Search

Despite growing efforts to halt distasteful content on social media, multilingualism has added a new dimension to this problem. The scarcity of resources makes the challenge even greater when it comes to low-resource languages. This work focuses on providing a novel method for abusive content detection in multiple low-resource Indic languages. Our observation indicates that a post's tendency to attract abusive comments, as well as features such as user history and social context, significantly aid in the detection of abusive content. The proposed method first learns social and text context features in two separate modules. The integrated representation from these modules is learned and used for the final prediction. To evaluate the performance of our method against different classical and state-of-the-art methods, we have performed extensive experiments on SCIDN and MACI datasets consisting of 1.5M and 665K multilingual comments, respectively. Our proposed method outperforms state-of-the-art baseline methods with an average increase of 4.08% and 9.52% in F1-scores on SCIDN and MACI datasets, respectively.

Pediatric pneumonia remains a significant global threat, posing a larger mortality risk than any other communicable disease. According to UNICEF, it is a leading cause of mortality in children under five and requires prompt diagnosis. Early diagnosis using chest radiographs is the prevalent standard, but limitations include low radiation levels in unprocessed images and data imbalance issues. This necessitates the development of efficient, computer-aided diagnosis techniques. To this end, we propose a novel EXplainable Contrastive-based Dilated Convolutional Network with Transformer (XCCNet) for pediatric pneumonia detection. XCCNet harnesses the spatial power of dilated convolutions and the global insights from contrastive-based transformers for effective feature refinement. A robust chest X-ray processing module tackles low-intensity radiographs, while adversarial-based data augmentation mitigates the skewed distribution of chest X-rays in the dataset. Furthermore, we actively integrate an explainability approach through feature visualization, directly aligning it with the attention region that pinpoints the presence of pneumonia or normality in radiographs. The efficacy of XCCNet is comprehensively assessed on four publicly available datasets. Extensive performance evaluation demonstrates the superiority of XCCNet compared to state-of-the-art methods.

Supervised Learning is a way of developing Artificial Intelligence systems in which a computer algorithm is trained on labeled data inputs. Effectiveness of a Supervised Learning algorithm is determined by its performance on a given dataset for a particular problem. In case of Supervised Learning problems, Stacking Ensembles usually perform better than individual classifiers due to their generalization ability. Stacking Ensembles combine predictions from multiple Machine Learning algorithms to make final predictions. Inspite of Stacking Ensembles superior performance, the overhead of Stacking Ensembles such as high cost, resources, time, and lack of explainability create challenges in real-life applications. This paper shows how we can strike a balance between performance, time, and resource constraints. Another goal of this research is to make Ensembles more explainable and intelligible using the Human-Centered approach. To achieve the aforementioned goals, we proposed a Human-Centered Behavior-inspired algorithm that streamlines the Ensemble Learning process while also reducing time, cost, and resource overhead, resulting in the superior performance of Supervised Learning in real-world applications. To demonstrate the effectiveness of our method, we perform our experiments on nine real-world datasets. Experimental results reveal that the proposed method satisfies our goals and outperforms the existing methods.

The widespread dissemination of false information through manipulative tactics that combine deceptive text and images threatens the integrity of reliable sources of information. While there has been research on detecting fake news in high resource languages using multimodal approaches, methods for low resource Indic languages primarily rely on textual analysis. This difference highlights the need for robust methods that specifically address multimodal fake news in Indic languages, where the lack of extensive datasets and tools presents a significant obstacle to progress. To this end, we introduce the Multimodal Multilingual dataset for Indic Fake News Detection (MMIFND). This meticulously curated dataset consists of 28,085 instances distributed across Hindi, Bengali, Marathi, Malayalam, Tamil, Gujarati and Punjabi. We further propose the Multimodal Multilingual Caption-aware framework for Fake News Detection (MMCFND). MMCFND utilizes pre-trained unimodal encoders and pairwise encoders from a foundational model that aligns vision and language, allowing for extracting deep representations from visual and textual components of news articles. The multimodal fusion encoder in the foundational model integrates text and image representations derived from its pairwise encoders to generate a comprehensive cross modal representation. Furthermore, we generate descriptive image captions that provide additional context to detect inconsistencies and manipulations. The retrieved features are then fused and fed into a classifier to determine the authenticity of news articles. The curated dataset can potentially accelerate research and development in low resource environments significantly. Thorough experimentation on MMIFND demonstrates that our proposed framework outperforms established methods for extracting relevant fake news detection features.

