Deep learning architectures have brought about new heights in computer vision, with the most common approach being the Convolutional Neural Network (CNN). Through CNN, tasks previously deemed unattainable, including facial recognition, autonomous driving systems, and sophisticated medical diagnostics, among others can now be achieved. Convolutional layers, non-linear processing units, and subsampling layers are used in conjunction throughout the several learning phases that make up CNN’s structure. Generally, 2D and 3D CNNs have been used to achieve impressive results across numerous areas, and several survey papers have been published to review their state-of-the-art applications. However, they are unsuitable in some domain-specific areas where temporal dynamics and dependencies must be captured. Examples of such domains are time series prediction and signal identification, which necessitates the use of one-dimensional signals. Recently, 1D-CNN has evolved and has been used to develop various state-of-the-art models that cut across numerous research fields. However, there has been no survey paper detailing the evolution and advancements in the applications of the 1D-CNN to several computer vision tasks. In addressing this gap, this paper provides the first exhaustive survey to examine the historical development of 1D-CNNs and elucidate their structural intricacies and architectural frameworks. It also highlights recent advancements in their applications across more than twelve distinct domains. Furthermore, this paper provides an overview of the significant challenges impacting the current state-of-the-art 1D-CNN training and deployment while highlighting potential directions for future research exploration. By carrying out this survey, researchers across several fields can have a comprehensive understanding of the evolution, structural intricacies, and recent advancements in the applications of 1D-CNNs across various computer vision tasks. This paper also equip researchers with the knowledge needed to address the significant challenges faced in the current state-of-the-art 1D-CNN hurdles.

Colorectal cancer occurs in the rectal of humans, and early detection has been proved to reduce its mortality rate. Colonoscopy is the standard used in detecting the presence of polyps in the rectal, and accurate segmentation of the polyps from colonoscopy images often provides helpful information for early diagnosis and treatment. Although existing deep learning models often achieve high segmentation performance when tested on the same dataset used in model training; still, their performance often degrades when applied to out-of-distribution datasets, leading to low model generalization or overfitting. This challenge is often associated with the quality of the features learnt from the input images. In this work, a novel Context Feature Refinement (CFR) module is proposed to address the challenge of low model generalization and segmentation performance. The CFR module is built to extract contextual information from the incoming feature map by using multiple parallel convolutional layers with progressively increasing kernel sizes. Using multiple parallel convolutions with different kernel sizes helped to extract more efficient multi-scale contextual information and thus enabled the network to effectively identify and segment small and fine details, as well as larger and more complex structures in the input images. Extensive experiments on three public benchmark datasets in CVC-ClinicDB, Kvasir-SEG, and BKAI-NeoPolyp showed that the proposed ConvSegNet model achieved jaccard, dice and F2 scores of 0.8650, 0.9177, and 0.9328 on CVC-ClinicDB, 0.7936, 0.8618, and 0.8855 on Kvasir-SEG, and 0.8045, 0.8747 and 0.8909 on BKAI-NeoPolyp datasets respectively. Also, an improved generalization performance was achieved by the ConvSegNet model, compared to the benchmark polyp segmentation models.

Intrusion detection in IoT networks is challenged by data heterogeneity, label scarcity, and privacy constraints. Traditional federated learning (FL) methods often assume IID data or require supervised labels, limiting their practicality. We propose G-PFL-ID, a graph-driven personalized federated learning framework for unsupervised intrusion detection in non-IID IoT systems. Our method trains a global graph encoder (GCN or GAE) with a DeepSVDD objective under a federated regularizer (FedReg) that combines proximal and variance penalties, then personalizes local models via a lightweight fine-tuning head. We evaluate G-PFL-ID on the IoT-23 (Mirai-based captures) and N-BaIoT (device-level dataset) under realistic heterogeneity (Dirichlet-based partitioning with concentration parameters $\alpha \in \{0.1,0.5,\infty \}$ and client counts $K\in \{10,15,20\}$ for IoT-23, and natural device-based partitioning for N-BaIoT). G-PFL-ID outperforms global FL baselines and recent graph-based federated anomaly detectors, achieving up to 99.46% AUROC on IoT-23 and 97.74% AUROC on N-BaIoT. Ablation studies confirm that the proximal and variance penalties reduce inter-round drift and representation collapse, and that lightweight personalization recovers local sensitivity—especially for clients with limited data. Our work bridges graph-based anomaly detection with personalized FL for scalable, privacy-preserving IoT security.

Human Activity Recognition (HAR) using wearable sensor data plays a vital role in health monitoring, context-aware computing, and smart environments. Many existing deep learning models for HAR incorporate MaxPooling layers after convolutional operations to reduce dimensionality and computational load. While this approach is effective in image-based tasks, it is less suitable for the sensor signals used in HAR. MaxPooling introduces a form of temporal downsampling that can discard subtle yet crucial temporal information. Also, traditional CNNs often struggle to capture long-range dependencies within each window due to their limited receptive fields, and they lack effective mechanisms to aggregate information across multiple windows without stacking multiple layers, which increases computational cost. In this study, we introduce Retentive-HAR, a model designed to enhance feature learning by capturing dependencies both within and across sliding windows. The proposed model intentionally omits the MaxPooling layer, thereby preserving the full temporal resolution throughout the network. The model begins with parallel dilated convolutions, which capture long-range dependencies within each window. Feature outputs from these convolutional layers are then concatenated along the feature dimension and transposed, allowing the Retentive Module to analyze dependencies across both window and feature dimensions. Additional 1D-CNN layers are then applied to the transposed feature maps to capture complex interactions across concatenated window representations before including Bi-LSTM layers. Experiments on PAMAP2, HAPT, and WISDM datasets achieve a performance of 96.40%, 94.70%, and 96.16%, respectively, which outperforms the existing methods with minimal computational cost.