Papers by DR.PRAVIN R KSHIRSAGAR
Optical and quantum electronics, Jan 30, 2024
Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing c... more Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing capabilities, making them ideal for connecting multiple users to the Internet of Things (IoT) for real-time applications. However, these networks face limitations in delay and energy, impacting the efciency of routing protocols. For devices to operate efectively over extended periods, optimizing these protocols is crucial. Addressing this, our study introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con- sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the proposed WOD-MCC, energy efciency, scalability, and network connectivity are empha- sized. In terms of data delivery, energy conservation, and delay reduction, our fndings indicate that the WOD-MCC method outperforms existing protocols. Keywords IoT-enabled WSNs · Data transmission · Reinforcement learning · Whale optimization-driven multi-criterion correlation · Cluster-based routing strategies
Optical and quantum electronics, Jan 30, 2024
Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing c... more Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing capabilities, making them ideal for connecting multiple users to the Internet of Things (IoT) for real-time applications. However, these networks face limitations in delay and energy, impacting the efciency of routing protocols. For devices to operate efectively over extended periods, optimizing these protocols is crucial. Addressing this, our study introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con- sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the proposed WOD-MCC, energy efciency, scalability, and network connectivity are empha- sized. In terms of data delivery, energy conservation, and delay reduction, our fndings indicate that the WOD-MCC method outperforms existing protocols. Keywords IoT-enabled WSNs · Data transmission · Reinforcement learning · Whale optimization-driven multi-criterion correlation · Cluster-based routing strategies
Journal of Imaging Informatics in Medicine, 2024
The highly contagious malaria disease is spread by the female Anopheles mosquito. This disease re... more The highly contagious malaria disease is spread by the female Anopheles mosquito. This disease results in a patient's death or incapacity to move their muscles, if it is not appropriately identified in the early stages. A Rapid Diagnostic Test (RDT) is a frequently used approach to find malaria cells in red blood cells. However, it might not be able to identify infections with small amounts of samples. In the microscopic detection model, blood stains are placed under a microscope for diagnosing malaria. But accurate diagnosis is hard in this method, particularly in developing nations where the disease is most common. The microscopic detection processes are expensive and time-consuming due to the usage of microscopes. The quality of the blood smears and the availability of a qualified specialist, who is skilled in recognizing the disease, impact the accuracy of malaria detection results. The traditional deep learning-based malaria identification models need more processing power. Therefore, a deep learning-based adaptive method is designed to detect malaria cells through the medical image. Hence, the images are gathered from the standard sites and then fed to the segmentation process. Here, the abnormality segmentation is carried out with the help of a developed Trans-MobileUNet + + (T-MUnet + +) network. Trans-MobileUNet + + captures global context, so it is well-suited for segmentation tasks. The segmented image is applied to the adaptive detection phase where the Adaptive and Atrous Convolution-based Recurrent MobilenetV2 (AA-CRMV2) model is designed for the effective recognition of malaria cells. The efficiency of the designed approach is elevated by optimizing the parameters from the AA-CRMV2 network with the help of the Updated Random Parameter-based Fennec Fox Optimization (URP-FFO) algorithm. Several experimental analyses are evaluated in the implemented model over classical techniques to display their effectualness rate.
IEEE , 2024
The healthcare sector receives a considerable amount of unprocessed data from wearable and porta... more The healthcare sector receives a considerable amount of unprocessed data from wearable and portable devices. However, traditional cloud-based models used to handle this type of data can pose risks such as exposing sensitive patient data to a network environment and increasing latency due to data storage
and time consumption. In response to these issues, an alternative strategy named TinyML was put forth by the scientific community to foster safe and autonomous models capable of gathering and processing datawithout the need for network exposure. To address these concerns more effectively, we put forward a versatile TinyML model specifically tailored for health monitoring systems. This model uses enhanced NASNet-XGBoost-based transfer learning methodology to adapt to various types of diseases using appropriate
healthcare data. The process begins by pre-processing raw health signals collected from patients using a combination of a wavelet soft threshold method and empirical wavelet transform-spectrum adaptive segmentation (EWT-SAS). A Tyrannosaurus-based NASNet model is then used to extract meaningful
features from these pre-processed signals. Once the features have been extracted, they are entered into an XGBoost model which can accurately predict various types of diseases based on the given data. This
particular approach achieved an impressive 95.4% average accuracy, 93.6% positive predictive value, 94.7% hit rate, and 96.3% selectivity. When compared to traditional models, this TinyML model shows a significant improvement in performance metrics, demonstrating increased effectiveness and accuracy in predicting
various diseases.
