TensorFlow Framework Research Articles

Survey on Multimodal Emotion Detection

As we know, many people suffer from unhappiness in today’s world, so there is a requirement for a system that recommends music based on human emotions such as anger, sadness, happiness, etc. In this paper, we propose a system named Multimodal Emotion Detection which helps people by suggesting music and movies based on their emotions. We implemented this system using the FER-2013 dataset, which contains 35,887 images of different emotions such as sadness, happiness, and anger. We used Python’s TensorFlow framework and Haar Cascade algorithms to recommend movies and music based on human facial emotions. The main concern in existing recommendation systems is manual sorting. To avoid this, we propose this model, which automatically plays music and movies without requiring much browsing time

Exploring the Efficiency of Hybrid Recommender Systems Implemented with TensorFlow Framework

In recent years, the field of recommendation systems has seen significant advancement with the introduction of hybrid approaches. These systems combine the strengths of multiple recommendation techniques to provide more accurate and diverse recommendations to users. In this research, we propose and evaluate the effectiveness of a hybrid recommender system that utilizes TensorFlow, an open-source machine learning framework, to implement the system. The proposed system combines both collaborative and content-based methods to remove the cold start problem and make personalized recommendations that can recommend similar movies to the users based on features extracted by the model. The results of our experiments demonstrate that the proposed hybrid system outperforms traditional singular methods and can be effectively implemented using TensorFlow. This research provides insights into the potential of TensorFlow for building efficient hybrid recommendation systems and the benefits of combining multiple recommendation techniques.

Impact of Pre-trained Weights on MobileNet Architectures for Animal Classification

This study aims to address the problem of improving animal image classification accuracy using different versions of MobileNet. Accurate animal classification plays a vital role in biodiversity protection, environmental monitoring, and agriculture. The research is significant because existing studies focus on specific models and datasets, leaving a gap in the comparative performance analysis of MobileNet versions. To address this issue, MobileNet V1, V2, and V3 models were utilized, both with and without ImageNet pre-trained weights. The models were trained on a dataset composed of 30,179 images from two sources, covering 13 animal categories. The experiment involved training the models over 10 epochs using a standard configuration of the TensorFlow framework, with accuracy serving as the primary evaluation metric.The results showed that MobileNet V3Large, with pre-trained weights, achieved the highest accuracy (97.43%), outperforming V1 and V2. Using pre-trained weights consistently enhanced performance, as models without pre-training exhibited lower accuracy and slower convergence. This study contributes by providing a comprehensive comparison of MobileNet versions in animal classification tasks, demonstrating the importance of pre-training and model architecture optimization for achieving high accuracy in image classification.

Agriculture Robot Using Image Processing

Background: Agriculture is a cornerstone of the economy, but traditional farming is labor-intensive and time-consuming. Advances in technology, such as Convolutional Neural Networks (CNNs) and robotics, can help address challenges like disease detection, weed control, and labor shortages. Tomatoes, a key crop, benefit from proper management using these innovations. Objective: This project aims to design and develop an agriculture robot using IoT and Machine Learning to automate farming tasks, detect tomato plant diseases, and manage weeds more efficiently. Methods: The robot is controlled by an ESP32 microcontroller connected via Wi-Fi for real-time monitoring. The system uses CNNs for disease detection in tomato plants, along with a custom-trained dataset using the TensorFlow framework. Mechanical arms perform tasks like seeding, watering, spraying fertilizers, and harvesting. A user interface for disease detection was designed for real time disease detection. Results: The model achieved an accuracy of 95.0% for disease detection, 95.56% for fruit detection, and 95.14% for plant detection. These results highlight the effectiveness of the robot in managing tomato crops. Conclusion: The agriculture robot provides a comprehensive solution to key farming challenges, enhancing efficiency through automation and improving crop health monitoring. The integration of IoT and ML offers a pathway toward sustainable and profitable agriculture, particularly in managing tomatoes. Further improvements and scaling could expand its application to other crops and farming tasks. Keywords: Machine Learning, Internet of Things, Agricultural Robot, Disease Detection, Convolutional Neural Networks, Mechanical Tasks.

