The manual extraction method of Agarwood resinous compound is laborious work, requires skilled workers, and is subject to human errors. Commercial Agarwood industries have been actively exploring using Computer Numerical Control (CNC) machines to replace human effort for this particular task. The CNC machine accepts a G-code script produced from a binary image in which the wood region that needs to be chiselled off is marked with (0, 0, 0) as its RGB value. Rather than requiring a human expert to perform the region marking, we propose using a Deep learning image segmentation method instead. Our setup involves a camera that captures the cross-section image and then passes the image file to a computer. The computer performs the automated image segmentation and feeds the CNC machine with a G-code script. In this article, we report the initial segmentation results achieved using a state-of-the-art Deep learning segmentation method and discuss potential improvements to refine the segmentation accuracy.
Recognizing various surgical tools, actions and phases from surgery videos is an important problem in computer vision with exciting clinical applications. Existing deep-learning-based methods for this problem either process each surgical video as a series of independent images without considering their dependence, or rely on complicated deep learning models to count for dependence of video frames. In this study, we revealed from exploratory data analysis that surgical videos enjoy relatively simple semantic structure, where the presence of surgical phases and tools can be well modeled by a compact hidden Markov model (HMM). Based on this observation, we propose an HMM-stabilized deep learning method for tool presence detection. A wide range of experiments confirm that the proposed approaches achieve better performance with lower training and running costs, and support more flexible ways to construct and utilize training data in scenarios where not all surgery videos of interest are extensively labelled. These results suggest that popular deep learning approaches with over-complicated model structures may suffer from inefficient utilization of data, and integrating ingredients of deep learning and statistical learning wisely may lead to more powerful algorithms that enjoy competitive performance, transparent interpretation and convenient model training simultaneously.
Deep learning methods in LiDAR-based archaeological research often leverage visualisation techniques derived from Digital Elevation Models to enhance characteristics of archaeological objects present in the images. This paper investigates the impact of visualisations on deep learning performance through a comprehensive testing framework. The study involves the use of eight semantic segmentation models to evaluate seven diverse visualisations across two study areas, encompassing five archaeological classes. Experimental results reveal that the choice of appropriate visualisations can influence performance by up to 8%. Yet, pinpointing one visualisation that outperforms the others in segmenting all archaeological classes proves challenging. The observed performance variation, reaching up to 25% across different model configurations, underscores the importance of thoughtfully selecting model configurations and LiDAR visualisations for successfully segmenting archaeological objects.
Close and continuous interaction with rich contacts is a crucial aspect of human activities (e.g. hugging, dancing) and of interest in many domains like activity recognition, motion prediction, character animation, etc. However, acquiring such skeletal motion is challenging. While direct motion capture is expensive and slow, motion editing/generation is also non-trivial, as complex contact patterns with topological and geometric constraints have to be retained. To this end, we propose a new deep learning method for two-body skeletal interaction motion augmentation, which can generate variations of contact-rich interactions with varying body sizes and proportions while retaining the key geometric/topological relations between two bodies. Our system can learn effectively from a relatively small amount of data and generalize to drastically different skeleton sizes. Through exhaustive evaluation and comparison, we show it can generate high-quality motions, has strong generalizability and outperforms traditional optimization-based methods and alternative deep learning solutions.
Hospital readmission, defined as patients being re-hospitalized shortly after discharge, is a critical concern as it impacts patient outcomes and healthcare costs. Identifying patients at risk of readmission allows for timely interventions, reducing re-hospitalization rates and overall treatment costs. This study focuses on predicting patient readmission within less than 30 days using text mining techniques applied to discharge report texts from electronic health records (EHR). Various machine learning and deep learning methods were employed to develop a classification model for this purpose. A novel aspect of this research involves leveraging the Bio-Discharge Summary Bert (BDSS) model along with principal component analysis (PCA) feature extraction to preprocess data for deep learning model input. Our analysis of the MIMIC-III dataset indicates that our approach, which combines the BDSS model with a multilayer perceptron (MLP), outperforms state-of-the-art methods. This model achieved a recall of 94% and an area under the curve (AUC) of 75%, showcasing its effectiveness in predicting patient readmissions. This study contributes to the advancement of predictive modeling in healthcare by integrating text mining techniques with deep learning algorithms to improve patient outcomes and optimize resource allocation.
