- Asst. Professor (Stage-III)
Department of Electronics Engg
Indian Institute of Technology
(Banaras Hindu University),
Varanasi (U.P.) 221005 INDIA - +91 9415390577
Dr. N. S. Rajput
IIT BHU, Electronics Engineering, Faculty Member
High-performance detection and estimation of gases/odors are challenging, especially in real-time gas sensing applications. Recently, efficient electronic noses (e-noses) are being developed using convolutional neural networks (CNNs).... more
High-performance detection and estimation of gases/odors are challenging, especially in real-time gas sensing applications. Recently, efficient electronic noses (e-noses) are being developed using convolutional neural networks (CNNs). Further, CNNs perform better when they operate on a minimal size of vector response. In this paper, dimensions of the operational vectors have been augmented by using virtual sensor responses. These virtual responses are obtained from the principal components of the physical sensor responses. Accordingly, two sets of data are upscaled as a one-dimensional one. Another level of upscaling is further obtained by using the mirror mosaicking technique. Hence, with our proposed novel approach, the final vector size for CNN operations achieves a new dimension. With this upscaled hybrid dataset, consisting of physical and virtual sensor responses, a simpler CNN has achieved 100 percent correct classification in two different experimental settings. To the best ...
Research Interests:
Disasters are crisis circumstances that put human life in jeopardy. During disasters, public communication infrastructure is particularly damaged, obstructing Search And Rescue (SAR) efforts, and it takes significant time and effort to... more
Disasters are crisis circumstances that put human life in jeopardy. During disasters, public communication infrastructure is particularly damaged, obstructing Search And Rescue (SAR) efforts, and it takes significant time and effort to re-establish functioning communication infrastructure. SAR is a critical component of mitigating human and environmental risks in disasters and harsh environments. As a result, there is an urgent need to construct communication networks swiftly to help SAR efforts exchange emergency data. UAV technology has the potential to provide key solutions to mitigate such disaster situations. UAVs can be used to provide an adaptable and reliable emergency communication backbone and to resolve major issues in disasters for SAR operations. In this paper, we evaluate the network performance of UAV-assisted intelligent edge computing to expedite SAR missions and functionality, as this technology can be deployed within a short time and can help to rescue most people...
Research Interests:
Ultra-low-power is a key performance indicator in 6G-IoT ecosystems. Sensor nodes in this eco-system are also capable of running light-weight artificial intelligence (AI) models. In this work, we have achieved high performance in a gas... more
Ultra-low-power is a key performance indicator in 6G-IoT ecosystems. Sensor nodes in this eco-system are also capable of running light-weight artificial intelligence (AI) models. In this work, we have achieved high performance in a gas sensor system using Convolutional Neural Network (CNN) with a smaller number of gas sensor elements. We have identified redundant gas sensor elements in a gas sensor array and removed them to reduce the power consumption without significant deviation in the node’s performance. The inevitable variation in the performance due to removing redundant sensor elements has been compensated using specialized data pre-processing (zero-padded virtual sensors and spatial augmentation) and CNN. The experiment is demonstrated to classify and quantify the four hazardous gases, viz., acetone, carbon tetrachloride, ethyl methyl ketone, and xylene. The performance of the unoptimized gas sensor array has been taken as a “baseline” to compare the performance of the optim...
Research Interests:
The increasing urbanization demands development of smart cities. Smart cities can be considered as to serve the requirement of its citizen in better way. The smart cities have many applications involving intelligent gas monitoring. In... more
The increasing urbanization demands development of smart cities. Smart cities can be considered as to serve the requirement of its citizen in better way. The smart cities have many applications involving intelligent gas monitoring. In this chapter we will find about the intelligent gas monitoring in smart city scenario. We will see the aspects of smart gas monitoring, understand the concept of gas sensing, requirement of gas monitoring viz., classification and quantification of gases/odors and the brief introduction about the gas sensing. Further, we will understand the application of blockchain in the intelligent gas monitoring.
Research Interests:
-The coexistence performance when high altitude platform (HAP) and terrestrial WiMAXsystems coexist within the same coverage area sharing a common 5.75 GHz frequency band is investigated. In this paper, the investigation of the... more
-The coexistence performance when high altitude platform (HAP) and terrestrial WiMAXsystems coexist within the same coverage area sharing a common 5.75 GHz frequency band is investigated. In this paper, the investigation of the possibility of utilizing the HAPS service in order to provide WiMAX coverage in the urban area is conducted. Taking into consideration of the acquired results, utilizing the isolation technique is one of the proposed solutions in order to enhance the system capability. This paper investigates the interference to noise ratio (INR) power control to provide coexistence performance. HAP can provide large coverage area at altitude 17-21km while WiMAX is used for mobile wireless network and can operate in unlicensed frequency band. By using dynamic spectrum access such as power control, these two systems can work effectively and efficiently. The modulation of HAP is varying from BPSK to 64QAM to identify which modulation need power control. For BPSK, the power control is not required. Meanwhile for 64QAM, power transmit from HAP is greater than terrestrial WiMAX. Therefore, INR power scheme was used to adjust the terre3trial power. By applying power #ontrol, better coexistence performance can be achieved.
Hyperspectral images consist of unique signature patterns for various physical objects. These unique signatures can be utilized to identify similar objects on a land used/ land cover. In this paper, a neutrally augmented methodology for... more
Hyperspectral images consist of unique signature patterns for various physical objects. These unique signatures can be utilized to identify similar objects on a land used/ land cover. In this paper, a neutrally augmented methodology for efficient object identification using hyperspectral images has been proposed. In the proposed scheme, first, the training samples of the known objects (viz. road, soil, and vegetation) are extracted from the hyperspectral cube. An elementary two-stage feed-forward artificial neural network (ANN) was then employed for correct identification of road, soil, and vegetation, within the training image. In the first stage of ANN, principal component analysis (PCA) has been applied for dimensionality reduction (retaining about 99.5% information) whereas the second stage has a simpler 15 neuron feed forward (FF) back-propagation (BP) ANN for correct identification of different objects. Eventually, the proposed scheme has been verified with the image of San Jo...
