Search

The development of artificial intelligence (AI) as a field has impacted almost all aspects of human life. More recently it has found a role in addressing developmental challenges, specifically the Sustainable Development Goals (SDGs). However, there are not enough systematic studies on analysis of the role of AI research towards the SDGs. Therefore, this article attempts to bridge this gap by identifying the major bibliometric trends and concept‐evolution trajectories in the area of AI applications for sustainable‐development goals. The research publication data for the last 20 years in the areas of artificial intelligence, machine learning, deep learning, and so forth, is obtained and computationally analysed using a framework comprising bibliometrics, path analysis and content analysis. The findings show an incremental trend in overall publications on the application of AI for SDGs across the different regions of the world. SDGs 3 (good health & well‐being) and 7 (affordable and clean energy) are found as the areas with the most applications of AI. In SDG3, the literature reflects application of AI techniques such as deep learning for precision and personalised medicine while in SDG7, a number of studies have employed AI techniques for the integration of systems for efficient generation of solar power and improving the energy efficiency of a building. Furthermore, SDG 4 (quality education), SDG 13 (climate action), SDG 11 (sustainable cities and communities) and SDG 16 (peace, justice and strong institutions) are the other SDGs where AI approaches and techniques are applied. The analytical results present a detailed insight of application of AI for achieving the SDGs. [ABSTRACT FROM AUTHOR]

Digital breast tomosynthesis (DBT) stands out as a highly robust screening technique capable of enhancing the rate at which breast cancer is detected. It also addresses certain limitations that are inherent to mammography. Nonetheless, the process of manually examining numerous DBT slices per case is notably time-intensive. To address this, computer-aided detection (CAD) systems based on deep learning have emerged, aiming to automatically identify breast tumors within DBT images. However, the current CAD systems are hindered by a variety of challenges. These challenges encompass the diversity observed in breast density, as well as the varied shapes, sizes, and locations of breast lesions. To counteract these limitations, we propose a novel method for detecting breast tumors within DBT images. This method relies on a potent dynamic ensemble technique, along with robust individual breast tumor detectors (IBTDs). The proposed dynamic ensemble technique utilizes a deep neural network to select the optimal IBTD for detecting breast tumors, based on the characteristics of the input DBT image. The developed individual breast tumor detectors hinge on resilient deep-learning architectures and inventive data augmentation methods. This study introduces two data augmentation strategies, namely channel replication and channel concatenation. These data augmentation methods are employed to surmount the scarcity of available data and to replicate diverse scenarios encompassing variations in breast density, as well as the shapes, sizes, and locations of breast lesions. This enhances the detection capabilities of each IBTD. The effectiveness of the proposed method is evaluated against two state-of-the-art ensemble techniques, namely non-maximum suppression (NMS) and weighted boxes fusion (WBF), finding that the proposed ensemble method achieves the best results with an F1-score of 84.96% when tested on a publicly accessible DBT dataset. When evaluated across different modalities such as breast mammography, the proposed method consistently attains superior tumor detection outcomes. [ABSTRACT FROM AUTHOR]

I will describe how our IT helps our business model in three dimensions: 1) Our technology platform offers our consumers the broadest range of data aggregation options including credit data, banking data, property information and payroll data. This interview provides insights into how a leading FinTech company - FinLocker is leveraging cloud and Artificial Intelligence (AI) technologies to offer solutions to multiple stakeholders in the mortgage industry, including mortgage originators, lenders, servicers, banks, credit unions, and credit counselors. [Extracted from the article]

Antral follicle Count (AFC) is a non-invasive biomarker used to assess ovarian reserves through transvaginal ultrasound (TVUS) imaging. Antral follicles' diameter is usually in the range of 2–10 mm. The primary aim of ovarian reserve monitoring is to measure the size of ovarian follicles and the number of antral follicles. Manual follicle measurement is inhibited by operator time, expertise and the subjectivity of delineating the two axes of the follicles. This necessitates an automated framework capable of quantifying follicle size and count in a clinical setting. This paper proposes a novel Harmonic Attention-based U-Net network, HaTU-Net, to precisely segment the ovary and follicles in ultrasound images. We replace the standard convolution operation with a harmonic block that convolves the features with a window-based discrete cosine transform (DCT). Additionally, we proposed a harmonic attention mechanism that helps to promote the extraction of rich features. The suggested technique allows for capturing the most relevant features, such as boundaries, shape, and textural patterns, in the presence of various noise sources (i.e., shadows, poor contrast between tissues, and speckle noise). We evaluated the proposed model on our in-house private dataset of 197 patients undergoing TransVaginal UltraSound (TVUS) exam. The experimental results on an independent test set confirm that HaTU-Net achieved a Dice coefficient score of 90 % for ovaries and 81 % for antral follicles, an improvement of 2 % and 10 % , respectively, when compared to a standard U-Net. Further, we accurately measure the follicle size, yielding the recall, and precision rates of 91.01 % and 76.49 % , respectively. [ABSTRACT FROM AUTHOR]

