Search

Good revenue has to be generated to run a company. Company needs data to segregate their customers to forecast their product sales or profits they wish to get. Proper decisions need to be taken by evaluating the data from their database. Paper work of grouping customers is a huge task and it is unsure about the accuracy of the results. After the introduction of Machine Learning, techniques in it are being used widely in various areas to uplift the accuracy of the outcomes and to find a better way of evaluation in every area. Here, customer segmentation using K-Means clustering helps in grouping the customers with the similar traits that helps to business in a better way. The elbow method applied here helps in finding the optimal number of clusters to be visualized.

With the advancement of color printing technology, fake currency note printing and duplicating the notes have been increasing rapidly on a vast scale. A few years ago, the printing was done in a print house, but now anybody with a simple laser can print a currency note with maximum accuracy. This may result in hyperinflation and may affect the citizens and the government mainly if not controlled at the earliest. So, we have come up with a system that detects fake currency in less time and efficiency. We use Vgg-16 (CNN) architecture. This model is trained to detect the presence of watermark and uv strips. After checking the note’s authenticity, it even displays the accuracy percentage. The data sets used here are created on our own by gathering the pics of fake and real currencies. We use concepts of image processing, tensor flow to read the image and make the machine learn. This system gives high-performance speed and works efficiently. The performance of a model is based upon the metrics such as accuracy, precision etc. This project is mainly used for detection of fake currency.

Human-computer interaction is a potential area of interest since the birth of the computer era. The chapter highlights the usage of electroencephalogram (EEG wave) signals to initiate a conveying medium for immobilized persons, who are not able to express their feelings, by the use of human brain waves or signals. In order to recognize the human feelings or expressions with some emotion by an disable persons, a classifier based on a gamma distribution is utilized. The characteristic of the human brain waves are extracted with the usage of cepstral coefficients. The extracted characteristic is classified into various emotion states using generalized gamma distribution. In order to experiment the proposed model, six healthy persons or subjects are taken aged between from 20 and 28, and a 64 electrode channel EEG system is considered to gather the EEG brain signals under audio as well as visual stimuli. In this chapter, the authors focused the study on four basic human emotions: boredom, sad, happy, and neutral.

4H-SiC Schottky photodetector array was fabricated by pulsed dc sputter deposition of palladium thin film as UV semitransparent Schottky contact on active pixel. Results of electro-optical characterization of these devices as a function of temperature varying from 33 to 393 K are presented. A peak spectral responsivity of 122 mAW−1 at 280 nm is observed. Further, spatial response uniformity for a 4 mm $\times4$ mm detector, scanned by UV spot of $100~\mu \text{m}$ diameter, is within ±5%, whereas the crosstalk between the pixels in $4\times 2$ detector array with a pixel size of $850\,\,\mu \text{m}\,\,\times 850\,\,\mu \text{m}$ is within 1.3%. Capacitance at near zero bias is around 11 pF and 4.79 pF at a reverse bias of 30 V. From the ${I}$ – ${V}$ characteristics, the calculated Schottky barrier height is 1.37 eV for 70 A thick palladium metal film on 4H-SiC as against the theoretical value of 1.96 eV. Operating temperature studies on detector UV response at 300 nm have shown that the photo-current response at 113 K falls to half of its peak value at ambient. The responsivity of the detectors at 248-nm wavelength is almost constant over a wide temperature range of 33 to 393 K.

The world we live in today is fully synchronized with the data being generated every second using cloud. One such company that delivers cloud services is “Salesforce.” Salesforce is a cloud-based software organization providing Customer-Relationship Management (CRM) services. This paper proposes the case escalation concept and how it can solve the issue mentioned by the customers in the specified time. Case Escalation, also known as Issue Resolution Process, is done when an issue reported by the customer is left unresolved. This mechanism will be crystal clear when a sample of data is taken. The data project the issues arriving at a pediatric hospital with different departments. An interesting feature of Salesforce will take a big hand in this application to resolve a problem regarding the purchase of licenses for each and every manager in each department, on a whole containing more than 50 departments. This feature helps to provide access of the application to the managers, executives, directors, president, vice president, to solve the case without having a licensed account on Salesforce. The cases will be solved depending on its priority whether high, moderate or low. This paper also defines the outline of stimulating traits for further improvements.

E-learning is one of the modes of learning which is gaining popularity nowadays. To analyze the effectiveness of the E-class, there are many ways like feedback at the end of the lecture. But analyzing at the end will not serve the purpose. By analyzing the feedback of the listeners during the class improves the quality of the E-class. This can be achieved by analyzing the face and acoustics of the listeners. In a few cases, the data may not be obtained from both modalities. So, a novel method is proposed which will continue to perform and successfully recognize emotions even when one modality is absent. Product trends can be predicted by using this model for market analysis and ads can be improvised to reach their end target. Thereby, the manufacturers will receive relevant and better product feedback which leads to a rise in product sales. Studying how users view these multimodal posts will be of interest to sociologists and psychologists. The suggested project will provide a platform for publishing research papers in reputed journals, provides an opportunity for manpower training.