Due to the growing volume of user generated content, hashtags are employed as topic indicators to manage content efficiently on social media platforms. However, finding these vital topics is challenging in microvideos since they contain substantial information in a short duration. Existing methods that recommend hashtags for microvideos primarily focus on content and personalization while disregarding relatedness among users. Moreover, the cold start user issue prevails in hashtag recommendation systems. Considering the above, we propose a hybrid filtering based MIcro-video haSHtag recommendatiON MISHON technique to recommend hashtags for micro-videos. Besides content based filtering, we employ user-based collaborative filtering to enhance recommendations. Since hashtags reflect users topical interests, we find similar users based on historical tagging behavior to model user relatedness. We employ a graph-based deep neural network to model user to user, modality to modality, and user to modality interactions. We then use refined modality specific and user representations to recommend pertinent hashtags for microvideos. The empirical results on three real world datasets demonstrate that MISHON attains a comparative enhancement of 3.6, 2.8, and 6.5 reported in percentage concerning the F1 score, respectively. Since cold start users exist whose historical tagging information is unavailable, we also propose a content and social influence based technique to model the relatedness of cold start users with influential users. The proposed solution shows a relative improvement of 15.8 percent in the F1 score over its content only counterpart. These results show that the proposed framework mitigates the cold start user problem.

Swift and accurate blood smear analysis is an effective diagnostic method for leukemia and other hematological malignancies. However, manual leukocyte count and morphological evaluation using a microscope is time-consuming and prone to errors. Conventional image processing methods also exhibit limitations in differentiating cells due to the visual similarity between malignant and benign cell morphology. This limitation is further compounded by the skewed training data that hinders the extraction of reliable and pertinent features. In response to these challenges, we propose an optimized Coupled Transformer Convolutional Network (CoTCoNet) framework for the classification of leukemia, which employs a well-designed transformer integrated with a deep convolutional network to effectively capture comprehensive global features and scalable spatial patterns, enabling the identification of complex and large-scale hematological features. Further, the framework incorporates a graph-based feature reconstruction module to reveal the hidden or unobserved hard-to-see biological features of leukocyte cells and employs a Population-based Meta-Heuristic Algorithm for feature selection and optimization. To mitigate data imbalance issues, we employ a synthetic leukocyte generator. In the evaluation phase, we initially assess CoTCoNet on a dataset containing 16,982 annotated cells, and it achieves remarkable accuracy and F1-Score rates of 0.9894 and 0.9893, respectively. To broaden the generalizability of our model, we evaluate it across four publicly available diverse datasets, which include the aforementioned dataset. This evaluation demonstrates that our method outperforms current state-of-the-art approaches. We also incorporate an explainability approach in the form of feature visualization closely aligned with cell annotations to provide a deeper understanding of the framework.

Future communication systems are anticipated to facilitate applications requiring high data transmission rates while maintaining energy efficiency. Hexagonal quadrature amplitude modulation (HQAM) offers this owing to its compact symbol arrangement within the two-dimensional (2D) plane. Building on the limitations of the current approaches, this letter presents a straightforward and precise approximation for calculating the symbol error probability (SEP) of HQAM in additive white Gaussian noise (AWGN) channel. The analytical and simulation results align across several signal-to-noise ratios (SNR). In addition, the proposed approximation is effective for accurately estimating the SEP of HQAM in scenarios with slow-fading, including those subject to Rayleigh fading., Comment: 5 pages, 7 figures

Mamba, a special case of the State Space Model, is gaining popularity as an alternative to template-based deep learning approaches in medical image analysis. While transformers are powerful architectures, they have drawbacks, including quadratic computational complexity and an inability to address long-range dependencies efficiently. This limitation affects the analysis of large and complex datasets in medical imaging, where there are many spatial and temporal relationships. In contrast, Mamba offers benefits that make it well-suited for medical image analysis. It has linear time complexity, which is a significant improvement over transformers. Mamba processes longer sequences without attention mechanisms, enabling faster inference and requiring less memory. Mamba also demonstrates strong performance in merging multimodal data, improving diagnosis accuracy and patient outcomes. The organization of this paper allows readers to appreciate the capabilities of Mamba in medical imaging step by step. We begin by defining core concepts of SSMs and models, including S4, S5, and S6, followed by an exploration of Mamba architectures such as pure Mamba, U-Net variants, and hybrid models with convolutional neural networks, transformers, and Graph Neural Networks. We also cover Mamba optimizations, techniques and adaptations, scanning, datasets, applications, experimental results, and conclude with its challenges and future directions in medical imaging. This review aims to demonstrate the transformative potential of Mamba in overcoming existing barriers within medical imaging while paving the way for innovative advancements in the field. A comprehensive list of Mamba architectures applied in the medical field, reviewed in this work, is available at Github.

