Diagnosing the root cause of an anomaly in a complex interconnected system is a pressing problem in today’s cloud services and industrial operations. We propose In-Distribution Interventions (IDI), a novel algorithm that predicts root cause as nodes that meet two criteria: 1) Anomaly: root cause nodes should take on anomalous values; 2) Fix: had the root cause nodes assumed usual values, the target node would not have been anomalous. Prior methods of assessing the fix condition rely on counterfactuals inferred from a Structural Causal Model (SCM) trained on historical data. But since anomalies are rare and fall outside the training distribution, the fitted SCMs yield unreliable counterfactual estimates. IDI overcomes this by relying on interventional estimates obtained by solely probing the fitted SCM at in-distribution inputs. We present a theoretical analysis comparing and bounding the errors in assessing the fix condition using interventional and counterfactual estimates. We then conduct experiments by systematically varying the SCM’s complexity to demonstrate the cases where IDI’s interventional approach outperforms the counterfactual approach and vice versa. Experiments on both synthetic and PetShop RCD benchmark datasets demonstrate that IDI consistently identifies true root causes more accurately and robustly than nine existing state-of-the-art RCD baselines. Code will be released at https://github.com/nlokeshiisc/IDI_release.

Modern Text-to-Image (T2I) Diffusion models have revolutionized image editing by enabling the generation of high-quality photorealistic images. While the de-facto method for performing edits with T2I models is through text instructions, this approach is non-trivial due to the complex many-to-many mapping between natural language and images. In this work, we address exemplar-based image editing - the task of transferring an edit from an exemplar pair to a content image(s). We propose Reedit, a modular and efficient end-to-end framework that captures edits in both text and image modalities while ensuring the fidelity of the edited image. We validate the effectiveness of Reedit through extensive comparisons with state-of-the-art baselines and sensitivity analyses of key design choices. Our results demonstrate that Reeditconsistently outperforms contemporary approaches both qualitatively and quantitatively. Additionally, Reedit boasts high practical applicability, as it does not require any task-specific optimization and is 4× faster than the existing state-of-the-art. The code and data for our work is available at https://reedit-diffusion.github.io/.

ABSTRACT The detection of brain tumours presents a significant challenge in the medical domain, where prompt and precise diagnosis is crucial as patient outcomes depend on it. Conventional deep neural networks perform well in carrying out various imaging tasks within the healthcare sector; however, their effectiveness often falls short of expectations in practical applications due to the substantial computational resources required and issues with reliability. In this research, an optimised and effective deep learning model founded on the DenseNet‐169 architecture is introduced for the classification of magnetic resonance imaging brain tumours, which is particularly advantageous for smart healthcare systems and information and communication technology (ICT) settings with limited computational capabilities. The model compression methodologies, including pruning and quantization, have been employed to significantly diminish the dimensions and intricacy of the model while achieving a classification accuracy of 97.07%. Furthermore, this endeavour necessitates the enhancement of the model's interpretability through the utilisation of explainable artificial intelligence methodologies such as Gradient‐weighted Class Activation Mapping (Grad‐CAM) and SHapley Additive exPlanations (SHAP), which will aid clinicians in highlighting crucial areas of the images and validating feature importance concerning the decisions rendered by the model. A comparative performance evaluation is conducted against DenseNet‐169, ResNet‐50 and various other models to delineate the superior efficacy of our model, rendering it exceptionally adept for knowledge‐driven, real‐time brain tumour diagnosis within smart healthcare and ICT systems where resources are constrained.

Smart glasses that support augmented reality (AR) have the potential to become the consumer's primary medium of connecting to the future internet. For the best quality of user experience, AR glasses must have a small form factor and long battery life, while satisfying the data rate and latency requirements of AR applications. To extend the AR glasses' battery life, the computation and processing involved in AR may be offloaded to a companion device, such as a smartphone, through a wireless connection. Sidelink (SL), i.e., the D2D communication interface of 5G NR, is a potential candidate for this wireless link. In this paper, we use system-level simulations to analyze the feasibility of NR SL for supporting AR. Our simulator incorporates the PHY layer structure and MAC layer resource scheduling of 3GPP SL, standard 3GPP channel models, and MCS configurations. Our results suggest that the current SL standard specifications are insufficient for high-end AR use cases with heavy interaction but can support simpler previews and file transfers. We further propose two enhancements to SL resource allocation, which have the potential to offer significant performance improvements for AR applications.

Device-to-device (D2D) communication using 5G New Radio (NR) sidelink (SL) is envisioned to be a key enabler of high speed, low latency applications, with automated driving being the prime use case. To meet the high data rate requirements, it is essential for SL devices to be able to operate in mmWave/sub-THz frequencies where bandwidth is abundant. Consequently, several enhancements will be needed to the current version of NR SL, which is mainly designed for sub-6 GHz frequencies. Beamforming based highly directional transmission/reception used at high carrier frequencies result in directional deafness in other directions. For SL UE autonomous resource allocation, termed as Mode 2 of NR SL in 3GPP, this results in a UE’s inability to detect transmissions not aligned to its primary direction of reception, which leads to high packet errors. In this paper, we focus on system wide performance of 3GPP based NR SL Mode 2 resource allocation for directional systems at mmWave/sub-THz frequencies. We propose a composite strategy that comprises paired SL control transmission and sensing, whereby SL UEs transmit and receive the SL control information in an additional “paired” direction, directly opposite to their intended direction of transmission. This helps eliminate hidden node interference while avoiding too many exposed nodes. System level simulations in NR V2X highway scenarios show significant performance improvement of the proposed scheme over conventional solutions like omnidirectional or directional transmission/reception of SL control information.