Springer , 2024
Abstract
Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their... more Abstract
Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing capabilities, making them ideal for connecting multiple users to the Internet of Things (IoT) for real-time applications. However, these networks face limitations in delay and energy, impacting the efciency of routing protocols. For devices to operate efectively over extended periods, optimizing these protocols is crucial. Addressing this, our study
introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con-
sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the
proposed WOD-MCC, energy effciency,scalability, and network connectivity are empha-sized. In terms of data delivery, energy conservation, and delay reduction, our fndings
indicate that the WOD-MCC method outperforms existing protocols.
Springer, 2021
Waste management is one of the world's biggest challenges, either in the developed or the emergin... more Waste management is one of the world's biggest challenges, either in the developed or the emerging economies. The biggest problem with pollution is that the compost heap is well flowed in public areas before the next sanitation period starts. Demographic expansion has caused the hygienic condition with regard to the waste management system to deteriorate considerably. Disposal of waste is a fundamental element in waste disposal. Gradually, the technologies of artificial intelligence (AI) gained popularity in offering different computer ways to solving intelligent waste problem. The management of misdefined issues, experiences and uncertainties and partial data were efficient for AI. Even though this work did conduct much study, very few evaluations demonstrated the influence of AI to resolve many difficulties of intelligent management of waste. Accurate evaluation of garbage amount and quality is critical to Smart waste management system development and design. However, it is a challenging task to anticipate the quantity of trash created, given the several characteristics and its variability. The framework utilized in this document is the convolution neural network, a suitable approach for estimating the waste mass.
Springer, 2024
Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing ... more Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing capabilities, making them ideal for connecting multiple users to the Internet of Things (IoT) for real-time applications. However, these networks face limitations in delay and energy, impacting the efciency of routing protocols. For devices to operate efectively over extended periods, optimizing these protocols is crucial. Addressing this, our study
introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con-
sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the proposed WOD-MCC, energy efciency, scalability, and network connectivity are empha-
sized. In terms of data delivery, energy conservation, and delay reduction, our fndings indicate that the WOD-MCC method outperforms existing protocols.
Keywords IoT-enabled WSNs · Data transmission · Reinforcement learning · Whale optimization-driven multi-criterion correlation · Cluster-based routing strategies
International Journal of Computer Technology and Electronics Engineering (IJCTEE), 2012
A reconfigurable structure allows us to provide a large number of resources that can be used in ... more A reconfigurable structure allows us to provide a large number of resources that can be used in different ways by different applications. This paper presents the design methodology of reconfigurable array multipliers. An 8-bit reconfigurable multiplier can execute one 8-bit and two 4-bit multiplications depending upon three control signals. The hardware overhead includes 192 two-input AND gates and 3
control signals. Comparing with the original 8-bit array multiplier which requires 4032 Full Adders and 4096 two-input
AND gates, the hardware overhead is very small. With additional metal lines for interconnections, the hardware
overhead will not increase the chip area. In other words, the high re-configurability of the developed circuit is achieved with negligible hardware overhead and virtually no performance overhead. The reconfigurable structure continues to use the conventional array multiplier with minor changes.
Index Terms : Reconfiguration, Multiplier, FPGA.