Automated data labeling techniques are crucial for accelerating the development of deep learning models, particularly in complex medical imaging applications. However, ensuring accuracy and efficiency remains challenging. This paper presents iterative refinement strategies for automated data labeling in facial landmark diagnosis to enhance accuracy and efficiency for deep learning models in medical applications, including dermatology, plastic surgery, and ophthalmology. Leveraging feedback mechanisms and advanced algorithms, our approach iteratively refines initial labels, reducing reliance on manual intervention while improving label quality. Through empirical evaluation and case studies, we demonstrate the effectiveness of our proposed strategies in deep learning tasks across medical imaging domains. Our results highlight the importance of iterative refinement in automated data labeling to enhance the capabilities of deep learning systems in medical imaging applications.
Edge detection is a long-standing problem in computer vision. Despite the efficiency of existing algorithms, their performance, however, rely heavily on the pre-trained weights of the backbone network on the ImageNet dataset. The use of pre-trained weights in previous methods significantly increases the difficulty to design new models for edge detection without relying on existing well-trained ImageNet models, as pre-training the model on the ImageNet dataset is expensive and becomes compulsory to ensure the fairness of comparison. Besides, the pre-training and fine-tuning strategy is not always useful and sometimes even inaccessible. For instance, the pre-trained weights on the ImageNet dataset are unlikely to be helpful for edge detection in Synthetic Aperture Radar (SAR) images due to strong differences in the statistics between optical images and SAR images. Moreover, no dataset has comparable size to the ImageNet dataset for SAR image processing. In this work, we study the performance achievable by state-of-the-art deep learning based edge detectors in publicly available datasets when they are trained from scratch, and devise a new network architecture, the multi-stream and multi-scale fusion net (msmsfnet), for edge detection. We show in our experiments that by training all models from scratch, our model outperforms state-of-the-art edge detectors in three publicly available datasets. We also demonstrate the efficiency of our model for edge detection in SAR images, where no useful pre-trained weight is available. Finally, We show that our model is able to achieve competitive performance on the BSDS500 dataset when the pre-trained weights are used.
In today's digital world, cyberbullying is a serious problem that can harm the mental and physical health of people who use social media. This paper explains just how serious cyberbullying is and how it really affects indi-viduals exposed to it. It also stresses how important it is to find better ways to detect cyberbullying so that online spaces can be safer. Plus, it talks about how making more accurate tools to spot cyberbullying will be really helpful in the future. Our paper introduces a deep learning-based ap-proach, primarily employing BERT and BiLSTM architectures, to effective-ly address cyberbullying. This approach is designed to analyse large vol-umes of posts and predict potential instances of cyberbullying in online spaces. Our results demonstrate the superiority of the hateBERT model, an extension of BERT focused on hate speech detection, among the five mod-els, achieving an accuracy rate of 89.16%. This research is a significant con-tribution to "Computational Intelligence for Social Transformation," prom-ising a safer and more inclusive digital landscape.
Earth observation (EO) satellite missions have been providing detailed images about the state of the Earth and its land cover for over 50 years. Long term missions, such as NASA's Landsat, Terra, and Aqua satellites, and more recently, the ESA's Sentinel missions, record images of the entire world every few days. Although single images provide point-in-time data, repeated images of the same area, or satellite image time series (SITS) provide information about the changing state of vegetation and land use. These SITS are useful for modeling dynamic processes and seasonal changes such as plant phenology. They have potential benefits for many aspects of land and natural resource management, including applications in agricultural, forest, water, and disaster management, urban planning, and mining. However, the resulting satellite image time series (SITS) are complex, incorporating information from the temporal, spatial, and spectral dimensions. Therefore, deep learning methods are often deployed as they can analyze these complex relationships. This review presents a summary of the state-of-the-art methods of modelling environmental, agricultural, and other Earth observation variables from SITS data using deep learning methods. We aim to provide a resource for remote sensing experts interested in using deep learning techniques to enhance Earth observation models with temporal information.
Cardiac Magnetic Resonance (CMR) is established as a non-invasive imaging technique for evaluation of heart function, anatomy, and myocardial tissue characterization. Quantitative biomarkers are central for diagnosis and management of heart disease. Deep learning (DL) is playing an ever more important role in extracting these quantitative measures from CMR images. While many researchers have reported promising results in training and evaluating models, model deployment into the imaging workflow is less explored. A new imaging AI framework, the InlineAI, was developed and open-sourced. The main innovation is to enable the model inference inline as a part of imaging computation, instead of as an offline post-processing step and to allow users to plug in their models. We demonstrate the system capability on three applications: long-axis CMR cine landmark detection, short-axis CMR cine analysis of function and anatomy, and quantitative perfusion mapping. The InlineAI allowed models to be deployed into imaging workflow in a streaming manner directly on the scanner. The model was loaded and inference on incoming images were performed while the data acquisition was ongoing, and results were sent back to scanner. Several biomarkers were extracted from model outputs in the demonstrated applications and reported as curves and tabular values. All processes are full automated. the model inference was completed within 6-45s after the end of imaging data acquisition.