Existing nuclei segmentation methods face challenges with hematoxylin and eosin (H&E) whole slide imaging (WSI) due to the variations in staining methods and nuclei shapes and sizes. Most existing approaches require a stain normalization step that may cause losing source information and fail to handle the inter-scanner feature instability problem. To mitigate these issues, this article proposes an efficient staining-invariant nuclei segmentation method based on self-supervised contrastive learning and an effective weighted hybrid dilated convolution (WHDC) block. In particular, we propose a staining-invariant encoder (SIE) that includes convolution and transformers blocks. We also propose the WHDC block allowing the network to learn multi-scale nuclei-relevant features to handle the variation in the sizes and shapes of nuclei. The SIE network is trained on five unlabeled WSIs datasets using self-supervised contrastive learning and then used as a backbone for the downstream nuclei segmentation network. Our method outperforms existing approaches in challenging multiple WSI datasets without stain color normalization. [ABSTRACT FROM AUTHOR]

Simple Summary: Inducible T-cell COStimulator (ICOS) is a biomarker of interest in checkpoint inhibitor therapy, and as a means of assessing T-cell regulation as part of a complex process of adaptive immunity. The aim of our study is to segment the ICOS positive cells using a lightweight deep-learning segmentation network. We aim to assess the potential of a convolutional neural network and transformer together that permits the capture of relevant features from immunohistochemistry images. The proposed study achieved remarkable results compared to the existing biomedical segmentation methods on our in-house dataset and surpassed our previous analysis by only utilizing the Efficient-UNet network. In this article, we propose ICOSeg, a lightweight deep learning model that accurately segments the immune-checkpoint biomarker, Inducible T-cell COStimulator (ICOS) protein in colon cancer from immunohistochemistry (IHC) slide patches. The proposed model relies on the MobileViT network that includes two main components: convolutional neural network (CNN) layers for extracting spatial features; and a transformer block for capturing a global feature representation from IHC patch images. The ICOSeg uses an encoder and decoder sub-network. The encoder extracts the positive cell's salient features (i.e., shape, texture, intensity, and margin), and the decoder reconstructs important features into segmentation maps. To improve the model generalization capabilities, we adopted a channel attention mechanism that added to the bottleneck of the encoder layer. This approach highlighted the most relevant cell structures by discriminating between the targeted cell and background tissues. We performed extensive experiments on our in-house dataset. The experimental results confirm that the proposed model achieves more significant results against state-of-the-art methods, together with an 8× reduction in parameters. [ABSTRACT FROM AUTHOR]

Breast cancer needs to be detected early to reduce mortality rate. Ultrasound imaging (US) could significantly enhance diagnosing cases with dense breasts. Most of the existing computer-aided diagnosis (CAD) systems employ a single ultrasound image for the breast tumor to extract features to classify it as benign or malignant. However, the accuracy of such CAD system is limited due to the large tumor size and shape variation, irregular and ambiguous tumor boundaries, and low signal-to-noise ratio in ultrasound images due to their noisy nature and the significant similarity between normal and abnormal tissues. To handle these issues, we propose a deep-learning-based radiomics method based on breast US sequences in this paper. The proposed approach involves three main components: radiomic features extraction based on a deep learning network, so-called ConvNeXt, a malignancy score pooling mechanism, and visual interpretations. Specifically, we employ the ConvNeXt network, a deep convolutional neural network (CNN) trained using the vision transformer style. We also propose an efficient pooling mechanism to fuse the malignancy scores of each breast US sequence frame based on image-quality statistics. The ablation study and experimental results demonstrate that our method achieves competitive results compared to other CNN-based methods. [ABSTRACT FROM AUTHOR]

Unplanned urbanization in developing cities has led to haphazard development, increasing disaster risks in densely populated areas. Despite being more disaster-prone, these dense settlements often lack essential emergency services. Delivering emergency services requires a high-resolution geodatabase of minor roads and their attributes, such as road width. Such information can be a crucial input for quantifying emergency vehicles (EVs) access in an area. To the best of our knowledge, no research has addressed this problem statement, making this paper the first to propose quantifying road width and using it to develop EVs accessibility maps. We propose a two-stage process to achieve these goals. In the first stage, we designed a deep neural network (DNN) to accurately organize built-up features, including minor roads using true-colour high-resolution satellite imagery of Pleiades-1A for Mumbai. In the second stage, we propose an algorithm to calculate road width and then compare it with EVs dimension (width) details to develop high-resolution accessibility maps. The model classified features with around 91.88% accuracy along with 90% Kappa coefficient, while the classification accuracy of minor roads in informal settlements was about 85.80%. We found that informal settlements have much less access to various EVs compared to formal settlements due to mixed signatures. The outcomes presented in this paper can be used as a decision-making tool to develop a geodatabase of road widths and EVs accessibility maps for efficient resource planning, which can ultimately lead to the development of disaster-resilient cities. • Extraction of minor-roads in dense informal settlements using Deep Learning (DL). • Algorithm to estimate road width from classified imagery. • Generation of high-resolution Emergency Vehicle (EV) accessibility maps for Mumbai, India. [ABSTRACT FROM AUTHOR]

