Convolutional Recurrent Neural Network Research Articles

Revolutionizing Drug Discovery: Harnessing Machine Learning Algorithms

Drug discovery is a crucial element of biomedical research, with the goal of finding and creating new medical treatments for a variety of illnesses. Yet, the conventional process of finding new drugs is frequently impeded by its intrinsic difficulties, such as expensive expenses, long durations, and poor success rates in trials with patients. Recently, the incorporation of machine learning (ML) algorithms has become a revolutionary method to streamline and improve different phases of drug discovery. This summary offers a glimpse into the rapidly growing area of drug discovery using machine learning algorithms, emphasizing its potential to transform the process of developing treatments. The usual process of discovering drugs involves various stages such as identifying the target, finding lead compounds, conducting preclinical tests, undergoing clinical trials, and obtaining regulatory approval. All these phases require a lot of labor, time, and resources, leading to high attrition rates and limited success in turning potential compounds into approved therapies. Nevertheless, researchers can enhance and speed up crucial parts of the drug discovery process by using ML algorithms. ML algorithms use data to aid in drug discovery by utilizing computational models to examine large quantities of biological, chemical, and clinical data. These algorithms can learn from various types of data, such as genomic data, chemical structures, protein interactions, and clinical outcomes, to discover hidden patterns, find new targets for drugs, and forecast the effectiveness and safety of potential treatments. Moreover, machine learning algorithms allow for the investigation of intricate connections between molecular structures and biological effects, making it easier to create improved drug candidates with better effectiveness and specificity. Important uses of machine learning in pharmaceutical research involve finding and confirming targets, screening compounds and improving leads, repurposing drugs, and tailoring treatments for individuals. Commonly used for classification and regression tasks, supervised learning algorithms like support vector machines and random forests predict compound activity, toxicity, and pharmacokinetic properties. Clustering and dimensionality reduction techniques utilized in unsupervised learning algorithms help analyze vast datasets and discover new drug-target interactions. Advanced abilities for analyzing molecular structures, virtual screening, and designing new drugs are provided by deep learning models like convolutional neural networks and recurrent neural networks. Multiple case studies demonstrate how ML algorithms can significantly impact drug discovery. Collaboration among academia, industry, and research institutions has resulted in the creation of new ML-based methods for drug development, identifying targets, and categorizing patients. Nevertheless, there are challenges accompanying the widespread use of ML in drug discovery. In healthcare, it is crucial to address ethical considerations, regulatory hurdles, and data privacy concerns to ensure the responsible and ethical use of ML algorithms. The potential for transforming drug discovery and therapeutic development is immense with the incorporation of machine learning algorithms. Through utilizing data-driven methods, researchers can speed up the discovery of new potential drugs, enhance the effectiveness of treatments, and ultimately enhance the results for patients. Ongoing innovation, teamwork, and cross-disciplinary studies are crucial to fully leverage the potential of ML in revolutionizing drug discovery and precision medicine.

Intelligent Analysis System for Teaching and Learning Cognitive Engagement Based on Computer Vision in an Immersive Virtual Reality Environment

The 20th National Congress of the Communist Party of China and the 14th Five Year Plan for Education Informatization focus on digital technology and intelligent learning and implement innovation-driven education environment reform. An immersive virtual reality (IVR) environment has both immersive and interactive characteristics, which are an important way of virtual learning and are also one of the important ways in which to promote the development of smart education. Based on the above background, this article proposes an intelligent analysis system for Teaching and Learning Cognitive engagement in an IVR environment based on computer vision. By automatically analyzing the cognitive investment of students in the IVR environment, it is possible to better understand their learning status, provide personalized guidance to improve learning quality, and thereby promote the development of smart education. This system uses Vue (developed by Evan You, located in Wuxi, China) and ECharts (Developed by Baidu, located in Beijing, China) for visual display, and the algorithm uses the Pytorch framework (Developed by Facebook, located in Silicon Valley, CA, USA), YOLOv5 (Developed by Ultralytics, located in Washington, DC, USA), and the CRNN model (Convolutional Recurrent Neural Network) to monitor and analyze the visual attention and behavioral actions of students. Through this system, a more accurate analysis of learners’ cognitive states and personalized teaching support can be provided for the education field, providing certain technical support for the development of smart education.

