Conference Presentations by SRIKANTH VEMURU
Springer, 2021
Breast cancer is most common in middle aged female population. It is the fourth most dangerous ca... more Breast cancer is most common in middle aged female population. It is the fourth most dangerous cancer compared to remaining cancers. In recent years breast cancer patients are significantly increasing so, the early diagnosis of cancer has become a necessary task in the cancer research, to facilitate subsequent clinical management of patients. The prevention of the breast cancer tumor is early detection of the tumor. Early detection of cancer can stop increase in tumor and saves lives. In the field of Machine Learning classification cancer patients are classified in to two types as benign or malignant. Different preprocessing techniques like filling missing values , applying correlation coefficient, Synthetic Minority Oversampling Technique (SMOTE) and 10-fold cross validations are implemented and aptly used to obtain the accuracy. The main context of this study is to identify key features from the dataset and analyze the performance evaluation of different machine learning algorithms like Random Forest Classifier, Logistic Regression , Support Vector Machine, Decision Tree, Gaussian Naive Bayes and k Nearest Neighbors. Based on the results of classification model which gives highest accuracy will be used as the best model for cancer prediction.
Papers by SRIKANTH VEMURU
2022 International Conference on Electronics and Renewable Systems (ICEARS)
Brain tumours will be the leading cause of death for about 9 million individuals worldwide in 202... more Brain tumours will be the leading cause of death for about 9 million individuals worldwide in 2020, according to WHO statistics. The most efficient strategy to prevent brain cancer deaths is to detect it early and treat it. A brain tumour is a mass of unusually large cells present in the central nervous system of the brain. People of various ages can be affected by this dangerous tumour. Brain tumours are classified into two types: malignant that are cancerous and benign that are not cancerous. Primary tumours are defined as those that begin in the brain and subsequently spread to other regions of the body, including the brain. Secondary tumours, also known as metastatic tumours, arise from primary tumours. Medical images may now be more easily interpreted to the rapid growth of image processing and soft computing technologies, which aids in early diagnosis and treatment. Because of technological improvements, the use of Computer-Aided Diagnostic (CAD) technologies for disease detection, prognosis prediction, and recurrence likelihood is increasing. This research work provides a brief survey about the feature extraction and tumour cell classification for the automatic detection and classification of brain tumours in MRI images.
In a fast emerging world, and the increasing need of consumers to perform business and financial ... more In a fast emerging world, and the increasing need of consumers to perform business and financial transactions over the mobile device has become inevitable. The mobile payments usage is set to grow exponentially. The mobile payments industry has expeditiously grown as new technologies emerge while security business needs financial institutions to acknowledge. The objective of this paper is to impart the consumer an NFC-enabled mobile payment system with enhanced security measures touching consumer transaction and the mobile device. Our proposed hybrid approach has key capabilities to its security framework serving as tokenization based payment method and authentication of the user & device both together with the use of Host Card Emulation cloud-based secure element which will provide flawless mobile payment knowledge for the consumer
Revista Gestão Inovação e Tecnologias, 2021
Feature selection approaches are used to improve the efficiency of the clinical databases in the ... more Feature selection approaches are used to improve the efficiency of the clinical databases in the machine learning classification. Since, most of the conventional feature selection and classification approaches are difficult to handle high dimensionality for pattern evaluation. Also these models are difficult to filter noise on different heterogeneous features. In this work, a hybrid data transformation and outlier detection methods are developed on the clinical databases to improve the classification accuracy. Experimental results show that the present model has better accuracy in evaluating the accuracy than the conventional models on clinical databases.
