Mathematics and Computer Science Research Papers (original) (raw)

Illumination invariance remains the most researched, yet the most challenging aspect of automatic face recognition. In this paper we investigate the discriminative power of colour-based invariants in the presence of large illumination changes between training and test data, when appearance changes due to cast shadows and non-Lambertian effects are significant. Specifically, there are three main contributions: (i) we employ a more sophisticated photometric model of the camera and show how its parameters can be estimated, (ii) we derive several novel colour-based face invariants, and (iii) on a large database of video sequences we examine and evaluate the largest number of colour-based representations in the literature. Our results suggest that colour invariants do have a substantial discriminative power which may increase the robustness and accuracy of recognition from low resolution images.

- by
- •
- Engineering, Electrical Engineering, Electronic Engineering, Computer Science
- by Garba jamiu
- •
- Mathematics, Mathematics and Computer Science

International Journal of Computer Science and Technology (IJCST) is devoted to fields of Computer Science and Technology. The IJCST is a open access peer-reviewed scientific journal published in electronic form as well as print form. The mission of this journal is to publish original contributions in its field in order to propagate knowledge amongst its readers and to be a reference publication.

The present study explored the effectiveness of GeoGebra in enhancing students’ active learning, performance and interest to learn mathematics. Much emphasis was put in teaching and learning exponential and logarithmic functions. The general intention was to investigate whether the use of ICT be used to improve the teaching and learning of mathematics in Rwandan Secondary Schools. The present study is an experimental research design that employed Grade 11 students of one secondary school within Kayonza district of Rwanda. Thus, sample of 34 Grade 11 students were taught exponential and logarithmic functions with the use of GeoGebra from 19 August 2019 to 30 October 2019. Before the intervention, a short group discussion with Grade 11 students was conducted to see the students’ attitudes about learning mathematics using ICT tools. Besides, a mathematics teacher was asked a challenging topic to teach within conventional classroom. After learning with the use of GeoGebra, an attitudina...

- by Fidele Ukobizaba and +1
- •
- Mathematics, Education, Educational Technology, Mathematics Education

Career development is the lifelong process of managing, learning, work, leisure and transition in order to move towards a personally determined and evolving preferred future for the youth. The increasing level of unemployment in developing countries is becoming a source of worry for government and societies at large. The inability of most graduates to secure a suitable job in their area study is a problem many have faced in recent time. In this project, we proposed an enhanced web based model for youth empowerment and career development which is an automated model that will automatically select qualified and certified candidates into the appropriate field of study. The Object Oriented and Design Methodology was used to analyse our findings because of its usability nature and to organize the interaction of the objects within the new system. The MinHash recommendation algorithm was applied to classify candidates using content based filtering approach with candidate’s work experience, the behaviour-based approach was used to test candidates profile details to determine suitability to job allocation of a suitable position in candidate career prospect. Our results showed efficiency in Time Complexity especially in areas that involve speed in access validation of unemployed youths and speed in processing application of an unemployed youth, with values for the evaluated parameters to be 10 and 5 seconds respectively as compared to the Existing System values of 22 and 25 seconds respectively, which further implies that our proposed system outperforms the existing system. In addition, the new system automatically matches and provide screening model to job applications from qualified candidates and the results show that the rate of successful job testing and assignment can be significantly be improved with the most qualified and suitable candidate being assigned the appropriate job which matches his/her course of study, thus streamlining the random selection and producing higher quality output thereby reducing unemployment in the labour market. This work will be beneficial to young graduates, to Government, and any other organization that deals with youth empowerment.

- by IJCSMC Journal
- •
- Mathematics, Computer Science, Object Oriented Programming, Information Technology

Worldwide Interoperability for Microwave Access (WiMAX) networks were expected to be the main Broadband Wireless Access (BWA) technology that provided several services such as data, voice, and video services including different classes of Quality of Services (QoS), which in turn were defined by IEEE 802.16 standard. Scheduling in WiMAX became one of the most challenging issues, since it was responsible for distributing available resources of the network among all users; this leaded to the demand of constructing and designing high efficient scheduling algorithms in order to improve the network utilization, to increase the network throughput, and to minimize the end-to-end delay. In this study, we presenedt a simulation study to measure the performance of several scheduling algorithms in WiMAX, which were Strict Priority algorithm, Round-Robin (RR), Weighted Round Robin (WRR), Weighted Fair Queuing (WFQ), Self-Clocked Fair (SCF), and Diff-Serv Algorithm.

