International Journal of Computer (IJC - Global Society of Scientific Research and Researchers, GSSRR)
Not a member yet
459 research outputs found
Sort by
An Efficient Method to Enhance Health Care Big Data Security in Cloud Computing Using the Combination of Euclidean Neural Network And K-Medoids Based Twin Fish Cipher Cryptographic Algorithm
Get PDFBig data is a phrase that refers to the large volumes of digital data that are being generated as a consequence of technology improvements in the health care industry, e-commerce, and research, among other fields. It is impossible to analyze Big Data using typical analytic tools since traditional data storage systems do not have the capacity to deal with such a large volume of data. Cloud computing has made it more easier for people to store and process data remotely in recent years. By distributing large data sets over a network of cloudlets, cloud computing can address the challenges of managing, storing, and analyzing this new breed of data It\u27s possible for private data to be leaked when it is kept in the cloud, as users have no control over it. This paper proposes a framework for a secure data storage by using the K-medoids-based twin fish cipher cryptographic algorithm. We first normalize the data using the Filter splash Z normalization and then apply the Euclidean neural network to compute similarity, which ensures data correctness and reduces computational cost. As a result, the suggested encryption strategy is used to encrypt and decode the outsourced data, thereby protecting private information from being exposed. The whole experiment was conducted using health data from a large metropolis from the Kaggle database. Using the recommended encryption method, users will be able to maintain their privacy while saving time and money by storing their large amounts of data on the cloud
Smart Application for Car Parking System at Nakhon Ratchasima Rajabhat University
Get PDFThis smart application, namely “CarPark”, was developed to solve vehicle parking problems at Nakhon Ratchasima Rajabhat University. Because, at present, there are many cars travel around Nakhon Ratchasima Rajabhat University each day, but parking at the university is limited. Therefore, it takes a long time to find parking, and sometimes drivers need to park in prohibited areas. This blocks entrances and exits. The “CarPark” application can be used to find a parking lot, a parking space, a car and a car owner. It can also be applied to motorcycles and expandable for users to use with many parking lots, parking spaces for an unlimited number of cars and motorcycles. Actual trialed users used parking spaces at all 30 buildings at Nakhon Ratchasima Rajabhat University. A total of 44 users, including executives, lecturers, students, staffs and external personnel, were assessed. The average application satisfaction score was 4.06, which is quite high. This smart application can also be used in any parking lot of any organization for any registered vehicle
Battery Lifetime Analysis of XBee Sensor Using Transmission Power and Period Approaches: A Case of Server Room Monitoring System
Get PDFIn the server room, it is necessary to monitor the appropriate temperature for the efficient use of electricity. Especially in hot regions and seasons. For example, April is the summer in Thailand where the temperature is about 35-40 OC every year, but the optimum temperature for the server room is about 20-22 OC. This paper presents the measurement of a wireless temperature system through the use of XBee sensors to monitor the real-time server room temperature. The system consists of an XBee sensor node, Gateway (GW), and IoT cloud server. In addition, the measuring device can use a wireless sensor, it is convenient and easy to install as well.Therefore, when choosing a wireless sensor device, it is necessary to test its performance in terms of both the period and the power transmission of the device. Such parameters affect the battery lifetime. The results of the measurement of the sensor’s energy efficiency measured the voltage drop of the device by adjusting the power transmitter and period of the XBee sensors. These parameters directly affect the battery power output and are expected to benefit users in the future
Design and Implementation of Decentralized Voting System on the Ethereum Blockchain
Get PDFThis work involves the design and implementation of a decentralized voting system on the Ethereum blockchain, which is a peer-to-peer network. The system is helpful in carrying out free and fair elections as information stored on the blockchain is immutable. This voting application uses solidity as the backend language and the web3 library for reading and interacting with the blockchain. JavaScript, Hyper Text Markup Language (HTML), and Cascading Style Sheets (CSS) are used to design the front end and the control logic for the website. The voting system works with the locally installed Ethereum node. The user visits the website and registers his details which are then uploaded to the blockchain in the cryptographically hashed pattern. After registering, the user is directed to the voting page, which reads the intelligent contract data and allows the user to cast his vote and at the same time update the blockchain. This system can be deployed in schools, organizations, countries, anywhere there is a need for governance and democratic voting. The prototype built was tested and found to be working perfectly
Measurement of LoRa-based Received Signal Strength Indication (RSSI) Using Point-to-Point Topology in a Seaside Area
Get PDFA data monitoring system’s performance analysis is fundamental to proving quality and networking efficiency. This paper presents the received signal strength indication (RSSI) measurements of wireless communication with point-to-point LoRa technology for use in the 433 MHz frequency band. The test was performed in the area of Chalathat beach, Songkhla province, Thailand, which has a barrier environment of trees along the shore and is opposite the Rajamangala University of Technology Srivijaya (RUTS). This demonstration was conducted in the actual location to observe the loss from coastal environment conditions from waves and sea breeze. In addition, the study aimed to determine the effect of signal performance by RSSI measurements. The test consisted of a transmitter (Tx) and a receiver (Rx) with a transmit power of 17 dBm and an antenna gain of 3 dBi on both Tx and Rx. The testing starts with RSSI measurements from a distance of 10 meters and increases the number of measures by 10 meters until data loss begins. The test results showed that communication distances could be connected up to 500 meters without packet loss, with RSSI as low as -107 dBm, and a correlation graph in the form of a logarithmic function with a reduced tendency. However, the RSSI value decreases as the distance increases. At the same time, the test results can indicate its effectiveness as a guide for further application of monitoring systems at the beach area
Information System and Marketing Channels as a Support for Small Textile Companies: Masaru S.A.