This paper presents a deep learning-based approach for hourly power outage probability prediction within census tracts encompassing a utility company's service territory. Two distinct deep learning models, conditional Multi-Layer Perceptron (MLP) and unconditional MLP, were developed to forecast power outage probabilities, leveraging a rich array of input features gathered from publicly available sources including weather data, weather station locations, power infrastructure maps, socio-economic and demographic statistics, and power outage records. Given a one-hour-ahead weather forecast, the models predict the power outage probability for each census tract, taking into account both the weather prediction and the location's characteristics. The deep learning models employed different loss functions to optimize prediction performance. Our experimental results underscore the significance of socio-economic factors in enhancing the accuracy of power outage predictions at the census tract level.
Nasopharyngeal carcinoma (NPC) is one of the understudied yet deadliest cancers in South East Asia. In Malaysia, the prevalence is identified mainly in Sarawak, among the ethnic of Bidayuh. NPC is often late-diagnosed because it is asymptomatic at the early stage. There are several tissue representations from the nasopharynx biopsy, such as nasopharyngeal inflammation (NPI), lymphoid hyperplasia (LHP), nasopharyngeal carcinoma (NPC) and normal tissue. This paper is our first initiative to identify the difference between NPC, NPI and normal cases. Seven whole slide images (WSIs) with gigapixel resolutions from seven different patients and two hospitals were experimented with using two test setups, consisting of a different set of images. The tissue regions are patched into smaller blocks and classified using DenseNet architecture with 21 dense layers. Two tests are carried out, each for proof of concept (Test 1) and real-test scenario (Test 2). The accuracy achieved for NPC class is 94.8% for Test 1 and 67.0% for Test 2.
Traffic forecasting is crucial for intelligent transportation systems. It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data. However, recent deep-learning architectures require intricate model designs and lack an intuitive understanding of the mapping from input data to predicted results. Achieving both accuracy and explainability in traffic prediction models remains a challenge due to the complexity of traffic data and the inherent opacity of deep learning models. To tackle these challenges, we propose a Traffic flow Prediction model based on Large Language Models (LLMs) to generate explainable traffic predictions, named xTP-LLM. By transferring multi-modal traffic data into natural language descriptions, xTP-LLM captures complex time-series patterns and external factors from comprehensive traffic data. The LLM framework is fine-tuned using language-based instructions to align with spatial-temporal traffic flow data. Empirically, xTP-LLM shows competitive accuracy compared with deep learning baselines, while providing an intuitive and reliable explanation for predictions. This paper contributes to advancing explainable traffic prediction models and lays a foundation for future exploration of LLM applications in transportation. To the best of our knowledge, this is the first study to use LLM for explainable prediction of traffic flows.
Aspect-based sentiment analysis predicts sentiment polarity with fine granularity. While graph convolutional networks (GCNs) are widely utilized for sentimental feature extraction, their naive application for syntactic feature extraction can compromise information preservation. This study introduces an innovative edge-enhanced GCN, named SentiSys, to navigate the syntactic graph while preserving intact feature information, leading to enhanced performance. Specifically,we first integrate a bidirectional long short-term memory (Bi-LSTM) network and a self-attention-based transformer. This combination facilitates effective text encoding, preventing the loss of information and predicting long dependency text. A bidirectional GCN (Bi-GCN) with message passing is then employed to encode relationships between entities. Additionally, unnecessary information is filtered out using an aspect-specific masking technique. To validate the effectiveness of our proposed model, we conduct extensive evaluation experiments on four benchmark datasets. The experimental results demonstrate enhanced performance in aspect-based sentiment analysis with the use of SentiSys.
Image forgery is a topic that has been studied for many years. Before the breakthrough of deep learning, forged images were detected using handcrafted features that did not require training. These traditional methods failed to perform satisfactorily even on datasets much worse in quality than real-life image manipulations. Advances in deep learning have impacted image forgery detection as much as they have impacted other areas of computer vision and have improved the state of the art. Deep learning models require large amounts of labeled data for training. In the case of image forgery, labeled data at the pixel level is a very important factor for the models to learn. None of the existing datasets have sufficient size, realism and pixel-level labeling at the same time. This is due to the high cost of producing and labeling quality images. It can take hours for an image editing expert to manipulate just one image. To bridge this gap, we automate data generation using image composition techniques that are very related to image forgery. Unlike other automated data generation frameworks, we use state of the art image composition deep learning models to generate spliced images close to the quality of real-life manipulations. Finally, we test the generated dataset on the SOTA image manipulation detection model and show that its prediction performance is lower compared to existing datasets, i.e. we produce realistic images that are more difficult to detect. Dataset will be available at https://github.com/99eren99/DIS25k .