Dynamically changing background ("dynamic background") still presents a great challenge to many motion-based video surveillance systems. In the context of event detection, it is a major source of false alarms. There is a strong need from the security industry either to detect and suppress these false alarms, or dampen the effects of background changes, so as to increase the sensitivity to meaningful events of interest. In this paper, we restrict our focus to one of the most common causes of dynamic background changes: that of swaying tree branches and their shadows under windy conditions. Considering the ultimate goal in a video analytics pipeline, we formulate a new dynamic background detection problem as a signal processing alternative to the previously described but unreliable computer vision-based approaches. Within this new framework, we directly reduce the number of false alarms by testing if the detected events are due to characteristic background motions. In addition, we introduce a new dataset suitable for the evaluation of dynamic background detection. It consists of real-world events detected by a commercial surveillance system from two static surveillance cameras. The research question we address is whether dynamic background can be detected reliably and efficiently using simple motion features and in the presence of similar but meaningful events such as loitering. Inspired by the tree aerodynamics theory, we propose a novel method named local variation persistence (LVP), that captures the key characteristics of swaying motions. The method is posed as a convex optimization problem whose variable is the local variation. We derive a computationally efficient algorithm for solving the optimization problem, the solution of which is then used to form a powerful detection statistic. On our newly collected dataset, we demonstrate that the proposed LVP achieves excellent detection results and outperforms the best alternative adapted from existing art in the dynamic background literature.

- by Ognjen Arandjelovic
- •
- Engineering, Electrical Engineering, Electronic Engineering, Computer Science

High dimensional data is frequently found in various field of study basically in the process of running data analysis; individuals have applied the various techniques available to manage high dimensional data. However, Principal Components Analysis (PCA) and Linear Discriminant Analysis (LDA) have been applied in high dimensional data, reducing the process of classifying features under consideration.

- by IJCSMC Journal
- •
- Computer Science, Robotics (Computer Science), Information Technology, Technology

Utilizing video study methodology where participants, as well as the researcher, analyzed their own video data, this research examined the nature of students talking aloud during peer collaborations in mathematics. The findings suggest that students engage in three types of talking aloud: (1) clarification of thinking (i.e. spontaneous utterances related to the mathematical task); (2) expressions of confusion (i.e. “I don’t understand!”), with the explicit intent of eliciting support from peers; or (3) a combination of (1) and (2). The findings also show that students do not perceive other students’ talking aloud as an inter-communicative gesture. This research highlights the importance emphasizing to students that talking aloud during peer collaborations should be viewed as a potential antecedent to communicative interaction and the importance of teaching students how to listen to one another.

- by Donna Kotsopoulos
- •
- Mathematics, Mathematics Education, Student Engagement, Cooperation

Blockchain allows transactions to be performed much faster than is possible in traditional centralized systems. To provide decentralized payment application to the users. It can be very cost effective. Using Ethereum and Solidity programming language we are creating payment application. Which will include adding functionalities such as depositing ether, gaining tokens, and withdrawing ether in exchange of tokens and also a creator fee. By using Ethereum blockchain technology we can create our own ERC20 token project. ERC20 token is a cryptocurrency built on top of the Ethereum blockchain.

- by IJCSMC Journal and +1
- •
- Computer Science, Computer Science Education, Wireless Networks (Computer Science), Mathematics and Computer Science
- by Ziad Alqadi
- •
- Mathematics, Computer Science, Information Technology, Technology

Dog breed identification problem has many inter-class similarities and makes it difficult to classify or identify dogs which have similarities, we have about 130 different dog breeds and they are identified by convolutional neural network using transfer learning pre-trained models ResNet50 to obtain an accuracy of 82.7%, we use OpenCV implementation to detect human faces and to predict the nearest resemblance to a breed of dog, so if misclassified as human the predicted breed can be known. We use 30 epochs and a batch size of 64 to achieve this accuracy.

