VOLUME 7, ISSUE 11, NOVEMBER 2018

Abstract: In this paper, we presented a Convolutional Neural Network (CNN) model for off-line Arabic handwritten character recognition. The proposed CNN model used the dataset which prepared by Sudan University of Science and Technology- Arabic Language Technology group. The dataset is pre-processed before feeding it to the CNN model. In the pre-processing, all the characters images are size normalized to fit in a 20 by 20 pixel and then centred in a scaled images of size 28×28 pixel using the centre of mass then all the images are converted to be having a black background and white foreground colours. The pre-processed images are fed to the CNN model, which is constructed using the sequential model of the Keras library under tensorflow environment. The accuracy obtained varied from 93.5% as test accuracy to 97.5% as training accuracy showing better results than other methods that used the same dataset.

Keywords: Convolutional Neural Network CNN, Handwritten Characters, Keras, pre-processing

Abstract: Text mining have gain huge momentum in recent years, with user-generated content becoming widely available. One keyuse is remark mining, with much attention being given to sentiment analysis and opinion mining. An essential step in the process of comment mining is text pre-processing; a step in which each linguistic term is assigned with a weight that commonly increase with its appearance in the studied text, yet is offset by the occurrence of the term in the domain of interest. A common practice is to use the well-known tf-idf formula to calculate these weights.This paper reveals the bias introduce by between-participants’ discourse to the study of comments in social media, and proposes an adjustment. We find that content extract from discourse is often highly correlated, resulting in dependence structures between observations in the study, thus introducing a statistical bias. Ignoring this bias can obvious in a non-robust analysis at best and can lead to an entirely wrong conclusion at worst. We propose a change to tf-idf that accounts for this bias. We show the effects of both the bias and correction with  seven Facebook fan pages data, covering different domains, including news, finance, politics, sport, shopping, and entertainment.

Keywords: Sentiment Analysis, Text Mining, Statistical Bias, Discourse, TF-IDF

Abstract: This paper describes a framework that works by collecting the trajectory data obtained from the sensors. The data is stored and processed in a way that helps in identifying events such as key activity areas, evolving activity, etc. It helps to attain better insight into the work habits of the population. Trajectory mining is either assumed that the time-ordered location data recorded as trajectories are either deterministic or that the uncertainty, e.g., due to equipment or technological limitations, is removed by incorporating some pre-processing routines.  Thus, the trajectories are processed as deterministic paths of mobile object location data. Probabilistic trajectory extraction and mining from uncertain trajectory data is the first phase analysis on the subject. It is also interested in identifying and developing alternative approaches with the use of which can make the approach more scalable, e.g. a trajectory compression scheme could be developed to further decrease the length of the trajectories. This paper proposes an efficient distributed mining algorithm to jointly identify a group of sensor data and discover their trajectory of sensor data in wireless sensor networks. Then, Map-Reduce algorithm (Probabilistic Suffix Tree) is introduced which utilizes the discovered group trajectory sensor data shared by the transmitting node.

Keywords: Trajectory mining, Wireless Sensor Networks, Map-Reduce algorithm, Pattern mining

Abstract: Object detection using deep neural network especially convolution neural networks. Object detection was previously done using only conventional deep convolution neural network whereas using regional based convolution network [3] increases the accuracy and also decreases the time required to complete the program. The dataset used is PASCAL VOC 2012 which contains 20 labels. The dataset is very popular in image recognition, object detection and other image processing problems. Supervised learning is also possible in implementing the problem using Decision trees or more likely SVM. But neural network work best in image processing because they can handle images well. 

Keywords: Object Detection; Neural Network, Artificial Neural Network (ANN), Feed-forward networks, Feedbacks networks

Abstract: These days, expanding number of shrewd administrations are being produced and sent in urban areas around the globe. IoT stages have developed to incorporate savvy city administrations and city assets, and in this way enhance city execution in the areas of transportation, crisis, condition, open security, and so on. In spite of the expanding insight of brilliant administrations and the modernity of stages, the wellbeing issues in shrewd urban communities are not tended to enough, particularly the wellbeing issues emerging from the coordination of keen administrations. Along these lines, CityGuard, a wellbeing mindful guard dog design is created. To the best of our insight, it is the primary design that recognizes and settle clashes among activities of different administrations thinking about both wellbeing and execution necessities. Before creating CityGuard, wellbeing and execution prerequisites and a range of contentions are indicated. Advanced models are utilized to examine optional impacts, and recognize gadget and ecological clashes. A recreation dependent on New York City is utilized for the assessment. .e results demonstrate that CityGuard (i) recognizes risky activities and accordingly keeps the city from security perils, (ii) identifies and settle two noteworthy kinds of contentions, i.e., gadget and ecological conflicts, and (iii) enhances the general city execution.

