Deep Learning Models for Road Passability Detection during Flood Events Using Social Media Data

Social media provide valuable information for disaster risk reduction as well as a disaster emergency response. Previous studies claim that social media data can be used in the emergency response effort, which is worthwhile for the Government, BNPB, as well as the community, to get a direct and credible information about the ongoing disaster situations. However, the social media data has not been widely used for emergency response and situational awareness in Indonesia. Therefore, in this paper we implement BERT method applied to a set of tweets related to Jakarta Flood in early 2020. We have crawled the tweet dataset during the Jakarta flood disaster in early 2020 which had become a trending topic on Twitter. We aim to identify the relevance tweets that may provide useful information related to emergency responses in disaster management. The experimental results indicate promising outcomes. However, the quality of the dataset greatly influences the system performance.

Introduction. The article considers the solution of the problem of detecting fires at technological facilities in automatic mode. To solve this problem, an approach was chosen to create a convolutional neural network capable of operating on a real-time video stream. Aims and Purposes. The aim of this work is to create a neural network capable of detecting flames and smoke in the image from CCTV cameras. The purposes of the work include: selection of the optimal architecture of the neural network in accordance with the latest research in this field; speeding up the chosen architecture using quantization and filter thinning techniques. Methods. Different architectures of convolutional neural networks performing the task of detecting objects in an image are considered. Their performance and quality of work are compared. The YOLOv5 architecture, its target function, training methods and ways of speeding up work are considered. Results and discu ssion. The paper shows the results of training a convolutional neural network of the YOLOv5 architecture for the task of flame and smoke detection, as well as how the results change when applying neural network acceleration methods. It was determined that the use of such acceleration methods such as quantization and filter cleaning can significantly increase up the speed of the neural network, while almost no loss in accuracy of operation. Conclusions. As a result of the conducted work, the architecture of the neural network was determined for performing the task of detecting a fire source. Based on the chosen architecture, a neural network was trained to detect flames and smoke in the image. The speed of its work allows to process video stream in real-time without using graphic accelerator.

Meetings are a common activity in professional contexts, and it remains challenging to endow vocal assistants with advanced functionalities to facilitate meeting management. In this context, a task like active speaker detection can provide useful insights to model interaction between meeting participants. Detection of the active speaker can be performed using only video based on the movements of the participants of a meeting. Depending on the assistant design and each participant position regarding the device, active speaker detection can benefit from information coming from visual and audio modalities. Motivated by our application context related to advanced meeting assistant, we want to combine audio and visual information to achieve the best possible performance. In this paper, we propose two different types of fusion (naive fusion and attention-based fusion) for the detection of the active speaker, combining two visual modalities and an audio modality through neural networks. In addition, the audio modality is mainly processed using neural networks. For comparison purpose, classical unsupervised approaches for audio feature extraction are also used. We expect visual data centered on the face of each participant to be very appropriate for detecting voice activity, based on the detection of lip and facial gestures. Thus, our baseline system uses visual data (video) and we chose a 3D Convolutional Neural Network (CNN) architecture, which is effective for simultaneously encoding appearance and movement. To improve this system, we supplemented the visual information by processing the audio stream with a CNN or an unsupervised speaker diarization system. We have further improved this system by adding visual modality information using motion through optical flow. We evaluated our proposal with a public and state-of-the-art benchmark: the AMI corpus. We analysed the contribution of each system to the merger carried out in order to determine if a given participant is currently speaking. We also discussed the results we obtained. Besides, we have shown that, for our application context, adding motion information greatly improves performance. Finally, we have shown that attention-based fusion improves performance while reducing the standard deviation.

A complete global flood event record helps researchers analyse the distribution law of global floods and better formulate and manage disaster prevention and reduction policies. This study used GRACE terrestrial water storage and precipitation data combined with high-frequency filtering, anomaly detection and flood potential index methods to successfully extract historical flood days quasi-globally between Apr. 1st, 2002, and Aug. 31st, 2016, and further compared and validated the results with Dartmouth Flood Observatory (DFO) data, Global Runoff Data Centre (GRDC) discharge data, news reports and social media data. The results showed that the floods extracted in this study can cover 81 % of the flood events in the DFO database and supplement many additional flood events not recorded by the DFO. Moreover, the probability of detection exceeding 0.5 reached 62 % in level-4 river basins compared to flood events derived from the GRDC discharge data. These detection capabilities and detection results are both good. We finally provided flood day products with 1° spatial resolution covering the range of 60° S–60° N from Apr. 1st, 2002, to Aug. 31st, 2016. This research provides a data foundation for the mechanistic analysis and attribution of global flood events.