Simplified neural architecture for efficient human motion prediction in human-robot interaction

Human motion prediction is essential for safe and effective human-robot interaction, but modeling the intricate spatio-temporal dynamics inherent in human movement remains challenging. While recent methods have advanced motion prediction accuracy, they rely on complex neural architectures such as Graph Convolutional Networks and Recurrent Neural Networks, demanding extensive hyperparameter tuning. To overcome this limitation, we propose a streamlined multi-stage layer incremental perceptron (MSLP) architecture that achieves competitive results with far fewer parameters, improving efficiency. The MSLP eschews the complexity of prevalent networks and instead takes a stepped refinement approach to predict intricate motions using a lightweight model. This simplified yet effective design enables nuanced learning of spatio-temporal relationships without exhaustive tuning. Specifically, the MSLP incorporates two key components: a multi-channel feature extraction and enhancement block (MFE-block) and a temporal feature extraction module (TFE-block). The MFE-block strengthens the representation of each action node by integrating multi-dimensional action features. The TFE-block then captures the contextual relationships between actions over time. Together, the MFE-block and TFE-block allow the MSLP to model the complex spatial and temporal dynamics of human movement using a streamlined architecture and minimal parameter tuning. When evaluated on established datasets including Human3.6 M, CMU, 3DPW, and AMASS, the proposed MSLP method achieves improved accuracy gains of 16.7%-67.0% over existing state-of-the-art techniques. Additionally, the MSLP significantly reduces the number of parameters by 35.7%-99.5% compared to prior architectures. We find that the proposed MSLP significantly improves both long-term prediction and generalization capabilities of the model.

Novel GCN Model Using Dense Connection and Attention Mechanism for Text Classification

Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) based text classification algorithms currently in use can successfully extract local textual features but disregard global data. Due to its ability to understand complex text structures and maintain global information, Graph Neural Network (GNN) has demonstrated considerable promise in text classification. However, most of the GNN text classification models in use presently are typically shallow, unable to capture long-distance node information and reflect the various scale features of the text (such as words, phrases, etc.). All of which will negatively impact the performance of the final classification. A novel Graph Convolutional Neural Network (GCN) with dense connections and an attention mechanism for text classification is proposed to address these constraints. By increasing the depth of GCN, the densely connected graph convolutional network (DC-GCN) gathers information about distant nodes. The DC-GCN multiplexes the small-scale features of shallow layers and produces different scale features through dense connections. To combine features and determine their relative importance, an attention mechanism is finally added. Experiment results on four benchmark datasets demonstrate that our model’s classification accuracy greatly outpaces that of the conventional deep learning text classification model. Our model performs exceptionally well when compared to other text categorization GCN algorithms.

ECARRNet: An Efficient LSTM-Based Ensembled Deep Neural Network Architecture for Railway Fault Detection

Accidents due to defective railway lines and derailments are common disasters that are observed frequently in Southeast Asian countries. It is imperative to run proper diagnosis over the detection of such faults to prevent such accidents. However, manual detection of such faults periodically can be both time-consuming and costly. In this paper, we have proposed a Deep Learning (DL)-based algorithm for automatic fault detection in railway tracks, which we termed an Ensembled Convolutional Autoencoder ResNet-based Recurrent Neural Network (ECARRNet). We compared its output with existing DL techniques in the form of several pre-trained DL models to investigate railway tracks and determine whether they are defective or not while considering commonly prevalent faults such as—defects in rails and fasteners. Moreover, we manually collected the images from different railway tracks situated in Bangladesh and made our dataset. After comparing our proposed model with the existing models, we found that our proposed architecture has produced the highest accuracy among all the previously existing state-of-the-art (SOTA) architecture, with an accuracy of 93.28% on the full dataset. Additionally, we split our dataset into two parts having two different types of faults, which are fasteners and rails. We ran the models on those two separate datasets, obtaining accuracies of 98.59% and 92.06% on rail and fastener, respectively. Model explainability techniques like Grad-CAM and LIME were used to validate the result of the models, where our proposed model ECARRNet was seen to correctly classify and detect the regions of faulty railways effectively compared to the previously existing transfer learning models.