Keywords: City Safety, City Simulation, Smart City, CityGuard, Conflict Detection

Abstract: A wireless sensor network is the prominent technology, which seeks lots of attention in the state of the art technology. It has its wide range of utilization aspects in almost all domains. The major challenge of the WSN seems to be the energy utilization and as a consequence the decline of the lifetime of the sensor nodes. This research addresses the problem of the energy drain in the sensor nodes lifetime, which as a result it ends up in the nodes death. This research proposes an algorithm to cope up with the energy utilization of the sensor nodes .Wireless sensor networks are deployed widely in sensitive applications like health care, surveillance and e-commerce domains. Compared with communication protocols, in terms of energy indulgence, ease of formation, and system epoch/quality of the network. Providing such a low-energy, ad hoc, distributed protocol will help pave the way for imminent micro sensor networks. It is evident from the MATLAB simulation that the proposed system works well efficient to cope up with energy efficient and novel clustering. In this research, novel constellation based wsn clustering protocol is proposed for the wireless sensor networks. It improves the efficiency of the energy consumption along with the improvement of the node lifetime values. The proposed strategy helps in improving the dynamic updating of the routing table, which may overcome the problem of the dead node sensing and cluster head value updating.

Keywords: Wireless Sensor Network, Routing Algorithm, MATLAB

Abstract: Blood is one of the most crucial element a human needs.  And it is the vital element of the life. Now a days, there are way more emergency situations where urgency of blood is there. in this paper, we have proposed a system of blood bank system using Android application. This application will managed and operated on line . in this the admin will access the whole information about the hospitals and the blood banks that have MMU with it , related to donor and the user. via this application you can check quickly the blood banks and the hospitals where the required blood group is needed. This application will give the nearest location of the blood bank or the hospital where  the blood is available. This app gives the list of the blood banks and the hospitals in nearby area.

Keywords: GSM/GPS Technologies, blood Analysis

Abstract: Land Surface Temperature (LST) may be a key variable in climatological and environmental studies.  However, correct measurements of LST over continents aren't nevertheless on the market for the  whole globe. This paper initial reviews the state of the science of land surface temperature (LST) estimates from remote sensing platforms, models, and in place approaches. In this thesis analysis a physics-based technique to retrieve LST from the MODIS daytime MIR information in channels twenty two (centered at 3.97 μm) and twenty three (centered at 4.06 μm). On the premise is radiative transfer theory within the MIR region, a bi-face reflectivity retrieval technique. During this technique to separate the mirrored star direct irradiance and also the radiances emitted by the surface and atmosphere. MIR Data Land Cover temperature measured is asserted once consecutive sub sequences that are extracted from one MODIS statistic transitions from one cluster to a different cluster and remains within the freshly appointed cluster for the remainder of the statistic.

Keywords: LST, MIR, Fuzzy Random Clustering, Land Cover Process, Image Clustering

Abstract: Software-Defined Radio (SDR) is a radio communication system where components that have been traditionally implemented in hardware (e.g. mixers, filters, amplifiers, modulators/demodulators, detectors, etc.) are instead implemented by means of software on a personal computer or embedded system. Reconfigurable Finite Impulse Response (RFIR) filter plays an important role in SDR systems, whose filter co-efficient change dynamically during runtime. In this paper, Low Cost Carry Bypass adder Reconfigurable Finite Impulse Response (LC-CBA-RFIR) is introduced to perform the RFIR filter operations. DRAM-based Reconfigurable Partial Product Generators (DRPPG) consists of MUX and dual port distributed RAM, which has co-efficient to perform a FIR filter operation. With the help of Verilog code, the RFIR filter architecture was verified in Modelsim software. The same Verilog code was used to analyse the FPGA performances such as LUT, flip flop, slice and frequency. After implementing FPGA, all the performance improved in LC-CBA-RFIR method compared to the conventional methods.

Keywords: Reconfigurable FIR, Carry bypass adder, DRAM-based Re-configurable partial product generator

Abstract: Social network analysis is an ​​active research area carrying important meanings in practice, enabling people to capture and manipulate complex information flows constantly running in the community. A social network is analyzed to find out the most influencing factor on the others, which is called the Key Player. Identifying a Key Player on a social network is an advantage for making good use of that social network for certain purposes. Studies have not yet been applied to a particular social network or community. It also does not focus on identifying the influence of individuals or their writings on the behaviour of the others. This study presents a new information network model that exerts influence among the vertices and builds a new formula to calculate the influence of information in accordance with the new information network model.