Sentiment analysis and emotion recognition in videos are challenging tasks, given the diversity and complexity of the information conveyed in different modalities. Developing a highly competent framework that effectively addresses the distinct characteristics across various modalities is a primary concern in this domain. Previous studies on combined multimodal sentiment and emotion analysis often overlooked effective fusion for modality integration, intermodal contextual congruity, optimizing concatenated feature spaces, leading to suboptimal architecture. This paper presents a novel framework that leverages the multi-modal contextual information from utterances and applies metaheuristic algorithms to learn the contributing features for utterance-level sentiment and emotion prediction. Our Graph-enhanced Cross-Modal Infusion with a Metaheuristic-Driven Network (GCM-Net) integrates graph sampling and aggregation to recalibrate the modality features for video sentiment and emotion prediction. GCM-Net includes a cross-modal attention module determining intermodal interactions and utterance relevance. A harmonic optimization module employing a metaheuristic algorithm combines attended features, allowing for handling both single and multi-utterance inputs. To show the effectiveness of our approach, we have conducted extensive evaluations on three prominent multi-modal benchmark datasets, CMU MOSI, CMU MOSEI, and IEMOCAP. The experimental results demonstrate the efficacy of our proposed approach, showcasing accuracies of 91.56% and 86.95% for sentiment analysis on MOSI and MOSEI datasets. We have performed emotion analysis for the IEMOCAP dataset procuring an accuracy of 85.66% which signifies substantial performance enhancements over existing methods.

The worldwide impact of the recent COVID-19 pandemic has been substantial, necessitating the development of accurate forecasting models to predict the spread and course of a pandemic. Previous methods for outbreak forecasting have faced limitations by not utilizing multiple sources of input and yielding suboptimal performance due to the limited availability of data. In this study, we propose a novel approach to address the challenges of infectious disease forecasting. We introduce a Multilateral Attention-enhanced GRU model that leverages information from multiple sources, thus enabling a comprehensive analysis of factors influencing the spread of a pandemic. By incorporating attention mechanisms within a GRU framework, our model can effectively capture complex relationships and temporal dependencies in the data, leading to improved forecasting performance. Further, we have curated a well-structured multi-source dataset for the recent COVID-19 pandemic that the research community can utilize as a great resource to conduct experiments and analysis on time-series forecasting. We evaluated the proposed model on our COVID-19 dataset and reported the output in terms of RMSE and MAE. The experimental results provide evidence that our proposed model surpasses existing techniques in terms of performance. We also performed performance gain and qualitative analysis on our dataset to evaluate the impact of the attention mechanism and show that the proposed model closely follows the trajectory of the pandemic.

Evidently, low-luminosity active galactic nuclei LLAGNs comprise of inner advective disk and outer geometrically thin disk. The wind is inevitable in LLAGNs, mainly interpreted indirect way, also the evidences are growing for the presence of wind in outer thin disk. We present a hydrodynamics HD model for wind from outer thin disk where the main driver is the inner disk irradiation (which is parameterized by a number $x$ in hydrostatic equilibrium equation with a slightly unbalancing role). The model works for a low intense irradiation or from a height $z_s$ in optically thin medium. We solve the model equations in cylindrical coordinate along the $z$-axis for a given radius $r$ with assuming a tiny vertical speed $v_z$ ($\ll c_s$ sound speed). The sonic point conditions assure an isobaric regime above the sonic height ($z^{max}$), in addition from the height $z_f (\ll z^{max}$) the radial pressure gradient also supports the fluid rotation, and both conjointly assure a wind ejection from the $z^{max}$ with fluid speed. The $z^{max}$ increases with $x$, and beyond a large $z^{max}$ (say $z^{max}_t$ corresponded to maximum $x$) there is no physical solution. We start the computation from outer radius $r_o^{thin}$ to inner $r_{in}^{thin}$ with Bondi mass accretion rate $\dot{M}_{Bondi}$, to explore the $r$ dependency of mass inflow rate $\dot{M}$ and wind properties. We constrain the model by fixing $\dot{M}$ at $r_{in}^{thin}$ from the observations of NGC 1097, and check the feasibility of model by comparing the energetics with observed bolometric luminosity. The wind is an equatorial with viewing angle $i>85$degree, and capable to generate red-/blue-shifted lines, it would be a general characteristics for LLAGNs., Comment: 15 figures