i-manager's Journal on Information Technology, 2012
Breast cancer is most common in middle aged female population. It is the fourth most dangerous ca... more Breast cancer is most common in middle aged female population. It is the fourth most dangerous cancer compared to remaining cancers. In recent years breast cancer patients are significantly increasing so, the early diagnosis of cancer has become a necessary task in the cancer research, to facilitate subsequent clinical management of patients. The prevention of the breast cancer tumor is early detection of the tumor. Early detection of cancer can stop increase in tumor and saves lives. In the field of Machine Learning classification cancer patients are classified in to two types as benign or malignant. Different preprocessing techniques like filling missing values , applying correlation coefficient, Synthetic Minority Oversampling Technique (SMOTE) and 10-fold cross validations are implemented and aptly used to obtain the accuracy. The main context of this study is to identify key features from the dataset and analyze the performance evaluation of different machine learning algorithms like Random Forest Classifier, Logistic Regression , Support Vector Machine, Decision Tree, Gaussian Naive Bayes and k Nearest Neighbors. Based on the results of classification model which gives highest accuracy will be used as the best model for cancer prediction.
Biomedical Engineering: Applications, Basis and Communications
Recently, there is an immense increase in the mortality rate of humans due to dangerous diseases,... more Recently, there is an immense increase in the mortality rate of humans due to dangerous diseases, which is becoming a greater issue across the globe. The only solution to this issue is the early detection of infectious diseases, so that the seriousness of their symptoms can be reduced before reaching an adverse stage. In recent days, associative rule mining, which is a computational insight strategy is being more commonly utilized for early risk prediction of the disease. In the case of rule mining, there is a massive count of the frequent patterns that might deviate from the detection mechanism. Therefore, different customized algorithms are being implemented. Among them, the Apriori algorithm is a standardized model which is good in detecting the more frequent patterns. But, owing to a huge count of candidates as well as scans of the database, the ties technique has become inefficient. Therefore, to override these issues and to find a promising solution for the early disease predi...
Opportunistic accessing of authorized spectrum by the Cognitive User's (CU's) without int... more Opportunistic accessing of authorized spectrum by the Cognitive User's (CU's) without interfering with the Licensed User's (LU's), this model enhances the utility of the accessible assigned spectrum bands, henceforth as it was only 6% of total licensed spectrum are currently being utilizing rest of the spectrum was completely misused. The raising interest in Cognitive Radio's (CR's) and in their applications additionally enhances the desire to construct Energy-Efficient CR (EECR) since it was a rising innovation what's more, to take care without bounds. Demand of CR's aim's the Ad-hoc structure of transmission, where power utilization is the significant issue in Ad hoc gadgets. Presently, there was a need to develop EE MAC protocol for CR Mesh Network. The proposed strategy of opportunistic spectrum radio access without making interference for the LU actions is taken into the consideration and engaged as the fundamental thought of this overview. C...
ABSTRACT-Next generation wireless communications will likely rely on integrated networks consisti... more ABSTRACT-Next generation wireless communications will likely rely on integrated networks consisting of multiple wireless technologies. Hybrid networks based, for instance, on systems such as WMAN and WLAN can combine their respective advantages on coverage and data rates. WLAN is provided in hotspots, places like coffee bars, airports, shopping centers etc. where the hotspots are covered by access points. As the mobile node moves, it may leave the current wireless network and enter another wireless network; vertical handoff should be taken to the new network so as to maintain the current connection. Existing methods require more time for the vertical handoff process, which causes serious problems for multimedia applications. Vertical handoff delay should be minimum to have seamless vertical handoff communication. To achieve seamless handoff communication a Layer2 handoff method is proposed. In this method, a mobile with two radios of dualmode capability, and WLAN having the extended...
Lecture Notes in Electrical Engineering, 2018
Mobile ad hoc network (MANET) consists of mobile nodes that communicate with one another through ... more Mobile ad hoc network (MANET) consists of mobile nodes that communicate with one another through radio communication channel. This wireless channel is vulnerable to security attacks. Thus, MANET needs a perfect security mechanism to secure network from security attacks. In literature, different security mechanisms have been designed to solve the security issues via cryptographic techniques. Security mechanisms should not cause overhead to MANET in terms of computation and storage, as this network is resource constrained. Thus, in this work, we compare the performance of cryptographic solutions that designed for MANET based on RSA and Chaotic maps. Performance results show that RSA is one of the best cryptographic algorithms to provide security, but its time complexity is more than the Chaotic Maps-based cryptography technique. Moreover, time complexity causes a negative impact on overall network performance; particularly end-to-end delay. We conclude from our work, Chaotic Maps-base...
