ORCID Profile
0000-0002-5252-3669
Current Organisations
B.Tech(CSE), M.Tech(IIIT), Ph.D.
,
University of Newcastle Australia
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Foundation of Computer Science
Date: 31-05-2011
DOI: 10.5120/2526-3437
Publisher: Hindawi Limited
Date: 21-08-2023
DOI: 10.1155/2023/6430987
Abstract: Systems that employ multicarrier code ision multiple access, commonly known as MC-CDMA, produce outstanding results in terms of both the performance of the system as a whole and the efficiency with which it uses the spectrum. However, multiple access strategies are susceptible to interference despite their high spectrum efficiency. This work aims to reduce multiple access interference (MAI) by developing an MC-CDMA receiver. When MC-CDMA deteriorates nonlinearly, standard receivers, namely, zero forcing (ZF), maximal ratio combining (MRC), minimum mean square error (MMSE), and equal gain combining (EGC), are unable to cancel MAI. Neural network (NN) receivers are a better option due to their nonlinear nature. Based on the simulation results, the suggested deep neural network- (DNN-)based schemes outperform the current baselines in terms of error handling and usability. This research explores the viability and effectiveness of a DNN-based receiver designed for MC-CDMA with nonlinearity degradations. The focus of this research is on MC-CDMA.
Publisher: Hindawi Limited
Date: 06-07-2022
DOI: 10.1155/2022/1388941
Abstract: Numerous wireless technologies have been integrated to provide 5th generation (5G) communication networks capable of delivering mission-critical applications and services. Despite considerable developments in a variety of supporting technologies, next-generation cellular deployments may still face severe bandwidth constraints as a result of inefficient radio spectrum use. To this end, a variety of appropriate frameworks have recently emerged that all aid mobile network operators (MNOs) in making effective use of the abundant frequency bands that other incumbents reserve for their own use. The proposed COCO model for Dynamic Spectrum Allocation (DSA) has 2 functionalities such as 1. Coherent PU-SU packet acceptance algorithm for Secondary User (SU) in DSA. 2. Consensus Algorithm for PU-SU Channel Reservation in DSA. To enable a 5G service with one-millisecond latency, interconnection ports between operators are expected to be required at every base station, which would have a significant influence on the topological structure of the core network. Additionally, just one radio network infrastructure would need to be created, which all operators would then be able to use. We allow change of PU SU characteristics to satisfy the needs of new services. These modifications are accomplished via the use of Coherent and Consensus Algorithms that regulate PU and SU through negotiation and allocation procedures. Our primary objective was to decrease interference, handoff latency, and the chance of blocking. In this paper, we describe our idea for employing COCO Model to address the issues of spectrum mobility, sharing, and handoff for Cognitive Radio Networks in 5G.
Publisher: Hindawi Limited
Date: 25-01-2023
DOI: 10.1155/2023/6662355
Abstract: This research article describes a novel optimization technique called simulink design optimization (SDO) to compute the optimal PID coefficients for an automatic voltage regulator (AVR). The time-domain performance of the proposed controller was analyzed using MATLAB/Simulation, and its performance was compared with that of water cycle algorithm, genetic algorithm, and local unimodal s ling algorithm-based PID controllers. The robustness of the proposed controller was verified by applying the disturbances to the generator field voltage and the lifier parameter uncertainty. The studies presented in literature were discussed the AVR loop stability using the Bode plot which will not give the minimum stability margins. This study proposes a novel stability analysis called disk-based stability analysis to authenticate the stability of the AVR loop which is obtained by the classical analysis. This stability was compared with the proposed stability analysis. The MATLAB results reveal that the SDO-PID controller regulates the terminal voltage of the generator precisely, is more robust to parameter uncertainty, and is more stable than the other controllers. The maximum allowable parameter uncertainty of the lifier model was identified as 102% of its nominal parameters. The stability margins are recognized as DGM = 10.40 dB and DPM = 56.50° for the AVR stability.