- by IJCSMC Journal
- •
- Mathematics, Computer Science, Algorithms, Information Technology

Cloud computing offerings a distinctive way to share distributed resources, cloud computing is a type of Internet-based sharing of distributed assets through web. It is a model that empowerment prevalent, on-demand access to a shared mutual pool of configurable processing property and computing resources. Consequently, security becomes a critical issue in cloud computing. Securing information is the key issue in the field of network security. Cryptography is stand out among the best method to improve data security. This paper discusses the role of cryptography in cloud computing to enhance the information and data security.

- by IJCSMC Journal
- •
- Management, Mathematics, Computer Science, Algorithms

This study presents the results of an analysis of high school chemistry textbooks and teacher-generated questions about gas laws. The materials that were analyzed consisted of 456 questions about gas laws found in seven grade 10 chemistry textbooks and 264 teacher-generated examination questions prepared by seven chemistry teachers from three schools. These questions were classified into three categories (recall, algorithmic, and conceptual); the conceptual questions (ConQ) were further classified into six subcategories (particulate, demonstration, tiered, laboratory, analogy, and series completion) using the descriptions provided on the Conceptual Questions and Challenge Problems website. The findings indicate that most of the textbook questions were algorithmic and that these textbooks were less likely to facilitate or encourage student comprehension of the properties and behaviors of gases or gas law theories. Furthermore, most of the textbook questions do not enable students to develop conceptual understanding and gain higher-order cognitive skills. Although the findings imply that most of the teacher-generated questions were ConQ, the large majority were partially conceptual type questions. The major implication of this research is the need for teachers, textbook writers, and academics to consider question types when creating questions or analyzing chemistry questions at all educational levels.

Advancements in Biomedical field provide lot of assistive devices to help deaf people and visually impaired people. When it comes to the subject of deaf-blind people (who losses both hearing and visual ability) availability of such devices are very limited. Tactile signaling and manual alphabets are the most commonly methods used to make the reciprocal communication between the impaired and the surrounding environment possible. Existing devices like MyVox, Sparsha are use braille tactile reading/writing to make communication between two deaf blind users. Assistive systems available in market are high cost and invasive. The proposed system is wearable, non-invasive, compact and low cost. It can recognize the speech and convert into Morse code vibrations. Raspberry Pi is used to convert speech into text using microphone and then each text changed to Morse code using raspberry pi. These signals will be sending to micro haptic vibrating motors through GPIO pins of raspberry pi which are attached with user's fingers.

- by IJCSMC Journal
- •
- Mathematics, Computer Science, Information Technology, Technology

Our aim is to estimate the perspective-effected geometric distortion of a scene from a video feed. In contrast to most related previous work, in this task we are constrained to using low-level, spatio-temporally local motion features only. This particular challenge arises in many semi-automatic surveillance systems which alert a human operator to potential abnormalities in the scene. Low-level, spatio-temporally local motion features are sparse (and thus require comparatively little storage space) and sufficiently powerful in the context of video abnormality detection to reduce the need for human intervention by more than 100-fold. This paper introduces three significant contributions: (i) we describe a dense algorithm for perspective estimation which uses motion features to estimate the perspective distortion at each image locus and then polls all such local estimates to arrive at the globally best estimate, (ii) we also present an alternative coarse algorithm which subdivides the image frame into blocks, and uses motion features to derive block-specific motion characteristics and constrain the relationships between these characteristics, with the perspective estimate emerging as a result of a global optimization scheme, and (iii) we report the results of an evaluation using nine large sets acquired using existing close-circuit television (CCTV) cameras, not installed specifically for the purposes of this work. Our findings demonstrate that both of the proposed methods are successful, their accuracy matching that of human labelling using complete visual data (by the constraints of the setup unavailable to our algorithms).

The problem of voting is still critical in terms of safety and security. This paper deals with the design and development of a web-based voting system using cloud computing and aadhaar card in order to provide a high performance with high security to the voting system. We also use web technology to make the voting system practical. The proposed Online Voting System allows the voters to authenticate using aadhaar no which is then matched with an already saved within a database that is retrieved from aadhaar card database of the government. The voting system is managed in a simpler way as all the users must login by aadhaar card number and password and click on his/her favorable candidates to cast the vote. This will increase the voting percentage in India and reduces the cost of voting process. By using aadhaar card identification it provides enough security which reduces the false votes.