Keywords: Key Player, Opinion Leader, Social Network, Virtual Community

Abstract: Cluster analysis may be a descriptive task that seeks to identify consistent cluster of object and it's additionally one in all the most analytical technique in data processing. K-mean is that the preferred partitional bunch technique. During this paper they have a tendency to discuss commonplace k mean formula and analyze the defect of k-mean formula. During this paper 3 dissimilar changed k-mean formulas are mentioned that take away the limitation of k-mean formula and improve the speed and potency of k-mean formula. Experiments supported the standard data UCI show that the projected technique can end up a high purity cluster results and eliminate the sensitivity to the initial centers to some extent. E.Coli dataset and Yeast dataset resides issue organism and altogether totally different super molecule assign in their cell. If that protein is wounded, then these cause varied infections that affected anatomy adversely. So, the target of this work is to classify proteins into altogether totally different cellular localization sites supported organic compound sequences of E.Coli bacterium and Yeast. It’s found that projected bunch provides correct result as compared to K-Mean and is perfect resolution to localization of proteins. It’s additionally called nearest neighbor looking. It merely clusters the datasets into given variety of clusters. Varied efforts are created to improve the presentation of the K-means bunch formula. Throughout this paper they’ve been briefed among the sort of a review the work distributed by the assorted researchers’ victimization K-means bunch. They have mentioned the restrictions and applications of the K-means bunch formula still. Detect our projected formula best resolution.

Keywords: Data Processing, Clustering Technique, Hierarchical Cluster, k-mean Cluster, Performance Accuracy, optimization algorithm

Abstract: Mining of data from large data sets and the process of discovering patterns using statistics, machine learning, data correlation, data plotting or data visualization and data evaluation are called data mining. Data analytics and data mining are a subset of Business Intelligence (BI). [1] In our previous paper titled “Data Analytics: Employee Turnover in a Company-1” the process of data pre-processing was demonstrated by writing a program in Python. Libraries like pandas, numpy, seaborn and matplotlib [2] of Python provide platform for computing, evaluation and visualization of acquired data. In this paper we demonstrate three analytical tools- plotting and evaluating, correlation and data prediction/Machine learning which are involved in data mining and analytics of company’s data. The company wants to understand the factors contributing to employee turnover and to think of various retention strategies.

Keywords: Python, analytical tools- plotting and evaluating, correlation and data prediction/Machine learning

Abstract: Tour Guide as the name goes is an advance yet highly promising system helping a tourist or any user to get accurate and best data in no time. This System is an Android Application and Uses Android Studio as its Front End and SQL Server as its Back End. The Application acts as a Tour Guide giving out outputs to the user for every input given to the system. The System is highly reliable as it uses google map API which are very accurate and same goes for the weather conditions, personal interest and budget to travel. This System tries the user to gives a heads-up giving the weather conditions to make sure that the user will be comfortable to visit the desired place. The User has options to select for the places he wants to visit for instance parks, beaches monuments or food joints and so on; the system will ask whether he is searching for the current. Locality or some other place.

Keywords: TSP, Geo-fencing, Shortest Path, Daily Tourism Behavior

Abstract: In this paper, we propose recipe recommendation system that using a data. With the power of web, aggregate world is related and particular customers of different countries are sharing the number of  recipe on the Net. Along these lines, thusly customers don't think about the each one of the recipe on the web. This paper presents a recipe recommendation system to recommend a set of dishes from the various Chinese regional cuisines for a certain flavor preference in terms of flavor similarity[1].Recipe contains differing fixings, cooking strategy, classes so on. Thusly, we think the recipe is combination of the extraordinary heterogeneous components. Most of the proposal structure relies upon the substance or group situated filtering to predict the new recipe of eagerness for a customer. Joining with the both the filtering techniques, we display a fruitful and wonderful structure for uniting the two methodologies in Recipe proposal system. A substantial part of the equation proposition system uses content information as fixings or cooking procedures of Recipe. We proposed novel way to deal with prescribe new recipes. With life style, diet habits has changed and work pressure increased which resulted in number of diseases, such as diabetes, Blood Pressure, heart problem etc. These diseases can be controlled to certain extent by avoiding uneven and inappropriate diet.[2].

Keywords: Recommendation System, Collaborative Filtering, Recipes, Content Information

Abstract: Human system is made up of many organs; of all brain is the first and the leading controller of the human system. Overload cells growing in an uncontrolled manner in brain is called as brain tumor which further leads to brain cancer. MRI(Magnetic Resonance Imaging) is a medical test which uses strong magnets to produce magnetic field and radio waves to generate 2/3 Dimensional image of different body organs and uses computer to analyze the taken image. The brain is composed of 3 types of materials: White Material (WM), Grey Matter (GM) and Cerebral Spinal Fluid (CSF).Through the MRI scan we can view the brain in three different ways: 1]The Axial MRI 2]The Sagittal MRI 3]The Coronal MRI. These images help the Doctor to identify whether that patient is suffering from cancer. The proposed system takes Brain MRI images as an input and pre-processing is performed on it (resizing and renaming).The images will be analyzed using advance imaging technologies. These technologies use Convolution Neural Network and deep learning approach for analysis. After analysis, classifying of whether given MRI images are normal or show a benign or malignant cancer is done automatically, that saves the radiologist’s time, increases accuracy and yield of diagnosis.

