ABSTRACT Accurate channel estimation is essential for optimising intelligent reflecting surface‐assisted multi‐user communication systems, particularly in dynamic indoor environments. Conventional techniques such as least squares (LS), linear minimum mean square error (LMMSE), and orthogonal matching pursuit (OMP) suffer from noise sensitivity and fail to effectively capture spatial dependencies in high‐dimensional intelligent reflecting surface (IRS)‐assisted channels. To overcome these limitations, this work proposes a deep learning‐driven ResNet+UNet framework that refines initial LS estimates using residual learning and multi‐scale feature reconstruction. While UNet enhances channel estimation through hierarchical processing, efficiently decreasing noise and enhancing estimate accuracy, ResNet gathers spatial features. Simulation results show that the proposed method significantly outperforms existing methods across various performance metrics. In NMSE versus signal‐to‐noise ratio assessments, the proposed approach surpasses convolutional deep residual network (CDRN) by 59%, OMP by 81%, LMMSE by 114%, and LS by 115%. When IRS elements are modified, it overcomes CDRN by 60%, OMP by 78%, LS by 107%, and LMMSE by 110%. Along with this, recommended structure performs more effectively than CDRN by 39%, OMP by 44%, LS by 122%, and LMMSE by 129% across various antenna configurations. The proposed approach is particularly beneficial for augmented reality (AR) applications, where real‐time, high‐precision channel estimation ensures seamless data streaming and ultra‐low latency, enhancing immersive experiences in AR‐based communication and interactive environments. These results illustrate the proposed method's scalability and resilience, making it a suitable choice for next‐generation IRS‐assisted wireless communication networks.

Visual servoing, the method of controlling robot motion through feedback from visual sensors, has seen significant advancements with the integration of optical flow-based methods. However, its application remains limited by inherent challenges, such as the necessity for a target image at test time, the requirement of substantial overlap between initial and target images, and the reliance on feedback from a single camera. This paper introduces Imagine2Servo†, an innovative approach leveraging diffusion-based image editing techniques to enhance visual servoing algorithms by generating intermediate goal images. This methodology allows for the extension of visual servoing applications beyond traditional constraints, enabling tasks like long-range navigation and manipulation without predefined goal images. We propose a pipeline that synthesizes subgoal images grounded in the task at hand, facilitating servoing in scenarios with minimal initial and target image overlap and integrating multi-camera feedback for comprehensive task execution. Our contributions demonstrate a novel application of image generation to robotic control, significantly broadening the capabilities of visual servoing systems. Real-world experiments validate the effectiveness and versatility of the Imagine2Servo framework in accomplishing a variety of tasks, marking a notable advancement in the field of visual servoing.

In large graphs such as those representing social or other affinity networks, one is often interested in finding dense clusters, i.e., subgraphs with relatively high connectivity, embedding in such graphs. Inspired by a classical approach called Hierarchical Mode Analysis, which works only for data in metric spaces, we introduce a novel algorithm called HIMAG (Hierarchi-cal Incremental Mode Analysis for Graphs) that detects dense subgraphs at multiple resolutions, while ignoring “non-dense” areas. We also provide a powerful multi-resolution visualization tool customized for the new algorithm. We present results on two standard benchmark social graph datasets as well as a motivating real-world application, to show the power of our approach and compare it with some standard graph partitioning algorithms that were retrofitted to produce dense clusters by pruning nondense data in a non-trivial manner. We are also open-sourcing the new dense graph datasets and tools to the community.

A key application of clustering data obtained from sources such as microarrays, protein mass spectroscopy, and phylogenetic profiles is the detection of functionally related genes. Typically, only a small number of functionally related genes cluster into one or more groups, and the rest need to be ignored. For such situations, we present Automated Hierarchical Density Shaving (Auto-HDS), a framework that consists of a fast hierarchical density-based clustering algorithm and an unsupervised model selection strategy. Auto-HDS can automatically select clusters of different densities, present them in a compact hierarchy, and rank individual clusters using an innovative stability criteria. Our framework also provides a simple yet powerful 2D visualization of the hierarchy of clusters that is useful for further interactive exploration. We present results on Gasch and Lee microarray data sets to show the effectiveness of our methods. Additional results on other biological data are included in the supplemental material.