- by IJCSMC Journal
- •
- Computer Science, Information Technology, Technology, Information Security

- by mohammadi fatima
- •
- Computer Science, Machine Learning, Data Mining, Fraud Detection And Prevention

Data mining is defined as the process in which useful information is extracted from the raw data. In order to acquire essential knowledge it is essential to extract large amount of data. This process of extraction is also known as misnomer. Currently in every field, there is large amount of data is present and analyzing whole data is very difficult as well as it consumes a lot of time. The prediction analysis is most useful type of data which is performed today. To perform the prediction analysis the patterns needs to generate from the dataset with the machine learning. The prediction analysis can be done by gathering historical information to generate future trends. So, the knowledge of what has happened previously is used to provide the best valuation of what will happen in future with predictive analysis. Crop production analysis is one of the applications of prediction analysis. The techniques which are designed so far the machine learning techniques. The machine learning techniques are applied with the feature extraction. In this paper, the machine learning techniques are reviewed in terms of technical description and outcomes.

- by IJCSMC Journal
- •
- Computer Science, Algorithms, Information Technology, Technology

The use of social networking websites has increased since last few decades. The social networking sites such as Twitter, Facebook, LinkedIn and YouTube are sources of human interaction, where the users are allowed to create and share their activities, thoughts and opinions pertaining to different subjects. These sites have not only connected large user populations but have also captured massive information associated with their daily interactions in the form of Big Data. This data provides unprecedented information about human behavior and social interactions. It makes it possible to understand who the users are, what their interests are and what they need. This information is vital for businesses to target potential consumers or seek customer opinions in the event of diversification as a business strategy. Thus, this work analyzes social media data to predict significant personality traits, i.e. qualities or characteristics specific to an individual, using the Big Five Model. The predictions can be applied to various domains like business intelligence, marketing, sociology and psychology. A parallelism between an individual’s personality traits and his/her linguistic information is explored for analytics.

- by Pawan Bhutani
- •
- Computer Science, Machine Learning, Data Mining, Fraud Detection And Prevention

At present, there is a job-crisis and it's very hard to find jobs for fresher students. Even if the students are having good talent, they are not able to find the right job. Some students are employed, but not at the place where they really should be. So, this Student Alumni job portal helps the employees to find job vacancies appropriately online. Then alumni students can post the job opening in their organization or any other opening they come across and view their profile from and contact if they expect from those students to be suitable for particular vacancy. So, hidden talent can be come out. In this portal there will be a direct interaction between the alumni and the students to find the jobs in related to their job preferences. Most of the time students depend on the job portals for finding the jobs. This is a novel approach for findings the jobs from their seniors or their faculty members. We have three roles in the project student, alumni and admin for the portal.

- by IJCSMC Journal
- •
- Mathematics, Computer Science, Algorithms, Information Technology

Nowadays with evolving technologies, it is possible to connect real world with virtual world by using some intelligent sensors or physical object. Internet of Things (IoT) is one of such technology. The rise of interest in IoT is leading to a new era in which all objects, devices and sensors that are connected over the internet. This will change the pattern of how we collect and analyse data to make our systems more efficient. This will in turn improve quality of mankind. Using IoT the user will be able to communicate and control physical devices. This survey paper describes and compares some major protocols like MQTT, AMQP, CoAP, XMPP, HTTP/HTTPS, RESTFUL SERVICES and WEBSOCKETS. Comparison of IoT protocols is done based on parameters like what type of transport, security, Architectural style it provides and how it works in Low power and lossy network. We have mentioned whether the protocol support Publisher/Subscriber mode or Request/response mode for communication. We have also discussed some major cloud platforms that are used in IoT like AWS, AZURE, firebase cloud computing. We have made comparative study on cloud platform based on its computing architecture, services, load balancing techniques and security.

- by IJCSMC Journal
- •
- Computer Science, Robotics (Computer Science), Information Technology, Technology

Majority of the issues faced by the farmers can be solved by technology not only from the R&D of hybrid plants and seeds but also by providing information about new markets, producing value added products when market is down, platforms to raise queries regarding agricultural problems, the fertilizers usage for these crops, the soil conditions in which these crops yield more, and the suitable climatic and environmental conditions for these crops, etc. This project FARMING ASSIST WEB APPLICATION is a prototype model to solve the issues faced by farmers in the current environment. This project will provide information about weather, current market, information about various
crops, fertilizer required at various intervals of time, best crop that is to be planted at your field, etc. This project can act as a survey to the farming issues without a field work.