Get PDFThe objective of this scientific article is to implement an information system that will help small and micro enterprises to improve their processes through online service platforms, which, when related to marketing channels, will offer the construction of sustainable competitive advantages, in consistent organizations as a contribution to the global systematization of small and micro enterprises. The methodology used is applied, causal correlational, non-experimental, carried out in the field, using the survey technique and a questionnaire as an instrument. Shapiro-Wilk was applied because n < 50 (n = 28). P - Value is less than 0.05 (p=0.001 for both variables), where it does not present normal distribution. Developing the hypothesis test, the significance level is less than 0.05 (0.020), we accept the research hypothesis. It is concluded that there is a relationship in the application of an information system related to the commercialization channels as a competitive support that will improve the processes in the company Masaru S.A
Sentiment Analysis of Nigerian Students’ Tweets on Education: A Data Mining Approach
Get PDFThe paper is aimed at investigating data mining technologies by acquiring tweets from Nigerian University students on Twitter on how they feel about the current state of the Nigerian university system. The study for this paper was conducted in a way that the tweet data collected using the Twitter Application was pre-processed before being translated from text to vector representation using a feature extraction technique such Bag-of-Words. In the paper, the proposed sentiment analysis architecture was designed using UML and the Naïve Bayes classifier (NBC) approach, which is a simple but effective classifier to determine the polarity of the education dataset, was applied to compute the probabilities of the classes. Furthermore, Naïve Bayes classifier polarized the tweets\u27 wording as negative or positive for polarity. Based on our investigation, the experiment revealed after data cleaning that 4016 of the total data obtained were utilized. Also, Positive attitudes accounted for 40.56%, while negative sentiments accounted for 59.44% of the total data having divided the dataset into 70:30 training and testing ratio, with the Naïve Bayes classifier being taught on the training set and its performance being evaluated on the test set. Because the models were trained on unbalanced data, we employed more relevant evaluation metrics such as precision, recall, F1-score, and balanced accuracy for model evaluation. The classifier\u27s prediction accuracy, misclassification error rate, recall, precision, and f1-score were 63 %, 37%, 63%, 62%, and 62% respectively. All of the analyses were completed using the Python programming language and the Natural Language Tool Kit packages. Finally, the outcome of this prediction is the highest likelihood class. These forecasts can be used by Nigerian Government to improve the educational system and assist students to receive a better education
Analysis of Biodegradable and Non-Biodegradable Materials Using Selected Deep Learning Algorithms
Get PDFIt is possible to divide the materials used in the world into recyclable and nonrecyclable. Biodegradable materials contain elements naturally degraded by microorganisms such as foods, plants, fruits, etc. Waste from this material can be processed into compost. non-biodegradable materials include materials that do not naturally decompose, such as plastics, metals, inorganic elements, etc. Waste from this material can only be reused by converting it into new materials. In this study, the classification of biodegradable and non-biodegradable materials was done using deep learning methods. Convolutional Neural Network (CNN) performs steps such as preprocessing and feature extraction in classification. 5430 images were used for the dataset. 70% of this dataset was used as training data, 15% as validation data, and 15% as test data. Of the Deep Learning methods, the pre-trained neural networks AlexNet, ShuffleNet, SqueezeNet, and GoogleNet were used. For each algorithm, the performances were evaluated by classifying them as biodegradable and non-biodegradable. With this study, we can identify, track, sort, and process waste materials by classifying materials
Empirical Study of MRI Brain Tumor Edge Detection Algorithms
Get PDFA brain tumor refers to the abnormal growth of cells that can be found in the brain or the skull. MRI is a type of advanced medical imaging that provides detailed information about the anatomy of the human soft tissues. Medical experts perform tumor segmentation using magnetic resonance imaging (MRI) data, which is an essential part of cancer diagnosis and treatment. Tumor detection refers to the methods that are used to diagnose cancer or other types of diseases. Edge detection is also one of the common methods that come under the process of treating medical images. The main objective of edge detection is discovering information about the shapes, transmission, and reflection of images. In this paper, we investigated the performance comparison MRI brain tumor edge detection Algorithms. The Canny, and Prewitt are used for investigation. As result, Canny edge detection is better than Prewitt in term of clarity and visibility for the tumor
System Biology and Machine Learning Framework for Prostate Cancer Survival Prediction
Get PDFProstate cancer (PC) is the most commonly diagnosed and the second most lethal malignancy in men. Proper understanding about the factors influencing the disease mechanism, response to the treatment and long term survival could facilitate effective disease management, treatment planning and decision making. Previous research initiatives reported a number of genes having impact on PC development but their genetic influence on the overall survival of the patients is still obscure. In this study, we fist identified PC related signature genes by analysing the RNA-seq transcriptomic data. Then we investigated the influence of those genes on the survival of PC patients using the clinical and transcriptomic data from the Cancer Genome Atlas (TCGA). Considering the univariate and multivariate analysis using the Cox proportional-hazards (CoxPH) model, we evidenced notable variation in the survival period between the altered and normal groups for two genes (APLN, and DUOXA1). We also identified ten hub genes such as CAV1, RHOU, TUBB4A, RRAS, EFNB1, ZWINT, MYL9, PPP3CA, FGFR2 and GATA3 in protein-protein interaction analysis that could be the source of potential therapeutic intervention. Moreover, several significant molecular pathways through functional enrichment analysis was obtained. After verification through functional studies, the identified genetic determinants could serve as therapeutic target for prolonged PC survival