Browse Items (11810 total)
Sort by:
-
Oral cancer analysis using machine learning techniques
Oral cancer staging is most required task of examining treatment and required medication for the patients. In oral cancer staging is of two types, namely, clinical and pathological. TNM (Tumor, Node, and Metastasis) staging is clinical system of predicting oral cancer stages, on the other hand Histology, p63 and podoplanin expressions are pathological staging system which is obtained after biopsy test. These staging systems are used in machine leaning techniques to analyze the different stages of oral cancer. The main aim of the paper is to classify different stages of oral cancer using machine learning techniques. The experimental work is based on clinical and pathological staging system. The data set used for this research work is based on Oral Leukoplakia. The data transformation is applied to standardize the data and the features were extracted using correlation coefficient. The extracted features were classified using Decision tree and random forest which are compared against other popular classification methods like SVM, KNN, MLP and Logistic Regression. From the experimental work, it is found that the various stage classification of oral cancer can be classified efficiently with help of Random Forest and Decision Tree. So the classification of various oral cancers can be performed with help of random forest and Decision Tree. International Research Publication House. -
An objective function based technique for devignetting fundus imagery using MST
Fundus photography is a powerful imaging modality that is utilized for detecting macular degeneration, retinal neoplasms, choroid disturbances, glaucoma and diabetic retinopathy. As the illumination source in fundus imaging is situated at the center of the fundus camera, the illumination at the peripheral regions of the images would be relatively less than the center, which is termed vignetting. Vignetting adversely affects the performance of computerized methods for analyzing fundus imagery. A devignetting method for fundus imagery based on the Modified Sigmoid Transform (MST) is proposed in this paper. Gain (A) and centering parameter (?) of MST have a crucial influence on its performance. For low values of the gain, local contrast is penalized, and the overall dynamic range is compressed. When the value of gain is very high, the images after the illumination correction will have a washed out appearance. The optimum value of gain is determined in this paper from an objective method based on two statistical indices, Average Gradient of Illumination Component (AGIC) and Error of Enhancement (EME). MST with gain value defined via objective methods is able to correct the uneven illumination in fundus images without penalizing the local contrast. The proposed method is compared with illumination equalization model, homomorphic filtering and Adaptive Gamma Correction (AGC) and was found to be superior in terms of naturality uniformity of background illumination, and computational speed. 2018 -
Formant frequency estimation of artificial larynx transducer speech using recurrent neural network
Human Beings communicate with each other by speaking. The speech as a signal has 2 components voiced and unvoiced speech. Voiced speech is produced by the excitation produced at glottis and unvoiced is produced by noise created at the mouth. The voiced components that is produced at glottis passes through the vocal tract and then reach the mouth. The nature of the speech is determined mostly at the vocal tract. But for some reason for some people the speech produced is not proper because of the organ problems or motor disorder issue. In these cases, the speech produced is called disordered speech and termed with the names like stammering, apraxia, dysar-theria and so on. In some case, the larynx is removed from human body because of cancer or other issues. For them, Artificial Larynx Transducer (ALT) is given to produce substitution voice. This paper aims at formant frequency estimation of the speech produced with the help of ALT using Recurrent Neural Network (RNN) method. The speech produced with the help of ALT will lack in naturalness and intelligibility. The direct noise coming from ALT device is called DREL noise. This also creates irritability to the listener. So in this paper, a method is proposed for the DREL noise removal and formant frequency estimation of the ALT speech. 2019, Institute of Advanced Scientific Research, Inc.. All rights reserved. -
A unique adventure - unity based 3D game
