Journal of Computer Based Parallel Programming
EISSN : 2582-2179
Published by: MAT Journals (A unit of ARV Infomedia Pvt. Ltd.) (10.46610)
Total articles ≅ 11
Latest articles in this journal
Published: 29 July 2022
Journal of Computer Based Parallel Programming, Volume 7, pp 26-33; https://doi.org/10.46610/jocpp.2022.v07i02.004
Chronic kidney disease (CKD) known as chronic renal disease is the situation where kidney loose their ability to filter the blood as they should. Early prediction and appropriate treatment can slow or stop down the progression of this CKD. Machine learning algorithms are an important aid for health care professionals to make accurate diagnosis in the early stages of this illness. In order to predict CKD, this study suggests using machine learning algorithms like Support Vector Machine (SVM) and Random Forest (RF). The final output uses minimum count of characteristics to predict if people have CKD or not.
Published: 16 June 2022
Journal of Computer Based Parallel Programming, Volume 7, pp 1-6; https://doi.org/10.46610/jocpp.2022.v07i02.001
Privacy is one of the most popular technologies in the IT industry. A lot of data is collected from users from various sources. The same IoT (Internet of Things) application raised concerns about privacy in IoT systems. Sensor data collects information about users' daily activities and makes life easier, but compromises privacy and security. Implementing privacy and security into applications is a huge challenge. This article presents common methods for maintaining privacy and protecting statistics in IoT applications. To this end, many encryption methods are analysed, and finally, a comparative analysis of personal information protection methods and their applications is presented.
Published: 28 February 2022
Journal of Computer Based Parallel Programming, Volume 7, pp 7-12; https://doi.org/10.46610/jocpp.2022.v07i01.002
SDN (Software-Defined Networking) is a new networking architecture that is enterprising, feasible, cost-effective and robust applications. This approach decouples network management and forwarding operations, allowing network control to be directly programmable while the underlying infrastructure is veiled for applications and network services. MQTT is a lightweight publish-subscribe network protocol for sending and receiving messages. It is made for communications with remote places when there are resource limits or network capacity limitations. The ESP8266EX-based NodeMCU development board is a small module that has a microcontroller, integrated Wi-Fi receiver, and transmitter. The findings of the performance evaluation show that IoT devices' computational overhead and energy consumption are decreased, as well as the total time of the handshake.
Published: 7 December 2021
Journal of Computer Based Parallel Programming, Volume 6; https://doi.org/10.46610/jocpp.2021.v06i03.005
Text detection in video frames provide highly condensed information about the content of the video and it is useful for video seeking, browsing, retrieval and understanding video text in large video databases. In this paper, we propose a hybrid method that it automatically detects segments and recognizes the text present in the video. Detection is done by using laplacian method based on wavelet and color features. Segmentation of detected text is divided into two modules Line segmentation and Character segmentation. Line segmentation is done by using mathematical statistical method based on projection profile analysis. In line segmentation, multiple lines of text in video frame obtained from text detection are segmented into single line. Character segmentation is done by using Connected Component. Analysis (CCA) and Vertical Projection Profile Analysis. The input for character segmentation is the line of text obtained from line segmentation, in which all the characters in the line are segmented separately for recognition. Optical character recognition is Processed by using template matching and correlation technique. Template matching is performed by comparing an input character with a set of templates, each comparison results in a similarity measure between the input characters with a set of templates. After all templates have been compared with the observed character image, the character’s identity is assigned with the most similar template based on correlation. Eventually, the text in video frame is detected, segmented, and processed to OCR for recognition.
Published: 26 November 2021
Journal of Computer Based Parallel Programming, Volume 6; https://doi.org/10.46610/jocpp.2021.v06i03.001
Handwritten character recognition a field of research in AI, computer vision, and pattern recognition. Devanagari handwritten Marathi compound character recognition is most tedious tasks because of its complexity as compared to other languages. As compound character is combination of two or more characters it becomes challenging task to recognize it. However, the researchers used various methods like Neural Network, SVM, KNN, Wavelet transformation to classify the features of compound Marathi characters and tried to give the accuracy in the recognition of it. But the problem of feature extraction, and time required is large. In this paper I am proposing the Offline handwritten Marathi compound character recognition using deep convolution neural network which reduces the computational time and increases the accuracy.