Power consumption is an important constraint in the design of induction heater in industrial heat... more Power consumption is an important constraint in the design of induction heater in industrial heater in industrial automation. We are using Hardware and software optimization with the help of PLC ladder logic system. We are adopting this technique in order to reach strong conclusion about their actual impact on the power consumption. The basic idea behind power management project is to manage the power in various loads. When any one load increases then one of the loads that is connected out of many is disconnected, in this priorities is assigned to various loads and with the help of hardware and relay logic we will try to manage the load automatically.
International Journal of Research in Engineering & Technology (IMPACT: IJRET), 2014
The main cause of human death is cardiovascular disease (CVD) in today's world. In order to comba... more The main cause of human death is cardiovascular disease (CVD) in today's world. In order to combat and diagnose this disease, many professionals are using mobile electrocardiogram (ECG) in remote monitoring system. ECG Feature Extraction plays a significant role in diagnosing most of the cardiac diseases. Here comprehensive review has been made for feature extraction of ECG signal analyzing, feature extracting and then classifying it have been proposed during the past time, and here we introduced Artificial Neural Network (ANN). To know the present condition of the heart Electrocardiography and is an important tool but it is a time consuming process to analyze a continuous ECG signal as it may contain thousands of continuous heart beats. Here we convert analog signal to digital one and then reverse of it, it helps in accurately diagnosing the signal. Also this paper presents a detection of some heart arrhythmias using Matlab is done. Hence we input ECG signals to the neural network, these signals are processed by ANN and we diagnose heart arrhythmias correctly. Most important thing in analysis of ECG signals is its fundamental features like amplitudes and intervals are required which determine the functioning of heart. Results shown here are explaining the diagnosis and classification of diseases.
International Journal of Engineering Innovation & Researc, 2012
The main objective of this paper is to make an
automated system to sort the front and rear tyre f... more The main objective of this paper is to make an
automated system to sort the front and rear tyre for car
manufacturing where they are used in numbers. The
objective of this study is to develop the image processing
algorithm using stationary wavelet transform to get the
normalized cropping images which would be suitable inputs
processing and detection. Testing is done using a real-time
visual recognition system. The Matlab software version
2010a is used to integrate all algorithms. The implementation
also consists of a prototype that emulates the sorting of tyres.
Consisting of a control system this hardware provides data
through the microcontroller based system to the Matlab code
which then activates the camera for image processing. It also
activates the motor differently to sort the different parts. The
result shows that the system can detect moving object
accurately on the belt conveyor and sort them accordingly as
required for the application
The main objective of this paper is to make an automated system to sort the front and rear tyre f... more The main objective of this paper is to make an automated system to sort the front and rear tyre for car manufacturing where they are used in numbers. The objective of this study is to develop the image processing algorithm using stationary wavelet transform to get the normalized cropping images which would be suitable inputs processing and detection. Testing is done using a real-time visual recognition system. The Matlab software version 2010a is used to integrate all algorithms. The implementation also consists of a prototype that emulates the sorting of tyres. Consisting of a control system this hardware provides data through the microcontroller based system to the Matlab code which then activates the camera for image processing. It also activates the motor differently to sort the different parts. The result shows that the system can detect moving object accurately on the belt conveyor and sort them accordingly as required for the application.
Journal of Data Acquisition and Processing Vol. 38 (3) July 2023 6322, 2023
This paper employs the use of a Deep Recurrent Neural Network approach
namely Long Short-Term Mem... more This paper employs the use of a Deep Recurrent Neural Network approach
namely Long Short-Term Memory (LSTM) to predict gender and singer name by analyzing audio vocal portions. The ultimate aim of this paper is to build two Long Short-Term Memory (LSTM) models, one for predicting singer gender or gender identification and the other for classifying singer name. The accuracy of different existing algorithms such as SVM, CNN and MLP is then compared to the LSTM algorithm. The MIR-1K dataset that contains audio recordings from singers is used to train all algorithms, including LSTM, SVM, CNN and MLP, with LSTM being the proposed algorithm and SVM, CNN and MLP being existing algorithms, to perform this integration model. The proposed LSTM approach for a deep recurrent neural network offers better performance than other existing ones. The
obtained results show that the effectiveness of the proposed model is used together with a good enough feature vector which works well than the existing methods.