Publisher: IGI Global
Date: 2021
Publisher: IEEE
Date: 17-12-2021
Publisher: CRC Press
Date: 17-02-2022
Publisher: Springer Science and Business Media LLC
Date: 09-06-2021
Publisher: GSC Online Press
Date: 30-05-2022
DOI: 10.30574/WJAETS.2022.6.1.0056
Abstract: Cancer is the foremost cause behind the most death pace of people around the world. Cancer of breast is the primary reason for mortality among females. There have been various investigation or experimentation aimed at the discovery and interpretation of facts has been done on early expectation and discovery of breast cancer disease to begin treatment and increment the opportunity of endurance. Utmost research targets x-ray pictures of the breasts. Although, photographs of the breasts made by X-rays occasionally produces a threat of fake recognition which can compromise the medical status of infectious person. It’s crucial and import to locate opportunity techniques that might be simpler to put into effect and work with extraordinary records sets, inexpensive and safer, which could produce an extra dependable prognosis. This research journal recommends an associated prototype of numerous DLA (Deep Learning Algorithms) including ANN (Artificial Neural Network) and CNN (Convolutional Neural Networks) for efficient breast cancer detection and prediction. The research exploration utilizes the x-rays image database (as base research datasets) for prediction, detection, and diagnosis of breast cancer. This anticipated research prototype may be associated with several clinical examination data i.e. text, audio, image, video, blood, urine and many more.
Publisher: Springer Science and Business Media LLC
Date: 09-2021
Publisher: Hindawi Limited
Date: 21-08-2022
DOI: 10.1155/2022/9399876
Abstract: The ability to determine infarction thickness using magnetic resonance perfusion modulated imaging (PWI) should assist physicians to decide how vigorously to treat severe stroke victims. Algorithms for predicting tissue fate have indeed been created, although they are largely based on hand-crafted characteristics extracted from perfusion pictures, which seem to be susceptible to background subtraction approaches. Researchers show how deep convolution neural networks (CNNs) can be used to predict final stroke infarction thickness only using primary perfusion data throughout this paper. The number of recoverable tissues determines the alternative treatments for patients with acute ischemic stroke. The accuracy of this measurement technique is currently restricted by a set threshold and limited imagining paradigms. The values collection from real-time sensors was used to create and evaluate this suggested deep learning-based stroke illness statistical method. Several deep-learning systems (CNN-LSTM, LSTM, and CNN-Bidirectional LSTM) that specialize in time series analysis prediction and classification were analyzed and compared. These findings show that noninvasive technologies that can simply measure brainwave activity by itself can forecast and track stroke illnesses in real-time throughout ordinary life are feasible. When compared with the previous measuring approaches, these findings are predicted to lead to considerable improvements in early stroke diagnosis at a lower cost and with less inconvenience.
Publisher: IGI Global
Date: 2020
DOI: 10.4018/978-1-7998-2742-9.CH021
Abstract: This chapter presents a comparative study of the proposed approaches (i.e., extended dark block extraction [EDBE], extended cluster count extraction [ECCE], and extended co-VAT approaches). This chapter evaluates pre-clustering and post-clustering algorithms on real-time data and synthetic datasets. Unlike traditional clustering algorithms, pre-clustering algorithms provide a prior clustering on different datasets. Simulation studies are carried out using datasets having both class-labeled and unlabeled information. Comparative studies are performed between results of existing pre-clustering and proposed pre-clustering approaches. A simulated RDI-based preprocessing method is also applied for data ersification. Extensive simulation on real and synthetic datasets shows that pre-clustering algorithms with simulated RDI-based pre-processing performs better compared to conventional post-clustering algorithms.