Research Interests:
New generation of wireless communication technologies gives people more convenience to connect to any wireless communication networks. Nowadays, subscribers want an effective and efficient communication technology which can support... more
New generation of wireless communication technologies gives people more convenience to connect to any wireless communication networks. Nowadays, subscribers want an effective and efficient communication technology which can support services to anyone in anywhere. Moreover, the weakness of terrestrial wireless communication technologies is unable to deliver broadband communication services to satisfy users who are living in thinly populated, remote, rural and hilly areas. Thus, we propose Tethered Balloon technology to provide broadband services, reduce the requirement of terrestrial infrastructure and make available broadband wireless communication connectivity, in thinly populated, remote, rural and hilly areas. We have examined various aspects of Worldwide Interoperability for Microwave Access (WiMAX) broadband service from Tethered Balloon to show the effectiveness of providing the service delivery. Here, broadband service delivery is analyzed and simulated using Optimized Network Engineering Tool (OPNET) Modeler 14.5. The simulation results show significantly the effectiveness of delivering WiMAX via Tethered Balloon technology.
Research Interests:
Subclasses classification is one of the major challenges in remote sensing (RS) scene classification. The area under observation, in order to classify agriculture and urban subclasses, requires efficient classification algorithms. Among... more
Subclasses classification is one of the major challenges in remote sensing (RS) scene classification. The area under observation, in order to classify agriculture and urban subclasses, requires efficient classification algorithms. Among such algorithms, deep learning algorithm based on Convolutional Neural Network (CNN) architecture is one such promising candidate to obtain the classified map. In this work, performance of a CNN network has been demonstrated on the data obtained from National Ecological Observatory Network (NEON) field site Domain 17 by considering different modality data and its subsequent fusion using the proposed model of CNN as applied on (i) the Hyperspectral, (ii) the Light Detection and Ranging (LiDAR) and then (iii) fused data respectively. Both the Hyperspectral and the LiDAR data have been fused at pixel level. Using the proposed methodology, a classified map is obtained with an overall accuracy of 96 percent for fused data.
Research Interests:
Research Interests:
Conventional methods for classifying SAR data, such as H-α decomposition, Wishart classifier etc. are quite complex and classifies data only on the basis of polarimetric information. With the advent of distinct feature types, their role... more
Conventional methods for classifying SAR data, such as H-α decomposition, Wishart classifier etc. are quite complex and classifies data only on the basis of polarimetric information. With the advent of distinct feature types, their role in land cover classification using SAR data could be analysed. For the sake of classification, researchers are extracting and combining several features in order to obtain the best attainable accuracy. But the usage of several feature type is not only increasing the computational complexity, but also the salience of each of the feature type remains unhighlighted. Hence, it became difficult to analyse that which feature type are best suitable for classification and selection of suitable features for land cover classification is challenging as each feature has its own significance level. Therefore, in this paper class wise, optimal feature selection for land cover classification has been performed using SAR data. For optimal feature selection, four types of feature set polarimetric features, texture features, color features and wavelet features have been examined. For class wise feature subset selection separability index criteria and classification results obtained using Naive Bayes classifier has been utilized. With the proposed methodology overall 10 features has been selected among the total 37 feature analysed with fine land cover classification accuracy of 91%.
Research Interests: Computer Science and IEEE
Survival from breast cancer strongly linked to the size of the tumor at the detection stage. Thus, the early stage detection of tumor of size as minimum as 1.0 mm radius is of great research interest. Currently used techniques for breast... more
Survival from breast cancer strongly linked to the size of the tumor at the detection stage. Thus, the early stage detection of tumor of size as minimum as 1.0 mm radius is of great research interest. Currently used techniques for breast cancer detection fails in 10-30% cases and it gives any positive results when the tumor grows in to a size more than 10.0 mm, this reduces the possibility for an early stage detection and thus the survival rate. Thus, in this paper an alternate method of breast cancer detection through microwave imaging is studied. A dielectric mixing model is used to compute the dielectric constant of the breast tissue with and without the malignant tissue and the proposed model is verified through the simulation in CST. Free space transmission and metal back method are used for the measurement of dielectric constant of the phantom containing one, two, three and four tumors of radius 1.0 mm each. The proposed dielectric mixing model can be applied to detect the changes in the dielectric constant of the tumor affected tissue of radius 1.0 mm which is not possible through any other existing methods.
Research Interests:
ABSTRACT In wireless environment, one of the key ingredients to provide efficient ubiquitous computing with guaranteed quality and continuity of service is the design of intelligent handoff algorithms. A handoff process can be the handoff... more
ABSTRACT In wireless environment, one of the key ingredients to provide efficient ubiquitous computing with guaranteed quality and continuity of service is the design of intelligent handoff algorithms. A handoff process can be the handoff used in order that the service can be continued uninterrupted. Efficient hand off algorithms enhance the capacity and Quality of Service (QoS) of cellular systems. QoS is the measure which defines the performance in any system. In this paper, the different path loss models have been used and then the received signal strength is calculated to determine the model that can be adopted to minimize the number of handoff. Estimation of path loss is very important in initial deployment of wireless network and cell planning. Handoff process enables a cellular system to provide such a facility by transferring an active call from one cell to another. Different approaches are proposed and applied in order to achieve better handoff service. HAP system can be considered as complementary to terrestrial cellular system being in an obstacle position. The key parameters and mathematical model is important for predicting signal coverage. Path loss models for macro cells such as Hata, Walfish-Ikegami and lee models are analysed.
