Explore the vast range of titles available.

The Internet is evolving rapidly, and billions of devices are being connected to it at the edge. Performance at the edge matters, and the role of the congestion control mechanism is important. Since the emergence of the Bottleneck Bandwidth and Round-trip propagation time (BBR) algorithm by Google, active research has been going on between BBR and TCP Cubic. BBR-v3 is the third version since its inception, and it has tried to address many of the shortcomings of its earlier versions. The issue of fairness with Cubic and Reno flows, the bandwidth overestimation issue in multi-flow scenarios, high packet transmission rate in shallow buffers, and queuing delays and packet losses during/after its startup phase. Not much research work is yet available on BBR-v3 evaluation with Cubic, especially in a variety of connectivity scenarios, such as wired and wireless together. In this paper, we evaluate BBR-v3 with Cubic and have proposed BBR-n+ (BBR Smart Exit) that refines the generic BBR's (BBR-v3) startup exit by detecting receive window limitations and empirically evaluate its performance with the generic BBR (BBR-v3). The early exit issue of BBR-v3 from the startup phase when the congestion window is receiver-limited is probed, and the Smart Exit algorithm has been proposed. It is the continuation of our work on BBR-n, and we have evaluated it using various performance metrics. The role of modern AQMs has been explored with our testing on Common Applications Kept Enhanced (CAKE) and Flow Queue Controlled Delay (FQ_CoDel) AQMs. Through the experiments, we conclude that BBR-n+ in the receive window limitation test provides a 15-20% median throughput gain over BBR-v3 under different receiver window sizes. A 150 ms reduction in HTTP delay when compared with BBR-v3 and a ~ 300 ms reduction versus Cubic. 17% improvement in ping latency compared to BBR-v3 and 45% with Cubic in the wired scenario with a strenuous load of multiple streams. BBR-n+ outperforms BBR-v3 and Cubic in most of the tested scenarios, though it still exhibits limitations, particularly in achieving fairness when competing against Cubic flows when the number of concurrent streams is eight or more.

Cardiac disease is the leading cause of death worldwide. Cardiovascular diseases can be prevented if an effective diagnostic is made at the initial stages. The ECG test is referred to as the diagnostic assistant tool for screening of cardiac disorder. The research purposes of a cardiac disorder detection system from 12-lead-based ECG Images. The healthcare institutes used various ECG equipment that present results in nonuniform formats of ECG images. The research study proposes a generalized methodology to process all formats of ECG. Single Shoot Detection (SSD) MobileNet v2-based Deep Neural Network architecture was used to detect cardiovascular disease detection. The study focused on detecting the four major cardiac abnormalities (i.e., myocardial infarction, abnormal heartbeat, previous history of MI, and normal class) with 98% accuracy results were calculated. The work is relatively rare based on their dataset; a collection of 11,148 standard 12-lead-based ECG images used in this study were manually collected from health care institutes and annotated by the domain experts. The study achieved high accuracy results to differentiate and detect four major cardiac abnormalities. Several cardiologists manually verified the proposed system’s accuracy result and recommended that the proposed system can be used to screen for a cardiac disorder.

Accurate emotion recognition in social media text is critical for applications such as sentiment analysis, mental health monitoring, and human-computer interaction. However, existing approaches face challenges like computational complexity and class imbalance, limiting their deployment in resource-constrained environments. While transformer-based models achieve state-of-the-art performance, their size and latency hinder real-time applications. To address these issues, we propose a novel knowledge distillation framework that transfers knowledge from a fine-tuned BERT-base teacher model to lightweight DistilBERT and ALBERT student models, optimised for efficient emotion recognition. Our approach integrates a hybrid loss function combining focal loss and Kullback-Leibler (KL) divergence to enhance minority class recognition, attention-head alignment for effective contextual knowledge transfer, and semantic-preserving data augmentation to mitigate class imbalance. Experiments on two datasets, Twitter Emotions 416 K samples, six classes, and Social Media Emotion 75 K samples, five classes, show that our distilled models achieve near-teacher performance 97.35% and 73.86% accuracy, respectively. with only a < 1% and < 6% accuracy drop, while reducing model size by 40% and inference latency by 3.2×. Notably, our method significantly improves F1-scores for minority classes. Our work sets a new state-of-the-art in efficient emotion recognition, enabling practical deployment in edge computing and mobile applications.