Car rental mobile application ensures safety of both the renter and the renter's automobile. By a score allocation method generated from data recorded over years ensures the trustworthiness of the driver and the vehicle. The data is pulled out based on the renter's Driver's Licence or the renter's car's RC Book and Insurance details obtained during login. When a user enters his details it will be verified with a database by an authority who awards a Credit score (out of 5), based on his prior history. Based on a renter's score the cars that are most likely to be available to him are displayed. Out of these he/she picks one and a request is sent to the renter. The renter on receiving the request chooses to give his car to the renter or decline the request. If the renter's scores are so low that he is not being accepted by any renter, He can be awarded with one of organization owned cars with higher fares and critical monitoring systems. In order to update scores in the database a routine verification will be done every 3 months and based on the findings the score will be increased or decreased by a defined value. This improves the efficiency of renting and lending cars and makes the process easier.

- by IJCSMC Journal and +2
- •
- Computer Science, Algorithms, Information Technology, Technology

With the advancement of motorization and robotization, modern unrest has happened in all pieces of the world. This has expanded the expectations for everyday comforts of the humanity and furthermore added to the financial development of the nation. IoT has changed itself to suite different fields. This undertaking is to plan IoT based transport passage observing framework which is actualized utilizing RFID reader and Arduino Mega. A model of the product must be created to catch the subtleties of the vehicle number, driver subtleties, passage and leave time of the specific vehicle alongside date. Entry time of vehicle ought to be caught utilizing RFID tag. It is then put away in the database in three squares, first the transports entering the grounds on schedule, at that point the transports entering the grounds late. At last the transports which never entered the grounds is put away in a different square and a notice is sent to the administrator as a SMS. Our paper presents test consequences of the framework to proficiently screen the college transport entering and leaving the grounds.

- by IJCSMC Journal
- •
- Computer Science, Information Technology, Technology, Educational Technology

ABSTRACT
This work borders on Online Vehicle Sales Management System. The current system of Online Vehicle Sales is faced with few technical issues, ranging from information regarding sales of cars is manually done e.g. product details, distributor details, purchases, and sales details. This calls for the need to develop a system that corrects this error. The design Vehicle Sales Management System Enable customers to purchase vehicles online with secure credit card payment gateway thereby reducing risk of travelling to purchase the car. The present system Register and keep the information about all Benny & Co. vehicles. The methodology adopted for this project is the Structured System Analysis and Design Methodology (SSADM). The new system helps car dealers to maintain vehicle for sale inventories, quickly create car sales listings, track and manage car sales.

Sudoku is a pretty popular number game. The goal of this game is to fill a 9x9 matrix with unique numbers, and there should not be repeated numbers in each row, column, or block. This paper proposed a solution to solve Sudoku using the Backtracking Algorithm. This algorithm is quite efficient because it does not have to check all the possibilities that exist, but which leads to only the solution that will be processed, namely by pruning every element that does not lead to the solution. Thus the time required is quite efficient and suitable for use in reasonably complex numbers games like sudoku. By implementing the backtracking algorithm in the sudoku game, the complexity of the algorithm can be as large 𝜽 (n3).

Cancer is a disease that develops in the human body due to gene mutation. Because of various factors, cells can become cancerous and grow rapidly, destroying normal cells at the same time. Support vector machines allow for accurate classification and detection of the classes. The advantage of kernel selection is to derive global learning rates for SVMs using the Genetic Folding algorithm. The developed GF algorithm outperforms traditional SVMs in the UCI Breast Cancer Wisconsin Diagnostic (BCWD) dataset under a certain comparative analysis, which is conducted under a set of conditions that describe the behavior of the compared algorithms. The observation that relates the GF performance appears to be comparable with SVM. The statistical analysis relies on a careful analysis of the ROC curve. Moreover, the GF algorithm shows that accuracy rates are obtained adaptively, that is, without knowing the parameters resulting from the margin conditions. The experimental results show that the ...