The number of gamers are increasing day by day and as a result the gaming industry has seen a huge growth. There was a curiosity to get the in-depth detail so as to how a game is developed. The final year project was a great opportunity to explore this field and to make something that would be fun as well as useful. The proposed work gives the detailed description about the entire process of game development. A game is created with three different levels. Each level comes with a particular set of objectives. The objectives of each level need to be attained in order to proceed to the next level. The environment in the game resembles the Christ Kengeri campus. For that, 3D model of Christ Kengeri campus is designed. 3D modeling is done in Unity and Blender software platform. A* is the search algorithm that has been used for pathfinding. The languages that Unity uses to operate with are objectoriented scripting languages. Scripting languages have its own syntax and the primary parts are called functions, variables and classes. Also each level has its own coding and is not linked with any other. In each level a new character is introduced. 2019, Institute of Advanced Scientific Research, Inc. All rights reserved. -
Dynamics of magneto-nano third-grade fluid with brownian motion and thermophoresis effects in the pressure type die
The non-transient dynamics of the non-Newtonian third-grade liquid driven by pressure type die in the presence of nanoparticles is studied. The fluid is dissipating and its properties are taken as unvarying. The governing partial differential equations system is developed and they are numerically solved after non-dimensionalization. The significance of pertinent parameters on flow fields is analyzed and discussed. The thermal field shows dual behaviour in the flow domain due to the impact of magnetism, Brownian motion and thermophoresis. 2019 by American Scientific Publishers All rights reserved. -
A pragmatic study on heuristic algorithms for prediction and analysis of crime using social media data
Advancement in technology and Social media has grown to become one amongst the foremost powerful communication channels in human history and this is where individuals are sharing their perspectives, thoughts, suppositions, and feelings. Law enforcement units are having hard time fighting crime with evergrowing population, regional issues and political con-sequences. The adoption of social media data for crime analysis is increasing day by day. Crime analysis can help use the resources wisely. A crime prediction alerts the department at the right time to focus their staff with better equipment in suspected areas. Crime analysis prevents threats to life and money loss in terms of damage. In recent days, the collection of crime data from different heterogeneous sources becomes a primary step for the crime analysis and prediction. In this paper Overview of Heuristic Based Crime Prediction and Analysis algorithms identified by different authors. Also, various sources of social media used for analysis and prediction are also reviewed in detail. This information can be considered for one of the prominent asset for crime investigation through social media data procedure and also, we had identified the different algorithms and research gaps of that algorithms with related to crime analysis and prediction. 2019, Institute of Advanced Scientific Research, Inc. All rights reserved. -
Imperative of revisiting the operational risk control architecture in public sector banks cyjdf (PSBs) in India: A qualitative analysis
The banking sector in India has contributed to economic growth, parity and equity while equally keeping focus on profit and social objectives. The successive prudential and regulatory reforms introduced in the banking sector have made it more robust and stronger to withstand the bubbles and external shocks. Still, the Indian banking sector in general and public-sector banks (PSBs) in particular have been suffering from the bank frauds. This study endeavors to cover the increasing incidences of banking frauds in PSBs and probes the weaknesses and chinks in the operational risk architecture at the PSBs in India. This study selects Punjab National Bank as a true representative of PSBs and treats it as a critical case study to apply the learning and findings to the PSBs in India. This qualitative analysis of the study revealed that the chinks in the operational risk control mechanism and lax corporate governance are the main reasons behind the increasing incidences of frauds at PSBs. The findings of the study showed that a strong corporate governance and compliance framework, robust risk management architecture, investment in people, technology and systems will go a long way in achieving tighter control and supervision, streamlining processes and, most of all, adhering to a culture of checks and balances. 2019 LLC CPC Business Perspectives. All Rights Reserved. -
IOT based application for monitoring electricity power consumption in home appliances
Internet of Things is one of the emerging techniques that help in bridging the gap between the physical and cyber world. In the Internet of Things, the different smart objects connected, communicate with each other, data is gathered from the smart objects and based on the need of the users, and the data gathered are queried and sent back to the user. IoT helps in monitoring electrical and physical parameters. Electricity consumption from electronic devices is one among such parameters that need to be monitored. The development of energy efficient schemes for the IoT is a challenging issue as the IoT becomes more complex due to its large scale the current techniques of wireless sensor networks cannot be applied directly to the IoT. To achieve the green networked IoT, this paper proposes a Wi-Fi enabled simple low cost electricity monitoring device that can monitor the electricity consumption on home appliances which helps to analyses the consumption of electricity on a daily and weekly basis. Copyright 2019 Institute of Advanced Engineering and Science. All rights reserved. -