Research Interests:
ABSTRACT The Tethered balloon is new technology for telecommunication that can overcome the limitation of terrestrial system and satellite system due to demand for high capacity in telecommunication. Tethered balloon provides large... more
ABSTRACT The Tethered balloon is new technology for telecommunication that can overcome the limitation of terrestrial system and satellite system due to demand for high capacity in telecommunication. Tethered balloon provides large coverage area with line of sight, which needs large number of base stations for coverage with terrestrial system; also reduce the delay time of the transmission compared to satellite system. Tethered balloon technology is studied in this paper for mobile communication purposes and some calculations are performed to show how path loss, coverage area and hight of Tethered balloon are related. The propagation model Hata model is used.
Research Interests: Computer Science and IEEE
The aim of model based decomposition is to express coherency matrix in terms of various scattering components (like, volume, surface, double bounce, and helix). In spite of this decomposition, ambiguity occurs in scattering response from... more
The aim of model based decomposition is to express coherency matrix in terms of various scattering components (like, volume, surface, double bounce, and helix). In spite of this decomposition, ambiguity occurs in scattering response from various land covers, like urban and vegetation. Deorientation process is believed to remove this ambiguity. However, there is a need to check whether decomposition methods and deorientation helps in identification of different land covers in terms of scattering mechanisms. To fulfil this task, in this paper, a study of four D decomposition methods with and without deorientation has been performed. The purpose of this study is to visualize the effect of deorientation on various land covers like, urban, vegetation, bare soil, water, and subsidence, in Jharia region, one of the major coal fields of India. Both visual and quantitative analysis have been performed for comprehensive evaluation of deorientation effect.
Research Interests:
Classification of water ice region on lunar surface with Mini-SAR data is quite challenging. Therefore, a probability density function (pdf) based pattern analysis approach has been applied to classify lunar surface. This paper represents... more
Classification of water ice region on lunar surface with Mini-SAR data is quite challenging. Therefore, a probability density function (pdf) based pattern analysis approach has been applied to classify lunar surface. This paper represents the pattern analysis approach to fit data points to a distribution function for understanding the distribution behaviour of Mini-SAR data which helps in developing a method based on density functions to differentiate two types of craters namely icy (type-I) and non-icy (type-II) craters. Circular polarization ratio (CPR) is a very important parameter in study of lunar surface. More specifically, the criterion CPR>1 is used to determine possible presence of water-ice deposits on lunar surface So, it's important to study distribution behaviour of CPR pixels and to determine best fitted distribution function representing this behaviour. Therefore, in this paper, pattern analysis techniques have been applied to differentiate two crater types based on the distribution behaviour of CPR. The best fitted function for CPR has been obtained as Generalized Extreme Value function which clearly differentiate type-I and type-II craters.
Research Interests:
Intelligent gas monitoring system is having its widespread applications. It essentially requires an accurate classification with precise quantification of gases/odors. Although, gas sensor arrays are capable of generating signatures... more
Intelligent gas monitoring system is having its widespread applications. It essentially requires an accurate classification with precise quantification of gases/odors. Although, gas sensor arrays are capable of generating signatures however, mostly these signatures are complex and have subtle information. Therefore, in this paper, an efficient sensory system has been proposed for intelligent gas monitoring. Concept of analysis space transformation has been utilized for accurate classification of gases/ odors. Also, the drawback of data preprocessing in quantification has been illustrated by comparing the quantifier performance for the processed and raw responses. Further, the proposed sensory system has elevated the classification accuracy from 96% to 98.74% along with the quantification accuracy from 17.65% to 94%.
Research Interests:
Remote sensing is the analytics of sensor data modalities to capture the earth's surface characteristics. The hyperspectral data widely used for surface material identification by using pixel-wise unique signature patterns. The... more
Remote sensing is the analytics of sensor data modalities to capture the earth's surface characteristics. The hyperspectral data widely used for surface material identification by using pixel-wise unique signature patterns. The true-color-composite (RGB) or/and a variety of false-color-composites (FCCs) used to classify various objects and features. In this paper, three novel FCCs have been proposed and compared with already existing popular FCCs. These FCCs have been analyzed using three different approaches viz., (i) k-means (ii) patch-based deep network and (iii) sample level mirror mosaicking (SLMM)-based deep network; for the classification of various objects or features viz., Vegetation, Soil, and Road. The open-source dataset provided by the National Ecological Observatory Network (NEON) has been used to show the efficacy of proposed FCCs and SLMM-based deep-network. Our proposed FCCs and SLMM-based deep networks outperform over all other considered FCCs and classificatio...
High Altitude platform station (HAPS) technology is a new technology that can perform the tasks currently handled using terrestrial and satellite systems. Anew broadband telecommunication systems has been recently proposed for provision... more
High Altitude platform station (HAPS) technology is a new technology that can perform the tasks currently handled using terrestrial and satellite systems. Anew broadband telecommunication systems has been recently proposed for provision of fixed, mobile and personal services adopting the use of high altitude platform station placed in a fixed position in the stratospheric layer at heights from 17-25 km. This paper examines the interference between HAPS and FWA (fixed wireless access). Hence the characteristic of the interference from single HAPS toward FWA based station established appropriate separation distance and off axis angle of FWA to avoid harmful interferences. The effect of interference on FWA depend on the parameter as elevation angle of the HAPS, elevation angle HAPS ground station as well as that the azimuth angles of the FWA station .Calculations are done by using MATLAB software following the ITU recommendation. Result shows interference reduces when separation distan...