Publisher: Institute of Advanced Engineering and Science
Date: 06-2020
DOI: 10.11591/IJAAS.V9.I2.PP85-92
Abstract: span Diabetes Mellitus is one of the growing fatal diseases all over the world. It leads to complications that include heart disease, stroke, and nerve disease, kidney damage. So, Medical Professionals want a reliable prediction system to diagnose Diabetes. To predict the diabetes at earlier stage, different machine learning techniques are useful for examining the data from different sources and valuable knowledge is synopsized. So, mining the diabetes data in an efficient way is a crucial concern. In this project, a medical dataset has been accomplished to predict the diabetes. The R-Studio and Pypark software was employed as a statistical computing tool for diagnosing diabetes. The PIMA Indian database was acquired from UCI repository will be used for analysis. The dataset was studied and analyzed to build an effective model that predicts and diagnoses the diabetes disease earlier. /span
Publisher: Springer Nature Singapore
Date: 2022
Publisher: IEEE
Date: 22-06-2022
Publisher: Hindawi Limited
Date: 30-11-2022
DOI: 10.1155/2022/1525615
Abstract: COVID-19 has sparked a global pandemic, with a variety of inflamed instances and deaths increasing on an everyday basis. Researchers are actively increasing and improving distinct mathematical and ML algorithms to forecast the infection. The prediction and detection of the Omicron variant of COVID-19 brought new issues for the health fraternity due to its ubiquity in human beings. In this research work, two learning algorithms, namely, deep learning (DL) and machine learning (ML), were developed to forecast the Omicron virus infections. Automatic disease prediction and detection have become crucial issues in medical science due to rapid population growth. In this research study, a combined Extended CNN-RNN research model was developed on a chest CT-scan image dataset to predict the number of +ve and −ve cases of Omicron virus infections. The proposed research model was evaluated and compared against the existing system utilizing a dataset of 16,733-s le training and testing CT-scan images collected from the Kaggle repository. This research article aims to introduce a combined ML and DL technique based on the combination of an Extended Convolutional Neural Network (ECNN) and an Extended Recurrent Neural Network (ERNN) to diagnose and predict Omicron virus-infected cases automatically using chest CT-scan images. To overcome the drawbacks of the existing system, this research proposes a combined research model that is ECNN-ERNN, where ECNN is used for the extraction of deep features and ERNN is used for exploration using extracted features. A dataset of 16,733 Omicron computer tomography images was used as a pilot assessment for this proposed prototype. The investigational experiment results show that the projected prototype provides 97.50% accuracy, 98.10% specificity, 98.80% of AUC, and 97.70% of F1-score. To the last, the study outlines the advantages being offered by the proposed model with respect to other existing models by comparing different parameters of validation such as accuracy, error rate, data size, time complexity, and execution time.
Publisher: Springer Nature Switzerland
Date: 2022
Publisher: Elsevier BV
Date: 2023
Publisher: Institute of Advanced Engineering and Science
Date: 12-2016
DOI: 10.11591/IJEECS.V4.I3.PP617-628
Abstract: Clustering is one of the technique or approach in content mining and it is used for grouping similar items. Clustering software datasets with mixed values is a major challenge in clustering applications. The previous work deals with unsupervised feature learning techniques such as k-Means and C-Means which cannot be able to process the mixed type of data. There are several drawbacks in the previous work such as cluster tendency, partitioning, less accuracy and less performance. To overcome all those problems the extended fuzzy adaptive resonance theory (EFART) came into existence which indicates that the usage of fuzzy ART with some traditional approach. This work deals with mixed type of data by applying unsupervised feature learning for achieving the sparse representation to make it easier for clustering algorithms to separate the data. The advantages of extended fuzzy adaptive resonance theory are high accuracy, high performance, good partitioning, and good cluster tendency. This EFART adopts unsupervised feature learning which helps to cluster the large data sets like the teaching assistant evaluation, iris and the wine datasets. Finally, the obtained results may consist of clusters which are formed based on the similarity of their attribute type and values.
Publisher: Horizon Research Publishing Co., Ltd.