In recent times, sentiment analysis research has achieved tremendous impetus on English textual data, however, a very less amount of research has been focused on Nepali textual data. This work is focused towards Nepali textual data. We have explored machine learning approaches and proposed a lexicon-based approach using linguistic features and lexical resources to perform sentiment analysis for tweets written in Nepali language. This lexicon-based approach, first pre-process the tweet, locate the opinion-oriented features and then compute the sentiment polarity of tweet. We have investigated both conventional machine learning models (Multinomial Naïve Bayes (NB), Decision Tree, Support Vector Machine (SVM) and logistic regression) and deep learning models (Convolution Neural Network (CNN), Long Short-Term Memory (LSTM) and CNN-LSTM) for sentiment analysis of Nepali text. These machine learning models and lexicon-based approach have been evaluated on tweet dataset related to Nepal Earthquake 2015 and Nepal blockade 2015. Lexicon based approach has outperformed than conventional machine learning models. Deep learning models have outperformed than conventional machine learning models and lexicon-based approach. We have also created Nepali SentiWordNet and Nepali SenticNet sentiment lexicon from existing English language resources as by-product. [ABSTRACT FROM AUTHOR]

This paper tries to map the research work carried out in the field of Big Data through a detailed analysis of scholarly articles published on the theme during 2010-16, as indexed in Scopus. We have collected and analyzed all relevant publications on Big Data, as indexed in Scopus, through a quantitative as well as textual characterization. The analysis attempts to dwell into parameters like research productivity, growth of research and citations, thematic trends, top publication sources and emerging topics in this field. The analytical study also investigates country-wise publications output and impact in terms of average citations per paper, country-level collaboration patterns, authorship and leading contributors (countries, institutions) etc. The scholarly publication data is also subjected to a detailed textual analysis method to identify key themes in Big Data research, disciplinary variations and thematic trends and patterns. The results produce interesting inferences. Quantitative measures show that there has been a tremendous increase in number of publications related to Big Data during last few years. Research work in Big Data, though primarily considered a sub-discipline of Computer Science, is now carried out by researchers in many disciplines. Thematic analysis of publications in Big Data show that it's a discipline involving research interest from fields as diverse as Medicine to Social Sciences. The paper also identifies major keywords now associated with Big Data research such as Cloud Computing, Deep Learning, Social Media and Data Analytics. This helps in a thorough understanding and visualization of the Big Data research area. [ABSTRACT FROM AUTHOR]

Automatic tumor segmentation in breast ultrasound (BUS) images is still a challenging task because of many sources of uncertainty, such as speckle noise, very low signal-to-noise ratio, shadows that make the anatomical boundaries of tumors ambiguous, as well as the highly variable tumor sizes and shapes. This article proposes an efficient automated method for tumor segmentation in BUS images based on a contextual information-aware conditional generative adversarial learning framework. Specifically, we exploit several enhancements on a deep adversarial learning framework to capture both texture features and contextual dependencies in the BUS images that facilitate beating the challenges mentioned above. First, we adopt atrous convolution (AC) to capture spatial and scale context (i.e., position and size of tumors) to handle very different tumor sizes and shapes. Second, we propose the use of channel attention along with channel weighting (CAW) mechanisms to promote the tumor-relevant features (without extra supervision) and mitigate the effects of artifacts. Third, we propose to integrate the structural similarity index metric (SSIM) and L1-norm in the loss function of the adversarial learning framework to capture the local context information derived from the area surrounding the tumors. We used two BUS image datasets to assess the efficiency of the proposed model. The experimental results show that the proposed model achieves competitive results compared with state-of-the-art segmentation models in terms of Dice and IoU metrics. The source code of the proposed model is publicly available at https://github.com/vivek231/Breast-US-project. • Efficient automated method for tumor segmentation in breast ultrasound (BUS) images. • Contextual information-aware conditional generative adversarial learning framework. • Capture spatial and scale context to handle very different tumor sizes and shapes. • Two BUS image datasets are used to assess the efficiency of the proposed model. [ABSTRACT FROM AUTHOR]