Discharge Capacity Estimation for Li-Ion Batteries: A Comparative Study

Li-ion batteries are integral to various applications, ranging from electric vehicles to mobile devices, because of their high energy density and user friendliness. The assessment of the Li-ion state of heath stands as a crucial research domain, aiming to innovate safer and more effective battery management systems that can predict and promptly report any operational discrepancies. To achieve this, an array of machine learning (ML) and artificial intelligence (AI) methodologies have been employed to analyze data from Li-ion batteries, facilitating the estimation of critical parameters like state of charge (SoC) and state of health (SoH). The continuous enhancement of ML and AI algorithm efficiency remains a pivotal focus of scholarly inquiry. Our study distinguishes itself by separately evaluating traditional machine learning frameworks and advanced deep learning paradigms to determine their respective efficacy in predictive modeling. We dissected the performances of an assortment of models, spanning from conventional ML techniques to sophisticated, hybrid deep learning constructs. Our investigation provides a granular analysis of each model’s utility, promoting an informed and strategic integration of ML and AI in Li-ion battery state of health prognostics. Specifically, a utilization of machine learning algorithms such as Random Forests (RFs) and eXtreme Gradient Boosting (XGBoost), alongside regression models like Elastic Net and foundational neural network approaches including Multilayer Perceptron (MLP) were studied. Furthermore, our research investigated the enhancement of time series analysis using intricate models like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) and their outcomes with those of hybrid models, including a RNN-long short-term memory (LSTM), CNN-LSTM, CNN-Gated Recurrent Unit (GRU) and RNN-GRU. Comparative evaluations reveal that the RNN-LSTM configuration achieved a Mean Squared Error (MSE) of 0.043, R-Squared of 0.758, Root Mean Square Error (RMSE) of 0.208, and Mean Absolute Error (MAE) of 0.124, whereas the CNN-LSTM framework reported an MSE of 0.039, R-Squared of 0.782, RMSE of 0.197, and MAE of 0.122, underscoring the potential of deep learning-based hybrid models in advancing the accuracy of battery state of health assessments.

Real-time Hazard Detection in Autonomous Vehicles: Deep Learning Approaches for Enhancing Road Safety

This examination explores ongoing risk location in independent vehicles through the use of profound learning philosophies, expecting to upgrade street security. Utilizing Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), the review centers around distinguishing and grouping dangers like people on foot, vehicles, obstructions, and street abnormalities in assorted driving situations. By examining information from locally available sensors including cameras, LiDAR, and radar, the profound learning models learn perplexing examples and portrayals, empowering them to settle on informed choices in powerful conditions. The trial results exhibit the viability of the proposed approaches, with CNN-based and RNN-based models accomplishing high exactness, accuracy, review, and F1-score upsides of 0.95, 0.93, 0.96, and 0.94 individually. These outcomes outperform those of conventional AI calculations and pattern techniques, displaying the predominance of profound learning in danger identification undertakings. Also, examinations with related work highlight the headways accomplished, featuring the capability of profoundly figuring out how to upgrade the well-being abilities of independent vehicles. In general, this examination adds to the continuous endeavors in creating solid and effective danger recognition frameworks, making ready for more secure and more dependable independent driving innovation.

Regular paper Comparative Analysis of Deep Learning Models for Sentiment Analysis on IMDB Reviews

