Santos Kumar Das

Bio: Santos Kumar Das is an academic researcher from National Institute of Technology, Rourkela. The author has contributed to research in topics: Wireless sensor network & Physical layer. The author has an hindex of 7, co-authored 66 publications receiving 192 citations. Previous affiliations of Santos Kumar Das include Indian Institute of Science.

Multi-directional temporal convolutional artificial neural network for PM2.5 forecasting with missing values: A deep learning approach

Abstract: Data imputation and forecasting are the major research areas in environmental data engineering. Solving those critical issues has an immense impact on air pollution management, consequently improving social, economic growth, and public health. Missing data is a common issue for all the domains, especially for environmental data analysis. Most of the research study tries to solve all these problems of time series data using different models. This research study presents a novel deep learning-based hybrid model architecture to solve these issues in a single training process. We come up with Multi-directional Temporal Convolutional Artificial Neural Network (MTCAN) model to impute and forecast PM2.5 pollutant concentration in a single training process. The main idea of the multi-directional properties of MTCAN is to interpolate the PM2.5 pollutant feature matrix to impute its value. Ultimately, it maintains the temporal correlation within the features' measurement and meteorological and pollutant variables to impute PM2.5 missing values. The MTCAN model performs feature learning and sequential modeling simultaneously with a wide range of past observations for long-term forecasting, minimizing memory size requirement and training cost. Experimental results indicate that the proposed model is superior to baseline pollution forecasting models, which prove its effectiveness in air quality modeling.

Temporal convolutional denoising autoencoder network for air pollution prediction with missing values

Abstract: In recent years, people are paying more attention to improve air quality levels to mitigate its negative impact on human health. So, effective air pollution control has become one of the hottest environmental issues. Accurate pollution prediction plays a vital role in air pollution control. However, air quality modeling faces challenges like long-term pollutant variations due to meteorological variables impact and missing values due to natural disaster or sensor shutdown. These issues make air quality models more complex and challenging to introspect. So, we developed Temporal Convolutional Denoising Autoencoder (TCDA) network, a hybrid PM2.5 prediction framework that can perform rapid extraction of complex dataset's features, handle missing values and improve PM2.5 prediction results. This research paper includes Temporal Convolutional Network (TCN) and Denoising Autoencoder (DAE) network to handle nonlinear multivariate massive datasets. The former utilizes parallel feature processing of Convolutional Neural Network (CNN) and temporal component modeling ability of Recurrent Neural Network (RNN), which helps for features extraction from complex dataset. The latter is to reconstruct the error to fine-tune the prediction results and handle missing values. The proposed model's prediction capability is evaluated by comparing its performance with other baseline models, which shows its performance superiority over other models.

A Vehicle Detection Technique Using Binary Images for Heterogeneous and Lane-Less Traffic

Abstract: Nowadays, providing a low-cost traffic management system in developing countries or in heterogeneous and lane-less traffic conditions is highly essential. It can help to manage traffic congestion, save fuel, save travel time, and enhance user safety. By keeping these as an objective, this article presents a vehicle detection method in heterogeneous and lane-less traffic by extracting a binary image from a discrete sensor array. The binary image is formed with a logic 1 or 0, which are recorded based on the occupancy status of the vehicles in an observed zone. The proposed method is demonstrated with virtual loops in video and with an array of micro-LiDARs. The width and length of the vehicle are obtained from the binary image , which is extracted from virtual loops in a video recording and classified the vehicles. Similarly, the width and height information is obtained using an array of micro-LiDARs and classified the vehicles. The proposed method can easily be implemented with minimal storage, minimum cost, less bandwidth, and less computation complexity than the conventional methods, such as image processing or video processing-based vehicle classification. The proposed classification methods are mathematically derived, implemented, and measured performance over real traffic scenarios. It can be adopted automatically to high or light traffic scenarios by adjusting the distance between observation zones. The detection accuracy of 98% is observed while extracting data from video and 91.3% while using micro-LiDARs. The proposed works are compared with existing techniques.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

Nonlinear Fractional Programming

Abstract: In this chapter we deal with the following nonlinear fractional programming problem: $$P:\mathop{{\max }}\limits_{{x \in s}} q(x) = (f(x) + \alpha )/((x) + \beta )$$ where f, g: R n → R, α, β ∈ R, S ⊆ R n . To simplify things, and without restricting the generality of the problem, it is usually assumed that, g(x) + β + 0 for all x ∈ S,S is non-empty and that the objective function has a finite optimal value.

Abnormal Event Detection in Videos using Spatiotemporal Autoencoder

Abstract: We present an efficient method for detecting anomalies in videos. Recent applications of convolutional neural networks have shown promises of convolutional layers for object detection and recognition, especially in images. However, convolutional neural networks are supervised and require labels as learning signals. We propose a spatiotemporal architecture for anomaly detection in videos including crowded scenes. Our architecture includes two main components, one for spatial feature representation, and one for learning the temporal evolution of the spatial features. Experimental results on Avenue, Subway and UCSD benchmarks confirm that the detection accuracy of our method is comparable to state-of-the-art methods at a considerable speed of up to 140 fps.

Optical Networks A Practical Perspective

Abstract: Thank you for downloading optical networks a practical perspective. Maybe you have knowledge that, people have look hundreds times for their favorite books like this optical networks a practical perspective, but end up in infectious downloads. Rather than reading a good book with a cup of coffee in the afternoon, instead they cope with some infectious bugs inside their laptop. optical networks a practical perspective is available in our digital library an online access to it is set as public so you can get it instantly. Our book servers saves in multiple countries, allowing you to get the most less latency time to download any of our books like this one. Kindly say, the optical networks a practical perspective is universally compatible with any devices to read.