Date: 03-2014
Publisher: IntechOpen
Date: 26-07-2022
DOI: 10.5772/INTECHOPEN.106999
Abstract: Health care system, lifestyle, Industrial growth, economy and livelihood of human-beings worldwide effected due to triggered global pandemic by COVID-19 virus originated and first reported from Wuhan city, Republic Country of China. COVID cases are difficult to predict and detect on its early stages due to that its spread and mortality is uncontrollable. RT-PCR (Reverse Transcription Polymerase Chain Reaction) is still first and foremost diagnostic methodology accepted worldwide, hence it creates a scope of new diagnostic tools and techniques of detection approach which can produce effective and faster results compared to its predecessor. Innovational through current studies that complements to the existence of COVID-19 to findings in Chest X-ray snap shots, the proposed research’s method makes use of present deep getting to know models (U-Net and ResNet) to method those snap shots and classify them as the positive patient or the negative patient of COVID-19. The proposed technique entails the pre-treatment phase through dissection of lung, getting rid of the environment which does now no longer provide applicable facts and can provide influenced consequences then after this, preliminary degree comes up with the category version educated below the switch mastering system and in conclusion, consequences are evaluated and interpreted through warmth maps visualization. The proposed research method completed a detection accuracy of COVID-19 round 99%.
Publisher: Hindawi Limited
Date: 07-11-2022
DOI: 10.1155/2022/4578838
Abstract: The healthcare system, lifestyle, industrial growth, economy, and livelihood of human beings worldwide were affected due to the triggered global pandemic by the COVID-19 virus that originated and was first reported in Wuhan city, Republic Country of China. COVID cases are difficult to predict and detect in their early stages, and their spread and mortality are uncontrollable. The reverse transcription polymerase chain reaction (RT-PCR) is still the first and foremost diagnostical methodology accepted worldwide hence, it creates a scope of new diagnostic tools and techniques of detection approach which can produce effective and faster results compared with its predecessor. Innovational through current studies that complement the existence of the novel coronavirus (COVID-19) to findings in the thorax (chest) X-ray imaging, the projected research’s method makes use of present deep learning (DL) models with the integration of various frameworks such as GoogleNet, U-Net, and ResNet50 to novel method those X-ray images and categorize patients as the corona positive (COVID + ve) or the corona negative (COVID -ve). The anticipated technique entails the pretreatment phase through dissection of the lung, getting rid of the environment which does now no longer provide applicable facts and can provide influenced consequences then after this, the preliminary degree comes up with the category version educated below the switch mastering system and in conclusion, consequences are evaluated and interpreted through warmth maps visualization. The proposed research method completed a detection accuracy of COVID-19 at around 99%.
Publisher: Springer Nature Singapore
Date: 2022
Publisher: Emerald
Date: 12-08-2022
Abstract: The present digital world’s challenging issue is COVID-19. This paper is related to the process of the COVID-19 treatment based on age, gender, symptoms and previous health issues. This paper gives the deep discussion about the prevention, symptoms, tests and treatment process. In this research work, the discussion is about vaccine invention and the side effects of the consumed medication. This paper gives a clear explanation of the types of vaccine, which are lopinavir, ritonavir, remdesivir, hydroxychloroquine, chloroquine and plasma therapy. Thereafter, the discussion is prolonged to Indian vaccine for COVID-19. This paper examines some of the COVID-19 treatment processes and difficulties, and finally, this paper aims to summarize and give an overview of the present preclinical research and clinical trials of potential candidates for COVID-19 treatments and vaccines. The required information has been taken from online databases such as PubMed, Science, Nature, PNAS and Cell. Papers included were published between December 2019 and July 2020. The current results indicate the most promising outcomes for dexamethasone as a treatment and vaccine. Further research is needed to identify safe and effective treatments and vaccines for COVID-19.