Keywords: MRI Images, U-Net, Ground Truth, Tensor Flow, Tumour, Brain, Processing, classification, Benign, Malignant

Abstract: In software maintenance, bug reports play an important role for the correctness of software packages. Unfortunately, a duplicate bug report problem arises because there are significant many duplicate bug reports in various software projects. Processing duplicate bug reports is thus time-consuming and has high cost of software maintenance. In this research, we propose a detection scheme based on the BM25 weighting and cluster shrinkage (BM25-CS) to enhance the detection performance. The effectiveness of this method is verified in an empirical study with three open-source projects, SVN, Argo UML, and Apache. The experimental results show that our method outperforms other detection schemes about 6-10% in all cases.

Keywords: Bug Reports, Duplication Detection, B25Weighting, Cluster Shrinkage

Abstract: Collaborative Time Tracking System for employees is believed to be found under one of many modules of a Project Management. It is crucial that the system to be developed in line with company’s business objectives. CTTS implementation is an internal application developed for efficient functioning of an organization is used to monitor all the employees of a particular organization working on various projects. In this implementation timesheet may record the start and end time of each employee tasks. The timesheet contain a detailed breakdown of tasks accomplished throughout the project. This information may be used for CheckIn and CheckOut of employee time, manage activity, task assign to employee, tracking the update status of each assigned projects and updating the note and management of each tasks, Generate a Timesheet Report for all employees, Sending an email to the project manager and fetching the system IP Address of each employee. The Collaborative time tracking implementation requires development of the following tasks: Get the projects and tasks assigned to an employee. Display a form to enter the number of hours spent by an employee on a task in a day like following: It should be possible to enter the timesheet either for one task at a time and one day at a time, It should be possible to enter the time for all the assigned tasks at a time, It should be possible to modify the note and status of all project task entered earlier. Once the timesheet are entered they cannot be modified. The basic concept of this system is to improve the process of task delegation and monitoring project performance for Project Manager and Project Staff, and logging it into a nice and well-defined database.

Keywords: Time Sheet Management, Timesheet implementation, Case Study, Intranet

Abstract: The accuracy in recognition and classification of the plant disease is highly significant for the successful farming of crop and this can be performed using image processing. This research is conversed various methods to segment the disease portion of the plant. This study also discussed some noise reduction techniques and image segmentation techniques for identification of infected leaf and the categorization of plant diseases. Image segmentation is the method of partitioning a digital image into numerous segments. The outcome of image segmentation is a group of segments that jointly cover the whole image, or a collection of contours acquired from the image. With regard to features namely texture, color and intensity every pixel in a region is similar.

Keywords: Segmentation, Fuzzy, Speckle, Histogram, Noise, Impulse, Thresholding

Abstract: Cloud computing is an attracting technology because of its significant usage in today’s era of technology. The cloud will bring changes to the IT industry and it’s also changing our life by providing users with new types of services. Today’s Cloud computing systems are appealing for their optimal cost, amazing scalability and flexibility, seamless access of resources and VoD (Video on Demand) functionality. Because this is a promising technology able to strongly modify the way computing and storage resources to be accessed. Through the provision of on-demand access to virtual resources available on the Internet, cloud systems offer services at three different levels: Infrastructure as a Service (IaaS), Platform as a Service (PaaS), and software as a service (SaaS) [7].The goal of this study is to discuss the consequential challenges involved in Cloud-Based Mobile Social TV to build successful systems that can be employed in the real world. This techniques with the help of VoD and good streaming quality can be used in Miscellaneous Platforms like PC, TV, and Smartphone etc. This review also discusses what are the technologies are used in the Cloud-Based Mobile Social TV and application of this system. It proposes several possible future directions and challenges in front of this system. Thus, it will be a good starting point for research projects on Cloud-Based Mobile Social TV with VoD as a useful technique can be isolated and applications, as well as future challenges, are focused.

Keywords: IaaS, PaaS, VoD, Adaptive Streaming

Abstract: Road accidents are a very common issue nowadays. The fatal road accidents causes a life loss of a number of people per day. The present innovation is proposed to make analysis in the same matter and will bring a change accordingly. The road accidents are mainly caused due to the excess light conditions, drunk and driving, the bad road surfaces, and the worse weather conditions. These causes are the prime reason for the road accidents. In the proposed innovation, the accidents causes are made to a fair analysis using the Apriori algorithm, Naive Bayes algorithm, and the K-means algorithm. Some suggestions of the road accidents management are made on the basis of obtained statistic, association and rules, classification models, and the clusters.

Keywords: Roadway Fatal Accidents, Association, Classification, Clustering

Abstract: In this paper we discuss about the clustering type of retrieving data from the database for data mining and also the algorithms used for clustering. We also analyse its best algorithm and the algorithm’s drawbacks if any, thus giving a successful review on it. We here discuss about k-means clustering, Fuzzy-c means clustering and Hierarchial Clustering from the knowledge gathered from various publications in journals given further at the end in the reference section.

