Early Fire Detection Using Long Short-Term Memory-Based Instance Segmentation and Internet of Things for Disaster Management

High-Efficiency Video Coding (HEVC) is the latest video coding standard developed by the Joint Collaborative Team on Video Coding (JCT-VC). An effective rate control mechanism plays a critical role in making the best possible use of the network resources. The coding performance can be maximised through the appropriate allocation of bits under the constraints of a total bit rate budget and the buffer size. Existing rate control strategies generally determine the rate control parameters according to previous encoding results. However, there is no priori-knowledge available when the first frame of a video sequence is encoded or scene changes occur. Consequently, it is challenging to choose appropriate rate control parameters in such cases. In order to address this issue, we investigated deep learning oriented methods and proposed a Convolutional Neural Network (CNN)-based rate control scheme for HEVC intra-coding. As the CNN has the advantage of local perception and the Coding Tree Unit's (CTU's) Quantisation Parameter (QP) value is determined during the CTU level rate control process, we applied the CNN at the CTU level as well to achieve an accurate QP prediction. An improved QP determination model (R-QP model) involving only two model coefficients (µ and v) was suggested to simplify the QP calculation process. A CNN was used to predict the model coefficients, namely µ and v. Our CNN has four convolution layers, two pooling layers and three fully connected layers. Each of the convolution layers contains a Rectified Linear Unit (ReLU). The last fully connected layer outputs the predicted values of µ and v. The images from the UCID dataset and the RAISE dataset were used to train the CNN. In order to obtain a universal model, none of the frames in the HEVC common test sequences were employed as training images. In order to achieve a reasonable bit budget allocation, a CNN-based framework was used to predict the bit consumption for each CTU according to the entire picture content that it contains. At the training stage, the network took the original images and the QP values as inputs, and the corresponding actual bit consumptions were used as the labels. Once the CNN coefficients have been obtained through training, the bit consumption for each CTU under different QP values can be directly predicted from the original images. The predicted bit consumption was subsequently used to readjust the bit budget for each CTU to achieve a more reasonable bit allocation. We implemented the proposed CNN-based rate control scheme in the HEVC reference software HM 16.9. As the priori-knowledge of the previous encoding results had not been considered in the proposed algorithm, only the first frame of each video sequence was encoded. The experimental results showed that our proposed scheme performs better than the default rate control implementation in the HEVC reference software, namely the BDBR is reduced by 1.33% on average while maintaining the same reconstructed picture quality. Compared with the state-of-the-art CNN-based rate control algorithm proposed by Li, our schemes achieved better coding efficiency. It can be concluded that the proposed R-QP model is effective in describing the rate-distortion relationship in HEVC, and the CNN-based bit allocation scheme is appropriate for ensuring that the best use of each bit is made.

Detection of brain tumor is very challenging task in today’s medical world. Nowadays, many doctors prefer ready-made methods to diagnose the tumor from given magnetic resonance imaging (MRI) images. Accurate and less time-consuming methods are used frequently to identify it. This paper introduces new techniques for finding and differentiating brain tumors. The new methods include support vector machine (SVM) and convolution neural network (CNN) with Softmax classifier. The SVM uses histogram of oriented gradients (HOGs) as a feature to label the given dataset. Further, the same feature of the test image is verified against labeled sets and classified. The SVM gives accuracy of 87.33%. In CNN, multilayer structure is used. It contains a convolution layer followed by the pooling layer and finally fully connected layer. In CNN, specifically, Alexnet is preferred for classification. In Alexnet, rectified linear unit (ReLU) is used as an activation function. At the output of it, Softmax is used as activation to classify the images. The CNN with Softmax classifier gives improved accuracy of 98.68%. In addition, the performance measures are also found out such as specificity, sensitivity, and precision. The sensitivity with SVM is 93.18%, and with CNN, it increases up to 100%. Comparing both methods with the obtained results, the CNN with Softmax classifier gives better results. Proposed method with CNN produces only one misclassified image as an advantage over the existing method, while SVM gives nine misclassified images. The methods are tested on 253 MRI images which are detected and classified correctly with Matlab.KeywordsSVMCNNHOGMRI