Journal of Pharmaceutical Research International
Background: Phytocompounds in medicinal plants have a wide range of properties and are alternativ... more Background: Phytocompounds in medicinal plants have a wide range of properties and are alternative medicines for those who cannot be helped by conventional medicine. Objective: In this work we have selected bioactive compounds from Hemidesmus indicus medicinal plant extracts. Methods: Gas chromatography and Mass spectrum studies were studied to identify the compounds present in the ethanolic extracts based on the retention time and area. Results: The identified compounds were used for anti-cancer activity by insilico method with BCL-2 which plays prominent role in causing cancer. Conclusion: Out of twenty selected compounds, docking results showedMethyl-1-Cyclohexane carboxylate and 1,2-diacetoxy-5-idohexane as best docked to the BCL-2.
Malicious software (malware) plays a vital role in cybercrime security. As the number of maliciou... more Malicious software (malware) plays a vital role in cybercrime security. As the number of malicious attacks and its target sources is increasing, it is difficult to find and prevent the attack due to its change in behaviour. Most of the traditional malware detection models are based on the statistical, analytical, and machine learning models. Detection of malware usually utilizes virus signature methods to defend against malicious software. Most antivirus tools to categorize malware depend on regular expression and pattern. Antivirus is less likely to update their databases to detect and prevent malware as file features have to update a newly created malware. The practically maximum human effort was required in order to generate attack signatures. In this paper, different types of malware detection models and their problems are discussed. This paper provides an extensive survey on the malware attack detection using traditional supervised, unsupervised models. Different types of malwa...
Cognitive radios (CRs) are the nearly novel innovation in which issues such as under-utilization ... more Cognitive radios (CRs) are the nearly novel innovation in which issues such as under-utilization of spectrum and shortage of spectrum is comprehended in light of the progressive thoughts. Intellectual radio permits gathering of clients to recognize and entrance for accessible spectrum assets for utilizing ideally. Late learning demonstrates that the vast majority of the selected spectrum was under-utilized. Then again, the expanding number of remote sight and sound applications prompts a spectrum shortage. CRs are proposed as a capable innovation for tackling the awkwardness among spectrum shortage and spectrum under-utilization. In CRs, spectrum detecting was completed by keeping that in mind at the end of the goal to find the idle spectrum sections. This manuscript demonstrates that quality & capacities of CRs procedures and makes that all the extra intense more than the other focused radio. Anxiety is specified on appliance zones, where CR procedures are executed and demonstrated...
Mobile ad hoc network design’s goal is to provide Internet connectivity anywhere and anytime rega... more Mobile ad hoc network design’s goal is to provide Internet connectivity anywhere and anytime regardless of geographical location. Application of MANET includes disaster recovery, military, and environment monitoring. Resource-constrained environment of MANET makes its communication operations very much challenging. Moreover, network nodes are equipped with constrained batteries and it is much tough to replace or recharge the batteries during the mission. Thus, MANET requires an energy-efficient mechanism to address the constraints. We are achieving the energy efficiency through network layer, as MANET is infrastructureless peer-to-peer network. We develop a new reactive energy-efficient routing protocol based on knapsack mechanism. It selects the routing path based on the current residual condition of network nodes. Simulation results conclude that our proposed method is better in comparison with the existing works E-AODV, MRPC with respect to network lifetime and link stability.