Published: 17 August 2021
Journal of Computer Based Parallel Programming, Volume 6; https://doi.org/10.46610/jocpp.2021.v06i02.006
In privacy-enhancing technology, it has been inevitably challenging to strike a maintain balance between privacy, efficiency and usability (utility). We propose a highly practical and efficient approach for privacy-preserving integration and sharing of datasets among a group of participants. At the heart of our solution is a new interactive protocol, Secure Channel. Through Secure Channel, each participant is able to randomize their datasets via an independent and untrusted third party, such that the resulting dataset can be merged with other randomized datasets contributed by other participants group in a privacy-preserving manner. Our process does not require any public or key sharing between participants in order to integrate different datasets. This, in turn, leads to a user can understand and use easily and scalable solution. Moreover, the accuracy of a randomized dataset which are returned by the third party can be securely verified by the other participant of group. We further demonstrate Secure Channel’s general utilities, using it to construct a structure preserving data integration protocol. This is mainly useful for, good quality integration of network traffic data.
Published: 28 July 2021
Journal of Computer Based Parallel Programming, Volume 6; https://doi.org/10.46610/jocpp.2021.v06i02.004
In recent years, photo-based social media has become one of the most common social media platforms. Understanding user preferences in user-generated images and making suggestions has become a major necessity due to the large number of images uploaded daily. Several types of hybrids have been suggested to improve the performance of the recommendations by combining different types of third-party information (e.g., image representation, interaction) with user object history. Previous research, however, has failed to incorporate complex factors that affect user preferences into the corresponding framework due to various image features created by users on social media. In addition, many of these hybrid models have used pre-defined weights to combine different types of data, resulting in less favorable performance. To this end, we present a consistent model for capturing public imagery in this paper. We define three key elements (i.e., upload history, social exposure, and proprietary information) that affect each user's preferences, where each item summarizes the content aspect from complex interactions between users and images, in addition to the basic matrix interest model matrix factorization proposal. After that, we create a consecutive natural attention network that demonstrates a consistent relationship between hidden user interests and known key elements (elements at each level and feature level). A sequential attention network will learn to pay attention to more or less content using embedding from higher learning models designed for each type of data. Finally, the availability of extensive tests on real-world information indicates that our proposed model is superior.
Published: 23 July 2021
Journal of Computer Based Parallel Programming, Volume 6; https://doi.org/10.46610/jocpp.2021.v06i02.003
Steganography is a way of hiding data in the context of an image, preventing a person from finding it by mistake. This is an explicit text file with an image file. Due to the need for steganography, we have proposed a new algorithm called the use of steganography. In our algorithm, we should have a cover and a message. It can be pixel-for-pixel in an image. In it, we will have to use every bit of encryption. This process will continue until the final track of encryption. After this step, the data is hidden in the image. We will send the image file to the client, and the client will need to change the process to download the source code to the image.
Published: 29 May 2021
Journal of Computer Based Parallel Programming, Volume 6; https://doi.org/10.46610/jocpp.2021.v06i02.001
Published: 14 August 2020
Journal of Computer Based Parallel Programming, Volume 5, pp 22-25; https://doi.org/10.46610/jocpp.2020.v05i02.005
Most of the people in this today’s world are unhealthy mainly due to the lack of intake of hygienic food and lack of exercise. Nowadays, most of the people are failed to be fit. Lack of fitness drastically can bring health issues for the human beings in their very small age. Each human being should take some step to maintain their body fitness to stay healthy. Most of the people feel inconvenient to go in search join of fitness class. So, each person needs a connectivity to their good fitness class. This could solve their problems without any inconvenience and could maintain body fit in an efficient way. So, considering all these issues, a web page has been developed to connect the fitness class coach and the joiner to their convenient region and conditions. We are providing the website in which the user of the system can register online to join the fitness class. Service offered by the class and the trainer information of the fitness class are provided in this system. Since, many good fitness classes may be localised to specific region hence some people cannot join due to distance issue. In this system, user can virtually attend classes in online mode they can preplan their schedule accordingly coach will be assigned to them.