The necessity for personal data protection has become increasingly critical in recent years. In this case, an identification system based on multimodal biometric integration is the best option for greatly enhancing and obtaining high performance accuracy. Finger vein is considered an extremely secure and reliable biometric modality used for authentication. Finger vein authentication is a recently developed biometric technology that has gained more attention in the past decade. The traditional methods of finger vein authentication techniques are affected by several factors, such as illumination variations and image misalignments, that lead to inefficient feature extraction. As a result, the authentication system’s overall performance suffers. A convolutional neural network (CNN) is a deep learning–based solution to finger vein authentication that solves the problems that older methods have. This research proposes a deep learning–based feature extraction methodology for finger vein pictures. A convolutional layer, a rectified linear unit (ReLU), batch normaliation, and average pooling layer, followed by a fully connected layer and a softmax layer, make up the proposed CNN. Using a separate collection of images from the SDUMLA finger vein database, the CNN is trained and evaluated, and the suggested approach achieves an overall accuracy of 99.84%.

The convolutional neural networks (CNN), including AlexNet, GoogleNet, VGGNet, etc. extract features for many computer vision problems which are very discriminative. The trained CNN model over one dataset performs reasonably well whereas on another dataset of similar type the hand-designed feature descriptor outperforms the same trained CNN model. The Rectified Linear Unit (ReLU) layer discards some values in order to introduce the non-linearity. In this paper, it is proposed that the discriminative ability of deep image representation using trained model can be improved by Average Biased ReLU (AB-ReLU) at the last few layers. Basically, AB-ReLU improves the discriminative ability in two ways: 1) it exploits some of the discriminative and discarded negative information of ReLU and 2) it also neglects the irrelevant and positive information used in ReLU. The VGGFace model trained in MatConvNet over the VGG-Face dataset is used as the feature descriptor for face retrieval over other face datasets. The proposed approach is tested over six challenging, unconstrained and robust face datasets (PubFig, LFW, PaSC, AR, FERET and ExtYale) and also on a large scale face dataset (PolyUNIR) in retrieval framework. It is observed that the AB-ReLU outperforms the ReLU when used with a pre-trained VGGFace model over the face datasets. The validation error by training the network after replacing all ReLUs with AB-ReLUs is also observed to be favorable over each dataset. The AB-ReLU even outperforms the state-of-the-art activation functions, such as Sigmoid, ReLU, Leaky ReLU and Flexible ReLU over all seven face datasets.

With applications ranging from postal services to digitized document processing, handwritten digit identification is a key problem in the fields of machine learning and computer vision. By utilizing their capacity to automatically extract hierarchical characteristics from unprocessed pixel data, Convolutional Neural Networks (CNNs) have become effective instruments for addressing this job. This study presents a thorough investigation of a CNN-based method that uses the MNIST dataset to recognize handwritten numbers. We explore the design, implementation, and performance assessment of the CNN model, demonstrating its ability to achieve high accuracy on tasks involving the recognition of numbers. We also go over the significance of our results for the larger picture of image categorization and suggest directions for further investigation and advancement. Key Words: CNN, MNIST, Convolutional Layer, Pooling layer, Max Pooling, Neural Networks, Preprocessing, Dropout Layer, Activation layer, Rectified Linear Unit (ReLU), Epochs, MNIST dataset

Because of huge damage caused by fire, the early fire detection becomes more and more important. With the rapid development of image and video processing, the fire detection technology based on video processing is becoming the focal point of some research due to its advantages of high intuitive, speed and anti-jamming capability. In this paper, we propose a method for early fire detection based on region growing. This method uses colour and motion information extracted from video sequences to detect fire. It can work both indoors and outdoors. Moreover, it detects fire at the beginning of the burning process, enabling an early response than would be possible with a conventional fire detector. The method performs the region growing segmentation to identify colour pixels in the scene and then identify moving pixels based on the ratio of height and width of suspected fire region and correlation coefficient. This method can get low false alarm rate by eliminating the fire-like colours because it just needs a fire pixel as the seed pixel.

Detecting curbs efficiently and at a low cost is essential for autonomous driving. Most of the existing methods rely on light detection and ranging, which is a complicated and costly solution. Therefore, this work propose an efficient method for detecting curbs in a single road image. This method utilizes the convolutional neural network (CNN) framework to localize the curb parts in the captured image. We built a feature-extraction CNN that can classify curb and no-curb regions. The relu, pooling, fully connected, softmax, and classification layers in the pretrained ResNet18 are replaced with ten new layers, which are relu, convolution2d, batchnormalization, dropout, fully connected, relu, maxpooling2d, fully connected, softmax, and classification layers. The comparison of several evaluation metrics to prove the effectiveness of the customized network structure for curb classification. The customized network structure is assembled in the Faster R-CNN detector to improve the performance of feature extraction both for classification and detection. In the detection stage, although the layer we used for feature extraction was the previous layer of the added layers, the detection experimental results demonstrate that our custom CNN network structure can improve the classification performance of the feature extraction layer.