The design of neural network models involves numerous complexities, including the determination of input vectors, choosing the number of hidden layers and their computational units, and specifying activation functions for the latter. The combinatoric possibilities are daunting, yet experience has yielded informal guidelines that can be useful. Alternatively, current research on genetic algorithms (GA) suggests that they might be of practical use as a formal method of determining ‘good’ architectures for neural networks. In this paper, we use a genetic algorithm to find effective architectures for backpropagation neural networks (BP). We compare the performance of heuristically designed BP networks with that of GA-designed BP networks. Our test domains are sets of problems having compensatory, conjunctive, and mixed-decision structures. The results of our experiment suggest that heuristic methods produce architectures that are simpler and yet perform comparatively well. © 1998 John Wiley & Sons, Ltd.

Natural disasters cause significant damage, casualties and economical losses. Twitter has been used to support prompt disaster response and management because people tend to communicate and spread information on public social media platforms during disaster events. To retrieve real-time situational awareness (SA) information from tweets, the most effective way to mine text is using natural language processing (NLP). Among the advanced NLP models, the supervised approach can classify tweets into different categories to gain insight and leverage useful SA information from social media data. However, high-performing supervised models require domain knowledge to specify categories and involve costly labelling tasks. This research proposes a guided latent Dirichlet allocation (LDA) workflow to investigate temporal latent topics from tweets during a recent disaster event, the 2020 Hurricane Laura. With integration of prior knowledge, a coherence model, LDA topics visualisation and validation from official reports, our guided approach reveals that most tweets contain several latent topics during the 10-day period of Hurricane Laura. This result indicates that state-of-the-art supervised models have not fully utilised tweet information because they only assign each tweet a single label. In contrast, our model can not only identify emerging topics during different disaster events but also provides multilabel references to the classification schema. In addition, our results can help to quickly identify and extract SA information to responders, stakeholders and the general public so that they can adopt timely responsive strategies and wisely allocate resource during Hurricane events.

Deep neural networks (DNNs) are advantageous for representing complex nonlinear relationships. This paper applies DNNs to source localization in a shallow water environment. Two methods are proposed to estimate the range and depth of a broadband source through different neural network architectures. The first adopts the classical two-stage scheme, in which feature extraction and DNN analysis are independent steps. The eigenvectors associated with the modal signal space are extracted as the input feature. Then, the time delay neural network is exploited to model the long term feature representation and constructs the regression model. The second concerns a convolutional neural network-feed-forward neural network (CNN-FNN) architecture, which trains the network directly by taking the raw multi-channel waveforms as input. The CNNs are expected to perform spatial filtering for multi-channel signals, in an operation analogous to time domain filters. The outputs of CNNs are summed as the input to FNN. Several experiments are conducted on the simulated and experimental data to evaluate the performance of the proposed methods. The results demonstrate that DNNs are effective for source localization in complex and varied water environments, especially when there is little precise environmental information.

Multilevel image segmentation with adaptive image context based thresholding

Social media data have emerged as a new source for detecting and monitoring disaster events. A number of recent studies have suggested that social media data streams can be used to mine actionable data for emergency response and relief operation. However, no effort has been made to classify social media data into stages of disaster management (mitigation, preparedness, emergency response, and recovery), which has been used as a common reference for disaster researchers and emergency managers for decades to organize information and streamline priorities and activities during the course of a disaster. This paper makes an initial effort in coding social media messages into different themes within different disaster phases during a time-critical crisis by manually examining more than 10,000 tweets generated during a natural disaster and referencing the findings from the relevant literature and official government procedures involving different disaster stages. Moreover, a classifier based on logistic regression is trained and used for automatically mining and classifying the social media messages into various topic categories during various disaster phases. The classification results are necessary and useful for emergency managers to identify the transition between phases of disaster management, the timing of which is usually unknown and varies across disaster events, so that they can take action quickly and efficiently in the impacted communities. Information generated from the classification can also be used by the social science research communities to study various aspects of preparedness, response, impact and recovery.

Natural disasters, such as flood events, are expected to increase in their frequency and severity, which results in higher flood risk without additional adaptation measures. The information gained from flood risk models is essential in flood risk management. However, vulnerability model components in the form of depth-damage curves are often a large driver of uncertainty and empirical vulnerability curves are rarely estimated due to a lack of damage data from flood events. This study uses a unique dataset with experienced damages and the implementation of flood damage mitigation (FDM) measures on the household level, collected after the flood event in the Netherlands in 2021. Two main findings emerge from an analysis of this dataset. First, depth-damage curves that control for several hazard, exposure and vulnerability indicators are estimated. These curves serve as an update to current input in flood risk models, where previous vulnerability estimates from the Netherlands are based from a flood event in the 1950s. Second, it is found that previous studies on the effectiveness of FDM measures are prone to a selection bias, as households that do and do not take FDM measures systematically differ in their risk profiles. By using an Instrumental Variable (IV)-estimation, this study overcomes this selection bias and finds significant reductions in flood damage to both buildings and household contents due to FDM measures.