- by Mohammad Mezher
- •
- Mathematics, Computer Science, Algorithms, Mathematics Education

The interaction between a nurse and patient depends majorly on the communication medium. The augmentation of the Internet of Things (IoT) in the recent era allows us to accommodate this technology in various aspects of our lives to make the process secure and reliable. We are using the knowledge of IoT for making this interaction system secure and easy to use. By introducing hand gestures for calling the attendee makes this device convenient to operate by the differently abled people. From this perspective, this paper presents a real-time nurse calling system based on the performed hand movements. Further, the gesture is detected by the accelerometer and processed by the micro controller. The corresponding message is sent to the attender's smartphone, and the nurse responds at the earliest. The device uses low-cost components such as Raspberry Pi, accelerometer and a heartbeat sensor.

- by IJCSMC Journal and +2
- •
- Information Systems, Mathematics, Computer Science, Information Technology

The computerized world we are living in has a ton of information and data that is utilized by an assortment of clients, for example, videos, books and articles. Different users like different content. Getting what each user likes can be irritating. Each online services provider always aims in having many clients. Recommender systems importance’s arises in such situations. The recommender framework proposes to a client some substance for example e.g. movies and books depending on what the user likes. In this research, a new movie recommender system is proposed, that will be able to improve the existing recommender systems. With this new recommender framework, the client will receive an improved forecast contrasted with different frameworks that as of now exist for example content-based filtering and collaborative-filtering. In order to overcome the disadvantages of the both methods (collaborative filtering algorithm (unsupervised learning) and content-based filtering algorithm (supervised learning)), the new system combines both methods. This will bring up a more stable system compared to the existing ones.

- by IJCSMC Journal and +1
- •
- Mathematics, Computer Science, Algorithms, Information Technology

This Project is focused on credit card fraud detection in real world scenarios. Nowadays credit card frauds are drastically increasing in number as compared to earlier times. Criminals are using fake identity and various technologies to trap the users and get the money out of them. Therefore, it is very essential to find a solution to these types of frauds. In this proposed project we designed a model to detect the fraud activity in credit card transactions. This system can provide most of the important features required to detect illegal and illicit transactions. As technology changes constantly, it is becoming difficult to track the behavior and pattern of criminal transactions. To come up with the solution one can make use of technologies with the increase of machine learning, artificial intelligence and other relevant fields of information technology; it becomes feasible to automate this process and to save some of the intensive amounts of labor that is put into detecting credit card fraud. Initially, we will collect the credit card usage data-set by users and classify it as trained and testing dataset using a random forest algorithm and decision trees. Using this feasible algorithm, we can analyze the larger data-set and user provided current data-set. Then augment the accuracy of the result data. Proceeded with the application of processing of some of the attributes provided which can find affected fraud detection in viewing the graphical model of data visualization. The performance of the techniques is gauged based on accuracy, sensitivity, and specificity, precision. The results is indicated concerning the best accuracy for Random Forest are unit 98.6% respectively.

- by IJCSMC Journal and +2
- •
- Computer Science, Machine Learning, Data Mining, Fraud Detection And Prevention

It’s a great resource for someone with a modest amount of professional programming experience and a basic knowledge of data structures and algorithms. Bentley covers a wide range of topics relevant to the working programmer, including multiple chapters with case studies of algorithmic development from Bentley’s life as a professional developer, a chapter on the importance of choosing the right data structure(s) for your program, program performance/tuning, and finally a number of chapters that discuss specific algorithms and data structures.

- by Camilo Vargas
- •
- Business, Business Administration, Computer Science, Software Engineering

This paper defines an-Autonomous Fire Fighting Robot‖ which recognizes and quenches the fire automatically. It detects the fire by using IR Flame sensor and Ultrasonic sensor is utilized for obstacles dodging. First as it moves near to the flame, then it detects the fire automatically and pumps motor to spray extinguisher which is controlled through motor driver circuit. Arduino Mega is used as microcontroller to program all the autonomous AI code and performing all the major functionalities. It is also connected to the local server by using Wi-Fi module. Our robot can help in all the organizations like banks, industries, factories, bakeries etc.