For the internet of medical things (IoMT) enabled long-term health monitoring and disease prediction applications, there is a demand for an automatic photoplethysmogram (PPG) signal quality assessment (SQA) for reducing false alarms and energy consumption. This paper presents a PPG-SQA method by using raw PPG signal and convolutional neural network (CNN) with optimal parameters. The main focus of this paper is to find an optimal number of filters (16, 32, 64) and number of layers (2 and 4 layers) with rectified linear unit (ReLU) activation function and to study robustness of trained CNN models by using unseen PPG datasets and different kinds of noise sources, which are not addressed in the past studies on the CNN-based PPG-SQA methods. Evaluation results showed that the 4 layer CNN-based method had the higher accuracy of 99.58% for noise-free PPG (NF-PPG) versus wrist-cup noisy PPG signal database (MA-DB01), 99.99% for NF versus random noises added PPG (RN-PPG) signals, and 75.80% for NF-PPG versus acceleration corrupted PPG signals (MA-DB02). For the unknown dataset, the 4-layer CNN model had the higher accuracy of 96.71% for NF-PPG versus MA-DB01 and 99.04% for NF versus RN-PPG, and the 2-layer CNN model had the higher accuracy of 76.16% for NF-PPG versus MA-DB02 PPG segments. Results demonstrate that the CNN-based PPG-SQA method with optimal parameters is not only improve the accuracy but can also reduce the computational load as compared with other existing methods.

Activation functions facilitate deep neural networks by introducing non-linearity to the learning process. The non-linearity feature gives the neural network the ability to learn complex patterns. Recently, the most widely used activation function is the Rectified Linear Unit (ReLU). Though, other various existing activation including hand-designed alternatives to ReLU have been proposed. However, none has succeeded in replacing ReLU due to their existing inconsistencies. In this work, activation function called ReLUMemristor-like Activation Function (RMAF) is proposed to leverage benefits of negative values in neural networks. RMAF introduces a constant parameter (α) and a threshold parameter (p) making the function smooth, non-monotonous, and introduces non-linearity in the network. Our experiments show that, the RMAF works better than ReLU and other activation functions on deeper models and across number of challenging datasets. Firstly, experiments are performed by training and classifying on multi-layer perceptron (MLP) over benchmark data such as the Wisconsin breast cancer, MNIST, Iris and Car evaluation. RMAF achieves high performance of 98.74%, 99.67%, 98.81% and 99.42% respectively, compared to Sigmoid, Tanh and ReLU. Secondly, experiments were performed on convolution neural network (ResNet) over MNIST, CIFAR-10 and CIFAR-100 data and observed the proposed activation function achieves higher performance accuracy of 99.73%, 98.77% and 79.82% respectively than Tanh, ReLU and Swish. Additionally, we experimented our work on deep networks i.e. squeeze network (SqueezeNet), Dense connected neural network (DenseNet121) and ImageNet dataset, which RMAF produced the best performance. We note that, the RMAF converges faster than the other functions and can replace ReLU in any neural network due to the efficiency, scalability and its similarity to both ReLU and Swish.

This research aims to develop a real-time monitoring system for peatland fire potential based on the Internet of Things (IoT) with a focus on early detection of potential peatland fires. The main problem to be solved is the lack of an effective system in the early detection of potential peatland fires, which can cause serious environmental impacts. The method used involves the use of air temperature, air humidity, soil moisture, and fire detection sensors integrated with alarm-based alerts. Data collection is done in real-time to provide a deeper understanding of peatland conditions and potential fire risks. The research results show that the developed system is capable of providing accurate and fast information related to peatland conditions, thus helping to prevent and reduce the impact of peatland fires. With this system, it is expected to increase efficiency in early fire detection and minimize the losses caused by peatland fires.