Aim. To study various network architecture options for implementing an electronic differential system in an electric vehicle. Materials and Methods. The study primarily used comparative analysis to identify the most rational neural network (NN) architecture for processing numerical data structured as arrays. Results. The analysis revealed that a deep learning neural network is the most effective choice. For future developments, and after experimental confirmation, a recurrent neural network could also be a viable option. Conclusion. The study confirmed that achieving the desired goal is not feasible using convolutional neural networks, large language models, random vector functional communication networks and radial-basis functional NNs.

Nowadays with the deployment of a large and dense heterogeneous networks more sophisticated algorithms for resource scheduling are needed. Implementing hard coded scheduling algorithms without taking into account the very specific dynamic of the traffic generated by the mobile users can lead to a network performance quite far from the optimal. By using novel machine learning (ML) algorithms we can store not only the raw traffic data and its variations but also build the so-called heat maps, reflecting the changes of the traffic over time, space and per user. Using neural network (NN) architectures, trained by the raw data statistics, we can store the network traffic model at minimum data storage without the need of keeping and looking up at the raw data. Using such NN architecture the network state in next time intervals could be predicted and this prediction used for decision making about how the network resources to be scheduled among the active mobile users. To implement adaptive resource scheduling named “AdaptSch” a neural network architecture with two main blocks is proposed. The simulation results show that by incorporating a neural classifier for adapting the resource scheduler we can utilize the advantages and the effectiveness of multiple scheduler algorithms and improve overall throughput and packet delay.

The aim of this paper is to investigate new neural network algorithms, architectures and models which are inspired by the image processing capability of the visual system in the human brain, and subsequently to apply these models to medical imaging(MI) applications. Realizing the neural network architecture on FPGA that supports parallelism and reconfigurability. A sincere attempt is taken up to implement the complex and massive parallel architecture on FPGA optimising speed, area, and power with out compromising on image quality and SNR that is a very important criteria for medical image compression. Multi layered neural network (NN) architecture is proposed for compression of high-resolution image, the architecture is implemented on FPGA as it supports reconfigurability. The architecture considered has N-M-N (64-4-64) multi-layered NN structure, which achieves compression ratio of (CR) 93.75. Compression ratio is reconfigurable with change in M. The architecture is generalized and can achieve compression ratios from 2 to 99, which is reconfigurable. Performance of any neural network architecture for compression depends on training; this architecture considers general back propagation training. The training is performed offline, with known set of image samples consisting most of the properties of any standard image. The Mean Square Error (MSE) computed during every iteration of training is scaled and fed back into the network to update the weight matrix at specific points, this reduces the training time. As the weight matrix occupies more space for storage, the redundancies in the weight matrix are exploited and a storage space is created with minimum memory requirement on FPGA. Compression ratios obtained demonstrate performance superiority of the network as compared with JPEG compression standard. Inserting noise on the compressed sets of data, tests the network performance. The hardware complexity, area requirement, speed is compared and discussed; there is a saving of 22% of space on FPGA, with 40% increase in speed, and reducing the power by 12%. The major advantage of this architecture is its reconfigurability on the architecture size that achieves different compression ratios.

Predicting the next activity of a running execution trace of a business process represents a challenging task in process mining. The problem has been already tackled by using different machine learning approaches. Among them, deep artificial neural networks architectures suited for sequential data, such as recurrent neural networks (RNNs), recently achieved the state of the art results. However, convolutional neural networks (CNNs) architectures can outperform RNNs on tasks for sequence modeling, such as machine translation. In this paper we investigate the use of stacked inception CNN modules for the next-activity prediction problem. The proposed neural network architecture leads to better results when compared to RNNs architectures both in terms of computational efficiency and prediction accuracy on different real-world datasets.

Disaster management urgently requires mechanisms for achieving situation awareness (SA) in a timely manner, allowing authorities to react in an appropriate way to reduce the impact on affected people and infrastructure. In such situations, no matter if they are human-induced like shootings or natural ones like earthquakes or floods, social media such as Twitter are frequently used communication channels, making them a highly valuable additional data source for enhancing SA. The challenge is, however, to identify out of the tremendous mass of irrelevant and non informative social media data those messages being really “informative”, i.e., contributing to SA in a certain disaster situation. Existing approaches on machine-learning driven informativeness classification most often focus on specific disaster types, such as shootings or floods, thus lacking general applicability and falling short in classification of new disaster events. Therefore, this article puts forward the following three contributions: First, in order to better understand the underlying social media data source, an in-depth analysis of existing Twitter data on 26 different disaster events is provided along temporal, spatial, linguistic, and source dimensions. Second, based thereupon, a cross-domain informativeness classifier is proposed being not focused on specific disaster types but rather allowing for classifications across different types. Third, the applicability of this cross-domain classifier is demonstrated, showing its accuracy compared to other disaster type specific approaches.