International Journal of VLSI Design, Microelectronics and Embedded System, 2020
Binary multipliers such as matrix and multilayer multipliers have undergone several changes regar... more Binary multipliers such as matrix and multilayer multipliers have undergone several changes regarding their structures and system characteristics. To reduce the number of gates in the binary multipliers and to increase speed, the internal structure of incomplete one-bit adder is investigated and pyramidal adder has been used. The use of pyramidal adders in binary multipliers is not successful in reducing the gate count and delay. To prove that a 4x4 bit Braun multiplier using pyramidal adder is designed in this project and a 16x16 bit pyramidal adder is designed as they are best as adders. To reduce gate count and delay a 16x16 bit Braun multiplier using 2.1 blocks is designed and simulation results are provided.
International Journal of Engineering Research and General Science Volume 3, Issue 5, September-October, 2015, 2015
Nonlinear dynamic signal processing is attracting several researchers owing to its complex behavi... more Nonlinear dynamic signal processing is attracting several researchers owing to its complex behavior which may be deterministic at macro level and may be in order but unruly behavior with respect to time is difficult to understand and interpret. EEG signals fall under such categories. Prediction of seizure in EEG is a challenging task. For this several prediction methodologies have been in use from time to time. But the complexity of signals which differ from person to person makes it complicated.. Keeping this view in mind, we propose to have better prediction of chaotic time series through this paper. Though there have been several attempts in the past, our research is related to use of ANFIS for chaotic time series prediction. Correlation dimension are the factors based on which convergent or divergent or chaotic nature of signal is predicted. In this paper we use correlation dimension for feature extraction providing to ANFIS model for giving précised result.
JETIR , 2020
This paper considers the issue about advanced mark age, and advances the code to actualize this. ... more This paper considers the issue about advanced mark age, and advances the code to actualize this. We can make a protected way for the transmission of any exchange or information. This strategy is utilized in the blockchain innovation. We can actualize it utilizing various strategies, here we are utilizing hash work. Here in this paper we have used the Xilinx 14.7 ISE design suit software for simulation.
International Journal of Engineering and Innovative Technology (IJEIT), 2012
This paper focuses on the recognition of the iris of eye for the security purpose. The objective ... more This paper focuses on the recognition of the iris of eye for the security purpose. The objective of this study is to develop the image processing algorithm using stationary wavelet transform to get the normalized cropping images which would be suitable inputs processing and detection. Testing is done using a real-time visual recognition system. The Matlab software version 7.6 is used to integrate all algorithms. The implementation also consists of a prototype that emulates the hardware response. Consisting of a control system this hardware provides data through the microcontroller based system to the Matlab code which then activates the camera for image processing. It also activates the buzzer for unrecognised image. The result shows that the system can detect iris accurately and give response accordingly as required for the application.
International Journal of Engineering Research and General Science Volume 3, Issue 5, September-October, 2015, 2015
Nonlinear dynamic signal processing is attracting several researchers owing to its complex behavi... more Nonlinear dynamic signal processing is attracting several researchers owing to its complex behavior which may be deterministic at macro level and may be in order but unruly behavior with respect to time is difficult to understand and interpret. EEG signals fall under such categories. Prediction of seizure in EEG is a challenging task. For this several prediction methodologies have been in use from time to time. But the complexity of signals which differ from person to person makes it complicated.. Keeping this view in mind, we propose to have better prediction of chaotic time series through this paper. Though there have been several attempts in the past, our research is related to use of ANFIS for chaotic time series prediction. Correlation dimension are the factors based on which convergent or divergent or chaotic nature of signal is predicted. In this paper we use correlation dimension for feature extraction providing to ANFIS model for giving précised result.