Keywords: Data Mining, Clustering, Algorithms, K-means Algorithm

Abstract: Virtualization refers to the act of something including virtual computer makes a unreal image of the storage space devices servers or network resources so that they can be used on multiple machines at the same time. With the latest growth in cloud computing technologies, security of the data becomes important. It is an enable technology allowing the design of an intelligent abstraction layer that hides the density of underlying software or hardware virtualization technology that can make things easier operations as well as allow Information Technology organizations to react faster to changing business demands. It allows multiple virtual computers to run on top of one physical computer and to share the hardware resources, such as printers, scanners, and modems. This increases the efficient use of the computer by low costs since only one physical computer is needed and running.  Cloud computing technology is one of the largest milestones in leading us to next generation technology and successful up business and Information Technology field. It helps to rise above the problem for the loss of data, accessing data whenever required and data security. This technology is mainly service oriented and focuses on reduction in low cost, hardware reduction and pay just for service concept.

Keywords: Virtualization, Cloud Computing, Data Security

Abstract: Data mining is a process of extracting useful knowledge from a large number of data sets, by using any of its methodology. It is a field of intersection between machine language, database and statistics. it is used in many fields for extraction knowledge and information about that particular area. Data mining is used to discover knowledge out of data and presenting it in an understandable way to humans. There are different process and techniques used to carry out data mining successfully.

Keywords: Machine Learning, Statistics, Database

Abstract: Wireless Sensor Network the existing cluster based technique may result in increased network works.             WSNs are spatially distributed autonomous sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. Sensor networks can contain hundreds or thousands of sensing nodes. The development of wireless sensor networks was motivated by military applications such as battlefield surveillance; Networks are used in many industrial and applications, such as industrial process and control, machine health monitoring.

Keywords: Sensor, Terrestrial, Reliability

Abstract: Data Mining knowledge and information from high databases has been recognized by many researchers as a key research topic in machine learning and Database system and in many industrial companies as an important area with an opportunity of major revenues .we present a multidimensional view of data mining. The major dimensions are data, knowledge, technologies and application. Researchers in some different fields have shown their great interest in data mining. In this section, we briefly outline methodology, user interaction. Data mining research has strongly impact society and will continue to do so in the future.

Keywords: Data Mining, Knowledge discovery

Abstract: Credit and debit card theft is the earliest forms of cybercrime. Now  a days it is one of the most common problem. Attackers often aim to steal such customer data by targeting the Point of Sale system. Modern POS are powerful computers equipped with a card reader and running specialized software. User devices are leveraged as input to the Point of Sale. In case where customer and vendor are disconnected from the network, no secured on-line payment is possible. FRODO is the first solution that can provide full secured on-line payments while being resilient to all currently known POS . Our solution improves the date approaches in terms of flexibility and security.

Keywords: FRODO, POS system (Point of Sale), Personally Identifiable Information(PII)

Abstract: Fifth generation mobile technology expanded as 5g technology. starting from generation 1g to 2.5g and 3g to 5g. It has seen an great increase in  technology. Based on mobile computing our day to day life changes. This paper displays increase in generation of mobile communication with 5th generation technology.5th generation network gives users affordable broadcast wireless connectivity also known as high speed connectivity. But the 5g term is not legally used. 5g is mainly used in development on worldwide wireless web.5th generation mainly targets on voice over IP(voIP)enable devices in which user can obtain high level call volume and data transmission.5th generation fulfill all needs which are required by the customers. The main target of 5G is the customer who want advanced feature in cellular  phones. The main aim of  5G is to connect to multiple wireless technologies. This upgraded mobile technology will support IPV6 and flat IP. It provides services similar to documentation and e-transactions and e-payments.

Keywords: IPV6, 0G,1G, 2G, 2.5G, 3G, 4G, 5G, World Wide Wireless Web, WPANs, e-transactions and e-payments

Abstract: Now a days, as information systems are more open to the Internet world, the importance of security for networks is increased. Security is the way of protection to safeguard a nation, persons  or  person against danger, damage, loss, and crime. Therefore text based passwords are not enough to counter such problems. This demands need for something well secured along with user friendly, Therefore Three level security is an user-friendly software. Where  it  have increased security by using 3 levels . Level-1 Text based password, Level-2 Image Based Authentication and Level-3 Generating  One Time Password.

Keywords: OTP, Text Authentication, Image Authentication

Abstract: The modern era has received a major up blow with the evolution of the robotic domain. The field of robotics is going through major transformation and development. They are already employed for entertainment purposes, assisting the elderly or performing surveillance on small kids. This paper using animations and kinematic tasks, focuses on the implementation and design of  the Darwin-OP.