Fusion model of wavelet transform and adaptive neuro fuzzy inference system for stock market prediction
Stock market prediction is one of the most important financial subjects that have drawn researchers attention for many years. Several factors affecting the stock market make stock market forecasting highly complicated and a difficult task. The successful prediction of a stock market may promise attractive benefits. Various data mining methods such as artificial neural network (ANN), fuzzy system (FS), and adaptive neuro-fuzzy inference system (ANFIS) etc are being widely used for predicting stock prices. The goal of this paper is to find out an efficient soft computing technique for stock prediction. In this paper, time series prediction model of closing price via fusion of wavelet-adaptive network-based fuzzy inference system (WANFIS) is formulated, which is capable of predicting stock market. The data used in this study were collected from the internet sources. The fusion forecasting model uses the discrete wavelet transform (DWT) to decompose the financial time series data. The obtained approximation and detailed coefficients after decomposition of the original time series data are used as input variables of ANFIS to forecast the closing stock prices. The proposed model is applied on four different companies previous data such as opening price, lowest price, highest price and total volume share traded. The day end closing price of stock is the outcome of WANFIS model. Numerical illustration is provided to demonstrate the efficiency of the proposed model and is compared with the existing techniques namely ANN and hybrid of ANN and wavelet to prove its effectiveness. The experimental results reveal that the proposed fusion model achieves better forecasting accuracy than either of the models used separately. From the results, it is suggested that the fusion model WANFIS provides a promising alternative for stock market prediction and can be a useful tool for practitioners and economists dealing with the prediction of stock market. 2019, Springer-Verlag GmbH Germany, part of Springer Nature. -
Workplace diversity and inclusion: Policies and best practices for organisations employing transgender people in India
Policies and best practices are suggested based on the viewpoints of transgender employees, human resources managers in charge of diversity and inclusion, and activists who work for the welfare of transgender people. Fifteen people were interviewed in depth and their responses were analysed to obtain insights into transgender employees' perception of well-being in the workplace, which will help organisations to develop appropriate human resource policies to protect the rights of their transgender employees in the workplace. Copyright 2019 Inderscience Enterprises Ltd. -
On the zero forcing number of graphs and their splitting graphs
In [10], the notion of the splitting graph of a graph was introduced. In this paper we compute the zero forcing number of the splitting graph of a graph and also obtain some bounds besides finding the exact value of this parameter. We prove for any connected graph ? of order n ? 2, Z[S(?)] ? 2Z(?) and also obtain many classes of graph in which Z[S(?)] = 2Z(?). Further, we show some classes of graphs in which Z[S(?)] < 2Z(?). Journal Algebra and Discrete Mathematics. -
Selection of Tightened-Normal-Tightened sampling scheme under the implications of intervened Poisson distribution
Tightened-normal-tightened (TNT) sampling scheme is one of the most frequently used sampling schemes for making decisions about the finished product lots by examining certain samples from the lots. TNT sampling scheme includes two attribute sampling plans, one for tightened inspection and other for normal inspection along with switching rules. This paper introduces a procedure for TNT by incorporating two single sampling plans (SSP) under the conditions of intervened Poisson distribution (IPD) for the lots which may have a possibility of someintervention during the production process. The paper also assesses the performance of the proposed scheme procedure through its operating characteristic curves. Also, the unity value table is provided for certain parameters of specified producer's risk and consumer's risk for shop floor conditions. Further, the efficiency of proposed TNT scheme over the individual SSP under the conditions of IPD is demonstrated with illustrations. 2019 University of the Punjab. -
Nanosheets of nickel, cobalt and manganese triple hydroxides/oxyhydroxides as efficient electrode materials for asymmetrical supercapacitors