Automatic Speaker Verification (ASV) systems are mostly being used for authentication of a known identity based on different voice features. The ASV involves a comparison of a speaker's voice with pre-stored training data or speaker model captured during the enrolment phase and also with an impersonator model of non-identical voices differing in gender as well as phone types. Thereafter, a score is assigned by the system and decides whether the test speaker is an enrolled speaker or an imposter. In the comprehensive classification of a certain problem, one of the most important processes is feature subset selection. It includes dimensionality reduction, attribute subset selection and variable subset selection and also an important step to reduce overfitting of data. This paper presents one of the methods to solve this feature selection problem using Ant Colony Optimization algorithm. This algorithm subsumes the performance of the classification into state transition rule. The optimal feature set is determined with the help of the pheromone from the ant colony. Finally, a feature set with maximum classification accuracy and small size is selected.

To obtain an overview of the content present in numerous documents, is a time-consuming task. Similarly, searching for specific information online, from multiple websites and webpages is a monotonous task. To avoid this, automatic text summarization is one of the most widely adopted techniques today to get a concise and brief outline of the information. In this paper, a novel process is proposed to generate an extractive summary of the information based on the user's query by extracting data from multiple websites over the internet. Web-scraping through Selenium is also discussed. The Term Frequency-Inverse Document Frequency (TF-IDF) algorithm is applied for text summarization. The proposed approach is unique and efficient for generating summaries as per the user's request.

Most of the rural areas keep declining and smart cities keep evolving in its own phase. Data is one of the most important resources to maintain as terabytes of data is collected from a single city. Data is analyzed using big data analysis and it can be stored by using the fog computing and it also describes how fog computing is effective in IoT when compared to cloud-based computing and how fog-based computing is introducing its innovative applications. The research work describes cloud and fog architecture and furthermore we will learn about a new experimental architecture. It is the combination of both fog based and cloud-based technologies. Fog computing is a technology that is rapidly influencing the emerging digital technologies and applications. There are many challenges in maintaining the data through fog computing technologies, these challenges are mentioned along with their security concerns that help for the transition from cloud to fog. This paper mainly tells us how fog computing would emerge as the future of IoT and how it would change the quality of life at an unprecedented rate.

Over the past two decades, the research on EEG-based brain–computer interaction (BCI) made the BCI systems better and better, but building a robust BCI system for practical use is still a goal to achieve. To identify emotions of immobilized individuals, neuroscan machines like encephalography (EEG) is utilized. It uses the physiological signals available from EEG data extracted from the brain signals of immobilized persons and tries to determine the emotions, but these results vary from machine to machine, and there exists no standardization process which can identify the feelings of the brain diseased persons accurately. In this paper, a novel method is proposed, Skew Gaussian Mixture Model (SGMM) to have a complete emotion recognition system which can identify emotions more accurately in a noisy environment from both the healthy individuals and sick persons. The results of the proposed system surpassed the accuracy rates of traditional systems.

Reusability is the quality of a piece of software, which enables it to be used again, be it partial, modified or complete. A wide range of modeling techniques have been proposed and applied for software quality predictions. Complexity and size metrics have been used to predict the number of defects in software components. Estimation of cost is important, during the process of software development. There are two main types of cost estimation approaches: algorithmic methods and non-algorithmic methods. In this work, using genetic programming which is a branch of evolutionary algorithms, a new algorithmic method is presented for software development cost estimation, using the implementation of this method; new formulas were obtained for software development cost estimation in which reusability of components is given priority. After evaluation of these formulas, the mean and standard deviation of the magnitude of relative error is better than related algorithmic methods such as COCOMO formulas.

Among all geophysical methods, resistivity methods are most widely used in ground water, mineral and oil exploration. The resistivity methods involve passage of current through two iron stakes into the ground and measuring potential by means of two other electrodes. What we measure in these methods is the resistivity of the ground, which we call as ‘apparent resistivity’. Practically a known amount of current (I) is sent into the ground using two metal stakes, called current electrodes, and the potential is measured using other two probes, called potential electrodes. The concept of apparent resistivity arises from the fact that the measured current between the two current (+I, -I) electrodes and voltage between the other two potential (P1 and P2) electrodes which are arranged in different configurations were introduced by various workers over the years in resistivity prospecting. the multi electrodes play a very significant role in the resistivity/IP prospecting, for detecting sub-surface formations and for studying sub-surface geological stratal architecture. In this type of surveys, a number of electrodes are planted on the ground surface maintaining an equal inter-electrode separation. The number of electrodes may be 12,24,48,72 or 96….depending upon type of the measuring system. For the present survey, IRIS make system called SYSCAL Pro-96 has been used for the field and lab studies. Most of the conventional electrode arrays viz., two-electrode, three-electrode, Wenner; Dipole-Dipole etc have been applied in different geological environs.