Damage of thin target plates impacted by conical projectiles with varying apex angles in ballistic application: experimental, FEA and ANN integrated approach

In the current study, an experimental setup consisting of smoothbore 30-caliber powder gun was employed to launch spherical projectiles (3 g/ϕ9) in the ballistic range of velocities from 500 to 1700 m/s and obliquity (0, 33 and 65°), impacting 2 mm thin Steel 1006 target plates. Crater dimensions (major and minor dia.) obtained from series of FE simulations run for the above configuaration was validated by corresponding experimental data. Subsequently, a fullscale 3D FE model considering 8-noded hexahedral elements was used to discretize SS304 conical projectiles (replacing spherical projectile) with various apex angles viz. 40°, 60°, 80° and 100° impacting on single (3 mm) and double layer (1.5 mm each) steel 1006 targets (replacing 2 mm target) in LS dyna. The material behavior was characterized using J–C strength and damage models, along with Gruneisen Equation of State. An erosion algorithm was used in the explicit FE code LS-DYNA to remove undesirable elements. In the next stage, Adam and Nadam optimizers have been employed in ANN models developed using Python code within the Tensor-Flow framework. The Keras Tuner library in the Tensor-Flow framework was used for hyper parameter tuning. The ANN models trained using simulation data successfully predicted the residual KE of conical projectiles with intermediate apex angles of 90°, 70°, and 50° across twelve different impact scenarios. The models with Adam and Nadam optimizers achieved mean squared error (MSE)/coefficient of determination (R2)/mean absolute percentage error (MAPE) values of 109.44/0.998/6.72 and 91.19/0.998/7.76, respectively.

Implementing handwritten text recognition using deep learning with TensorFlow: An MNIST dataset approach

Handwritten text recognition (HTR) is a pivotal technology with extensive applications in document digitization, postal automation, and educational tools. This paper delves into the implementing a deep learning-based system for recognizing handwritten digits using TensorFlow and the MNIST dataset. The MNIST dataset, a widely-used benchmark, comprises 60,000 training images and 10,000 testing images of handwritten digits, each standardized to a 28x28 pixel grayscale format. Leveraging the power of Convolutional Neural Networks (CNNs), our model effectively extracts features and classifies digits with high accuracy. The model architecture consists of multiple convolutional layers for feature extraction, pooling layers for dimensionality reduction, and fully connected layers for classification. Preprocessing steps include normalizing pixel values and one-hot encoding the labels, ensuring the data is optimally formatted for training. The TensorFlow framework, known for its robustness and scalability, facilitates the development and deployment of the model. Through a series of experiments, the model demonstrates impressive performance, achieving high accuracy on the MNIST test set. This paper underscores the potential of deep learning in handwritten text recognition. It sets the stage for future enhancements, such as recognizing more complex handwritten texts and optimizing the system for practical applications. The results highlight the effectiveness of deep learning techniques in overcoming the challenges associated with handwritten text recognition, paving the way for advanced, real-world implementations.

Deep Learning model based on CNN using Keras and TensorFlow to determine real time melting point of chemical substances

Deep learning is a subset of machine learning that uses artificial neural networks inspired by human cognitive systems. Although this is a newly approach recently it became very popular and effective. In many applications deep learning become most successful approach where machine learning has been successful at certain rates. In the succession of these the proposed deep learning model is suitable for melting point detection apparatus which determine melting point of chemical substances this apparatus generally used in pharmaceutical and chemical industries. Proposed deep learning model classify images of chemical’s state (Solid or Liquid) by deep neural network (DNN) it consists of TensorFlow framework, libraries like Keras and activation function like ReLu, sigmoid, MaxPool and Flatten to determine melting point of chemical substances. The proposed model enables to TensorFlow architecture, which can determine the melting point of chemicals in real time on a single board computer. This use python as a programming language, TensorFlow framework and keras library. The input image data mainly focuses on chemical’s state, there are 2 categories of chemical’s state either solid or liquid. The Deep Neural Network (DNN) chosen as the best practice for the training process because it provides high accuracy. The results discussed in terms of the image classification accuracy in percentage. The images from two class label gets maximum accuracy is 99.72% and maximum validation accuracy is 99.37% same as liquid’s image and the average value of accuracy 84.17% or higher after certain epochs.