Keywords: Sensor, Actuator, Button, Humanoid, Robot

Abstract: Morse code key is the earliest method used in Radio Telegraphy. To increase security and confidentiality of data in cloud environment, the DNA sequences are used with Morse code and zigzag pattern, for encoding scheme. Use of Morse code and Zigzag pattern makes the intruder much harder to steal original data. Furthermore, the proposed scheme is implemented and the accuracy of encryption and decryption of data is verified.

Keywords: Morse code, DNA sequences, Cloud Computing, Morse Pattern, Zigzag Pattern,  Encryption, Decryption

Abstract: A shopping mall is a place where wide varieties of items are available. Many shopping malls use barcode scanning system. As this system is time consuming, people have to wait in a long queue at the billing counter. To overcome this problem, smart shopping cart is introduced. This proposed system uses RFID technology. Every product is attached with Radio Frequency Identification (RFID) tag. For scanning this tag RFID reader is used which is attached to the cart. As a result bill is generated in the cart itself and is displayed on the LCD which saves the time of the customer.

Keywords: Radio Frequency Identification, Liquid Crystal Display

Abstract: Agriculture is the backbone of many developing nations and plays a major role in their economy. In our country, it accounts for 13.9% of Indian GDP and about 50% of the workforce. But the yield is poor because of backward traditional farming approach and techniques. If we adapt a new technology with olden farming practices, it will be possible to boost the overall yield and improve the condition of agriculture in our country. We decided to implement this project for agricultural survey by using a UAV to help farmers improve crop quality and increase their earnings. The agriculture farm is surveyed by an infrared camera which shows the difference between infected or diseased crops and matured crops, it can also show weeds or pests and to a certain extent monitor the soil moisture levels. The drone can be used spray pesticides or irrigate the crops. The innovative frame design will allow the drone to be transported safely and easily.

Keywords: UAV, APM, OpenCV, ESC, NDVI

Abstract: Communication through voice is one of the main components of affective computing in human-computer interaction. [5]In this type of interaction, properly comprehending the meanings of the words or the linguistic category and recognizing the emotion included in the speech is essential for enhancing the performance. In order to model the emotional state, the speech waves are utilized, which bear signals standing for emotions such as boredom, fear, joy and sadness etc...So we can find different speech signals of each subject. The most significant features that transfer the variations in the tone are classified into pitch and intensity categories. We can use, eleven features, namely, pitch, intensity, the first four formants and their bandwidths and standard deviation, are extracted. The proposed method first digitizes the signal to extract the required properties. According to emotional Prosody studies, the tone of every person’s voice can be characterized by its pitch, loudness or intensity, timbre, speech rate and pauses, whose changes convey different information from the speaker to the listener.[6]

Keywords: Speaker recognition, vocal emotion recognition, sentimental analysis, Emotion prediction, Text mining

Abstract: Cloud computing offers utility -oriented IT services to users. Cloud computing provides us cheaper, faster, flexible, efficient environment. Cloud computing provides multitudinous benefits to both service provider and customer. A fresh look at the way secure communications is currently being done has been undertaken as a consequence of the large hacking's that have taken place recently.[1]Due to large  advancement many companies are migrating to cloud environment. However, the security of cloud computing has been a challenging one. DNA cryptography is used to encrypt message for secure communication on cloud computing environment. Protecting sensitive data is challenging task in cloud environment. For increased security, the recommended approach is to combine two or more methods – processes, DNA cryptography and Morse pattern. DNA cryptography with Morse pattern is difficult to fabricate, which makes the attacker much harder to steal the original data.[2] Use of Morse code and Zigzag pattern makes the attacker much harder to steal original data. Furthermore, the proposed scheme is implemented and the accuracy of encryption and decryption of data is verified.

Keywords: Morse code, DNA sequences, Cloud Computing, Morse Pattern, Zigzag Pattern, Data Block Security, Encryption, Decryption, Key Rotation.

Abstract: The LI-FI is the newest technology in the Field of wireless communication. Nowadays many people are using internet to fulfil their task through wired or wireless technologies. As the number of users is increasing, the rate of data transmission in the wireless network automatically decreases. WI-FI provides us speeds near about 150mbps as per IEEE 802.11n but still it is not able to fulfil the requirement of the user because of such reasons we are introducing LI-FI. According to the German psychist Harald Hass LI-FI provides more speed (10megabits per second minimum) data transmission by using visible light. So here in this condition we are analysing the LI-FI/WI-FI. It’s the same idea band behind infrared remote controls but far more powerful. Haas says his invention, which he calls D-LIGHT, can produce data rates faster than our average broadband connection. Recently, parking vehicle is most tedious job. Hence, in order to solve this problem, a reliable system is proposed. our system solves the current parking problems by offering guaranteed parking reservations with the lowest possible cost and searching time for drivers and the highest revenue and resource utilization for parking managers.