The importance of gastric cancer (GC) and the role of deep learning techniques in categorizing GC histopathology images have recently increased. Identifying the drawbacks of traditional deep learning models, including lack of interpretability, inability to capture complex patterns, lack of adaptability, and sensitivity to noise. A multi-channel attention mechanism-based framework is proposed that can overcome the limitations of conventional deep learning models by dynamically focusing on relevant features, enhancing extraction, and capturing complex relationships in medical data. The proposed framework uses three different attention mechanism channels and convolutional neural networks to extract multichannel features during the classification process. The proposed framework’s strong performance is confirmed by competitive experiments conducted on a publicly available Gastric Histopathology Sub-size Image Database, which yielded remarkable classification accuracies of 99.07% and 98.48% on the validation and testing sets, respectively. Additionally, on the HCRF dataset, the framework achieved high classification accuracy of 99.84% and 99.65% on the validation and testing sets, respectively. The effectiveness and interchangeability of the three channels are further confirmed by ablation and interchangeability experiments, highlighting the remarkable performance of the framework in GC histopathological image classification tasks. This offers an advanced and pragmatic artificial intelligence solution that addresses challenges posed by unique medical image characteristics for intricate image analysis. The proposed approach in artificial intelligence medical engineering demonstrates significant potential for enhancing diagnostic precision by achieving high classification accuracy and treatment outcomes.

Electrocardiogram (ECG) is the most common and low-cost diagnostic tool used in healthcare institutes for screening heart electrical signals. The abnormal heart signals are commonly known as arrhythmia. Cardiac arrhythmia can be dangerous, or in most cases, it can cause death. The arrhythmia can be of different types, and it can be detected by an ECG test. The automated screening of arrhythmia classification using ECG beats is developed for ages. The automated systems that can be adapted as a tool for screening arrhythmia classification play a vital role not only for the patients but can also assist the doctors. The deep learning-based automated arrhythmia classification techniques are developed with high accuracy results but still not adopted by healthcare professionals as the generalized approach. The primary concerns that affect the success of the developed arrhythmia detection systems are (i) manual features selection, (ii) techniques used for features extraction, and (iii) algorithm used for classification and the most important is the use of imbalanced data for classification. This study focuses on the recent trends in arrhythmia classification techniques, and through extensive simulations, the performance of the various arrhythmia classification and detection models has been evaluated. Finally, the study presents insights into arrhythmia classification techniques to overcome the limitation in the existing methodologies.

During the 'Arab Spring,' young tech savvy activists led uprisings in a dozen countries across North Africa and the Middle East. At first, digital media allowed democratization movements to develop new tactics for catching dictators off guard. Eventually, authoritarian governments worked social media into their own counter-insurgency strategies. What have we learned about the role of digital media in modern protest? Digital media helped to turn individualized, localized, and community-specific dissent into structured movements with a collective consciousness about both shared grievances and opportunities for action. Adapted from the source document.

Deep learning (DL) enables the creation of computational models comprising multiple processing layers that learn data representations at multiple levels of abstraction. In the recent past, the use of deep learning has been proliferating, yielding promising results in applications across a growing number of fields, most notably in image processing, medical image analysis, data analysis, and bioinformatics. DL algorithms have also had a significant positive impact through yielding improvements in screening, recognition, segmentation, prediction, and classification applications across different domains of healthcare, such as those concerning the abdomen, cardiac, pathology, and retina. Given the extensive body of recent scientific contributions in this discipline, a comprehensive review of deep learning developments in the domain of diabetic retinopathy (DR) analysis, viz., screening, segmentation, prediction, classification, and validation, is presented here. A critical analysis of the relevant reported techniques is carried out, and the associated advantages and limitations highlighted, culminating in the identification of research gaps and future challenges that help to inform the research community to develop more efficient, robust, and accurate DL models for the various challenges in the monitoring and diagnosis of DR.