Research Interests:
In this paper, a reduced complexity twostage feed-forward neural network has been employed for on-line classification and quantification of gases/odors. At the classification stage, sensor response for an unknown gas/odor sample is... more
In this paper, a reduced complexity twostage feed-forward neural network has been employed for on-line classification and quantification of gases/odors. At the classification stage, sensor response for an unknown gas/odor sample is processed to identify its class. Now, at the quantification stage, concentration of this sample is predicted by an expert neural network, dedicatedly trained for quantification of that kind of gas/odor. Experimentally, a total of 21 neurons (4 neurons as the input nodes, 5 neurons in the classification network and 12 neurons in the quantification network) were used considering Thick-film Tin-Oxide sensor array responses for four gases/odors (viz. Acetone, Carbon Tetra-chloride, Ethyl Methyl Ketone and Xylene). It is reported that a reduced complexity two-stage ANN, designed following the proposed scheme, can reproducibly discriminate varieties of gases/odors. Classification of test samples has been ‘all correct’ while a very low mean squared error (0.0115...
This paper propounds a novel scheme of mitigation for reducing co-channel interference between HAPGS (High Altitude Platform Ground Station) and radio relay stations. Firstly, in terms of the deployment parameters such as distance between... more
This paper propounds a novel scheme of mitigation for reducing co-channel interference between HAPGS (High Altitude Platform Ground Station) and radio relay stations. Firstly, in terms of the deployment parameters such as distance between HAPGS, elevation angle of the HAPGS as well as that the azimuth angles of the radio relay station. Then, the effects on radio relay station are due to the rainy conditions between HAPGS and radio relay stations. All calculations are done by using Matlab following the ITU-R recommendations. The results show the interference to noise ratio caused at radio relay station from HAPGS decrease, when distance between HAPGS and radio relay stations increases. The minimum separation distance required to obtain an optimum interference is shown for various azimuth angles in clear sky and rainy conditions.
Research Interests:
Hyperspectral images have recently become one of the finest basis for highly accurate identification of objects. Such images, however, are very large in size and carry huge information. Processing and handling of such information is also... more
Hyperspectral images have recently become one of the finest basis for highly accurate identification of objects. Such images, however, are very large in size and carry huge information. Processing and handling of such information is also quite resource savvy and require complex algorithms as well. In this paper, an intelligent classification method has been proposed. Using two independent, simple feed-forward artificial neural networks (ANN), a 426 band hyperspectral image has been first processed for dimensionality reduction to 15 principal components (PCs) using standardized principal component analysis (SPCA), containing 98.86% of the original information. In the second stage, these 15 PCs have been utilized to train another ANN and three different objects viz. road, soil and vegetation have been accurately identified using supervised learning. Only a portion of hyperspectral image data was used as training set and three unique signature patterns were created in the form of patte...
Research Interests:
Autonomous taxies are in high demand for smart city scenario. Such taxies have a well specified path to travel. Therefore, these vehicles only required two important parameters. One is detection parameter and other is control parameter.... more
Autonomous taxies are in high demand for smart city scenario. Such taxies have a well specified path to travel. Therefore, these vehicles only required two important parameters. One is detection parameter and other is control parameter. Further, detection parameters require turn detection and obstacle detection. The control parameters contain steering control and speed control. In this paper a novel autonomous taxi model has been proposed for smart city scenario. Deep learning has been used to model the human driver capabilities for the autonomous taxi. A hierarchical Deep Neural Network (DNN) architecture has been utilized to train various driving aspects. In first level, the proposed DNN architecture classifies the straight and turning of road. A parallel DNN is used to detect obstacle at level one. In second level, the DNN discriminates the turning i.e. left or right for steering and speed controls. Two multi layered DNNs have been used on Nvidia Tesla K 40 GPU based system with Core i-7 processor. The mean squared error (MSE) for the detection parameters viz. speed and steering angle were 0.018 and 0.0248 percent, respectively, with 15 milli seconds of real-time response delay.
Research Interests:
The accuracy of estimated fractional vegetation cover (FVC) depends on selecting the best suitable input features, precise ground information, and a prediction model. Therefore, in this paper, four machine learning (ML) algorithms, namely... more
The accuracy of estimated fractional vegetation cover (FVC) depends on selecting the best suitable input features, precise ground information, and a prediction model. Therefore, in this paper, four machine learning (ML) algorithms, namely Support Vector Regression (SVR), Random Forest Regression (RFR), K-Nearest Neighbors (KNN), and Linear Regression (LR), are used for FVC estimation using different vegetation indices (VI) as input features. Estimated FVC is compared with the ground truth FVC, which has been calculated with the high-resolution drone images, and their R-square values are calculated. R-square value is used for the assessment of the best input features and model. RFR and KNN emerge as the best suitable ML models in comparison to SVR and LR. The obtained R-square values for the RFR model with the input features used as NDVI, PAVI, SAVI, and MSAVI are 0.873, 0.869, 0.869, and 0.862, respectively. NDVI, PAVI, SAVI, and MSAVI perform better in comparison to other features. Hence, they are permuted together and used as input features, and their results on all the algorithms are moderately better. The highest R-square value obtained is 0.878 when SAVI and PAVI are used as input features for the RFR model.