A method for phase estimation of X-ray pulsar signals: Combining a transformer network structure and a two-dimensional profile map

The high-precision phase estimation of X-ray pulsar signals is crucial for X-ray pulsar navigation. This paper introduces a novel feature modeling method named Two-Dimensional Profile Map (2D-PM), which enhances the time-domain information of the period axis using the epoch folding algorithm. Compared to traditional profiles, the newly proposed 2D-PM model exhibits richer information content, and greater robustness in terms of folding period precision. Furthermore, a new time-series neural network structure, inspired by groundbreaking advancements in the field of Natural Language Processing (NLP), is developed using the TensorFlow framework. This structure is designed to learn the proposed features and achieve precise phase estimation. The paper also outlines training schemes and debugging strategies for hyperparameters. To test the method, sample sets were created using simulated data and Rossi X-ray Timing Explorer (RXTE) observational data. These samples are specifically designed to enhance feature consistency and the generalization capability of the network. The effectiveness of the proposed method is demonstrated through a comparative analysis with traditional cross-correlation algorithms. The results confirm a high degree of alignment between the network outputs and the feature model, highlighting the significant potential of the proposed method for application in X-ray pulsar navigation.

Facial Emotion Recognition with Deep Neural Network: A Study of Visual Geometry Group-16 (VGG16) Technique with Data Augmentation for Improved Precision

Emotions play a significant role in both verbal and nonverbal communication. Facial emotion recognition has applications in various sectors where we can get real-time feedback about student activeness by detecting their expression. In this paper, we aim to provide an improved deep-learning technique to detect emotions by using publicly available datasets to perform this detection. To get more data for the well-being of the Machine Learning Model, we have used data augmentation using the TensorFlow framework. Visual Geometry Group-16 (VGG16) is a convolutional neural network of 16 layers deep. There has been an alteration to the default VGG16 structure to get better classification results. Various optimization algorithms and loss functions increase the model’s accuracy. We have used many evaluation parameters from the technical side, like precision, accuracy, recall, Area Under the Receiver Operating Characteristic Curve (AUC), and F1 Score. The proposed model has an accuracy of 89% while having a precision of 81 percent for classification. We have achieved an F1 Score of 0.42 and an area under the ROC curve (AUC) of 0.734. Overall, it would be beneficial for analyzing and categorizing positive and negative emotions, which would aid in detecting signs of stress, anxiety, and burnout, as well as taking preventive actions to enhance well-being.

An artificial neural network based deep collocation method for the solution of transient linear and nonlinear partial differential equations

A combined deep machine learning (DML) and collocation based approach to solve the partial differential equations using artificial neural networks is proposed. The developed method is applied to solve problems governed by the Sine–Gordon equation (SGE), the scalar wave equation and elasto-dynamics. Two methods are studied: one is a space-time formulation and the other is a semi-discrete method based on an implicit Runge–Kutta (RK) time integration. The methodology is implemented using the Tensorflow framework and it is tested on several numerical examples. Based on the results, the relative normalized error was observed to be less than 5% in all cases.

Emotion recognition from Burmese speech based on fused features and deep learning method

Burmese language is challenging for speech emotion classification. Moreover, it is lack of resource and few research was made in this topic. To solve the challenging problem, novel feature extraction for Burmese language is proposed. For lack of resource, Burmese speech emotion corpus called BMISEC is built. To support the challenging problem, the advantages of feature extractions are fused to create a robust feature. Four features are fused. Novel text-tone feature, local binary pattern, mel-frequency cepstral coefficient and discrete wavelet transform are fused. To progress the performance, deep learning method called DenseNet-Emotion is used for classification. Support vector machine is used in DenseNet’s classifier layer. To show the robustness of the proposed system, three types of experiments are made on Tensorflow framework. They are ablation study, experiments with three publicly available datasets and experiments with the previous research methods and they are compared with the proposed method. It is found that feature fusion is superior to only one feature in emotion recognition. BMISEC gets better performance than other datasets. Moreover, the proposed method gets the superior result than previous research methods. The proposed method gets the accuracy of 88.388% for 50 epochs.