Keywords: Dynamic Pricing, Dynamic Resource Allocation, Li-Fi, Smart Car Parking

Abstract: With the increasing number of images users share through social sites, maintaining privacy has become a major problem. Users find very difficult to keep control on the privacy of their shared contents and end up inadvertently losing the privacy of their shared content. To address this issue we propose a system which will not only provide user with self-designing of privacy policy for their shared images but also the system will itself use the history result and provide a privacy policy for new users. The system will use data mining algorithm to access the history dataset and predict a privacy policy for new user accessing the data. System will also provide user with refined searching approach for image search where user can submit an image or query or both together to get expected output which will be set of images. Our system will be provide user with secure access to images with privacy policy changing as per user thus making owners data safe and secure.

Keywords: Privacy, photo sharing, online content, social network

Abstract: Web of things has been broadly associated for home, industry, and various distinctive applications. For these applications, secure information transmission transforms into an essential issue to ensure the structure prosperity. Mixed encryption technique is another cryptographic perspective and it can be associated with the Internet of Things. It gives the benefit of the symmetric key and unbalanced key execution. It engages strong security and low computational flightiness. The proposed procedure mulls over that a cream encryption figuring which has been coordinated remembering the true objective to diminish risks and redesigning encryption's speed and less computational unpredictability. The inspiration driving this cross breed computation is information uprightness, arrangement, non-revocation in data exchange for Internet of things.

Keywords: Web of Things (IOT), Digital Signature Algorithm (DSA), AES Algorithm

Abstract: Now a days, social media is hot topic on research. Millions of the peoples express their views on social media. This huge data will beneficial for better product marketing. But, because of massive of volume of reviews, end-users can’t read all reviews in order to solve this problem lot of researchers has been carried out sentiment analysis.

Sentiment analysis is the automated process of understanding and opinion about a given subject from return or written language. Most of sentiment analysis & opinion mining work focuses on binary classification & ternary classification of texts. But our novel idea is to classify the text or sentences into multiple classes. Using Hotel Reviews datasets we classify the sentences into multiple classes like happy, sad, hungry, love etc. In dataset various sentences contains the hashtags, URL’s, operators it cannot change the analysis of the sentences or meaning of that sentence but it create the confusion while determining the result. So we can apply the pre-processing method to remove all these things. After that the feature extraction method is apply on the processed dataset to extract their aspects. Later, this aspects are used to calculate the positive and negative polarity in sentence.  Then the model is trained on training dataset using supervised learning method. The training consist of the pairs of input and the corresponding answer vector and the current model is run with the training dataset and produces a result. By using machine learning algorithm or NLP algorithms, the classification will give the better accuracy & these analyses will be helpful for product developer and end-user.

Keywords: Sentiment Analysis, Machine Learning, Feature Extraction

Abstract: Retrieving information is an active research area over the years. The main focus is to improve the accuracy of the retrieval systems, and it is seen as one time execution process. It is inadequate for real-world applications when this is seen as long running processes. One of the drawbacks of retrieval is that it needs to be started from the scratch to entire warehouse when there is an interruption. To overcome this Parse Tree Query Language is high level extraction query language is used that enables information retrieval over parse trees. Parse Tree Query Language is an extension of the linguistic query language and intermediate output of each text processing component is stored so that only the improved component has to be deployed to the entire warehouse. Retrieval is performed on both the previously processed data from the unchanged components as well as the updated data generated by the improved component. Performing such kind of enhanced retrieval can result in a huge reduction of processing time and   provides quality to the retrieval.

Keywords: Text mining, query languages, Information Retrieval

Abstract: In this paper, decentralized traffic light control using wireless sensor network. The system architecture is classified into three layers; the wireless sensor network, the localized traffic flow model policy, and the higher level coordination of the traffic lights agents. The wireless sensors are deployed on the lanes going in and out the intersection. These sensors detect vehicles’ number, speed, etc. and send their data to the nearest Intersection Control Agent (ICA) which, determines the flow model of the intersection depending on sensors’ data (e.g., number of vehicles approaching a specific intersection). Coping with dynamic changes in the traffic volume is one of the biggest challenges in intelligent transportation system (ITS). Our main contribution is the real-time adaptive control of the traffic lights. Our aim is to maximize the flow of vehicles and reduce the waiting time while maintaining fairness among the other traffic lights. Each traffic light controlled intersection has an intersection control agent that collects information from the sensor nodes. An intersection control agent manages its intersection by controlling its traffic lights.

Keywords: Automated traffic system, Arduino mega, Ultrasonic sensor, Buzzer, Light Emitting Diode (LED) ; Dual 7-Segment Display Internet of Things (IoT),Traffic congestion. Wi-Fi module ESP 8266

Abstract: An Electrocardiogram (ECG) could be defined as a continuous recording of electrical signals of the heart against time. Analysis of ECG by identifying the various features and traits could help us detect the various cardiac peculiarities. Automatic classification of ECG has evolved as an emerging tool in medical diagnosis for effective treatments. The work proposed in this paper has been implemented using MATLAB that presents an algorithm to detect the various features and the possible abnormalities it could represent. ECG signals in this work are collected across various databases. The processing of the data was done on the Lead-II ECG signals. In addition to that, this paper also provides a comparative study of various methods proposed by researchers used to detect and evaluate P peaks thus helping us obtain the results accurately, thus enabling precise calculations of the waveforms.

