Figure 7 - uploaded by Vanlalhruaia Vanlalhruaia
Content may be subject to copyright.
Feed-forward neural network model Given a training set of m examples and K output labels, the overall cost function with regularization for neural network is given by í µí°½ í µí¼ = − 1 í µí±
Context in source publication
Context 1
... use a neural network having three layers: an input layer, two hidden layer and an output layer as shown in figure 7 in which Θ (i) is the network parameters to be obtained, g(z (i) ) is the value obtained by applying sigmoid function to the product of θ and the previous layer value, ℎ í µí¼ (í µí±¥ í µí± ) í µí± = í µí± í µí± 3 is the activation of the k-th output unit, L is the total number of layers and í µí± í µí± is the number of units in layer í µí± [20]. Given a training example (í µí±¥ í µí±¡ , í µí±¦ í µí±¡ ), we first run a forward pass to compute all the activation throughout the network. ...
Similar publications
Citations
... This task revolves around the automatic categorization of images into predefined classes based on their visual content. One prominent approach employed in this endeavor is pattern recognition, which involves the extraction of distinctive features from the objects or elements under examination [3]. Essentially, this method seeks to characterize information by identifying and discerning significant features within the objects themselves [4]. ...
This study presents a comprehensive evaluation of logistic regression in contrast to a hybrid model combining VGG16 with logistic regression for image classification tasks. The research findings illuminate a striking performance disparity between these two approaches, shedding light on the profound impact of integrating deep learning techniques into image classification. The transition from logistic regression to the VGG16-based hybrid model marks a notable turning point in our investigation. The VGG16 architecture, renowned for its prowess as a feature extractor, showcases an impressive 53.33% surge in accuracy compared to the conventional logistic regression model. This substantial leap underscores the model's capacity to decipher complex image characteristics that elude traditional statistical methods. Furthermore, precision, a crucial metric in classification tasks, experiences a substantial 53% augmentation when adopting the VGG16 hybrid approach. This enhancement signifies the hybrid model's ability to minimize false positives, making it particularly valuable in scenarios where precision holds paramount importance. Equally noteworthy is the substantial 54% improvement observed in both recall and F1-score, emphasizing the VGG16 hybrid model's remarkable capacity to identify and retrieve a higher proportion of true positives while maintaining a balance between precision and recall. This not only amplifies the model's ability to correctly classify images but also mitigates the risk of overlooking relevant instances. These compelling findings underscore the critical role of deep learning, specifically convolutional neural networks (CNNs), in the realm of image classification. The utilization of CNNs, exemplified by the VGG16 architecture, emerges as a game-changer, enabling the capture of intricate image features and patterns that traditional logistic regression struggles to discern. Generally, this study advocates for the integration of advanced deep learning techniques, like VGG16, in image classification endeavors. The substantial performance gains witnessed in accuracy, precision, recall, and F1-score reinforce the pivotal role of convolutional neural networks in enhancing the effectiveness of image classification tasks. By harnessing the power of deep learning, we unlock new horizons in image analysis, paving the way for more accurate and efficient classification systems
... Unlike in other technical works wherein developers exercise their minds extensively to come up with efficient algorithms to attain the desired objective in output. The field of machine learning gives computers the capabil-B Mohit Ranjan Panda mohit.pandafcs@kiit.ac.in 1 ity to learn and evolve without any explicit user algorithms [18]. The machine carefully extracts insights from the input dataset obtaining the necessary contours and prediction function to perform accurate classification and prediction works, respectively [18]. ...
... The field of machine learning gives computers the capabil-B Mohit Ranjan Panda mohit.pandafcs@kiit.ac.in 1 ity to learn and evolve without any explicit user algorithms [18]. The machine carefully extracts insights from the input dataset obtaining the necessary contours and prediction function to perform accurate classification and prediction works, respectively [18]. The field of machine learning, computer vision and behavioral sciences have evolved to the extent of having an application in almost every specific sector of the current world, the sectors wholly leveraging the capability of these fields are human-computer communication, health care, security and emotion extraction [13]. ...