Enhancing Smart City Infrastructure: An Iot-Integrated System Approach for Real-Time Urban Management

Objectives: The primary objective of this study is to evaluate the effects of new information technologies on the workability, scalability, and reliability of urban installations. This study also aims to enhance smart city infrastructure by integrating various Internet of Things (IoT) systems, particularly for real-time smart city management. Methods : A complete experimental setup was established in a controlled urban environment encompassing numerous IoT technologies, such as environmental sensors, traffic management units, and public security systems, as well as data communication units. The Tensorflow framework, along with Python, was used to perform simulations and experiments. The system design was categorised into four key levels: data reception and transmission, computation, network and data analytics, and application. The proposed systems were subsequently tested in real-world environments, including zones frequently hosting urban events, to analyse key performance indicators. Findings : The results demonstrate significant improvements in urban management through IoT initiatives, including a 25% reduction in fine particulate matter (PM2.5) and nitrogen dioxide (NO2) levels, leading to decreased respiratory hospital admissions and enhanced air quality and health benefits. Additionally, notable advancements were observed in noise control, energy efficiency, and emergency response. Specifically, the findings recorded a 10 dB decrease in nighttime noise, a 30% reduction in energy consumption for public lighting, and a 40% faster emergency response time. These outcomes highlight the broad impact of IoT on urban sustainability and safety. Novelty : This paper introduces a novel concept focused on the design perspective of IoT-connected systems to boost smart city infrastructure, with particular emphasis on the real-time management of urban environments. Keywords: Smart Cities, IoT Technologies, Urban Infrastructure, Real ­Time Urban Management, System Architecture

Audio Classification on the FSDKaggle2018 Dataset using Tensorflow, Keras

This project explores audio classification leveraging representation learning within the TensorFlow framework. The methodology focuses on the initial engineering of wave features derived from raw audio data, which are subsequently used to train convolutional neural networks (CNNs) for effective representation learning. By transforming the audio signals into a structured format amenable to convolutional processing, our system is designed to capture the intrinsic properties and patterns embedded in the sound waves. The feature engineering process is detailed where various envelope features such as the homomorphic envelogram, hilbert envelogram and wavelet decompositions help in extracting meaningful information from the raw audio signals. These engineered features provide a robust foundation for the subsequent layers of convolutional networks. The CNNs are meticulously architected to learn hierarchical representations, effectively capturing both low-level and high-level audio characteristics.This study attempts to reinforces the significance of tailored feature engineering in deep learning and demonstrate an effective audio classification pipeline using representation learning and open up new avenues for research in audio signal processing and machine learning.

Research on agricultural environmental monitoring Internet of Things based on edge computing and deep learning

Abstract With the continuous advancement of agricultural Internet of Things (IoT) technologies, real-time monitoring of agricultural environments has become increasingly significant. This monitoring provides valuable information on pest and disease occurrences and corresponding ecological conditions. However, as the agricultural environments have extensive coverage, the number of monitoring IoT devices and the volume of information will rapidly increase. This leads to a surge in network traffic and computing demands. To address this issue, this article proposes an agricultural environmental monitoring IoT system that utilizes edge computing and deep learning technologies. It combines the Long-Range Wide Area Network (LoRaWAN) for long-range transmission with pest recognition and counting modules. By offloading workloads traditionally processed in the cloud to edge nodes, the proposed system effectively reduces transmission and cloud computing pressures for the agricultural monitoring IoT. Simulation experiments demonstrate stable LoRaWAN protocol-based data transmission at the edge, with an overall packet loss rate of less than 5%, meeting the transmission quality requirements. Moreover, this article investigates a pest recognition and counting method based on deep learning technology. Pest images, captured by monitoring nodes, are recognized and counted online using the TensorFlow framework. Experimental results indicate an accuracy of 89% in pest recognition. By digitally transmitting pest image recognition results to the cloud, the proposed system significantly alleviates transmission and cloud computing pressures for the monitoring IoT.

