Aravind Kumar Madam
Research Subjects
Aravind Kumar Madam has a total of 85 co-authors. Here are the top co-authors by number of shared publications:
Srinivas Bachu
Marri Laxman Reddy Institute of Technology and Management, Dundigal,Dept. of ECE,Hyderabad,Telangana,India
4 shared publicationsBala Sindhuri Kandula
3 shared publicationsNaluguru Udaya Kumar
Marri Laxman Reddy Institute of Technology and Management, Dundigal,Dept. of ECE,Hyderabad,Telangana,India
3 shared publicationsSangeeta Singh
3 shared publicationsShaik Masthan Basha
Vignan's Institute of Management & Technology for Women
3 shared publicationsA M S V Sushma
2 shared publications
Latest Publications
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Smart Control of Traffic Light Using Deep Learning
Traffic congestion is becoming one of the critical issues with increasing population and automobiles in cities. Traffic jams not only cause extra delay and stress for the drivers, but also increase fuel consumption and air pollution. Although it seems to pervade everywhere, megacities are the ones most affected by it. And its ever-increasing nature makes it necessary to calculate the road traffic density in real-time for better signal control and effective traffic management. The traffic controller is one of the critical factors affecting traffic flow. Therefore, the need for optimizing traffic control to better accommodate this increasing demand arises. This paper is utilizing traffic cameras and YOLO object detection algorithms to estimate traffic density at all lanes and then adjust red and green signal time. Cameras will take snapshot of all lanes every five seconds and then estimate traffic at lanes and based on density green and red signal time will be adjusted.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSmart Control of Traffic Light Using Deep Learning
Traffic congestion is becoming one of the critical issues with increasing population and automobiles in cities. Traffic jams not only cause extra delay and stress for the drivers, but also increase fuel consumption and air pollution. Although it seems to pervade everywhere, megacities are the ones most affected by it. And its ever-increasing nature makes it necessary to calculate the road traffic density in real-time for better signal control and effective traffic management. The traffic controller is one of the critical factors affecting traffic flow. Therefore, the need for optimizing traffic control to better accommodate this increasing demand arises. This paper is utilizing traffic cameras and YOLO object detection algorithms to estimate traffic density at all lanes and then adjust red and green signal time. Cameras will take snapshot of all lanes every five seconds and then estimate traffic at lanes and based on density green and red signal time will be adjusted.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Radix 2/24 and 2/25 Split Radix Fast Fourier Transform Designs for Reduced Multipliers with Twiddle Factor Approximation
This work proposes a novel method for designing split-radix Fast Fourier Transform architecture. The new Radix-2/24 and Radix-2/25 data flow algorithms that are proposed in this paper have effective twiddle factor multiplier reduction. FFT with the radix of split initially modified so that all the twiddle multipliers are placed at two stages and the less important multiplier of multiplication with w81 replaced by two-point butterfly followed by shift register. This technique significantly reduces the twiddle factor of w81 multiplication, which in turn lowers the overall multipliers for higher order FFT. Three real multipliers are used to produce complex multiplication, and five real additions are used to further reduce multipliers. Comparing the proposed data flow designs to other recent existing ones will result in lower overall multipliers. The proposed designs use less power than other recent existing designs.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRadix 2/24 and 2/25 Split Radix Fast Fourier Transform Designs for Reduced Multipliers with Twiddle Factor Approximation
This work proposes a novel method for designing split-radix Fast Fourier Transform architecture. The new Radix-2/24 and Radix-2/25 data flow algorithms that are proposed in this paper have effective twiddle factor multiplier reduction. FFT with the radix of split initially modified so that all the twiddle multipliers are placed at two stages and the less important multiplier of multiplication with w81 replaced by two-point butterfly followed by shift register. This technique significantly reduces the twiddle factor of w81 multiplication, which in turn lowers the overall multipliers for higher order FFT. Three real multipliers are used to produce complex multiplication, and five real additions are used to further reduce multipliers. Comparing the proposed data flow designs to other recent existing ones will result in lower overall multipliers. The proposed designs use less power than other recent existing designs.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Radix 2/24 and 2/25 Split Radix Fast Fourier Transform Designs for Reduced Multipliers with Twiddle Factor Approximation
This work proposes a novel method for designing split-radix Fast Fourier Transform architecture. The new Radix-2/24 and Radix-2/25 data flow algorithms that are proposed in this paper have effective twiddle factor multiplier reduction. FFT with the radix of split initially modified so that all the twiddle multipliers are placed at two stages and the less important multiplier of multiplication with w81 replaced by two-point butterfly followed by shift register. This technique significantly reduces the twiddle factor of w81 multiplication, which in turn lowers the overall multipliers for higher order FFT. Three real multipliers are used to produce complex multiplication, and five real additions are used to further reduce multipliers. Comparing the proposed data flow designs to other recent existing ones will result in lower overall multipliers. The proposed designs use less power than other recent existing designs.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRadix 2/24 and 2/25 Split Radix Fast Fourier Transform Designs for Reduced Multipliers with Twiddle Factor Approximation