... Regression which is a binary classification model (2 classes) involves determining the relationship among variables via a training and testing environment and in the end, efficiently determines the class of the concerned test data [18]. Logistic regression, unlike the linear regression, can create a nonlinear boundary between two classes. ...
The feedback process in the contemporary world is done on a timely basis filled particularly by the individual concerned. This hectic procedure often turns out to be peer-driven jeopardization of the primary objective of the process. To prevent this vulnerability, this work proposes a dynamic method of generating feedback automatically based on emotion classification by nonlinear logistic regression model and neural network-based convolutional neural networks (CNN). For a given test sample, our working project detects multiple faces followed by the cropping of these detected faces and finally, these cropped faces are stored in a destination folder. Iterating through the contents in this destination folder one by one, first, the binary classifier logistic regression gives a probabilistic output in the form of a percentage, the level of interest found on the concerned cropped facial image. Second, these iterated contents are passed on to the sophisticated CNN model, having the capability to detect and extract specific emotion features from an image. The CNN gives a detailed analysis report of the concerned individual by classifying them into emotions like Anger, Disgust, Contempt, Happiness, Neutral, Surprise or Fear. The outputs of these two models that are machine-generated feedback, would effectively encourage organizational, structural or end-user policy changes necessary to develop and evolve in the current competitive world.
... Logistic regression algorithm is used a lot in face recognition systems; the literature provides evidence for this [11] [23]. In 2014, C. Zhou et al, exemplified its use. ...
Background: The fundamental need for authentication and identification of humans using their physiological, behavioral or biological characteristics, continues to be applied extensively to secure localities, property, financial transactions, etc. Biometric systems based on face characteristics, continue to attract the attention of researchers, major public and private services. In the literature, many methods have been deployed by different authors. The best performance must be found in order to be able to recommend the most effective method. So, the main objective of thisarticle is to make a comparative study of different existing techniques.Methods: A biometric system is generally composed of four stages: acquisition of facial images, preprocessing, extraction of characteristics and finally classification. In this work, the focus is on machine learning algorithms for classification. These algorithms are: Support Vector Machines (SVM), Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), Random Forests (RF), Logistic Regression (LR), Naive Bayesian Classification (NB: Naive Bayes’ Classifiers) and deep learning techniques such as Convolutional Neural Networks (CNN). The comparison criterion is the average performance, calculated using three performance measures: recognition rate, confusion matrix, and the Area Under Receiver Operating Characteristic (ROC) curve.Results: Based on this criterion, the performance comparison of selected machine learning algorithms, shows that CNN is the best, with an average performance of 100.00% On ORL face database. However, on the YALE database, classical algorithms such as artificial neural networks have obtained the best performances, the highest being a rate of 100%.Discussion: Deep learning techniques are very efficient in image classification as proven by the results on the ORL database. However, their inefficiency on YALE face database is due to the small size of this database which is inappropriate for some deep learning algorithms. But this weakness can be corrected by image augmentation techniques. The comparison of these results with existing state-of-the-art methods is nearly the same. Authors achieved performances of 94.82%, 95.79%, 96.15%, 96.44%, 97.27%, 98.52% and 98.95% for NB, KNN, RF, LR, ANN, SVM and CNN classifiers, respectively. Finally, in depth discussion, it is concluded that between all these approaches which are useful in face recognition, the CNN is the best classification algorithm.
... We compared three methods for classifying tomatoes as ripe or unripe and rotten. The basic ML models we used are: Logistic regression (LR) (Hruaia et al., 2017), Support Vector Machine (SVM) (Sun et al., 2015) and k-Nearest Neighbour (kNN) (Amato and Falchi, 2010). Comparison studies (Abd Rahman et al., 2015) state that LR is more stable in its prediction for binary classification, having less inference time for the classification process. ...