Publisher: Hindawi Limited
Date: 23-05-2022
DOI: 10.1155/2022/3818107
Abstract: In analysis of data, objects have mostly been characterized by a set of characteristics known as attributes, which together contained only one value for each object. Besides that, a few attributes in reality could include with more than a single value such as from a human beside multiple profession characterizations, practises, communication methods, and capabilities, in addition to shipping addresses, of that kind of attributes are referred to as multivalued attributes and are typically regarded as null attributes when data is processed employing machine learning procedures. Throughout this article, another similarity mechanism is introduced that is defined around including multivalued characteristics which can be used for grouping. We propose a model to analyse each factor’s relative prominence for different data collection challenges in order to enable the selection among the most suited multivalued elements. The suggested methodology is a clustering technique for development and evolution that employs fuzzy c-means clustering and retains the new and more effective membership component by implementing the proposed similarity metric. Clustering of multivalued variables using fuzzy c-means is the efficient grouping criteria that results any methodology to group-related data appears viable. The results show that our assessment not only improves previous segmentation methods on the multivalued cluster-based architecture but also helps in the improvement of the standard similarity metrics.
Publisher: Scientific Research Publishing, Inc.
Date: 2022
Publisher: Hindawi Limited
Date: 18-07-2023
DOI: 10.1155/2023/6490026
Abstract: A smart energy management controller is required for effective source coordination and load demand management. This work proposes a novel instantaneous current reference technique for use in power management of hybrid power systems (HPS), both autonomous and interconnected with the grid. A grid integrated hybrid power system (GI-HPS) includes both the AC grid and additional sources used in industrial and commercial environments. Solar photovoltaic (SPV) panels, wind turbine generators, proton exchange membrane fuel cells, and batteries are all part of the test system. The suggested energy management system (SEMS) manages power from the hybrid power source and the energy storage components to meet the load needs. The recommended SEMS can transit between 12 different modes of operation to fulfil the load demand requirements. The SEMS employs a scaling factor N to accelerate the rate at which the measured current approaches the reference current. The proposed scaling factor significantly improves the SEMS’s dynamic performance since it can quickly respond to the changes in the source and load characteristics. The dependability of an HPS powered by a variety of renewable energy sources can also be improved.
Publisher: Elsevier BV
Date: 2022
Publisher: River Publishers
Date: 05-12-2022
Publisher: Emerald
Date: 07-11-2022
DOI: 10.1108/IJPCC-06-2022-0236
Abstract: A proper understanding of malware characteristics is necessary to protect massive data generated because of the advances in Internet of Things (IoT), big data and the cloud. Because of the encryption techniques used by the attackers, network security experts struggle to develop an efficient malware detection technique. Though few machine learning-based techniques are used by researchers for malware detection, large amounts of data must be processed and detection accuracy needs to be improved for efficient malware detection. Deep learning-based methods have gained significant momentum in recent years for the accurate detection of malware. The purpose of this paper is to create an efficient malware detection system for the IoT using Siamese deep neural networks. In this work, a novel Siamese deep neural network system with an embedding vector is proposed. Siamese systems have generated significant interest because of their capacity to pick up a significant portion of the input. The proposed method is efficient in malware detection in the IoT because it learns from a few records to improve forecasts. The goal is to determine the evolution of malware similarity in emerging domains of technology. The cloud platform is used to perform experiments on the Malimg data set. ResNet50 was pretrained as a component of the subsystem that established embedding. Each system reviews a set of input documents to determine whether they belong to the same family. The results of the experiments show that the proposed method outperforms existing techniques in terms of accuracy and efficiency. The proposed work generates an embedding for each input. Each system examined a collection of data files to determine whether they belonged to the same family. Cosine proximity is also used to estimate the vector similarity in a high-dimensional area.