Deep Learning models are incredibly data-hungry and require very large labeled datasets for supervised learning. As a consequence, these models often suffer from overfitting, limiting their ability to generalize to real-world examples. Recent advancements in diffusion models have enabled the generation of photorealistic images based on textual inputs. Leveraging the substantial datasets used to train these diffusion models, we propose a technique to utilize generated images to augment existing datasets. This paper explores various strategies for effective data augmentation to improve the out-of-domain generalization capabilities of deep learning models.
Forecasting rainfall in tropical areas is challenging due to complex atmospheric behaviour, elevated humidity levels, and the common presence of convective rain events. In the Indian context, the difficulty is further exacerbated because of the monsoon intra seasonal oscillations, which introduce significant variability in rainfall patterns over short periods. Earlier investigations into rainfall prediction leveraged numerical weather prediction methods, along with statistical and deep learning approaches. This study introduces deep learning spatial model aimed at enhancing rainfall prediction accuracy on a finer scale. In this study, we hypothesize that integrating physical understanding improves the precipitation prediction skill of deep learning models with high precision for finer spatial scales, such as cities. To test this hypothesis, we introduce a physics informed ConvLSTM2D model to predict precipitation 6hr and 12hr ahead for Mumbai, India. We utilize ERA5 reanalysis data select predictor variables, across various geopotential levels. The ConvLSTM2D model was trained on the target variable precipitation for 4 different grids representing different spatial grid locations of Mumbai. Thus, the use of the ConvLSTM2D model for rainfall prediction, utilizing physics informed data from specific grids with limited spatial information, reflects current advancements in meteorological research that emphasize both efficiency and localized precision.
Deep learning techniques have been demonstrated to surpass preceding cutting-edge machine learning techniques in recent years, with computer vision being one of the most prominent examples. However, deep learning models suffer from significant drawbacks when deployed in resource-constrained environments due to their large model size and high complexity. Knowledge Distillation is one of the prominent solutions to overcome this challenge. This review paper examines the current state of research on knowledge distillation, a technique for compressing complex models into smaller and simpler ones. The paper provides an overview of the major principles and techniques associated with knowledge distillation and reviews the applications of knowledge distillation in the domain of computer vision. The review focuses on the benefits of knowledge distillation, as well as the problems that must be overcome to improve its effectiveness.
Quadratic Assignment Problem (QAP) is a practical combinatorial optimization problems that has been studied for several years. Since it is NP-hard, solving large problem instances of QAP is challenging. Although heuristics can find semi-optimal solutions, the execution time significantly increases as the problem size increases. Recently, solving combinatorial optimization problems by deep learning has been attracting attention as a faster solver than heuristics. Even with deep learning, however, solving large QAP is still challenging. In this paper, we propose the deep reinforcement learning model called the two-stage graph pointer network (GPN) for solving QAP. Two-stage GPN relies on GPN, which has been proposed for Euclidean Traveling Salesman Problem (TSP). First, we extend GPN for general TSP, and then we add new algorithms to that model for solving QAP. Our experimental results show that our two-stage GPN provides semi-optimal solutions for benchmark problem instances from TSPlib and QAPLIB.
Color Doppler echocardiography enables visualization of blood flow within the heart. However, the limited frame rate impedes the quantitative assessment of blood velocity throughout the cardiac cycle, thereby compromising a comprehensive analysis of ventricular filling. Concurrently, deep learning is demonstrating promising outcomes in post-processing of echocardiographic data for various applications. This work explores the use of deep learning models for intracardiac Doppler velocity estimation from a reduced number of filtered I/Q signals. We used a supervised learning approach by simulating patient-based cardiac color Doppler acquisitions and proposed data augmentation strategies to enlarge the training dataset. We implemented architectures based on convolutional neural networks. In particular, we focused on comparing the U-Net model and the recent ConvNeXt models, alongside assessing real-valued versus complex-valued representations. We found that both models outperformed the state-of-the-art autocorrelator method, effectively mitigating aliasing and noise. We did not observe significant differences between the use of real and complex data. Finally, we validated the models on in vitro and in vivo experiments. All models produced quantitatively comparable results to the baseline and were more robust to noise. ConvNeXt emerged as the sole model to achieve high-quality results on in vivo aliased samples. These results demonstrate the interest of supervised deep learning methods for Doppler velocity estimation from a reduced number of acquisitions.