- by IJCSMC Journal
- •
- Robotics, Mathematics, Computer Science, Algorithms

High-speed networks and ubiquitous Internet access become available to users for access anywhere at anytime. Cloud computing is a concept that treats the resources on the Internet as a unified entity, a Cloud storage is a model of networked online storage where data is stored in virtualized pools of storage which are generally hosted by third parties. Hosting companies operate large data centers, The data center operators, in the background, virtualized the resources according to the requirements of the customer and expose them as storage pools, which the customers can themselves use to store files or data objects. Physically, the resource may span across multiple servers. Data robustness is a major requirement for storage systems. There have been many proposals of storing data over storage servers. One way to provide data robustness is to replicate a message such that each storage server stores a copy of the message. A decentralized erasure code is suitable for use in a distributed storage system.

- by IJCSMC Journal
- •
- Computer Science, Information Technology, Technology, Encryption

Character recognition is the process of detecting and processing a character or words and storing it in textual format. This project aims to build a character recognition system to digitize the ancient Tamil script and additionally translate the obtained script to modern Tamil. Although technologies around image processing are almost at perfection for languages like English and other modern languages, recognition of ancient scripts is still elusive. Conventional methods used by the Archaeological department convert the documents manually, which is possible only with the help of an expert. The proposed system will cross out such a need and will enable the common man to decipher the ancient scripts from inscriptions and manuscripts and also digitize, and also enable to process the data using Natural Language Processing. The system incorporates Convoluted Neural Networks to extract the features from each character to detect and translate the character to modern Tamil with 94.6 % accuracy.

- by IJCSMC Journal
- •
- Mathematics, Computer Science, Image Processing, Computer Engineering

There have been a lot of developments towards the Humans Computers Interaction (HCI). Many modules have been developed to help the physical world interact with the digital world. Here, the proposed paper serves to be a new approach for controlling mouse movement using Colored object and marker motion tracking. The project mainly aims at mouse cursor movements and click events based on the object detection and marker identification. The software is developed in Python Language and OpenCV and PyAutoGUI for mouse functions. We have used colored object to perform actions such as movement of mouse and click events. This method mainly focuses on the use of a Web Camera to develop a virtual human computer interaction device in a cost effective manner.

- by IJCSMC Journal and +2
- •
- Computer Science, Human Computer Interaction, Information Technology, Computer Vision

The image processing is the technique which can process the digital information stored in the form of pixels. This research work is related to plant disease detection. The plant disease detection has the various phases like pre-processing, segmentation, feature extraction and classification. In this paper, various techniques of plant disease detection are reviewed in terms of certain parameters. It is analyzed that classification methods are most efficient techniques for the disease detection.

- by IJCSMC Journal and +2
- •
- Mathematics, Computer Science, Information Technology, Technology

Traditional approaches to extract useful Keyphrase from a sentence rely heavily on human effort. In this paper, to overcome this challenge, Automatic Keyphrase Extraction algorithm has been used to extract a Keyphrase efficiently that reduces the scope for human errors and saves time. The Machine Learning algorithms detect the Keyphrase from a sentence that the user feeds as an input and sets a reminder using the Keyphrase. RAKE and Textrank algorithms help to extract Keyphrase or important terms of a given text document. RAKE and TextRank techniques applied to find and analyze the best possible way of extracting the Keyphrase efficiently. With slight modifications to the code, the algorithms can be implemented to serve different application domain such as message or threat decoding in military purposes and can be extended to use in speech-to-text translation and sentimental analysis of the data.

- by IJCSMC Journal
- •
- Mathematics, Computer Science, Algorithms, Natural Language Processing

Fire is as destructive as it is useful. Without a proper pro-active approach to preventing fire
outbreaks, the results could be extremely disastrous when they occur. Thus, there is a need for a fast and
convenient way of reporting fire incidents. The growing usage of smartphones provides a way of equipping
the public with a means of reporting fire incidents to ensure prompt response and proper management of the
incidents. In this paper, we analyze the manual process of reporting fire outbreaks and design an automated
FEAP – a mobile application, to enable the public to quickly alert nearest fire emergency units of any
possible fire incidents. We developed FEAP with the aid of the Software Development Life Cycle (SDLC)
phases and Unified Modeling Language (UML) which was used as a model to visualize the design view of the
application. An Entity Relationship Diagram (ERD) was used for database design and a simple Graphical
User Interface (GUI) prototype of the proposed application was designed. Our work highlights a practical
application of analysis and design concepts in developing a software to providing an efficient solution in
reporting fire outbreaks.

- by IJCSMC Journal and +2
- •
- Computer Science, Information Technology, Technology, Fire and Emergency Services