Publisher: IEEE
Date: 13-10-2022
Publisher: Springer Nature Singapore
Date: 2022
Publisher: Hindawi Limited
Date: 23-09-2022
DOI: 10.1155/2022/7143707
Abstract: Oceans cover more than 75% of the planet’s land surface, making it the most water-rich place on the Earth. We know very little about oceans because of the extraordinary activities that take place in the depths. Underwater wireless sensors are devices that are able to monitor and record the physical and environmental parameters of their surroundings, as well as transmit these data in a continuous manner to one of the source sensors. The network that is formed by the collection of these underwater wireless sensors is referred to as an underwater wireless sensor network (UWSN). The analysis of performance parameters is thought to be most effectively done with this particular technology. In this paper, we will investigate various performance parameters in a random waypoint mobility model by shifting the maximum speed of a node and altering the number of nodes in the model. These parameters include average transmission delay, average jitter, average pathloss, percentage of utilization, and energy consumed in transmit, receive, and idle modes. The QualNet 7.1 simulator is utilized in order to conduct analyses and performance studies.
Publisher: Springer Nature Singapore
Date: 2023
Publisher: Opast Group LLC
Date: 06-07-2022
Abstract: The OMICRON case that tainted human beings become first observed in China towards the end of 2021. From that point, OMICRON has spread practically all nations on the planet. To conquer this issue, it requires a fast work to recognize people tainted with OMICRON all the more rapidly. This research article proposes that RNN techniques to be utilized for rapid detection and predicting of OMICRON infections. RNN is finished utilizing the Elman agency and implemented to the OMICRON dataset gathered from Kaggle. The dataset accommodates of 75% preparing information and 25% analyzing information. The learning boundaries utilized were the most extreme age, secret hubs, and late learning. Results are for this exploration results show the level of precision is 88.28. Oddity is one of the elective conclusions for potential OMICRON illness is Recurrent Neural Network (RNN).
Publisher: Springer Singapore
Date: 2022
Publisher: Hindawi Limited
Date: 09-11-2022
DOI: 10.1155/2022/9418392
Abstract: The planet Earth is the most water-rich place because oceans cover more than 75% of its land area. Because of the extraordinary activities that occur in the depths, we know very little about oceans. Underwater wireless sensors are tools that can continuously transmit data to one of the source sensors while also monitoring and recording the physical and environmental parameters of their surroundings. An underwater wireless sensor network (UWSN) is the name given to the network created by the collection of these underwater wireless sensors. This particular technology is the most efficient way to analyse performance parameters. A network path is chosen to send traffic by using the routing method, a process that is also known as a protocol. The routing protocols ad-hoc on-demand distance vector (AODV), dynamic source routing (DSR), dynamic manet on demand routing protocol (DYMO), location-aided routing 1 (LAR 1), optimized link state routing (OLSR), source-tree adaptive routing optimum routing approach (STAR-ORA), zone routing protocol (ZRP), and STAR-least overhead routing approach (STAR-LORA) are a few models of routing techniques. By changing the number of nodes in the model and the maximum speed of each node, performance parameters such as average transmission delay, average jitter, percentage of utilisation, and power used in transmit and receive modes are explored. The results obtained using QualNet 7.1 simulator suggest the suitability of routing protocols in the UWSN.
Publisher: IEEE
Date: 03-03-2023
Publisher: Auricle Technologies, Pvt., Ltd.
Date: 15-01-2021
Abstract: Lung disease is one of the significant reasons for malignancy related passing because of its forceful nature and postponed discoveries at cutting edge stages. Early discovery of disease would encourage in sparing a huge number of lives over the globe consistently. Lung malignant growth discovery at beginning time has gotten significant and furthermore simple with picture handling and profound learning systems. Lung Cancer side effects are persistent cough, chest torment that deteriorates with profound breathing, roughness, unexplained loss of hunger and weight, coughing up blood or rust-shaded mucus, brevity of breath, bronchitis, pneumonia or different diseases that continue repeating. Lung quiet Computer Tomography (CT) check pictures are utilized to identify and arrange the lung knobs and to recognize the threat level of that knob. Extended Convolutional Neural Networks (ECNN) work achieved relative examination with parameters like precision, time intricacy and elite, lessens computational cost, and works with modest quantity of preparing information is superior to the current framework. consumers.
Publisher: Horizon Research Publishing Co., Ltd.
Date: 04-2014
No related grants have been discovered for Dr. Asadi Srinivasulu.