Transition metals play a significant role in energy storage applications mainly as electrode materials in supercapacitors. In this work, triple hydroxide/oxyhydroxide nanosheets of a nickel, cobalt and manganese (NCM) composite were electrochemically deposited on carbon cloth (CC) and used as electrode materials in supercapacitors. In a three electrode system the composite delivered a specific capacitance of 707 F g -1 at a current density of 3 A g -1 which retained its stability even at a higher current density of 50 A g -1 . An asymmetric supercapacitor (ASC) was assembled and characterized using NCM as the positive electrode, activated carbon as the negative electrode and Whatman filter paper soaked in KOH as the separator. The device operated in a working potential window of 1.75 V and it delivered a power density of 13.12 kW kg -1 and an energy density of 23.7 W h kg -1 . 2019 The Royal Society of Chemistry. -
Power law in tails of bourse volatility evidence from India
Inverse cubic law has been an established Econophysics law. However, it has been only carried out on the distribution tails of the log returns of different asset classes (stocks, commodities, etc.). Financial Reynolds number, an Econophysics proxy for bourse volatility has been tested here with Hill estimator to find similar outcome. The Tail exponent or ? ? 3, is found to be well outside the Levy regime (0 < ? < 2). This confirms that asymptotic decay pattern for the cumulative distribution in fat tails following inverse cubic law. Hence, volatility like stock returns also follow inverse cubic law, thus stay way outside the Levy regime. This piece of work finds the volatility proxy (econophysical) to be following asymptotic decay with tail exponent or ? ? 3, or, in simple terms, inverse cubic law. Risk (volatility proxy) and return (log returns) being two inseparable components of quantitative finance have been found to follow the similar law as well. Hence, inverse cubic law truly becomes universal in quantitative finance. Bikramaditya Ghosh, M. C. Krishna, 2019. -
Drinking straw from coconut leaf: A study of its epicuticular wax content and phenol extrusion properties
Background and Objectives: Plastics are a ubiquitous part of our daily life but now posing a major threat to marine life, animal and human health. More than 50% of the manufactured plastic including straws are being disposed of after single-use. There is an increasing need to mitigate this trend so that the damage could be brought under control. The aim of this research was to develop a compostable, eco-friendly alternative to plastic straws using the leaves of Cocos nucifera L. Materials and Methods: The biochemical properties of 6 varieties of Cocos nucifera L. leaflets were studied in order to screen the most suitable material for making sustainable straws. Epicuticular wax content was analyzed to choose the best variety for preparation of hydrophobic straws. Total antioxidant activity, total tannin content, phenolic and flavonoid content were assayed to evaluate the potential functionality of the leaflets. The phenol extrusion properties of the material were also checked in acidic and normal beverages. Results: Estimation of epicuticular wax and phytochemical analysis in all 6 varieties revealed that all varieties of Cocos nucifera L. leaves provide a potent biomaterial for straw preparation. Silicon 732 was found to be a good adhesive agent for straw preparation. Phenol extrusion assays revealed that there is a negligible difference in the release of phytochemicals before and after dipping of straws in the beverages. Conclusion: The outcome of this research opens up vistas to carry out further research in a hitherto unexplored area of utilizing the leaf of Cocos nucifera in a novel way with far reaching economic and employment implications. 2019 Jyoti Jeena James et al. -
IoT based heart monitoring and alerting system with cloud computing and managing the traffic for an ambulance in India
Global Burden of Disease Report, released in Sept 2017, shows that Cardiovascular Diseases caused 1.7 million deaths (17.8%) in 2016 and it is the leading cause of deaths in India [1]. According to the Indian Heart Association, 25% of all heart attacks happen under the age of 40. In most cases, the initial heart attacks are often ignored. Even post-diagnosis, as per government data [2], 50% of heart attack cases reach the hospital in more than 400 minutes against the ideal window time of 180 minutes; post which damage is irreversible. The delay is often attributed to delay in reaching a hospital or receiving primary aid. In India, traffic conditions also add to the grimace of the situation. Although the government is taking various measures; a holistic solution is required to minimize the delay at each of the steps like accessing the patient situation, contacting the Medical aid or making available the nearest aid possible. In this paper, we aim at providing the holistic solution using the Internet of Things technology (IOT) along with data analytics. IoT enables real-time capturing and computation of medical data from smart sensors built-in wearable devices. The amalgamation of Internet-based services with Medical Things (Smart sensors) enhance the chances of survival of patients. The proposed system analyses the inputs collected from the sensors fit with the patients prone to cardiovascular diseases to ascertain the emergency situation. In addition, to these data, the system also considers age, maximum and minimum heart rate. Based on computational results received from the input parameters, the system triggers the alert to emergency contacts such as the close relatives of the patient, doctors, the hospitals and nearby ambulance. The proposed system combines with the optimized navigation platform to guide the medical assistance to find the fastest route. Copyright 2019 Institute of Advanced Engineering and Science. All rights reserved. -