Research Interests:
Convolutional neural networks (CNNs) are top-rated to classify hyperspectral images. Usually, these use the spectral-spatial approach (SSA), in which the patch corresponding to each pixel to be classified extracted from the hyperspectral... more
Convolutional neural networks (CNNs) are top-rated to classify hyperspectral images. Usually, these use the spectral-spatial approach (SSA), in which the patch corresponding to each pixel to be classified extracted from the hyperspectral image. The size of the patches' spatial neighborhood plays a vital role in the complexity of the designed CNN model. The complexity of the model proportionately increases according to the spatial size of patches. Generally, patches are of odd-squared spatial size centering at the corresponding pixel. In this paper, a novel approach based on mirror mosaicking (MMA) has been proposed. It has been compared with the spectral-spatial approach using minimally sized patches. The proposed approach has been proved computationally efficient along with competitive classification performance. A dataset provided by National Ecological Observatory Network (NEON) has been used for the experimentation, which has three major classes, viz. vegetation, soil, and road.
Research Interests:
Land cover classification in the remote sensing has been done using various deep learning algorithms; and higher classification accuracies have been achieved. Such classification is based on the maximum membership fraction (MMF), when we... more
Land cover classification in the remote sensing has been done using various deep learning algorithms; and higher classification accuracies have been achieved. Such classification is based on the maximum membership fraction (MMF), when we use Convolutional Neural Network (CNN). MMF is basically the maximum probability fraction. A pixel under prediction has been assigned to that class which has maximum fraction out of the corresponding fractions for all land cover classes. Various methodologies exist for pure pixel extraction and used for hyperspectral unmixing. An assumption has been taken that MMF and abundance used in the case of unmixing are similar. Both MMF and abundance follow the rule of sum to one. In this paper, a classification method has been implemented using CNN to achieve better classification accuracy. Thereafter number of pure pixels extracted based on the various MMF thresholds.
Research Interests:
The development of the Internet of Things (IoT) technology and their integration in smart cities have changed the way we work and live, and enriched our society. However, IoT technologies present several challenges such as increases in... more
The development of the Internet of Things (IoT) technology and their integration in smart cities have changed the way we work and live, and enriched our society. However, IoT technologies present several challenges such as increases in energy consumption, and produces toxic pollution as well as E-waste in smart cities. Smart city applications must be environmentally-friendly, hence require a move towards green IoT. Green IoT leads to an eco-friendly environment, which is more sustainable for smart cities. Therefore, it is essential to address the techniques and strategies for reducing pollution hazards, traffic waste, resource usage, energy consumption, providing public safety, life quality, and sustaining the environment and cost management. This survey focuses on providing a comprehensive review of the techniques and strategies for making cities smarter, sustainable, and eco-friendly. Furthermore, the survey focuses on IoT and its capabilities to merge into aspects of potential to...
Research Interests:
In this paper, a typical scenario has been considered wherein gas sensor array responses from a WAN deployed sensor network are being received hourly, 24×7. From every sensor node, we are retrieving Static as well as Dynamic Responses... more
In this paper, a typical scenario has been considered wherein gas sensor array responses from a WAN deployed sensor network are being received hourly, 24×7. From every sensor node, we are retrieving Static as well as Dynamic Responses with 16 sensing elements generating a .csv file of 9 MB size. Considering 1000 sensor nodes, the data received at the Hadoop Cluster at our Data Centre would be about 9 GB, which can be even more if more number of nodes, over larger geographical area and/or higher density of nodes is considered. Hence, (i) to receive and store such a huge data from a sensor network and (ii) to analyse the received data, we explored the suitability of Apache Flume and Apache Mahout to deliver high performance computational scalability on Hadoop Distributed File System. In this work, an implementation methodology for realization of such a scalable system has been presented by considering a sensor network for air pollution observation over a large geographical area, as an example.
Research Interests:
In order to provide committed Quality of Service (QoS) to the users, telecommunication service providers use different resource allocation techniques. One of such schemes is the adaptive bandwidth allocation technique. QoS is improved by... more
In order to provide committed Quality of Service (QoS) to the users, telecommunication service providers use different resource allocation techniques. One of such schemes is the adaptive bandwidth allocation technique. QoS is improved by minimizing the probability of dropping and blocking calls and by allocating channels, optimally. In this paper, reserved channel technique has been considered for High Altitude Platform (HAP) based communication services deployment. Such implementation is especially feasible in HAP as, on a single HAP, multiple mobile cells are created and optimal resource allocation could be done, centrally. By varying the value of reserved channels and reserved channels for hand-off, we report that the probability of blocking of a new call and successful hand-off of an ongoing call is greatly improved.
Research Interests:
In order to provide committed Quality of Service (QoS) to the users, telecommunication service providers use different resource allocation techniques. One of such schemes is the adaptive bandwidth allocation technique. QoS is improved by... more
In order to provide committed Quality of Service (QoS) to the users, telecommunication service providers use different resource allocation techniques. One of such schemes is the adaptive bandwidth allocation technique. QoS is improved by minimizing the probability of dropping and blocking calls and by allocating channels, optimally. In this paper, reserved channel technique has been considered for High Altitude Platform (HAP) based communication services deployment. Such implementation is especially feasible in HAP as, on a single HAP, multiple mobile cells are created and optimal resource allocation could be done, centrally. By varying the value of reserved channels and reserved channels for hand-off, we report that the probability of blocking of a new call and successful handoff of an ongoing call is greatly improved.