The significance of instrument recognition based on audio signals lies in its broad potential across diverse fields such as music education, intelligent technology, and even medical diagnosis. In this study, we focus on tackling the challenges posed by the OpenMIC-2018 (Open Museum Identification Challenge-2018) dataset. Leveraging the powerful nonlinear modeling capabilities of convolutional neural networks (CNNs), the research aims to address common interference factors in instrument recognition, such as background noise, pitch variations, and volume fluctuations during performances. By effectively mitigating these challenges, this approach enhances the accuracy and precision of instrument recognition, offering valuable contributions to both academic research and practical applications. Firstly, FFT (fast Fourier transform) is used to extract MFCC (Mel-frequency cepstral coefficient), chroma, time-domain, and spectral energy from each audio frame. Initial CNN models with 10 different hyperparameters are trained, and the prediction results are merged with the original features. Then, one-dimensional convolutional layers are used for spectral feature convolution operations, and pooling layers are used for downsampling. ReLU (rectified linear unit) is used as the activation function and nonlinearity is applied. Dropout layers are added between convolutional layers and a portion of neurons are randomly set to zero. Next, the learning rate is adjusted based on cross-validation. For multi-label classification tasks, a binary cross-entropy loss is used and parameters are updated through backpropagation algorithm. Finally, a secondary CNN model is used. The merged features are input and the prediction results are obtained. The research results indicate that the innovative method used achieves an average accuracy of 0.92 on OpenMIC-2018, with an accuracy of 0.97 for accordion, flute, and organ, realizing relatively precise instrument recognition.

Early fire detection is an important factor that can reduce economic and environmental damage and reduce the number of victims. Despite the growing popularity of neural networks as a modern method for solving problems in computer vision, methodological problems often arise in works in this subject area, leading to a decrease or complete devaluation of practical results. This study is devoted to finding such problems among existing works on fire detection. The first section contains a contrast analysis of two works, during which 11 meta-criteria were identified to assess the quality of studies. The second section contains an overview of several works devoted to fire detection in various conditions, both by «classical» methods and using convolutional neural networks. The importance of the correct choice of metrics, the need to choose a model as a process, and a full description of the source data are shown.

Motivation: Certain studies use short-TE MRS to estimate metabolites such as gamma-aminobutyric acid. The findings of such studies hinge on the correlation of this technique to the gold-standard edited MRS technique. Goal(s): We investigate how the false negative rate and false positive rate of studies vary as a function of correlation between short-TE and MEGA-edited metabolite estimates. Approach: Simulated data was used to numerically estimate the false positive and false negative rates, using parameters obtained from the literature. Results: We show that these studies can have largely inflated false positive and false negative rates as compared to their nominally designed values. Impact: The false negative and false positive rate can be markedly inflated when using short-TE MRS to estimate metabolites such as gamma-aminobutyric acid. This calls for increased caution in interpreting results, and the accommodation of these effects when designing statistical analyses.

Rectified linear units (ReLU) are known to be effective in many deep learning methods. Inspired by linear-mapping technique used in other super-resolution (SR) methods, we reinterpret ReLU into point-wise multiplication of an identity mapping and a switch, and finally present a novel nonlinear unit, called a selection unit (SU). While conventional ReLU has no direct control through which data is passed, the proposed SU optimizes this on-off switching control, and is therefore capable of better handling nonlinearity functionality than ReLU in a more flexible way. Our proposed deep network with SUs, called SelNet, was top-5th ranked in NTIRE2017 Challenge, which has a much lower computation complexity compared to the top-4 entries. Further experiment results show that our proposed SelNet outperforms our baseline only with ReLU (without SUs), and other state-of-the-art deep-learning-based SR methods.

The rising threat of heat-related and fire incidents underscores the urgent need for advanced thermal and fire detection systems to ensure timely and accurate responses. This report presents a smart fire detection project utilizing the YOLOv5 deep learning model. The project aims to design an early fire detection system with real-time capabilities. The proposed system implements a convolutional neural network (CNN) and the YOLOv5 real-time object identification system, enhancing fire detection through anchor box optimization. In the incident of a fire, the system sends an alert to the user’s Telegram app bot via the Internet of Things (IoT), assisting in taking necessary precautions. The project demonstrates notable efficiency in fire detection and alerting capabilities, with system evaluation metrics showing an F1 score of 95%, mAP@50 of 97%, accuracy 96.3%, and a recall rate of 89%. These results underscore the system's reliability and precision. The project contributes significantly to Sustainable Development Goals (SDG), goal 9 for industry, innovation, and infrastructure, and 11 for sustainable cities and communities highlighting its potential to enhance fire safety measures in various settings.