High energies emissions observed in X-ray binaries (XRBs), active galactic nuclei (AGNs) are linearly polarized. The prominent mechanism for X-ray is the Comptonization process. We revisit the theory for polarization in Compton scattering with unpolarized electrons, and note that the ($k \times k'$)-coordinate (in which, ($k \times k'$) acts as a $z$-axis, here $k$ and $k'$ are incident and scattered photon momentum respectively) is more convenient to describe it. Interestingly, for a fixed scattering plane the degree of polarization PD after single scattering for random oriented low-energy unpolarized incident photons is $\sim$0.33. At the scattering angle $\theta$ = 0 or $\theta \equiv$ [0,25$^o$], the modulation curve of $k'$ exhibits the same PD and PA (angle of polarization) of $k$, and even the distribution of projection of electric vector of $k'$ ($k'_e$) on perpendicular plane to the $k$ indicates same (so, an essential criteria for detector designing). We compute the polarization state in Comptonization process using Monte Carlo methods with considering a simple spherical corona. We obtain the PD of emergent photons as a function of $\theta$-angle (or alternatively, the disk inclination angle $i$) on a meridian plane (i.e., the laws of darkening, formulated by \citealp{Chandrasekhar1946}) after single scattering with unpolarized incident photons. To explore the energy dependency we consider a general spectral parameter set corresponding to hard and soft states of XRBs, we find that for average scattering no. $\langle N_{sc}\rangle$ $\sim$1.1 the PD is independent of energy and PA $\sim 90^o$ ($k'_e$ is parallel to the disk plane), and for $\langle N_{sc}\rangle$ $\sim$5 the PD value is maximum for $i=45^o$. We also compare the results qualitatively with observation of IXPE for five sources., Comment: 16 figures, 3 tables (Key words: X-rays: individual: 4U 1630-47, Cyg X-2, GX 9+9, XTE J1701-462, Cyg X-1); Accepted for publication in PASA

In this paper, we consider a dual-hop mixed THz-RF system model for backhaul-fronthaul applications where the link between source and destination is established only through the relay node in which decode-and-forward relaying protocol is used. The THz link suffers from the joint impact of antenna misalignment and stochastic characteristics of wireless channels, including the effect of environmental conditions such as pressure, humidity, and temperature. The envelope of THz link in the first hop follows a generalized $\alpha-\mu$ distribution, and for the RF end, the Nakagami-$m$ distribution is considered. In this context, we obtain new closed-form expressions of the cumulative density function and the moment-generating function of the end-to-end signal-to-noise ratio. Further, we derive the average symbol error rate expressions for coherent rectangular quadrature amplitude modulation (RQAM) and coherent hexagonal QAM (HQAM), as well as the non-coherent modulation scheme. The asymptotic behavior is also discussed to examine the system's diversity. Furthermore, the impact of several parameters, such as fading coefficients of individual links and antenna misalignment, as well as the distance between nodes, are also highlighted in the system's performance. Moreover, Monte Carlo simulations are used to validate the presented analytical framework. Finally, the presented numerical insights aid in the extraction of practical design principles.

We investigate the possible presence of quasi-periodic oscillation (QPO) signals in 2103 blazars from the Zwicky Transient Facility (ZTF) time-domain survey. We detect a low-frequency QPO signal in five blazars observed over these 3.8-year-long optical r-band ZTF light curves. These periods range from 144 days to 196 days detected at $\gtrsim 4\sigma$ significance levels in both the Lomb-Scargle periodogram and Weighted Wavelet Z-transform analyses. We find consistent results using the phase dispersion minimization technique. A similar peak is detected in the g-band light curves at a slightly lower significance of 3$\sigma$. Such nearly periodic signals on these timescales in optical wavebands most likely originate from a precessing jet with high Lorentz factor, closely aligned to the observer's line of sight or the movement of plasma blobs along a helical structure in the jet., Comment: Submitted to MNRAS, 15 pages, 10 figures, 2 tables