Within the domain of natural language processing, sentiment analysis assumes a fundamental position, facilitating the comprehension of societal perspectives and opinions, thereby playing a pivotal role in understanding public sentiment. In this study, an examination and comparison of deep learning architectures was conducted on IMDB movie reviews. We evaluated the performance of Basic Recurrent Neural Networks, Long Short-Term Memory (LSTM), Gated Recurrent Neural Unit (GRU), Bidirectional LSTM, Bidirectional GRU and 1D Convolutional Neural Networks (Conv1D) based on their training, validation, and testing accuracies. Our results indicate that while LSTM achieved the highest accuracy of 99.91% on the training data, GRU demonstrated superior performance (88.28%) on the validation dataset. Interestingly, Bidirectional GRU emerged as the top-performing model (87.54%) on the testing data, showcasing its robustness in generalizing to unseen instances. These findings highlight the importance of evaluating model performance across multiple datasets to assess their real-world effectiveness. Furthermore, our comparative analysis provides valuable understanding of the advantages and limitations of each model, offering practical guidance for selecting the optimal framework for sentiment analysis endeavors. Overall, this research contributes to the progress of such methodologies and deep learning approaches in natural language processing.

Review on Human Pose Estimation using AI Fitness Tracker

Human pose estimation, a fundamental computer vision task, has witnessed significant advancements with the advent of deep learning techniques. This paper provides an overview of recent developments in human pose estimation, focusing on the application of convolutional neural networks (CNNs) and recurrent neural networks (RNNs). We explore the distinctions between 2D and 3D pose estimation, highlighting the challenges and solutions for each. The paper discusses the various techniques for single-person and multi-person pose estimation, as well as the trade-offs between part-based and holistic approaches. Additionally, we delve into the real-time and offline aspects of pose estimation and the significance of temporal analysis in videos. Lastly, we touch on the translation of 2D pose information into 3D space. This review underscores the practical implications of human pose estimation in diverse fields such as sports analysis, healthcare, surveillance, and entertainment. The dynamic nature of this field, fueled by ongoing research and technological advancements, promises to unlock new possibilities for human-computer interaction, augmented reality, and beyond. This abstract provides an overview of the paper's focus on deep learning in the context of human pose estimation and highlights the key aspects of the field. You can further tailor it to your specific paper or presentation needs. Keywords: Human pose estimation, camera, Artificial intelligence, Machine learning

Tractography with T1-weighted MRI and associated anatomical constraints on clinical quality diffusion MRI.

Diffusion MRI (dMRI) streamline tractography, the gold-standard for in vivo estimation of white matter (WM) pathways in the brain, has long been considered as a product of WM microstructure. However, recent advances in tractography demonstrated that convolutional recurrent neural networks (CoRNN) trained with a teacher-student framework have the ability to learn to propagate streamlines directly from T1 and anatomical context. Training for this network has previously relied on high resolution dMRI. In this paper, we generalize the training mechanism to traditional clinical resolution data, which allows generalizability across sensitive and susceptible study populations. We train CoRNN on a small subset of the Baltimore Longitudinal Study of Aging (BLSA), which better resembles clinical scans. We define a metric, termed the epsilon ball seeding method, to compare T1 tractography and traditional diffusion tractography at the streamline level. We show that under this metric T1 tractography generated by CoRNN reproduces diffusion tractography with approximately three millimeters of error.

Convolution neural network hyperparameter optimization using modified particle swarm optimization

Based on the literature review, a convolutional neural network (CNN) is one of the deep learning techniques most often used for classification problems, especially image classification. Various approaches have been proposed to improve accuracy performance. In CNN architecture, parameter determination is very influential on accuracy performance. Particle swarm optimization (PSO) is a type of metaheuristic algorithm widely used for hyperparameter optimization. PSO convergence is faster than genetic algorithm (GA) and attracts many researchers for further studies such as genetic algorithms and ant colony. In PSO, determining the value of the weight parameter is very influential on accuracy. Therefore, this paper proposes CNN hyperparameter optimization using modified PSO with linearly decreasing randomized weight. The experiments use the modified National Institute of Standards and Technology (MNIST) dataset. The accuracy of the proposed method is superior, and the execution time is slower to random search. In epoch 1, epoch 3, and epoch 5, the proposed method is superior to baseline CNN, linearly decreasing weight PSO (LDWPSO), and RL-based optimization algorithm (ROA). Meanwhile, the accuracy performance of the proposed method is superior to previous studies, namely LeNet-1, LeNet-2, LeNet-3, PCANet-2, RANDNet-2, CAE1, CAE-2, and bee colony. Otherwise, lost to PSO-CNN, distributed PSO (DPSO), recurrent CNN, and CNN-PSO. However, the four methods have a complex architecture and wasteful execution time.

