Skip to main content

A Learning-rate Optimization Technique for Object Detection Accuracy Enhancement | Chapter 14 | New Approaches in Engineering Research Vol. 14

Because of their specific capability for Image Recognition, Deep Learning [1] models have recently been used primarily in Object Detection algorithms. These models extract features from input images and videos [2] to identify items present. Image processing, video analysis, speech recognition, biomedical image analysis, biometric recognition, iris recognition, national security applications, cyber security, natural language processing [3], weather forecasting applications, renewable energy generation scheduling, and other applications are all possible with these models. These models use the Convolution Neural Network (CNN) [3, which consists of several artificial neuron layers. The learning rate, the training batch size, the validation batch size, the activation function, and the drop-out rate are all aspects that influence the accuracy of Deep Learning models. These parameters are known as hyper-parameters. The accuracy of Object Detection is determined by the Hyper-Parameters used. Finding the appropriate settings for these parameters is thus a complex undertaking. Fine-tuning is a technique for determining which Hyper-Parameters are most beneficial in enhancing Object Detection precision.

Selecting an incorrect Hyper-Parameter value causes data to be over-fitted or under-fitted. When training data is higher than what is required, over-fitting occurs, resulting in learning noise and erroneous Object Detection [4]. When a model is unable to capture the data's trend, under-fitting occurs, resulting in more erroneous testing or training outcomes.

This article achieves a balance between Over-Fitting and Under-Fitting by adjusting the 'Learning rate' of various Deep Learning Models. This study considers four Deep Learning Models for experimentation: VGG-16, VGG-19, InceptionV3 and Xception. The best zone of Learning-rate for each model is examined in terms of maximum Object Detection accuracy. This study investigates the prediction accuracy of a dataset of 70 object classes by altering the'Learning-Rate' while keeping the rest of the Hyper-Parameters constant. The impact of 'Learning-Rate' on Object Detection accuracy is discussed in this article, which also suggests an optimum accuracy zone. This approach aids in the computation of Objection Detection Accuracy while reducing computational effort.


Author (S) Details

Chamarty Anusha
Computer Science & Systems Engineering, Andhra University College of Engineering, Andhra University, Visakhapatnam (AP), India.

P. S. Avadhani
Computer Science & Systems Engineering, Andhra University College of Engineering, Andhra University, Visakhapatnam (AP), India.


View Book:-  https://stm.bookpi.org/NAER-V14/article/view/3533


Comments

Popular posts from this blog

Greening Regional Airports: A Vision for Carbon Neutral Infrastructure | Chapter 12 | Contemporary Perspective on Science, Technology and Research Vol. 3

 This study provides an overview of the energy demand of a regional airport, divided into individual time horizons. The electrification of aircraft systems raises the question of whether airports will be among the largest electricity consumers in our infrastructure in the future. Sustainability and especially emission reductions are significant challenges for airports that are currently being addressed. The Clean Sky 2 project GENESIS addresses the environmental sustainability of hybrid-electric 50-passenger aircraft systems in a life cycle perspective to support the development of a technology roadmap for the transition to sustainable and competitive electric aircraft systems. This article originates from the GENESIS research and describes various options for ground power supply at a regional airport. Potential solutions for airport infrastructure with a short (2030), medium (2040), and long (2050) time horizon are proposed. In addition to the environmental and conservation benefi...

There is No Standard Model of ZFC and ZFC2 | Chapter 03 | Advances in Mathematics and Computer Science Vol. 1

In this Chapter we obtain a contradictions in formal set theories under assumption that these theories have omega-models or nonstandard model with standard part. An possible generalization of Lob’s theorem is considered. Main results are: (i) ¬Con(ZF C+ ∃ M ZFC st ), (ii) ¬Con(N F+ ∃ M NF st ), (iii) ¬Con(ZF C 2 ), (iv) let k be an inaccessible cardinal then ¬Con(ZF C+ ∃ κ), (v) ¬Con(ZF C+ (V=L)), (vi) ¬Con(ZF+ (V=L)). Author   Details: Jaykov Foukzon Israel Institute of Technology, Haifa, Israel Men'kova Elena Romanovna All-Russian Research Institute for Optical and Physical Measurements, Moscow, Russia Read full article: http://bp.bookpi.org/index.php/bpi/catalog/view/46/221/408-1 View Volume: https://doi.org/10.9734/bpi/amacs/v1

Occipital Dermal Sinus Tract Causing Craniospinal Infection: A Review | Chapter 13 | New Visions in Medicine and Medical Science Vol. 4

  Dermal sinus is a rare congenital condition characterized by a pathological tract connecting the skin to deeper tissues of the central nervous system, potentially leading to severe infectious complications. It arises from a failure in the separation of ectodermal layers during early gestation. Diagnosing dermal sinus tract in newborns requires a careful physical examination, focusing on midline dimples in the occipital region associated with cutaneous abnormalities like hairy nevus or hyperpigmentation. The presence of drainage, abnormal hair distribution, or localized swelling may indicate a sinus tract. Regular examination for dimples or sinuses is recommended for infants and children with recurrent meningitis or infections. Early detection is crucial to prevent severe complications like meningitis, with Staphylococcus aureus being a common causative organism. Neuroradiological studies, including computed tomography (CT) scan and magnetic resonance imaging (MRI), with histopath...