Research Interests:
Exponential growth in the number of subscribers of mobile communication services has prompted service providers to maintain high level of quality of service (QoS). QoS performance is usually measured in terms of the probability of call... more
Exponential growth in the number of subscribers of mobile communication services has prompted service providers to maintain high level of quality of service (QoS). QoS performance is usually measured in terms of the probability of call blocking and probability of call dropping parameters. Recently, high altitude platform (HAP) is being explored to deploy mobile communication services due to various advantages. In this paper, a modified call admission control (CAC) technique has been proposed. We propose a novel CAC technique which uses two schemes viz. “bandwidth reservation” and “degradation scheme” to deliver the desired QoS. Under the ‘bandwidth reservation scheme’, we allocated dedicated bandwidth to each category of service. Consequently, when a new call request arrives and when there are no more channels available, in that particular class; we use the ‘adaptive degradation scheme’ under which the allocated bandwidth of each channel is reduced slightly and additional channels are created and hence allocated to the new call request. Using these schemes in conjunction with CAC, better bandwidth utilization has been obtained over preferred category of committed QoS and the connections services enjoy more available bandwidth with improve in the blocking probability and dropping probability.
Research Interests:
The application of Synthetic Aperture Radar (SAR) data for estimating soil moisture in the vegetated covered areas is still challenging task because variation of the vegetation over the soil surface is difficult to predict. Thus, there is... more
The application of Synthetic Aperture Radar (SAR) data for estimating soil moisture in the vegetated covered areas is still challenging task because variation of the vegetation over the soil surface is difficult to predict. Thus, there is a need to develop such an approach for soil moisture retrieval which can minimize the vegetation effects. Various models are available in the literature for soil moisture retrieval but either these models are very complex or they required more than one satellite data. Therefore, in this paper, an attempt has been made for minimizing the crop effect while retrieving the soil moisture by using same satellite data (i.e., PALSAR data) only. For this purpose, the application of polarimetric information may be useful because polarimetric indices give physical significance in discriminating the vegetated cover areas from other regions (water bodies, urban areas, bare soil) of the earth's surface. So, these polarimetric indices have been critically analyzed for the minimization of crop effect and a model has been developed for soil moisture retrieval by using the polarimetric indices SPAN and RVI.
Research Interests:
Research Interests:
Research Interests:
One of the most successful algorithms that bring realism in the world of 3-D generation is fast phong shading. The digital image data is rapidly expanding in quantity and heterogeneity. The traditional information retrieval techniques... more
One of the most successful algorithms that bring realism in the world of 3-D generation is fast phong shading. The digital image data is rapidly expanding in quantity and heterogeneity. The traditional information retrieval techniques does not meet the user's demand, so there is ...
Research Interests:
Aerial telecommunications have been investigated for three decades through the design and evaluation of stratospheric platforms able to offer multiple types of wireless services. HAP may be airplanes or airships and may be manned or... more
Aerial telecommunications have been investigated for three decades through the design and evaluation of stratospheric platforms able to offer multiple types of wireless services. HAP may be airplanes or airships and may be manned or unmanned with autonomous operation coupled with remote control from the ground. There is increasing interest in the development of airspace platforms in recent years, for example, HAP carrying equipment for telecommunications, remote sensing or digital broadcasting. The multiple types of platform are able to carry a communication payload at different altitudes. Regarding the altitude of aerial communication, there are three categories of balloons, High Altitude Platforms (HAP), Medium Altitude platform (MAP) and Low Altitude Platform (LAP). HAPs provide an excellent option for emergency communications, their survivability during a disaster and ability to be continuously on station offer an ideal solution for an emergency communications capability. This p...
Research Interests:
Recently, artificial neural networks have been utilized to improve handoff algorithms due to its ability to handle large data in fast processing. ANN helps in taking the handoff decision based on RSS, speed, traffic intensity, and... more
Recently, artificial neural networks have been utilized to improve handoff algorithms due to its ability to handle large data in fast processing. ANN helps in taking the handoff decision based on RSS, speed, traffic intensity, and directivity. RBF network is used for making a handoff decision to the chosen neighbor BS. Efficient handoff algorithm enhances the capacity and QoS of cellular systems. Handoff algorithm used in wireless cellular systems to decide when and to which BS to handoff in order that the services can be continued uninterrupted. HAPs considered as a complementary base station to mobiles in an obstacle position and the capacity of system is more efficient with the goodness of HAPs. As a revolutionary wireless system, HAPS can supply services for uncovered area improving total capacity of service-limited area by a terrestrial BS. This paper presents novel approaches for the design of high performance handoff algorithm that exploit attractive features. This paper prop...
Research Interests:
A number of Earth observing satellite missions carrying onboard passive microwave instruments operate in frequency channels in close proximity in terms of frequency, polarization, incidence angle, system noise, etc., which, however,... more
A number of Earth observing satellite missions carrying onboard passive microwave instruments operate in frequency channels in close proximity in terms of frequency, polarization, incidence angle, system noise, etc., which, however, results in difference in their measurements. In order to remove such differences in the measurements from two or more sensors, cross-calibration of brightness temperature may be desired. Present study provides a procedure to calibrate such measurements from one sensor with another while they do not need to have any common period of operation. Study demonstrates the technique using measurements from AMSR-2 and TMI onboard GCOM-W1 and TRMM. Relationships between their corresponding channels are established using radiative transfer simulations. The relationship thus established when applied to their actual near-concurrent observations found to have the root mean square error of 3.15 K to 6.18 K between them compared to 3.71 K to 10.4 K found without calibration.