A new surrogate method for the neutron kinetics calculation of nuclear reactor core transients

Reactor core transient calculation is very important for the reactor safety analysis, in which the kernel is neutron kinetics calculation by simulating the variation of neutron density or thermal power over time. Compared with the point kinetics method, the time-space neutron kinetics calculation can provide accurate variation of neutron density in both space and time domain. But it consumes a lot of resources. It is necessary to develop a surrogate model that can quickly obtain the temporal and spatial variation information of neutron density or power with acceptable calculation accuracy. This paper uses the time-varying characteristics of power to construct a time function, parameterizes the time-varying characteristics which contains the information about the spatial change of power. Thereby, the amount of targets to predict in the space domain is compressed. A surrogate method using the machine learning is proposed in this paper. In the construction of a neural network, the input is processed by a convolutional layer, followed by a fully connected layer or a deconvolution layer. For the problem of time sequence disturbance, a structure combining convolutional neural network and recurrent neural network is used. It is verified in the tests of a series of 1D, 2D and 3D reactor models. The predicted values obtained using the constructed neural network models in these tests are in good agreement with the reference values, showing the powerful potential of the surrogate models.

Combined convolution recurrent neural network for the classification of dysarthria speech

Dysarthria is a neuromotor articulation condition that affects a person and weakens their tongue and lip muscles, and it additionally affects their capability to talk. Diffusion of factors, such as numbness, terrible coordination, and susceptible speech-generating muscle groups, can contribute to the condition. Cerebral palsy, Parkinson’s disorder, stroke, or some other kind of traumatic brain harm might also lead to dysarthria. People with dysarthria are not able to talk on a consistent basis because their speech is unclear and their phonemes are spoken irregularly because of trouble transferring the tongue, lips, and jaw as easily as in everyday speech. Dysarthric speech is stated to be 15 times slower than an ordinary speech.

Hand Gesture Controller

Abstract: The rapid evolution of human-computer interaction has spurred significant progress in gesture recognition technologies, placing a specific emphasis on diverse applications. This paper highlights key advancements in machine learning algorithms tailored for gesture recognition, including deep learning approaches that have notably improved the accuracy and robustness of hand tracking systems. Furthermore, the integration of hand gesture control into wearable devices and its implications for everyday technology usage are thoroughly examined. This paper relies on the formidable capabilities of Deep Learning, specifically Convolutional Neural Networks and Recurrent Neural Networks, to decipher and translate hand gestures into actionable directives. The implementation of the Hand Gesture Controller necessitates the integration of a camera or sensor module capable of capturing intricate hand movements. Real-time image processing and feature extraction are essential components, facilitating the provision of input data to the Deep Learning model. As technology progresses, this interface emerges as a versatile tool capable of enhancing productivity and inclusivity across various domains. The paper concludes with a discussion on future directions in hand gesture controller development, exploring anticipated technological advancements, novel use cases, and the potential for increased accessibility. In summary, the "Hand Gesture Controller using Deep Learning" project signifies a substantive stride forward in human-computer interaction, introducing an innovative interface that promises a future where devices seamlessly respond to innate gestures, thereby rendering technology more accessible and user-focused.

Efficient feature extraction and hybrid deep learning for early identification of uterine fibroids in ultrasound images

AbstractNon‐cancerous growths called uterine fibroids develop in the uterus. They can vary in size, location, and number, and can produce symptoms including excessive menstrual flow, pelvic discomfort, and reproductive problems. Early detection of uterine fibroids is important because it allows for timely intervention and appropriate management strategies. Extracting meaningful features from ultrasound (US) images requires robust and effective techniques. However, different feature extraction methods may yield varying results, and the choice of technique can influence the accuracy of fibroid detection. This paper presents an efficient approach for early detection of uterine fibroids in US images. Our proposed technique combines efficient feature extraction methods and a hybrid deep learning approach. Firstly, we employ the well‐known canny edge detection algorithm to accurately identify the edges of the fibroid region in the US images. This step helps in segmenting the target edge portion for further analysis. Additionally, we introduce an improved bird swarm optimization (IBSO) algorithm to extract a comprehensive set of features, utilizing both known features and newly obtained features. This approach enhances the accuracy of fibroid detection in uterine images. The proposed method uses a convolutional recurrent neural network (CRNN) to accurately detect and treat uterine fibroids, ensuring timely diagnosis and treatment. Our proposed IBSO‐CRNN model produces accuracy rates of 99.897% and 97.568% on the augmented and original datasets, respectively.