Clustering problems often involve datasets where only a part of the data is relevant to the problem, e.g., in microarray data analysis only a subset of the genes show cohesive expressions within a subset of the conditions/features. The existence of a large number of non-informative data points and features makes it challenging to hunt for coherent and meaningful clusters from such datasets. Additionally, since clusters could exist in different subspaces of the feature space, a co-clustering algorithm that simultaneously clusters objects and features is often more suitable as compared to one that is restricted to traditional "one-sided" clustering. We propose Robust Overlapping Co-Clustering (ROCC), a scalable and very versatile framework that addresses the problem of efficiently mining dense, arbitrarily positioned, possibly overlapping co-clusters from large, noisy datasets. ROCC has several desirable properties that make it extremely well suited to a number of real life applications.

In classical clustering, each data point is assigned to at least one cluster. However, in many applications only a small subset of the available data is relevant for the problem and the rest needs to be ignored in order to obtain good clusters. Certain nonparametric density-based clustering methods find the most relevant data as multiple dense regions, but such methods are generally limited to low-dimensional data and do not scale well to large, high-dimensional datasets. Also, they use a specific notion of “distance”, typically Euclidean or Mahalanobis distance, which further limits their applicability. On the other hand, the recent One Class Information Bottleneck (OC-IB) method is fast and works on a large class of distortion measures known as Bregman Divergences, but can only find a single dense region. This article presents a broad framework for finding k dense clusters while ignoring the rest of the data. It includes a seeding algorithm that can automatically determine a suitable value for k . When k is forced to 1, our method gives rise to an improved version of OC-IB with optimality guarantees. We provide a generative model that yields the proposed iterative algorithm for finding k dense regions as a special case. Our analysis reveals an interesting and novel connection between the problem of finding dense regions and exponential mixture models; a hard model corresponding to k exponential mixtures with a uniform background results in a set of k dense clusters. The proposed method describes a highly scalable algorithm for finding multiple dense regions that works with any Bregman Divergence, thus extending density based clustering to a variety of non-Euclidean problems not addressable by earlier methods. We present empirical results on three artificial, two microarray and one text dataset to show the relevance and effectiveness of our methods.

In traditional clustering, every data point is assigned to at least one cluster. On the other extreme, one class clustering algorithms proposed recently identify a single dense cluster and consider the rest of the data as irrelevant. However, in many problems, the relevant data forms multiple natural clusters. In this paper, we introduce the notion of Bregman bubbles and propose Bregman bubble clustering (BBC) that seeks k dense Bregman bubbles in the data. We also present a corresponding generative model, soft BBC, and show several connections with Bregman clustering, and with a one class clustering algorithm. Empirical results on various datasets show the effectiveness of our method.

Unsupervised learning methods often involve summarizing the data using a small number of parameters. In certain domains, only a small subset of the available data is relevant for the problem. One-Class Classification or One-Class Clustering attempts to find a useful subset by locating a dense region in the data. In particular, a recently proposed algorithm called One-Class Information Ball (OC-IB) shows the advantage of modeling a small set of highly coherent points as opposed to pruning outliers. We present several modifications to OC-IB and integrate it with a global search that results in several improvements such as deterministic results, optimality guarantees, control over cluster size and extension to other cost functions. Empirical studies yield significantly better results on various real and artificial data.

1 Introduction Real life transactional data often poses challenges such as very large size, high dimensionality, skewed distribution, sparsity, seasonal variations and market-drift or migration [1, 2]. Most studies have taken a static view of the data while making predictions about a customer's buying behavior, market segmentation, etc. [3, 4]. A notable exception is recent work on temporal association rule mining, dealing with incremental characteristics and change, for example, see [5, 6]. This paper focusses on the problem of segmenting customers visiting a rapidly growing e-tailer. The segments are dynamic and seasonal, so preprocessing and trend characterization is key. We use a real-life data belonging to an e-commerce business and referred to as Horizon data in this paper, provided by KD1 (since then acquired by Net Perceptions) to illustrate the issues. In Section 2, the Horizon data is summarized. Section 3 quantifies market migration for choosing the appropriate period of data. Based on seasonal variations in purchasing behavior, a novel seasonality detection and partitioning scheme is described. Some of the market migration and oscillation results on Horizon data are also presented. Section 4 describes a new concept called Cluster Space for converting this high dimensional (> 10, 000) data into a continuous low dimensional space using a graph based clustering called VBACC [7] on the seasonally partitioned data. Motion detection and visualization schemes are introduced, and some interesting trends found in the Horizon data are described.