This work proposes a novel method for designing split-radix Fast Fourier Transform architecture. The new Radix-2/24 and Radix-2/25 data flow algorithms that are proposed in this paper have effective twiddle factor multiplier reduction. FFT with the radix of split initially modified so that all the twiddle multipliers are placed at two stages and the less important multiplier of multiplication with w81 replaced by two-point butterfly followed by shift register. This technique significantly reduces the twiddle factor of w81 multiplication, which in turn lowers the overall multipliers for higher order FFT. Three real multipliers are used to produce complex multiplication, and five real additions are used to further reduce multipliers. Comparing the proposed data flow designs to other recent existing ones will result in lower overall multipliers. The proposed designs use less power than other recent existing designs.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Smart and Sustainable Irrigation Integrated with Threat Deterrence
Countries worldwide are catching up with the trend to better agricultural activities through modern meansbased techniques. The first one to be done is to improve the irrigation system, which is essential for water use and can significantly help sustainable development goals. On the other hand, crop protection is also necessary for the increasing growth of the agriculture industry. In this light, this article aims to create an open-source microcontroller system that automates watering and preserves crops using intelligent methods. Using real-time data from soil moisture sensors, the system initiates irrigation cycles only when necessary, optimizing water usage, particularly in areas with limited water supplies. In addition, laser sensors will detect animal infiltration in crop fields. Signs provided to the user via a GSM module indicate whether the motor should be turned on or off if animals are observed or rain is forecasted. In addition, an electric fence will be built to administer a slight jolt to any animals who touch it to prevent animal encroachment. In addition, ultrasonic sensors are used to detect birds and safeguard crops from harm. This comprehensive approach tries to increase crop productivity while conserving.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSmart and Sustainable Irrigation Integrated with Threat Deterrence
Countries worldwide are catching up with the trend to better agricultural activities through modern meansbased techniques. The first one to be done is to improve the irrigation system, which is essential for water use and can significantly help sustainable development goals. On the other hand, crop protection is also necessary for the increasing growth of the agriculture industry. In this light, this article aims to create an open-source microcontroller system that automates watering and preserves crops using intelligent methods. Using real-time data from soil moisture sensors, the system initiates irrigation cycles only when necessary, optimizing water usage, particularly in areas with limited water supplies. In addition, laser sensors will detect animal infiltration in crop fields. Signs provided to the user via a GSM module indicate whether the motor should be turned on or off if animals are observed or rain is forecasted. In addition, an electric fence will be built to administer a slight jolt to any animals who touch it to prevent animal encroachment. In addition, ultrasonic sensors are used to detect birds and safeguard crops from harm. This comprehensive approach tries to increase crop productivity while conserving.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Fast Image Encryption Based on Random Image Key
Internet plays an important role in circulating a huge amount of multimedia. An example of this multimedia is the image. To send an image over the network secretly, the sender tries to find encryption algorithm to hide image information. This paper aims at designing an efficient encryption algorithm for color image using random image key generated with minimum time execution for encryption and decryption operations. XOR operation is used here to make more diffusion of the encrypted image to maintain a higher level of security upon transference than it is with the original image.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFast Image Encryption Based on Random Image Key
Internet plays an important role in circulating a huge amount of multimedia. An example of this multimedia is the image. To send an image over the network secretly, the sender tries to find encryption algorithm to hide image information. This paper aims at designing an efficient encryption algorithm for color image using random image key generated with minimum time execution for encryption and decryption operations. XOR operation is used here to make more diffusion of the encrypted image to maintain a higher level of security upon transference than it is with the original image.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Design and Simulation of Core Image Processing Techniques using MATLAB and Verilog
Image processing enhances visual information for effective analysis in domains such as medical imaging, satellite observation, and digital media. This work presents the fundamental pre-processing operations such as Posterize, Red Channel Extraction, Red Tint, and Warm Red Tint-on test images using a MATLAB-Verilog co-design approach.. MATLAB is used for file conversion while Verilog models the algorithms for functional verification. Simulation results confirm the correctness of the operations and highlight the framework's potential as a scalable foundation for real-time image enhancement applications.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDesign and Simulation of Core Image Processing Techniques using MATLAB and Verilog
Image processing enhances visual information for effective analysis in domains such as medical imaging, satellite observation, and digital media. This work presents the fundamental pre-processing operations such as Posterize, Red Channel Extraction, Red Tint, and Warm Red Tint-on test images using a MATLAB-Verilog co-design approach.. MATLAB is used for file conversion while Verilog models the algorithms for functional verification. Simulation results confirm the correctness of the operations and highlight the framework's potential as a scalable foundation for real-time image enhancement applications.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Facial Emotions Recognition Using CNN
Nowadays, deep learning techniques know a big success in various fieldsincluding computervision. Indeed, a convolutional neural networks (CNN) model can be trained to analyze imagesand identify face emotion. In this paper, we create a system that recognizes students' emotionsfrom their faces. Our system consists of three phases: face detection using Haar Cascades, normalization and emotion recognition using CNN on FER 2013 database with seven type of expressions. Obtained results show that face emotion recognition is feasible consequently,itcanhelptomodify theirpresentation accordingtotheemotions.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFacial Emotions Recognition Using CNN