Uploads
Papers by DR.PRAVIN R KSHIRSAGAR
and time consumption. In response to these issues, an alternative strategy named TinyML was put forth by the scientific community to foster safe and autonomous models capable of gathering and processing datawithout the need for network exposure. To address these concerns more effectively, we put forward a versatile TinyML model specifically tailored for health monitoring systems. This model uses enhanced NASNet-XGBoost-based transfer learning methodology to adapt to various types of diseases using appropriate
healthcare data. The process begins by pre-processing raw health signals collected from patients using a combination of a wavelet soft threshold method and empirical wavelet transform-spectrum adaptive segmentation (EWT-SAS). A Tyrannosaurus-based NASNet model is then used to extract meaningful
features from these pre-processed signals. Once the features have been extracted, they are entered into an XGBoost model which can accurately predict various types of diseases based on the given data. This
particular approach achieved an impressive 95.4% average accuracy, 93.6% positive predictive value, 94.7% hit rate, and 96.3% selectivity. When compared to traditional models, this TinyML model shows a significant improvement in performance metrics, demonstrating increased effectiveness and accuracy in predicting
various diseases.
Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing capabilities, making them ideal for connecting multiple users to the Internet of Things (IoT) for real-time applications. However, these networks face limitations in delay and energy, impacting the efciency of routing protocols. For devices to operate efectively over extended periods, optimizing these protocols is crucial. Addressing this, our study
introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con-
sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the
proposed WOD-MCC, energy effciency,scalability, and network connectivity are empha-sized. In terms of data delivery, energy conservation, and delay reduction, our fndings
indicate that the WOD-MCC method outperforms existing protocols.
introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con-
sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the proposed WOD-MCC, energy efciency, scalability, and network connectivity are empha-
sized. In terms of data delivery, energy conservation, and delay reduction, our fndings indicate that the WOD-MCC method outperforms existing protocols.
Keywords IoT-enabled WSNs · Data transmission · Reinforcement learning · Whale optimization-driven multi-criterion correlation · Cluster-based routing strategies
control signals. Comparing with the original 8-bit array multiplier which requires 4032 Full Adders and 4096 two-input
AND gates, the hardware overhead is very small. With additional metal lines for interconnections, the hardware
overhead will not increase the chip area. In other words, the high re-configurability of the developed circuit is achieved with negligible hardware overhead and virtually no performance overhead. The reconfigurable structure continues to use the conventional array multiplier with minor changes.
Index Terms : Reconfiguration, Multiplier, FPGA.
automated system to sort the front and rear tyre for car
manufacturing where they are used in numbers. The
objective of this study is to develop the image processing
algorithm using stationary wavelet transform to get the
normalized cropping images which would be suitable inputs
processing and detection. Testing is done using a real-time
visual recognition system. The Matlab software version
2010a is used to integrate all algorithms. The implementation
also consists of a prototype that emulates the sorting of tyres.
Consisting of a control system this hardware provides data
through the microcontroller based system to the Matlab code
which then activates the camera for image processing. It also
activates the motor differently to sort the different parts. The
result shows that the system can detect moving object
accurately on the belt conveyor and sort them accordingly as
required for the application
namely Long Short-Term Memory (LSTM) to predict gender and singer name by analyzing audio vocal portions. The ultimate aim of this paper is to build two Long Short-Term Memory (LSTM) models, one for predicting singer gender or gender identification and the other for classifying singer name. The accuracy of different existing algorithms such as SVM, CNN and MLP is then compared to the LSTM algorithm. The MIR-1K dataset that contains audio recordings from singers is used to train all algorithms, including LSTM, SVM, CNN and MLP, with LSTM being the proposed algorithm and SVM, CNN and MLP being existing algorithms, to perform this integration model. The proposed LSTM approach for a deep recurrent neural network offers better performance than other existing ones. The
obtained results show that the effectiveness of the proposed model is used together with a good enough feature vector which works well than the existing methods.