Smartphone Camera for Angiographic Computer Vision in Vascular Medicine

Aim: This study aimed to develop a TensorFlow Lite algorithm for angiography classification and to deploy it on a basic mobile smartphone device, thereby verifying the proof of concept for creating a comprehensive end-to-end mobile computer vision application for vascular medicine. Materials and Methods: After ethical approval by the local ethics committee, we collected institutional and open source peripheral angiograms of lower limbs. The angiograms were labeled by a researcher with more than 10 years of experience in vascular surgery. The labeling included dividing the angiograms according to their anatomical pattern into the Global Limb Anatomic Staging System (GLASS). The model was developed using the open-source TensorFlow framework for general image classification and deployed as an Android application. Results: The model utilized 700 angiograms, distributed as follows within the femoropoliteal GLASS disease (fp) categories: fp0 – 187 images, fp1 – 136 images, fp2 – 128 images, fp3 – 97 images, fp4 – 152 images. The reference dataset included 372 non-angiographic images (not_angio). Consequently, the entire model included 1,072 images. After training and deployment, the model demonstrated the following performance: a mean accuracy of 0.72. The best self-reported accuracy per class was for fp0 0.72, fp4 0.83 and not_angio 1.0 classes. Conclusion: We discovered that a smartphone camera could be utilized for angiographic computer vision through end-to-end applications accessible to every healthcare professional. However, the predictive abilities of the model are limited and require improvement. The development of a robust angiographic computer vision smartphone application should incorporate an upload function, undergo validation through head-to-head human-machine comparisons, potentially include segmentation, and feature a prospective design with explicit consent for using collected data in the development of AI models.

A comprehensive comparison of various machine learning algorithms used for predicting the splitting tensile strength of steel fiber-reinforced concrete

Incorporating steel fibers into concrete effectively enhances its tensile strength by managing crack formation, increasing toughness and ductility, and reducing brittleness, making it a valuable choice for various applications, including bridge decks. Thus, the objective of this research is to employ the machine learning (ML) technique to estimate the splitting tensile strength (STS) of steel fiber-reinforced concrete (SFRC) that incorporates hooked industrial steel fibers (ISF) using SFRC mixtures collected from various research papers in this field. The dataset comprises 116 data points from various research papers. Utilizing the recursive feature elimination with cross-validation and leave-one-out (RFECV-LOO) method, the most influential parameters, including ISF content, water-to-cement ratio (W/C), cement content (C), fine aggregate content (FA), superplasticizer (SP), and fly ash, were identified to train the ML models. Eight statistical metrics, including the root mean squared error (RMSE), mean squared error (MSE), mean absolute error (MAE), coefficient of determination (R2), mean absolute percentage error (MAPE), mean bias error (MBE), statistical test (Tstat), and scatter index (SI) were employed as metrics to assess model performance. Various ML models including multiple linear regression (MLR), ridge regression (Ridge), lasso regression (Lasso), elastic net regression (ElasticNet), k-nearest neighbor (KNN), support vector regression (SVR), categorical boosting (CatBoost), light gradient boosting model (LightGBM), random forest (RF), gradient boosting (GB), extreme gradient boosting (XGB), adaptive boosting (AdaBoost), and multilayer perceptron (MLP) were employed to predict the SFRC’s STS. The Python programming language, TensorFlow framework as well as the Scikit-learn packages, were used to run the models. Among the various ML methods, SVR demonstrated higher accuracy, achieving an R2 of 0.930, RMSE of 0.502, and MAE of 0.330. In contrast, linear regression models, especially Lasso with an R2 of 0.631, RMSE of 0.854, and MAE of 0.710, exhibited the least effective performance when it came to predicting the STS of SFRC. Moreover, the performance of the developed ML models was approved through sensitivity analysis as well as parametric analysis.

Enhancing mask detection performance based on YOLOv5 model optimization and attention mechanisms

Due to the COVID-19 pandemic, there has been a significant increase in the usage of masks, leading to more complex scenarios for mask detection techniques. This paper focuses on optimizing the performance of mask detection using the You Only Look Once (YOLO) v5 model. In this study, the yolov5 target detection model was employed for training the mask dataset. Diverse model improvement techniques were explored to enhance the model's capability to capture crucial features and differentiate masks from the background in complex scenarios. Finally, the modified model was compared with the earlier original target detection model to identify the most considerable performance gain. The CSPDarknet design with the TensorFlow framework is utilized in this study, and the Attention Mechanism module is implemented through the Keras library. The objective is to optimize the three feature layers between the backbone network and the neck by integrating multiple attention mechanisms. This will enable the model to more quickly and accurately capture important features when dealing with complex scenarios by adjusting the feature map weights. Additionally, in the feature pyramid network, shallow feature maps are fused with deeper feature maps in a certain order to determine the most efficient feature fusion method. Finally, this study identified the optimal combination of attention mechanism and feature fusion through ablation experiments. The results of the experiment demonstrate that the combination of SE block and shallow feature fusion (SE + FF2 model) can greatly enhance category confidence, leading to an improved model performance.