Hybrid generation and energy storage systems can enhance asset flexibility, enabling various services and optimizing financial performance. From a generation asset owner perspective, the decision to hybridize includes selecting an energy storage system that maximizes financial performance of the energy storage investment. Yet, existing tools to optimize energy storage sizing are either too rudimentary or too complex for most asset owners to implement (i.e., require specialized engineering and software knowledge and a high-performance computer to run). This work presents a deep learning-based battery sizing optimization tool for hybridizing generation facilities. The tool uses deep learning technique to predict revenue over a broad search space of potential battery sizes, estimate capital and operations costs (including accounting for battery degradation), and calculate financial performance of each potential battery system investment; an output is a recommendation of battery that maximizes financial performance. The tool is tested and validated for hydropower generation and is publicly available on Idaho National Laboratory's GitHub page (https://github.com/idaholab/Hydro%5fHybrids), documented in Zenodo (https://zenodo.org/record/7562692#.Y9Q7anbMKUm), and accessible through an intuitive web app (hydrohybrids.inl.gov). This tool will help a greater cross-section of generation owners consider investments in battery systems, increasing their revenue and helping them compete in rapidly evolving electrify markets. [ABSTRACT FROM AUTHOR]

• A curated high-quality dataset of 12,698 YouTube comments and replies in Hindi-English code-mixed language for misogynistic attitude detection is proposed. • The dataset provides for two tasks- first to identify optimistic, pessimistic, or neutral attitude in content and then labelling comments into the categories of suggestion, appreciation, criticism, offensive, or none. • A set of algorithmic models comprising techniques from machine learning, deep learning and transformer-based models are applied. • The mBERT model gives best performance on both subtasks, with macro average F1 scores of 0.59 and 0.52, and weighted average F1 scores of 0.66 and 0.65, respectively. • The experimental evaluation and results confirm the suitability of the dataset and the real-world applications and future extension possibilities of the work are discussed. Social media platforms are now not only a medium for expressing users views, feelings, emotions and sentiments but are also being abused by people to propagate unpleasant and hateful content. Consequently, research efforts have been made to develop techniques and models for automatically detecting and identifying hateful, abusive, vulgar, and offensive content on different platforms. Although significant progress has been made on the task, the research on design of methods to detect misogynistic attitude of people in non-English and code-mixed languages is not very well-developed. Non-availability of suitable datasets and resources is one main reason for this. Therefore, this paper attempts to bridge this research gap by presenting a high-quality curated dataset in the Hindi-English code-mixed language. The dataset includes 12,698 YouTube comments and replies, with each comment annotated under two-level categories, first as optimistic and pessimistic, and then into different types at second level based on the content. The inter-annotator agreement in the dataset is found to be 0.84 for the first subtask, and 0.79 for the second subtask, indicating the reasonably high quality of annotations. Different algorithmic models are explored for the task of automatic detection of the misogynistic attitude expressed in the comments, with the mBERT model giving best performance on both subtasks (reported macro average F1 scores of 0.59 and 0.52, and weighted average F1 scores of 0.66 and 0.65, respectively). The analysis and results suggest that the dataset can be used for further research on the topic and that the developed algorithmic models can be applied for automatic detection of misogynistic attitude in social media conversations and posts. [ABSTRACT FROM AUTHOR]

The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the color, texture and shapes of skin lesions. Existing deep learning-based skin lesion segmentation algorithms are expensive in terms of computational time and memory. Consequently, running such segmentation algorithms requires a powerful GPU and high bandwidth memory, which are not available in dermoscopy devices. Thus, this article aims to achieve precise skin lesion segmentation with minimum resources: a lightweight, efficient generative adversarial network (GAN) model called SLSNet, which combines 1-D kernel factorized networks, position and channel attention, and multiscale aggregation mechanisms with a GAN model. The 1-D kernel factorized network reduces the computational cost of 2D filtering. The position and channel attention modules enhance the discriminative ability between the lesion and non-lesion feature representations in spatial and channel dimensions, respectively. A multiscale block is also used to aggregate the coarse-to-fine features of input skin images and reduce the effect of the artifacts. SLSNet is evaluated on two publicly available datasets: ISBI 2017 and the ISIC 2018. Although SLSNet has only 2.35 million parameters, the experimental results demonstrate that it achieves segmentation results on a par with the state-of-the-art skin lesion segmentation methods with an accuracy of 97.61%, and Dice and Jaccard similarity coefficients of 90.63% and 81.98%, respectively. SLSNet can run at more than 110 frames per second (FPS) in a single GTX1080Ti GPU, which is faster than well-known deep learning-based image segmentation models, such as FCN. Therefore, SLSNet can be used for practical dermoscopic applications. • A lightweight and fully automatic skin lesion segmentation model is proposed. • A multiscale mechanism is introduced to extract features at different scales. • The position attention module controls the spatial inter-dependencies. • The channel attention module controls the channel inter-dependencies. • The combination of binary cross-entropy, Jaccard index, and L1 loss is used. [ABSTRACT FROM AUTHOR]