Keywords: Electrocardiogram (ECG), Lead-II Configuration, P waves, Heart Defects, Matlab.

Abstract: In India, we have government bodies like Municipal Corporation responsible for maintaining cities. It is Municipal Corporation’s responsibility to provide various services. It is their duty to address citizen’s problems and give response to them. Whenever any citizen has to register complaint he/she has to visit municipal corporation. This is tedious and time-consuming process. It needs lot of paper work like writing letter with detailed information about problem. Due to emergence of internet many complaint sites are developed to provide citizens to lodge complaint in an online way. But today’s generation tend use smart phones and mobile application instead of websites. So, considering current trends mobile application can be used instead of websites. Mobile application will not only be helpful to citizens but also make municipal corporation work feasible. Many features of smart phones like location sharing through GPS will be helpful to locate accurate area of problem.

Keywords: Mobile Application, Citizen, Municipal Corporation, Complaint, Online

Abstract: The biometric is a study of human behavior and features. Face recognition is a technique of biometric. Various approaches are used for it. Authentication & Identification has become major issue in today’s digital world. Face recognition plays a significant role in authentication & identification. In this paper several existing face detection and recognition approaches are analyzed and discussed. Each approached is discussed briefly & compared with the other in terms of key evaluation parameters. As face detection is the elementary yet an important step towards automatic face recognition, main goal of this paper is to come up with an approach that is a good candidate for face detection and face recognition.

Keywords: Face Detection, Face Detection, Skin Color Modeling, Haar like Feature, Principle Component Analysi, Face Recognition, Haar Cascade, LBP, Eigenfaces, Fisherfaces.

Abstract: Human life is depending on demand. This data is categories as "Big Data" due to its three Volume, Variety and Velocity. Most of this data is unstructured, quasi structured or semi structured and it is heterogeneous in nature. The volume and the heterogeneity of data with the speed it is generated, makes it difficult for the present computing infrastructure to manage Big Data. Due to its specific nature of Big Data, it is stored in distributed file system architectures. Hadoop and HDFS by Apache is widely used for storing and managing Big Data. Analyzing Big Data is a challenging task as it involves large distributed file systems which should be fault tolerant, flexible and scalable. Map Reduce is widely been used for the efficient analysis of Big Data. Traditional DBMS techniques like Joins and Indexing and other techniques like graph search is used for classification and grouping of Big Data. These techniques are being adopted to be used in Map Reduce. In this paper we suggest basic over Hadoop and Hadoop Distributed File System (HDFS).

Keywords: Hadoop Distributed File System (HDFS), Relational Databases, Non-structured or semi-structured data model (NoSQL)

Abstract: The needs and expectations of modern-day applications are changing in the sense that they not only need computing resources (processing power, memory or disk space), but also the ability to remain available to service user requests almost constantly 24 hours a day and 365 days a year. These needs and expectations of today’s applications result in challenging research and development efforts in both the areas of computer hardware and software. Parallel supercomputers have been in the mainstream of high-performance computing for the last ten years. The decline of the dedicated parallel supercomputer has been compounded by the emergence of commodity-off-the-shelf clusters of PCs and workstations. Hence, the idea of the cluster came into front with certain recent technical capabilities, particularly in the area of networking, have brought this class of machine to the vanguard as a platform to run all types of parallel and distributed applications. This literature provides all the technical details required to implement the Beowulf Cluster in order to achieve high performance as well as high availability. The literature gives an overview of the features the system provides with.

Keywords: Beowulf Cluster, Building a Beowulf Cluster, Pattern Matching, Handling Node Border Issues

Abstract: In real world application, video security is becoming more important now-a-days due to the happening of unwanted events in our surroundings. Moving object detection is a challenging task in low resolution video, variable lightening conditions and in crowed area due to the limitation of pattern recognition techniques and it looses many important details in the visual appearance of the moving object.[1]Video surveillance system is a process of monitoring and analysing video sequences for the purpose of checking the behaviour, activities and other certain information in a video sequence. It is really a very upcoming area in the real time system. It takes lot of data to storage in computer system. In Manual video surveillance the video contents are analysed by human being and this type of Manual systems are mostly used in real time system. But Semi- automated video surveillance system consists of both human intervention and up to some extent of video processing. The function of the video capture section is to take input video data from the individual cameras connected in the local area network and each of the cameras is accessed through the different IP address. And captured video is correct and failure in the video.

Keywords: Semi- Automated Video Surveillance, K-means Algorithm, Object Detecting, Image Analysis, Image Identification, Image Understanding