An empirical analysis of similarity measures for unstructured data
With fast growth in size of digital text documents over internet and digital repositories, the pools of digital document is piling up day by day. Due to this digital revolution and growth, an efficient and effective technique is required to handle such an enormous amount of data. It is extremely important to understand the documents properly to mine them. To find coherence among documents text similarity measurement pays a humongous role. The goal of similarity computation is to identify cohesion among text documents and to make the text ready for the required applications such as document organization, plagiarism detection, query matching etc. This task is one of the most fundamental task in the area of information retrieval, information extraction, document organization, plagiarism detection and text mining problems. But effectiveness of document clustering is highly dependent on this task. In this paper four similarity measures are implemented and their descriptive statistics is compared. The results are found to be satisfactory. Graphs are drawn for visualization of results. 2019 COMPUSOFT, An international journal of advanced computer technology. -
Experimenting with scalability of Beacon controller in software defined network
In traditional network, a developer cannot develop software programs to control the behavior of the network switches due to closed vendor specific configuration scripts. In order to bring out innovations and to make the switches programmable a new network architecture must be developed. This led to a new concept of Software Defined Networking(SDN). In Software defined networking architecture, the control plane is detached from the data plane of a switch. The controller is implemented using the control plane which takes the heavy lift of all the requests of the network. Few of the controllers used in SDN are Floodlight, Ryu, Beacon, Open Daylight etc. In this paper, authors are evaluating the performance of Beacon controller using scalability parameter on network emulation tool Mininet and IPERF. The experiments are performed on multiple scenarios of topology size range from 50 to 1000 nodes and further analyzing the controller performance. BEIESP. -
An overlap-based human gait cycle detection
Identification of a person by his/her style of walking is referred as gait recognition. Gait is one among the biometric used for human identification. In gait recognition, an inevitable step for accurate feature extraction is gait cycle detection. In this paper, a novel gait cycle detection algorithm based on the concept of overlap between legs during locomotion is proposed. To identify overlap, zero-crossing counts of silhouette frames as well as bottom halves of silhouette frames are considered. The efficiency of this algorithm is tested using normal walking sequence of subjects with 90 viewing angle from CASIA B as well as TUM-IITKGP human gait databases. The results obtained shows that gait cycle can be easily and efficiently detected with zero-crossing count of silhouette frames. Further zero-crossing counts taken from bottom halves of silhouette frames gives better performance. Copyright 2019 Inderscience Enterprises Ltd. -
Effect of variable viscosity on marangoni convective boundary layer flow of nanofluid in the presence of mixed convection
The effect of variable viscosity on Marangoni convection in immediate vicinity of the plate is discussed. The mathematical model of the problem is highly nonlinear partial differential equations transforms into two nonlinear ordinary differential equations by applying suitable similarity transformations. The reduced similarity equivalences are then solved numerically by RungeKutta Fehlberg-45 order method. The consequences of pertinent parameters like variable viscosity parameter, convection parameter and volume fraction are analyzed on various flow fields. The results acquired are on par with erstwhile published results. The results of the present study shows that for greater values of angular momentum the buoyancy effects dominate, augmentation in mixed convection carries away the free convection currents from the plate, increase in volume fraction of solid enhances the thermal conductivity of the fluid and it is important to note that Marangoni effect is constructive for cooling processes. 2019 by American Scientific Publishers All rights reserved.