Industries are generating massive amounts of data due to increased automation and interconnectedness. As data from various sources becomes more available, the extraction of relevant information becomes crucial for understanding complex systems’ behavior and performance. The growing volume and complexity of time-series data in diverse industries have created a demand for effective anomaly detection methods. Detecting anomalies in multivariate time-series data presents unique challenges, such as the presence of multiple correlated variables and intricate relationships among them. Traditional approaches often fall short in detecting anomalies, making deep learning methods a promising solution. This review article provides a comprehensive analysis of different deep learning techniques for anomaly detection in time-series data, examining their applicability across various industries and discussing the associated challenges. The article emphasizes the significance of deep learning in detecting anomalies and offers valuable insights to inform decision-making processes. Furthermore, it proposes recommendations for model developers, advocating for the development of hybrid models that combine different deep learning techniques and the exploration of attention mechanisms in Recurrent Neural Networks (RNNs). These recommendations aim to overcome the challenges associated with deep learning-based anomaly detection in multivariate time-series data.

Skin cancers are increasing at an alarming rate, and detection in the early stages is essential for advanced treatment. The current segmentation methods have limited labeling ability to the ground truth images due to the numerous noisy expert annotations present in the datasets. The precise boundary segmentation is essential to correctly locate and diagnose the various skin lesions. In this work, the lesion segmentation method is proposed as a Markov decision process. It is solved by training an agent to segment the region using a deep reinforcement-learning algorithm. Our method is similar to the delineation of a region of interest by the physicians. The agent follows a set of serial actions for the region delineation, and the action space is defined as a set of continuous action parameters. The segmentation model learns in continuous action space using the deep deterministic policy gradient algorithm. The proposed method enables continuous improvement in performance as we proceed from coarse segmentation results to finer results. Finally, our proposed model is evaluated on the International Skin Imaging Collaboration (ISIC) 2017 image dataset, Human against Machine (HAM10000), and PH² dataset. On the ISIC 2017 dataset, the algorithm achieves an accuracy of 96.33% for the naevus cases, 95.39% for the melanoma cases, and 94.27% for the seborrheic keratosis cases. The other metrics are evaluated on these datasets and rank higher when compared with the current state-of-the-art lesion segmentation algorithms.

Semantic segmentation annotation helps train computer vision based Artificial Intelligence models where each image pixel is assigned to a specific object class. The model developers try to identify the features helpful for determining the objects of interest by using various supervised deep learning techniques. However, this is a difficult task due to the complexity of object structures. Two difficulties arise in the current approaches for semantic segmentation. The pixel-wise label approach is costly to obtain and is time consuming. Second, the datasets taken for the semantic segmentation task are not balanced since certain classes are present more than the others. This biases the model performance to the most represented ones. We propose a new reinforced active learning strategy based on a deep reinforcement learning algorithm. This work presents a modified Deep $Q$ Learning formulation for active learning. An agent learns the strategy of selecting a subset of small image regions, which are more knowledgeable than the whole set of images from an unlabeled data pool. The decision on the area of selection is dependent on the assumptions and segmentation model uncertainties taken for training purposes. We use the CamVid and RGB indoor test scenes dataset to evaluate the proof of concept. Our results infer that our approach demands more labels from under-represented groups than the baselines, thus enhancing their efficiency and mitigating the class imbalance. Our method’s performance is superior to the conventional deep learning models in detecting 8 out of 11 classes on the Camvid road segmentation scene dataset. It achieves an accuracy of 90.56%, a mIoU score of 87.17%, and a BF score of 93.14%. On the SUNRGB indoor scenes dataset, it gives an accuracy of around 75.82% and a BF score of 77.25%, thus outperforming the current state-of-the-art methods.

Video object segmentation’s primary goal is to automatically extract the principal object(s) in the foreground from the background in videos. The primary focus of the current deep learning-based models is to learn the discriminative representations in the foreground over motion and appearance in small-term temporal segments. In the video segmentation process, it is difficult to handle various challenges such as deformation, scale variation, motion blur, and occlusion. Furthermore, relocating the segmentation target in the next frame is difficult if it is lost in the current frame during the segmentation process. This work aims at solving the zero-shot video object segmentation issue in a holistic fashion. We take advantage of the inherent correlations between the video frames by incorporating a global co-attention mechanism to overcome the limitations. We propose a novel reinforcement learning framework that provides competent and fast stages for gathering scene context and global correlations. The agent concurrently calculates and adds the responses of co-attention in the joint feature space. To capture the different aspects of the common feature space, the agent can generate multiple co-attention versions. Our framework is trained using pairs (or groups) of video frames, which adds to the training content, thus increasing the learning capacity. Our approach encodes the important information during the segmentation phase by a simultaneous process of various reference frames that are subsequently utilized to predict the persistent and conspicuous objects in the foreground. The proposed method has been validated using four commonly used video entity segmentation datasets: SegTrack V2, DAVIS 2016, CdNet 2014, and the Youtube-Object dataset. On the DAVIS 2016, the results reveal that the proposed results boost the state-of-the-art techniques on the F1 Measure by 4%, SegTrack V2 by a Jaccard Index of 12.03%, and Youtube Object by a Jaccard Index of 13.11%. Meanwhile, our algorithm improves the accuracy by 8%, F1 Measure by 12.25 %, and precision by 14% on the CdNet 2014, thus ranking higher than the current state-of-the-art methods.