High precision temperature measurement for cryogenic temperature sensors based on deep learning technology

Nonlinear error compensation is a significant factor that affects the measurement accuracy of temperature sensors. Cryogenic temperature sensors require a precise calibration technique to achieve accurate temperature measurements. BP (Back Propagation) neural networks are not suitable for sensor temperature prediction due to slow convergence and poor learning ability. In this study, a Chebyshev polynomial-based BiLSTM (Bi-directional Long Short-Term Memory) algorithm (C-BiLSTM) is proposed to improve the accuracy of measurement. Firstly, we demonstrate vacuum packaged temperature sensors based on zirconium oxynitride (ZrOxNy) thin films with ultra-high sensitivity at cryogenic temperatures. Secondly, a dataset consisting of sensor resistance and temperature values was obtained from five above-mentioned sensors, which contains 29 calibration points in the temperature range of 16 K-300 K measured by the Calibration System. Then, the dataset was divided into two temperature ranges (16 K-54.358 K and 40 K-300 K). In the range 16–54.358 K, 14 set-points are selected as training set and 3 set-points as testing set. In the range 40–300 K, 12 set-points are selected as training set and 2 set-points as testing set. Thirdly, a neural network model was built and trained using the TensorFlow framework. By comparing C-BiLSTM we proposed with the BP neural network and BiLSTM, the results show that the C-BiLSTM model converges faster and greatly improves the prediction accuracy after adding Chebyshev polynomial features. The fitting error and prediction error are less than 1 mK in the temperature range of 16 K-40 K. They can also keep less than 10 mK even at the wide temperature range of 40 K-300 K, which is a significant improvement respect to improving the accuracy of temperature measurement.

Exploring the effect of depth and width of CNN models on binary classification of dogs and cats

Convolutional neural networks (CNNs), one of the trendiest study areas in recent years, have garnered a lot of interest. Their performance is particularly notable in speech recognition, target identification, and picture recognition. The performance of a convolutional neural network model is particularly crucial because convolutional neural networks deal with problems that demand enormous amounts of data and have strict standards for result correctness. The convolutional neural network model's depth and width are the first two parameters that are examined in this paper, which is built on the Tensorflow framework. Next, the impact of depth on the accuracy of model's prediction is examined. The model's accuracy and loss are then used as a benchmark to assess its quality; at the same time, the performance of the model can be discussed in relation to the impact of width by selecting a different number of neurons with various convolutional kernel sizes; Finally, A combinational convolutional, the experiments' result show that, with a classification accuracy of up to 95.4%, the combinatorial convolutional neural network outperforms a model with single depth or width.

Deep learning for sustainable agriculture: Weed classification model to optimize herbicide application

<p>Herbicides, chemical substances designed to eliminate weeds, find widespread use in agriculture to eradicate unwanted plants and enhance crop productivity, despite their adverse impacts on both human health and the environment. The study involves the construction of a neural network classifier employing a Convolutional Neural Network (CNN) through Keras to categorize images with corresponding labels. This research paper introduces two distinct neural networks: a basic neural network and a hybrid variant combining CNN with Keras. Both networks undergo training and testing, yielding an accuracy of 30% for the basic neural network, whereas the hybrid neural network achieves an impressive 97% accuracy. Consequently, this model significantly diminishes the need for herbicide spraying over crops such as fruits, vegetables, and sugarcane, aiming to safeguard humans, animals, birds, and the environment from the detrimental effects of harmful chemicals. Functioning as the elevated API within the TensorFlow framework, Keras furnishes a user-friendly and immensely efficient interface tailored to address machine learning (ML) challenges, particularly in the realm of contemporary deep learning. Encompassing all facets of the machine learning process, from data manipulation to fine-tuning hyper parameters to deployment, Keras was meticulously crafted to expedite rapid experimentation.</p>