Harvesting tomatoes in agriculture is a time-consuming and repetitive task. Different techniques such as accurate detection, classification, and exact location of tomatoes must be utilized to automate harvesting tasks. This paper proposes a perception pipeline (P2Ag) that can effectively harvest tomatoes using instance segmentation, classification, and semantic mapping techniques. P2Ag is highly optimized for embedded hardware in terms of performance, computational power and cost. It provides decision-making approaches for harvesting along with perception techniques, using a semantic map of the environment. This research offers an end-to-end perception solution for autonomous agricultural harvesting. To evaluate our approach, we designed a simulator environment with tomato plants and a stereo-vision sensor. This paper reports results on detecting tomatoes (actual and simulated ) and marking each tomato’s location in 3D space. In addition, the evaluation shows that the proposed P2Ag outperforms the state-of-the-art implementations.
... In the literature, Logistic Regression has been shown to have impressive accuracy rates with training and testing images. This approach is only made more impressive because the program used reduced image sizes when making these comparisons to cut down on computational space and time [7]. ...
... In the literature, Logistic Regression has been shown to have impressive accuracy rates, with both training and testing images. This is only made more impressive due to the fact that the program used reduced image sizes when making these comparisons, in an effort to cut down on computational space and time [24]. ...
In the ever-changing world of computer security and user authentication, the username/password standard is becoming increasingly outdated. Using the same username and password across multiple accounts and websites leaves a user open to vulnerabilities, and the need to remember multiple usernames and passwords feels very unnecessary in the current digital age. Authentication methods of the future need to be reliable and fast, while maintaining the ability to provide secure access. Augmenting traditional username-password standard with face biometric is proposed in the literature to enhance the user authentication. However, this technique still needs an extensive evaluation study to show how reliable and effective it will be under different settings.
Local Binary Pattern (LBP) is a discrete yet powerful texture classification scheme, which works particularly well with image classification for facial recognition. The system proposed here strives to examine and test various LBP configurations to determine their image classification accuracy. The most favorable configurations of LBP should be examined as a potential way to augment the current username and password standard by increasing their security with facial biometrics.
... Similar to the grayscale images, binary images are often used in image recognition applications, as binarization is quite advantageous in applications such as medical image processing, document image analysis and face recognition. Singh and Singh [64] performed face recognition according to the features extracted from the binary images. The binary image of the whole face was used as a feature for artificial neural network (ANN). ...
Human activity recognition (HAR) has quite a wide range of applications. Due to its widespread use, new studies have been developed to improve the HAR performance. In this study, HAR is carried out using the commonly preferred KTH and Weizmann dataset, as well as a dataset which we created. Speeded up robust features (SURF) are used to extract features from these datasets. These features are reinforced with bag of visual words (BoVW). Different from the studies in the literature that use similar methods, SURF descriptors are extracted from binary images as well as grayscale images. Moreover, four different machine learning (ML) methods such as k-nearest neighbors, decision tree, support vector machine and naive Bayes are used for classification of BoVW features. Hyperparameter optimization is used to set the hyperparameters of these ML methods. As a result, ML methods are compared with each other through a comparison with the activity recognition performances of binary and grayscale image features. The results show that if the contrast of the environment decreases when a human enters the frame, the SURF of the binary image are more effective than the SURF of the gray image for HAR.
Nowadays curiosity of human being is expanded toward sea. It is difficult to explore the uses of robots by human being. So, people use robots to explore sea and that robot is popularly known as Autonomous Underwater Vehicle (AUV). The work aims toward classification of fish. Embedded systems are generally used to explore seabed. Embedded system is capable of operating heavy software and sensitive technology. In this work, CNN is used for the purpose of classification and Logistic Regression is used as a classifier. Fish4knowledge dataset is used for validating the work. Using evaluation criteria including accuracy, precision, recall, and F1-score, the suggested work is contrasted with several classifier types. In the result section, it is clearly shown that logistic regression is giving best result out of all the classifiers. In this proposed work 95% accuracy was achieved.