Automatic Speaker Verification is the authentication of a claimed identity based on characteristics of voice. A speaker verification system compares a person's voice with a speaker model or stored voiceprint captured during enrollment as well as an imposter model of different voices, genders and phone types. The system then assigns a confidence score and then makes a decision whether to let the person proceed, to ask for additional voice samples or to refuse entry. Feature subset selection is one of the most concerned processes in the overall classification process of a particular problem. It was also named as dimensionality reduction, attribute subset selection and variable subset selection. For automatic speaker verification (ASV), feature subset selection is one of the first modules. The objective of the paper is to select a most relevant subset of features for error-free optimized classification in the speech domain. In this paper a novel method for speaker verification is proposed using Hybrid Ant Bee Colony optimization to increase the verification rate. Equal Error Rate (EER) is the standard measure which evaluates the projected procedure. Speaker verification system's accuracy rates surpassed the results of traditional systems after applying proposed optimization algorithm; the optimized feature subset was 85% with an average accuracy rate of 95.27%.

Speech Processing has been developed as one of the vital provision region of Digital Signal Processing. Speaker recognition is the methodology of immediately distinguishing who is talking dependent upon special aspects held in discourse waves. This strategy makes it conceivable to utilize the speaker's voice to check their character and control access to administrations, for example voice dialing, data administrations, voice send, and security control for secret information. A review on speaker recognition and emotion recognition is performed based on past ten years of research work. So far iari is done on text independent and dependent speaker recognition. There are many prosodic features of speech signal that depict the emotion of a speaker. A detailed study on these issues is presented in this paper. Index Terms—Emotion recognition, feature extraction, speaker recognition.

Managing the mobility efficiently in wireless networks causes critical issue, in order to support mobile users. To support global mobility in IP networks The Mobile Internet Protocol (MIP) has been proposed. The Hierarchical MIP (HMIP) and Dynamic HMIP (DHMIP) strategies are also proposed for providing high signaling delay. Our proposal approach “Multicast HMIP strategy” limits the registration processes in the GFAs. For high-mobility MTs, MHMIP provides lowest mobility signaling delay compared to the HMIP and DHMIP approaches. However, it is resource consuming strategy unless for frequent MT mobility. Hence, we propose an analytic model to evaluate the mean signaling delay and the mean bandwidth per call according to the type of MT mobility. In our analysis, the MHMIP gives the best performance among the DHMIP and MIP strategies in almost all the studied cases. The main contribution of this paper is to implement the MHMIP and provide the analytic model that allows the comparison of MIP, DHMIP and MHMIP mobility management approaches.

Lots of work has been done on speech and speaker recognition. Many technologies were developed for the analysis of speech waveforms. Musical instrument recognition is an important aspect of music information retrieval system. In this paper we analyzed features for musical instruments recognition and a brief study on music similarity. Music similarity search is done by using mel-frequency cepstral coefficients (MFCC), linear predictive coefficients (LPC) and the classifier used is K- Nearest Neighbor with Dynamic Time Warping.

In speech processing for speaker verification, feature subset selection is one of the key components. Feature Subset Selection (FS) also played a vital role in the fields like pattern recognition, image processing, data mining, and gene selection. In a real world problem related to speech domain, speech sample contains a large number of relevant and irrelevant features. To increase the speaker verification rate, one needs to use the optimization technique for feature selection after the feature extraction technique. The ultimate goal is to select the most relevant subset of features for error free optimized classification in the speech domain. In this regard a novel feature subset selection algorithm is proposed using Bat algorithm and Multi Objective Optimization technique. Results of the experiment shows the proposed algorithm surpassed the accuracy rates shown by the conventional systems.

This paper suggest a well-organized information system for facilitate the litigation procedures Information System courts. The purpose is to decrease the duration of processing cases in courts. The aspiration is to save the time and effort of judges and lawyer. In addition, we make use of the advantages of electronic systems and reducing traffic especially in developed countries. Advanced Encryption Standard is used to encrypt all the manipulated data for each case. All read document are encrypted to attain secure information system Litigation process. This is because the big data for all cases will be stored on cloud environment.

The capacity of ad hoc networks can be severely limited due to interference constraints. One way of using improving the overall capacity of ad hoc networks is by the use of smart antennas. Smart antennas allow the energy to be transmitted or received in a particular direction as opposed to disseminating energy in all directions. This helps in achieving significant spatial re-use and thereby increasing the capacity of the network. However, the use of smart antennas presents significant challenges at the higher layers of the protocol stack. In particular, the medium access control and the routing layers will have to be modified and made aware of the presence of such antennas in order to exploit their use. In this paper we examine the various challenges that arise when deploying such antennas in ad hoc networks and the solutions proposed thus far in order to overcome them. The current state of the art seems to suggest that the deployment of such antennas can have a tremendous impact in terms of increasing the capacity of ad hoc networks.

“An expression of concern has been received concerning the auspices under which the above paper has been prepared. This expression of concern is placed here for completeness” The publisher would like to apologise for any inconvenience caused.