Nowadays, deep learning techniques know a big success in various fieldsincluding computervision. Indeed, a convolutional neural networks (CNN) model can be trained to analyze imagesand identify face emotion. In this paper, we create a system that recognizes students' emotionsfrom their faces. Our system consists of three phases: face detection using Haar Cascades, normalization and emotion recognition using CNN on FER 2013 database with seven type of expressions. Obtained results show that face emotion recognition is feasible consequently,itcanhelptomodify theirpresentation accordingtotheemotions.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
A Novel Multi-wavelet Oriented Auto-encoder for Intrusion Detection in IoT System
IoT devices become more integrated into daily life, they are increasingly vulnerable to cyberattacks, compromising user confidentiality. Although existing intrusion detection techniques for IoT systems have been developed, they often fail to accurately classify attacks. This paper presents a novel approach for detecting intrusions in IoT devices by combining advanced feature extraction and deep learning techniques. The proposed method first pre-processes dataset images to enhance data quality by filtering out irrelevant information. A unique Aquila Optimized Convolutional Neural Network (AO-CNN) is then applied to extract optimal features. The proposed AO-CNN incorporates an optimization technique called Aquila Optimizer that fine-tunes the CNN's ability to extract more relevant and discriminative features from the IoT data. For attack detection, an innovative Attention-Based Multi-Wavelet-Oriented Autoencoder (AMV-AE) is designed for more precise attack classification. The Attention Mechanism is the model to focuses on the most relevant features, ensuring that the key patterns indicative of an attack are not lost during the detection process. Multi-Wavelet Transform enhances feature representation by capturing both time and frequency domain characteristics of the data, making it particularly effective in identifying subtle anomalies that may indicate an intrusion. The key novelty of this approach lies in the integration of AO-CNN for feature optimization and AMV-AE for superior detection accuracy. Evaluated on the NSL-KDD dataset, the model achieves a recall of 98.49% and an accuracy of 99.35% while demonstrating reduced inference time and memory usage, outperforming existing methods.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Novel Multi-wavelet Oriented Auto-encoder for Intrusion Detection in IoT System
IoT devices become more integrated into daily life, they are increasingly vulnerable to cyberattacks, compromising user confidentiality. Although existing intrusion detection techniques for IoT systems have been developed, they often fail to accurately classify attacks. This paper presents a novel approach for detecting intrusions in IoT devices by combining advanced feature extraction and deep learning techniques. The proposed method first pre-processes dataset images to enhance data quality by filtering out irrelevant information. A unique Aquila Optimized Convolutional Neural Network (AO-CNN) is then applied to extract optimal features. The proposed AO-CNN incorporates an optimization technique called Aquila Optimizer that fine-tunes the CNN's ability to extract more relevant and discriminative features from the IoT data. For attack detection, an innovative Attention-Based Multi-Wavelet-Oriented Autoencoder (AMV-AE) is designed for more precise attack classification. The Attention Mechanism is the model to focuses on the most relevant features, ensuring that the key patterns indicative of an attack are not lost during the detection process. Multi-Wavelet Transform enhances feature representation by capturing both time and frequency domain characteristics of the data, making it particularly effective in identifying subtle anomalies that may indicate an intrusion. The key novelty of this approach lies in the integration of AO-CNN for feature optimization and AMV-AE for superior detection accuracy. Evaluated on the NSL-KDD dataset, the model achieves a recall of 98.49% and an accuracy of 99.35% while demonstrating reduced inference time and memory usage, outperforming existing methods.
- Open Access
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Forecasting Energy Consumption Using Arima Models
The paper is aimed at contributing to the body of knowledge that exist in the area of energy forecasting by reviewing relevant empirical works on energy forecasting using ARIMA models. This paper is relevant in the face of frequent power outage and the dependence on external economies for energy supply. The study is based on secondary data obtained from electronic journals through archival studies. In all 10 articles were selected through purposive sampling method and were analysis using content analysis method. The results indicate that future energy consumption is expected to increase in economies in which these forecasts have been done. Hence, energy use must be efficient to avoid energy crisis in future. Future research should look at review of works on forecasting in a comparative manner comparing other models that have been used in forecasting energy demand. The paper is limited by the use of only secondary data.
- 31 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessForecasting Energy Consumption Using Arima Models
The paper is aimed at contributing to the body of knowledge that exist in the area of energy forecasting by reviewing relevant empirical works on energy forecasting using ARIMA models. This paper is relevant in the face of frequent power outage and the dependence on external economies for energy supply. The study is based on secondary data obtained from electronic journals through archival studies. In all 10 articles were selected through purposive sampling method and were analysis using content analysis method. The results indicate that future energy consumption is expected to increase in economies in which these forecasts have been done. Hence, energy use must be efficient to avoid energy crisis in future. Future research should look at review of works on forecasting in a comparative manner comparing other models that have been used in forecasting energy demand. The paper is limited by the use of only secondary data.