and time consumption. In response to these issues, an alternative strategy named TinyML was put forth by the scientific community to foster safe and autonomous models capable of gathering and processing datawithout the need for network exposure. To address these concerns more effectively, we put forward a versatile TinyML model specifically tailored for health monitoring systems. This model uses enhanced NASNet-XGBoost-based transfer learning methodology to adapt to various types of diseases using appropriate
healthcare data. The process begins by pre-processing raw health signals collected from patients using a combination of a wavelet soft threshold method and empirical wavelet transform-spectrum adaptive segmentation (EWT-SAS). A Tyrannosaurus-based NASNet model is then used to extract meaningful
features from these pre-processed signals. Once the features have been extracted, they are entered into an XGBoost model which can accurately predict various types of diseases based on the given data. This
particular approach achieved an impressive 95.4% average accuracy, 93.6% positive predictive value, 94.7% hit rate, and 96.3% selectivity. When compared to traditional models, this TinyML model shows a significant improvement in performance metrics, demonstrating increased effectiveness and accuracy in predicting
various diseases.
Wireless Sensor Networks (WSNs) are rapidly integrating into various felds due to their sensing capabilities, making them ideal for connecting multiple users to the Internet of Things (IoT) for real-time applications. However, these networks face limitations in delay and energy, impacting the efciency of routing protocols. For devices to operate efectively over extended periods, optimizing these protocols is crucial. Addressing this, our study
introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con-
sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the
proposed WOD-MCC, energy effciency,scalability, and network connectivity are empha-sized. In terms of data delivery, energy conservation, and delay reduction, our fndings
indicate that the WOD-MCC method outperforms existing protocols.
introduces a machine learning-optimized routing protocol tailored for IoT-enabled WSNs. This protocol efciently manages IoT devices, emphasizing energy efciency and mobil-ity. We present the Whale Optimization-Driven Multi-Criterion Correlation (WOD-MCC) method, which consistently updates routing strategies based on insights from energy con-
sumption and trafc patterns, ensuring efective routing decisions. This method evaluates device energy levels and node access to reduce data congestion and energy consumption while preserving the connectivity of IoT devices. For the performance evaluation of the proposed WOD-MCC, energy efciency, scalability, and network connectivity are empha-
sized. In terms of data delivery, energy conservation, and delay reduction, our fndings indicate that the WOD-MCC method outperforms existing protocols.
Keywords IoT-enabled WSNs · Data transmission · Reinforcement learning · Whale optimization-driven multi-criterion correlation · Cluster-based routing strategies
control signals. Comparing with the original 8-bit array multiplier which requires 4032 Full Adders and 4096 two-input
AND gates, the hardware overhead is very small. With additional metal lines for interconnections, the hardware
overhead will not increase the chip area. In other words, the high re-configurability of the developed circuit is achieved with negligible hardware overhead and virtually no performance overhead. The reconfigurable structure continues to use the conventional array multiplier with minor changes.
Index Terms : Reconfiguration, Multiplier, FPGA.
automated system to sort the front and rear tyre for car
manufacturing where they are used in numbers. The
objective of this study is to develop the image processing
algorithm using stationary wavelet transform to get the
normalized cropping images which would be suitable inputs
processing and detection. Testing is done using a real-time
visual recognition system. The Matlab software version
2010a is used to integrate all algorithms. The implementation
also consists of a prototype that emulates the sorting of tyres.
Consisting of a control system this hardware provides data
through the microcontroller based system to the Matlab code
which then activates the camera for image processing. It also
activates the motor differently to sort the different parts. The
result shows that the system can detect moving object
accurately on the belt conveyor and sort them accordingly as
required for the application
namely Long Short-Term Memory (LSTM) to predict gender and singer name by analyzing audio vocal portions. The ultimate aim of this paper is to build two Long Short-Term Memory (LSTM) models, one for predicting singer gender or gender identification and the other for classifying singer name. The accuracy of different existing algorithms such as SVM, CNN and MLP is then compared to the LSTM algorithm. The MIR-1K dataset that contains audio recordings from singers is used to train all algorithms, including LSTM, SVM, CNN and MLP, with LSTM being the proposed algorithm and SVM, CNN and MLP being existing algorithms, to perform this integration model. The proposed LSTM approach for a deep recurrent neural network offers better performance than other existing ones. The
obtained results show that the effectiveness of the proposed model is used together with a good enough feature vector which works well than the existing methods.