Information Extraction from Product Labels: A Machine Vision Approach

This research tackles the challenge of manual data extraction from product labels by employing a blend of computer vision and Natural Language Processing (NLP). We introduce an enhanced model that combines Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) in a Convolutional Recurrent Neural Network (CRNN) for reliable text recognition. Our model is further refined by incorporating the Tesseract OCR engine, enhancing its applicability in Optical Character Recognition (OCR) tasks. The methodology is augmented by NLP techniques and extended through the Open Food Facts API (Application Programming Interface) for database population and text-only label prediction. The CRNN model is trained on encoded labels and evaluated for accuracy on a dedicated test set. Importantly, our approach enables visually impaired individuals to access essential information on product labels, such as directions and ingredients. Overall, the study highlights the efficacy of deep learning and OCR in automating label extraction and recognition.

Research on the Vision-Based Dairy Cow Ear Tag Recognition Method.

With the increase in the scale of breeding at modern pastures, the management of dairy cows has become much more challenging, and individual recognition is the key to the implementation of precision farming. Based on the need for low-cost and accurate herd management and for non-stressful and non-invasive individual recognition, we propose a vision-based automatic recognition method for dairy cow ear tags. Firstly, for the detection of cow ear tags, the lightweight Small-YOLOV5s is proposed, and then a differentiable binarization network (DBNet) combined with a convolutional recurrent neural network (CRNN) is used to achieve the recognition of the numbers on ear tags. The experimental results demonstrated notable improvements: Compared to those of YOLOV5s, Small-YOLOV5s enhanced recall by 1.5%, increased the mean average precision by 0.9%, reduced the number of model parameters by 5,447,802, and enhanced the average prediction speed for a single image by 0.5 ms. The final accuracy of the ear tag number recognition was an impressive 92.1%. Moreover, this study introduces two standardized experimental datasets specifically designed for the ear tag detection and recognition of dairy cows. These datasets will be made freely available to researchers in the global dairy cattle community with the intention of fostering intelligent advancements in the breeding industry.

Unlocking the potential: CRNN-driven flexible mechanical sensors for intelligent sensing and beyond

In our rapidly evolving society, intelligent technology has become a driving force across various sectors, leading to transformative progress. This paper explores the integration of Convolutional Recurrent Neural Network (CRNN) algorithms with flexible sensors, showcasing their remarkable potential in enhancing data processing and interpretation. The synergy between CRNN and flexible sensors holds great promise in diverse domains, including health monitoring and industrial automation. Our comprehensive evaluation of the CRNN model reveals exceptional performance in classification and regression tasks, highlighting its adaptability to complex and varied sensor data. Additionally, confusion matrix analysis provides insights into multi-class classification scenarios, reinforcing the model's reliability. A comparative analysis against traditional machine learning techniques demonstrates the superiority of CRNN in handling time-series data. In conclusion, the integration of CRNN with flexible sensors is set to revolutionize intelligent sensing technology, opening new avenues for innovation and problem-solving in various industries. This collaborative approach not only enhances data accuracy and reliability but also paves the way for groundbreaking technologies and applications yet to be imagined. The future of intelligent sensing is here, and it is both exciting and promising, with CRNN-driven flexible sensors leading the way towards a more intelligent and connected world.

Recognition of Converter Steelmaking State Based on Convolutional Recurrent Neural Networks

Recognition of Converter Steelmaking State Based on Convolutional Recurrent Neural Networks

DEW: A wavelet approach of rare sound event detection.

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.