15 February 2021 in IEEE Access
This paper considers the problem of anomaly detection in an outdoor environment where surveillance cameras are usually installed to monitor activities of general public. A novel solution is proposed which combines audio and visual data to automatically detect abnormal activities. The proposed anomaly detection algorithm makes use of both visual and audio features to automatically detect anomalous activities in scenes. Visual features such as optical flow technique combined with particle swam optimization and social force model are used, whereas, acoustic features such as, energy, zero crossing rate, volume, spectral-centroid, spectral spread, spectral roll-off, spectral flux, cross correlation and the mel-frequency cepstral coefficients (MFCCs) are used. An anomaly inference is developed which is based on both visual and audio features. The performance of the proposed algorithm is evaluated by testing it on the publicly available UMN datasets combined with the audio recordings. The proposed algorithm is compared with state-of-the-art techniques and is shown to achieve improved performance in terms of accuracy.
25 January 2021 in IEEE Access
With growing security threats, many online and offine frameworks have been proposed for anomaly detection in video sequences. However, existing online anomaly detection techniques are either computationally very expensive or lack desirable accuracy. This research work proposes a novel particle filtering based framework for online anomaly detection which detects video frames with anomalous activities based upon the posterior probability of activities in a video sequence. The proposed method also detects anomalous regions in anomalous video frames. We propose novel prediction and measurement models to accurately detect anomalous video frames and anomalous regions in video frames. Novel prediction model for particle prediction and likelihood model for assigning weights to these particles are proposed. These models efficiently utilise variable sized cell structure which creates variable sized sub-regions of scenes in video frames. Furthermore, they efficiently extract and utilise information from the video frame in the form of size, motion and location features. The proposed framework is tested on UCSD and LIVE datasets and compared with the existing state-of-the-art algorithms in the literature. The proposed anomaly detection algorithm outperforms the state-of-the art algorithms in terms of reduced Equal Error Rate (EER) with comparatively lesser processing time.
11 November 2020 in IEEE Access
The advancements in Edge computing have paved the way for deep learning in real-time systems. One of the beneficiaries is an adaptive traffic control system that responds to real-time traffic observations by governing the signal phase and timings. Reinforcement Learning (RL) is extensively utilized in the literature in order to decrease traffic congestion in a road network. However, most of the previous works leverage centralized and cloud-based RL due to the computational complexity of underlying deep neural networks (DNN). Therefore, a persistent challenge towards adopting Edge learning is in devising a Multi-Agent RL in which agents are simplified, and their state spaces are localized but they perform comparable to the centralized RL. This article presents a Collaborative and Adaptive Signaling on the Edge (CASE), a novel Multi-Agent RL approach to control the traffic signals’ phase and timing. Each signalized intersection in the road network is provided with an Edge Learning Platform which hosts an RL-Agent that observes local traffic states and learns an optimum signal policy. Moreover, CASE allows collaboration among RL-Agents by sharing their signal phase and timings to achieve convergence and performance. This collaboration is limited to one’s direct neighbours only to minimize the computational complexity. We performed rigorous evaluations in terms of the choice of RL methods and their state space/reward and found that our collaborative state-space has resulted in a performance comparable to a centralized RL yet with a cost similar to the decentralized RL. Finally, a performance comparison of the CASE controller ported to the state-of-the-art Edge learning platforms is presented in this article. The results show that the proposed CASE controller can achieve real-time performance when ported to a general-purpose GPU-based platform. This arrangement achieves more than 8 times improvement in computational time over conventional embedded platforms.
1 January 2021 in Complexity
In computer networks, vertices represent hosts or servers, and edges represent as the connecting medium between them. In localization, some special vertices (resolving sets) are selected to locate the position of all vertices in a computer network. If an arbitrary vertex stopped working and selected vertices still remain the resolving set, then the chosen set is called as the fault‐tolerant resolving set. The least number of vertices in such resolving sets is called the fault‐tolerant metric dimension of the network. Because of the variety of applications of the metric dimension in different areas of sciences, many generalizations were proposed, and fault tolerant is one of them. In this paper, we computed the fault‐tolerant metric dimension of triangular snake, ladder, Mobius ladder, and hexagonal ladder networks. It is important to observe that, in all these classes of networks, the fault‐tolerant metric dimension and metric dimension differ by 1.
28 March 2024 in PLOS ONE
This paper presents a novel sound event detection (SED) system for rare events occurring in an open environment. Wavelet multiresolution analysis (MRA) is used to decompose the input audio clip of 30 seconds into five levels. Wavelet denoising is then applied on the third and fifth levels of MRA to filter out the background. Significant transitions, which may represent the onset of a rare event, are then estimated in these two levels by combining the peak-finding algorithm with the K-medoids clustering algorithm. The small portions of one-second duration, called ‘chunks’ are cropped from the input audio signal corresponding to the estimated locations of the significant transitions. Features from these chunks are extracted by the wavelet scattering network (WSN) and are given as input to a support vector machine (SVM) classifier, which classifies them. The proposed SED framework produces an error rate comparable to the SED systems based on convolutional neural network (CNN) architecture. Also, the proposed algorithm is computationally efficient and lightweight as compared to deep learning models, as it has no learnable parameter. It requires only a single epoch of training, which is 5, 10, 200, and 600 times lesser than the models based on CNNs and deep neural networks (DNNs), CNN with long short-term memory (LSTM) network, convolutional recurrent neural network (CRNN), and CNN respectively. The proposed model neither requires concatenation with previous frames for anomaly detection nor any additional training data creation needed for other comparative deep learning models. It needs to check almost 360 times fewer chunks for the presence of rare events than the other baseline systems used for comparison in this paper. All these characteristics make the proposed system suitable for real-time applications on resource-limited devices.