In this study, the proposed method involves the confident insertion of π-spacer fragments between donor and acceptor parts of a newly designed (A1-D-A2) molecule into the reference molecule (PP2). Frontier molecular orbitals study using MPW1PW91/6-31G(d,p) level of DFT demonstrates that all designed molecules possess a lower band gap (2.62–3.35 eV) in comparison to R (3.77 eV). The absorption properties clearly show that all the designed molecules (DD1–DD8) have higher absorption values (434.44–566.40 nm) in the gas phase and (498.65–624.01 nm) in the solvent phase compared to R values of 380.32 nm in the gas phase and 415.61 nm in the solvent phase. Significant LHE values and the lowest λ e values (0.0062–0.0110 eV) are observed in the designed molecules. This study will help researchers to design molecules for the development of efficient PSCs devices.

Semi-supervised joint classification of Hyperspectral Images (HSIs) and LiDAR-derived Digital Surface Models (DSMs) remains challenging due to scarcity of labeled pixels, strong intra-class variability, and the heterogeneous nature of spectral and elevation features. In this work, we propose a Hybrid Mamba–Graph Fusion Network (HMGF-Net) with Multi-Stage Pseudo-Label Refinement (MS-PLR) for semi-supervised hyperspectral–LiDAR classification. The framework employs a spectral–spatial HSI backbone combining 3D–2D convolutions, a compact LiDAR CNN encoder, Mamba-style state-space sequence blocks for long-range spectral and cross-modal dependency modeling, and a graph fusion module that propagates information over a heterogeneous pixel graph. Semi-supervised learning is realized via a three-stage pseudolabeling pipeline that progressively filters, smooths, and re-weights pseudolabels based on prediction confidence, spatial–spectral consistency, and graph neighborhood agreement. We validate HMGF-Net on three benchmark hyperspectral–LiDAR datasets. Compared with a set of eight state-of-the-art (SOTA) baselines, including 3D-CNNs, SSRN, HybridSN, transformer-based models such as SpectralFormer, multimodal CNN–GCN fusion networks, and recent semi-supervised methods, the proposed approach delivers consistent gains in overall accuracy, average accuracy, and Cohen’s kappa, especially in low-label regimes (10% labeled pixels). The results highlight that the synergy between sequence modeling and graph reasoning in combination with carefully designed pseudolabel refinement is essential to maximizing the benefit of abundant unlabeled samples in multimodal remote sensing scenarios.

Advancements in satellite sensor technology have enabled access to diverse remote sensing (RS) data from multiple platforms. Hyperspectral Image (HSI) data offers rich spectral detail for material identification, while LiDAR captures high-resolution 3D structural information, making the two modalities naturally complementary. By fusing HSI and LiDAR, we can mitigate the limitations of each and improve tasks like land cover classification, vegetation analysis, and terrain mapping through more robust spectral–spatial feature representation. However, traditional multi-scale feature fusion models often struggle with aligning features effectively, which can lead to redundant outputs and diminished spatial clarity. To address these issues, we propose the Cross Attention Bridge for HSI and LiDAR (CAB-HL), a novel dual-path framework that employs a multi-stage cross-attention mechanism to guide the interaction between spectral and spatial features. In CAB-HL, features from each modality are refined across three progressive stages using cross-attention modules, which enhance contextual alignment while preserving the distinctive characteristics of each modality. These fused representations are subsequently integrated and passed through a lightweight classification head. Extensive experiments on three benchmark RS datasets demonstrate that CAB-HL consistently outperforms existing state-of-the-art models, confirm that CAB-HL consistently outperforms in learning deep joint representations for multimodal classification tasks.