018 .

[21]  Adam P. Piotrowski,et al.  Impact of deep learning-based dropout on shallow neural networks applied to stream temperature modelling , 2020 .

[22]  Daniel L. K. Yamins,et al.  A Task-Optimized Neural Network Replicates Human Auditory Behavior, Predicts Brain Responses, and Reveals a Cortical Processing Hierarchy , 2018, Neuron.