Research Interests:
Limited dimensionality of the dataset obtained from an electronic nose (EN) is due to the number of elements in the sensor array used generally in the range of 4-8 elements only. Further, large number of sensor data can be generated by... more
Limited dimensionality of the dataset obtained from an electronic nose (EN) is due to the number of elements in the sensor array used generally in the range of 4-8 elements only. Further, large number of sensor data can be generated by sampling the sensor responses both during the transient and steady states. The lowerdimensionality of sensor data prohibits the use of a convolutional neural network (CNN)-based pattern recognition techniques because the kernels of a CNN cannot be used on the obtained sample vectors to extract the features. In this paper, we have proposed a novel approach to enhance the data dimensionality keeping the sensor response characteristics absolutely unaltered. By leveraging the concept of mirror mosaicking technique, we have upscaled the input sample vectors into a 6×6 2-D input arrays to train the shallow CNN. Using the proposed approach, all the 16-unknown steady-state test samples classified accurately which are not used during the training. Moreover, th...
Efficient hand-off algorithm enhances the capacity and quality of service (QoS) of cellular systems. Hand-off algorithm is used in wireless cellular systems to decide when and to which base station (BS) will receive the handoff call,... more
Efficient hand-off algorithm enhances the capacity and quality of service (QoS) of cellular systems. Hand-off algorithm is used in wireless cellular systems to decide when and to which base station (BS) will receive the handoff call, without any service interruption. High altitude platforms (HAPs) is considered as a complementary BS to mobiles in an obstacle position. HAPs can supply services to uncovered areas of terrestrial systems, thus with the goodness of HAPs total capacity in a service-limited area will be improved. Recently, artificial neural network (ANN) has been utilized to improve hand-off algorithms due to its ability to handle large data. As a revolutionary wireless system, ANN helps in taking the hand-off decision based on receive signal strength, speed, traffic intensity, and directivity. Radial based function network is used for making a hand-off decision to the chosen neighbor BS. This paper presents novel approaches of combining HAPs and terrestrial system in a pa...
Research Interests:
This paper propounds a novel scheme of mitigation for reducing co-channel interference between HAPGS (High Altitude Platform Ground Station) and radio relay stations. Firstly, in terms of the deployment parameters such as distance between... more
This paper propounds a novel scheme of mitigation for reducing co-channel interference between HAPGS (High Altitude Platform Ground Station) and radio relay stations. Firstly, in terms of the deployment parameters such as distance between HAPGS, elevation angle of the HAPGS as well as that the azimuth angles of the radio relay station. Then, the effects on radio relay station are due to the rainy conditions between HAPGS and radio relay stations. All calculations are done by using Matlab following the ITU-R recommendations. The results show the interference to noise ratio caused at radio relay station from HAPGS decrease, when distance between HAPGS and radio relay stations increases. The minimum separation distance required to obtain an optimum interference is shown for various azimuth angles in clear sky and rainy conditions.
In this paper, we present a neurally optimized resource allocation scheme suitable for differentially modulated relay networks. In order to minimize the average symbol error rate (SER), energy as well as the location of the considered... more
In this paper, we present a neurally optimized resource allocation scheme suitable for differentially modulated relay networks. In order to minimize the average symbol error rate (SER), energy as well as the location of the considered relay has been optimized neurally. Neurally implemented closed-form solution has been presented for the single-relay case, while numerically searchable neural model has been developed for multiple-relay cases. Analytical and simulated comparisons confirm that the neurally optimized systems deliver considerable improvement when compared with the un-optimized systems, and the minimum
SER could be achieved with neural optimization of energy-location aspect of the relays.
SER could be achieved with neural optimization of energy-location aspect of the relays.
In conventional relay systems eavesdropping is a major impediment during secure communication. Accordingly, by considering neural cooperative jamming strategies for two-hop relay networks, the eavesdropping has been wiretapped in the... more
In conventional relay systems eavesdropping is a major impediment during secure communication. Accordingly, by considering neural cooperative jamming strategies for two-hop
relay networks, the eavesdropping has been wiretapped in the relay channels, in both hops. In this approach, the normally inactive nodes in the relay network have been used as cooperative jamming sources to confuse the eavesdropper. Linear pre-coding schemes have been considered for two scenarios where single or multiple data streams are transmitted via a decode-and-forward (DF) relay, under the assumption that global channel state information (CSI) is available. For the case of single data stream transmission, we have derived the closed-form jamming beam-formers and its corresponding optimal power allocation. Generalized singular value decomposition
(GSVD)-based secure relaying schemes, implemented neurally, are proposed for the transmission of multiple data streams. The optimal power allocation is found for the GSVD relaying scheme using pre-trained neural network.
Based on this result, a GSVD-based neural cooperative jamming scheme has been proposed which shows significant improvement in terms of secrecy rate compared to the approach without jamming. Furthermore, the case involving an eavesdropper with unknown CSI has also been investigated in this paper.
Simulation results show that the secrecy rate is dramatically increased when inactive nodes in the relay network participate in cooperative jamming.
relay networks, the eavesdropping has been wiretapped in the relay channels, in both hops. In this approach, the normally inactive nodes in the relay network have been used as cooperative jamming sources to confuse the eavesdropper. Linear pre-coding schemes have been considered for two scenarios where single or multiple data streams are transmitted via a decode-and-forward (DF) relay, under the assumption that global channel state information (CSI) is available. For the case of single data stream transmission, we have derived the closed-form jamming beam-formers and its corresponding optimal power allocation. Generalized singular value decomposition
(GSVD)-based secure relaying schemes, implemented neurally, are proposed for the transmission of multiple data streams. The optimal power allocation is found for the GSVD relaying scheme using pre-trained neural network.
Based on this result, a GSVD-based neural cooperative jamming scheme has been proposed which shows significant improvement in terms of secrecy rate compared to the approach without jamming. Furthermore, the case involving an eavesdropper with unknown CSI has also been investigated in this paper.
Simulation results show that the secrecy rate is dramatically increased when inactive nodes in the relay network participate in cooperative jamming.