2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA), 2017
Wireless sensor networks have emerged as a promising technology in last few years, that encouragi... more Wireless sensor networks have emerged as a promising technology in last few years, that encouraging a deep innovation in the field of structural monitoring. The main benefits of wireless sensor networks are little interference, self-organization and fast deployment. Structural Health Monitoring (SHM) implements a detection of damages and characterization strategy for engineering structures. For railway track main concern regarding SHM are alignment of tracks, formation of crack, corrosion of tracks material, deformation of tracks and missing tracks. In current scenario Structural health monitoring of railway track is done using various methods like oral communication through telephone, wired sensor network deployed over railway tracks, through GPS communication technology but response time of these methods is high. This proposed method aims to implement Wireless Sensor Network (WSN) for Structural Health Monitoring (SHM) of railway tracks. This prototype will enhance the response ti...
Feature selection techniques play a vital role in the real-time medical databases. Since, most of... more Feature selection techniques play a vital role in the real-time medical databases. Since, most of the medical databases contain high dimensionality and large data size, it is difficult to find an essential key feature using traditional feature sub-set selection approaches. Also, conventional medical data filtering techniques fail to find the essential outliers due to large data size and feature space. In this work, a hybrid outlier detection and data transformation approaches are implemented to remove the noise in the medical databases. Proposed data filtering module is applicable to high dimensional data size and feature space for classification problem. Experimental results are simulated on different medical datasets such as tonsil and trauma databases with different feature space size and data size. Simulation results proved that the proposed outlier detection approach has better noise detection rate than the conventional approaches.
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 2021
Disease prediction plays a significant role in the life of people, as predicting the threat of di... more Disease prediction plays a significant role in the life of people, as predicting the threat of diseases is necessary for citizens to live life in a healthy manner. The current development of data mining schemes has offered several systems that concern on disease prediction. Even though the disease prediction system includes more advantages, there are still many challenges that might limit its realistic use, such as the efficiency of prediction and information protection. This paper intends to develop an improved disease prediction model, which includes three phases: Weighted Coalesce rule generation, Optimized feature extraction, and Classification. At first, Coalesce rule generation is carried out after data transformation that involves normalization and sequential labeling. Here, rule generation is done based on the weights (priority level) assigned for each attribute by the expert. The support of each rule is multiplied with the proposed weighted function, and the resultant weigh...
First International Conference on Sustainable Technologies for Computational Intelligence, 2019
CRWMN is an emerging method which makes efficient utilization of spectrum by allocating opportuni... more CRWMN is an emerging method which makes efficient utilization of spectrum by allocating opportunistically, within the Industrial-Scientific-Medical (ISM) bands or licensed bands. Enthusiasm for the improvement of cognitive radio wireless mesh network is a result of utilizing under-usage of spectrum by the licensed users, by permitting unlicensed user to utilize. The main aim of CR in WMN is to encourage the unlicensed users for utilizing the licensed spectrum without affecting the licensed user’s communication. In this paper, a MAC protocol was developed for allocating spectrum opportunistically. Additionally, an in-depth experimental analysis was performed on the proposed MAC to validate the efficiency of the proposed protocol. As a result, we allocate spectrum opportunistically by focusing on reducing access delay, interference, and hidden terminal problems and also it enhanced the throughput.
Since the evolution of m-commerce, security and entrustment of digitized transactions have become... more Since the evolution of m-commerce, security and entrustment of digitized transactions have become of captious concern to financial institutions. Card information hacking has caused money losses around the world, therefore it is imperative for financial institutions to get rid of such losses. Currently, the number of mobile payment schemes have been purposed but primarily the schemes aim attention at transaction security, fraud detection and prevention, not on data at rest encryption in mobile payments. Therefore, this work aims attention to encrypt sensitive static data residing at database server in mobile payments. Data at rest is the static data i.e., card details of the users which resides at the server. It is essential to ensure that the sensitive data of the payment users stay protected so as to prevent the adversaries looking for unauthorized access to the data. The encryption of data at rest is accomplished at the database level in this work. Cryptography is increasingly bei...
Uploads
Conference Presentations by SRIKANTH VEMURU
Papers by SRIKANTH VEMURU