Many astrophysical sources, e.g., cataclysmic variables, X-ray binaries, active galactic nuclei, exhibit a wind outflow, when they reveal a multicolor blackbody spectrum, hence harboring a geometrically thin Keplerian accretion disk. Unlike an advective disk, in the thin disk, the physical environment, like, emission line, external heating, is expected to play a key role to drive the wind outflow. We show the wind outflow in a thin disk attributing a disk irradiation effect, probably from the inner to outer disks. We solve the set of steady, axisymmetric disk model equations in cylindrical coordinates along the vertical direction for a given launching radius $(r)$ from the midplane, introducing irradiation as a parameter. We obtain an acceleration solution, for a finite irradiation in the presence of a fixed but tiny initial vertical velocity (hence thin disk properties practically do not alter) at the midplane, upto a maximum height ($z^{max}$). We find that wind outflow mainly occurs from the outer region of the disk and its density decreases with increasing launching radius, and for a given launching radius with increasing ejection height. Wind power decreases with increasing ejection height. For $z^{max} < 2r$, wind outflow is ejected tangentially (or parallel to the disk midplane) in all directions with the fluid speed same as the azimuthal speed. This confirms mainly, for low mass X-ray binaries, (a) wind outflow should be preferentially observed in high-inclination sources, (b) the expectation of red and blue shifted absorption lines., Comment: 17 pages, 10 figures

Blazars host the most powerful persistent relativistic conical jet -- a highly collimated anisotropic flow of material/plasma. Motivated by this, we explore the blazar's broadband spectral energy distribution (SED) in an anisotropic flow of plasma which emits via synchrotron and inverse Compton (IC) mechanism. The flow is conical with two velocity components: a highly relativistic flow component along the jet axis and a random perpendicular component with average random Lorentz factor $\langle \gamma^{ran} \rangle$ $<<$ than the average component along the jet axis $\langle \gamma \rangle$. Assuming a broken power-law electron population, we calculated the broadband SED using synchrotron and IC processes assuming a cylindrical (of radius R and length L) emission region. For the IC process, we used Monte Carlo approach. We found that such anisotropic flow can reproduce blazars broadband emission as well as general short and high amplitude variability, indicating that spectral and temporal variability are not sufficient to distinguish among existing models. We demonstrate this by reproducing SEDs of FSRQ 3C 454.3 and three BL Lacs objects OJ 287, S5 0716+714, PKS 2155-304. Our formalism and set-up also allow us to investigate the effect of the geometry and dimension of emission region on observed broadband spectra. We found that the SEDs of low synchrotron peak (LSP) blazar can be explained by considering only SSC (synchrotron self-Compton) if R/L ($<$ 0.01), broadly mimicking a spine-sheath geometry. In general, the degeneracy between non-thermal particle number density and length of the emission region (L) allow us to reproduce any variability in terms of particle number density., Comment: 22 pages, 11 figures

As the research on beyond 5G heats up, we survey and explore power and bandwidth efficient modulation schemes in details. In the existing publications and in various communication standards, initially square quadrature amplitude modulation (SQAM) constellations (even power of 2) were considered. However, only the square constellations are not efficient for varying channel conditions and rate requirements, and hence, odd power of 2 constellations were introduced. For odd power of 2 constellations, rectangular QAM (RQAM) is commonly used. However, RQAM is not a good choice due to its lower power efficiency, and a modified cross QAM (XQAM) constellation is preferred as it provides improved power efficiency over RQAM due to its energy efficient two dimensional (2D) structure. The increasing demand for high data-rates has further encouraged the research towards more compact 2D constellations which lead to hexagonal lattice structure based constellations, referred to as hexagonal QAM (HQAM). In this work, various QAM constellations are discussed and detailed study of star QAM, XQAM, and HQAM constellations is presented. Generation, peak and average energies, peak-to-average-power ratio, symbol-error-rate, decision boundaries, bit mapping, Gray code penalty, and bit-error-rate of star QAM, XQAM, and HQAM constellations with different constellation orders are presented. Finally, a comparative study of various QAM constellations is presented which justifies the supremacy of HQAM over other QAM constellations. With this, it can be claimed that the use of the HQAM in various wireless communication systems and standards can further improve the performance targeted for beyond 5G wireless communication systems.