In the next generation networks (NGN), i.e. beyond the third-generation (3G) networks, multiple wireless technologies would be coexisting in a heterogeneous wireless access network environment. Also, the use of a common IP core to realize... more
In the next generation networks (NGN), i.e. beyond the third-generation (3G) networks, multiple wireless technologies would be coexisting in a heterogeneous wireless access network environment. Also, the use of a common IP core to realize the user-focused service delivery would be inevitable. The coexistence of heterogeneous radio access technologies (RATs) would noticeably amplify the difference of different platforms of high-speed multimedia services, such as video on demand, mobile gaming, web browsing, video streaming, VoIP and e-commerce etc. Seamless inter system roaming across heterogeneous wireless access networks would also be a major feature in the architecture of Next Generation Wireless Networks. The future users of mobile communication would look at ‘Always Best Connected (ABC)’ in the complementary access technologies like WLAN, Wi-Max, UMTS etc. coexisting with HAPs and Satellite backed up networks. Efficient user roaming and switching management of available radio resources, therefore, becomes decisive in providing the network stability with suitable QoS provisioning in NGN.
With this view, intelligent Call Admission Control (CAC) becomes the challenge foreseeable in future technological developments, to ensure better Radio Resource Management (RRM) and delivery of committed QoS to the users. Neuro-Fuzzy techniques to extend linguistic controls and real-time learnability are therefore candidates for future exploration. Using these techniques, call blocking probability would be lowered further, in spite of keeping the resource utilization at an optimum level.
Accordingly, in this paper, we are proposing an approach for neuro-fuzzy query processing in which membership function values are used to evaluate the fuzzy attribute of the query. Then a neural decision maker generates the reverse SQL to identify respective users. By considering a real life mobile scenario, we have demonstrated and compared the efficacy of this approach w.r.t. the traditional approaches.
With this view, intelligent Call Admission Control (CAC) becomes the challenge foreseeable in future technological developments, to ensure better Radio Resource Management (RRM) and delivery of committed QoS to the users. Neuro-Fuzzy techniques to extend linguistic controls and real-time learnability are therefore candidates for future exploration. Using these techniques, call blocking probability would be lowered further, in spite of keeping the resource utilization at an optimum level.
Accordingly, in this paper, we are proposing an approach for neuro-fuzzy query processing in which membership function values are used to evaluate the fuzzy attribute of the query. Then a neural decision maker generates the reverse SQL to identify respective users. By considering a real life mobile scenario, we have demonstrated and compared the efficacy of this approach w.r.t. the traditional approaches.
In this paper, a novel scheme based of neural processing has been proposed. By considering the non-cooperative distributed wireless amplifying-and-forward relay networks, optimal relay matrices have been estimated neutrally. Either... more
In this paper, a novel scheme based of neural processing has been proposed. By considering the non-cooperative distributed wireless amplifying-and-forward relay networks, optimal relay matrices have been estimated neutrally. Either partial-band noise jamming or non-symmetrical node geometry and under fading conditions, the channels connecting any two nodes, have been analyzed theoretically. Then, the minimum mean squared error criterion has been used for the optimality assessment. A simple feed-forward LM trained BP Neural Network has been trained over the MSE criterion and the optimality has been estimated neutrally. With the derived optimum relay amplifying matrices, the bit error rate has been then compared for the values, estimated neutrally and mathematically, for various simulated situations.
In this paper, a novel scheme based of neural processing for its use in cooperative communication, has been proposed. In order to achieve better connectivity and higher data rates in wireless fading channels, cooperative communication... more
In this paper, a novel scheme based of neural processing for its use in cooperative communication, has been proposed. In order to achieve better connectivity and higher data rates in wireless fading channels, cooperative communication using decode and forward (DF)-based distributed relays is one important solution. In distributed relay networks, each relay has an independent local oscillator which when unsynchronized results in the presence of multiple carrier frequency offsets (CFOs) at the destination. The maximum likelihood estimator (MLE) for estimating the multiple CFOs requires a two dimensional grid search involving matrix inversion for each search point. Thus, the multiple CFO and channel estimation is computationally prohibitive and challenging in distributed relay networks.
In this paper, we propose a simple neural estimator for multiple CFO and channel estimation at the destination by exploiting the fact that the relays receive information from a common source and the information could be largely redundant. Computer simulations show that the mean square error (MSE) performance of the proposed neural estimator is close to the Cramer-Rao lower bound for small carrier frequency synchronization errors at the relays.
In this paper, we propose a simple neural estimator for multiple CFO and channel estimation at the destination by exploiting the fact that the relays receive information from a common source and the information could be largely redundant. Computer simulations show that the mean square error (MSE) performance of the proposed neural estimator is close to the Cramer-Rao lower bound for small carrier frequency synchronization errors at the relays.
This paper propounds a novel scheme of parametric mitigation for reduced co-channel interference between the HAPs and FWA terminals using neural networks. Firstly, an in-depth analysis of the stratosphere-to-earth co-channel interference... more
This paper propounds a novel scheme of parametric mitigation for reduced co-channel interference between the HAPs and FWA terminals using neural networks. Firstly, an in-depth analysis of the stratosphere-to-earth co-channel interference produced by high-altitude platforms (HAPs) has been presented. Then, in terms of the deployment parameters such as HAP’s mobility, azimuth and elevation angles of the terrestrial microwave links (TMLs) and gradual high-altitude platform network (HAPN) loading, the fractional degradation in performance has been assessed. Now, artificial neural networks (ANNs) have been trained and used to mitigate the performance degradation at various specified parametric combination of deployment of the HAPs. Simulations demonstrate that the proposed methodology of ANN usage may lead to a more efficient use of the spectrum shared between the two services.