Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
A Machine Learning Model on Virtual University of Senegal's Educational Data Based on Lambda Architecture
Get PDFNowadays, a new form of learning has emerged in higher education. This is e-Learning. Lessons are taught on a Learning Content Management Systems (LCMS). These platforms generate a large variety of data at very high speed. This massive data comes from the interactions between the system and the users and between the users themselves (Learners, Tutors, Teachers, administrative Agents). Since 2013, UVS (Virtual University of Senegal), a digital university that offers distance learning through Moodle and Blackboard Collaborate platforms, has emerged. In terms of statistics, it has 29340 students, more than 400 active Tutors and 1000 courses. As a result, a large volume of data is generated on its learning platforms. In this article, we have set up an architecture allowing us to execute all types of queries on all data from platforms (historical data and real-time data) in order to set up intelligent systems capable of improving learning in this university. We then set up a machine learning model as a use case which is based on multiple regression in order to predict the most influential learning objects on the learners' final mark according to his learning activities
Aquatic Iguana: A Floating Waste Collecting Robot with IoT Based Water Monitoring System
Get PDFWater pollution is a major problem worldwide. In order to tackle the pollution and keeping the water resources clean, this paper presents an affordable and advanced floating garbage removing robot called "Aquatic Iguana". The robot moves around the surface of the water and collects floating waste material such as plastic, packets, leaves, etc. Along with the waste-collecting system, the robot also includes water monitoring with pH, turbidity, temperature sensors, and a live streaming feature, increasing the capacity to a greater extent. We have developed this robot to ensure the cleaning of water resources and to create a strong data set of water quality for future predictions. The use of this technology will ensure the safety of all aquatic animals and plants
Implementation of Secure Work From Home System Based on Blockchain using NS3 Simulation
Get PDFWork from Home (WFH) is an activity carrying out official duties, completing outputs, coordination, meetings, and other tasks from the residence of employees. Implement WFH many users use the zoom application has vulnerabilities. The network architecture used refers to the simple experiment network. In Secure WFH there are 3 offices connected through a router. Each client in each office is connected to the router via a Virtual Private Network (VPN) on a peer-to-peer (P2P). That architecture has 18 nodes that will be simulated. Secure WFH simulation with blockchain combines secure WFH with a bitcoin code simulator from Arthur Gervais's. Implementation of blockchain on secure WFH can increase security but the resulting speed decreases. The decrease in speed when implementing secure WFH is due to the generate block process and the verification process
Designing Android-Based Fasting Reminder (Shiyam) Applications
No full textIndonesia is a country with Muslim majority. Muslims implement fasting as one of important Islamic pillar. Information regarding fasting is substantial for Muslims, especially warnings of imsak, sahur and iftar times. Integration of information related to fasting schedules and provisions in mobile devices especially Android is a promising solution for Muslims. So that, the design of the fasting reminder (Shiyam) application is notable to perform. This application was developed based on the Waterfall model which emphasizes the development of systematic and sequential information systems. The implementation of the Shiyam application which focuses on the aspect of fasting can provide detailed fasting-related information and provides warnings at the time of imsak, iftar and sahur which can help Muslims in carrying out their worship
Aggressive driving behaviour classification using smartphone's accelerometer sensor
Get PDFAggressive driving is the most common factor of road accidents, and millions of lives are compromised every year. Early detection of aggressive driving behaviour can reduce the risks of accidents by taking preventive measures. The smartphone's accelerometer sensor data is mostly used for driving behavioural detection. In recent years, many research works have been published concerning to behavioural analysis, but the state of the art shows that still, there is a need for a more reliable prediction system because individually, each method has it's own limitations like accuracy, complexity etc. To overcome these problems, this paper proposes a heterogeneous ensemble technique that uses random forest, artificial neural network and dynamic time wrapping techniques along with weighted voting scheme to obtain the final result. The experimental results show that the weighted voting ensemble technique outperforms to all the individual classifiers with average marginal gain of 20%
The Effect of Using Histogram Equalization and Discrete Cosine Transform on Facial Keypoint Detection
Get PDFThis study aims to figure out the effect of using Histogram Equalization and Discrete Cosine Transform (DCT) in detecting facial keypoints, which can be applied for 3D facial reconstruction in face recognition. Four combinations of methods comprising of Histogram Equalization, removing low-frequency coefficients using Discrete Cosine Transform (DCT) and using five feature detectors, namely: SURF, Minimum Eigenvalue, Harris-Stephens, FAST, and BRISK were used for test. Data that were used for test were obtained from Head Pose Image and ORL Databases. The result from the test were evaluated using F-score. The highest F-score for Head Pose Image Dataset is 0.140 and achieved through the combination of DCT & Histogram Equalization with feature detector SURF. The highest F-score for ORL Database is 0.33 and achieved through the combination of DCT & Histogram Equalization with feature detector BRISK
Genetic Programming Approach for Classification Problem using GPU
Get PDFGenetic programming (GP) is a machine learning technique that is based on the evolution of computer programs using a genetic algorithm. Genetic programming have proven to be a good technique for solving data set classification problems but at high computational cost. The objectives of this research is to accelerate the execution of the classification algorithms by proposing a general model of execution in GPU of the adjustment function of the individuals of the population. The computation times of each of the phases of the evolutionary process and the operation of the model of parallel programming in GPU were studied. Genetic programming is interesting to parallelize from the perspective of evolving a population of individuals in parallel
Steady-state response feature extraction optimization to enhance electronic nose performance
Get PDFFeature extraction of electronic nose (e-nose) output response aims to reduce information redundancy so that the e-nose performance can be improved. The use of different sensor types and sample targets can affect the optimization of feature extraction. This research used six types of metal oxide sensors, TGS 813, 822, 825, 826, 2620, and 2611 in an e-nose system to detect three types of herbal drink. Five kinds of feature extraction methods on the original response curve in a steady-state response were used, namely, baseline difference, logarithmic difference, local normalization, global normalization, and global autoscaling. The results of feature extraction were fed into a Principal Component Analysis (PCA) system. As a result, global autoscaling and normalization had the highest total sum of the first and second principal components of 96.96%, followed by local normalization (90.18%), logarithm, and baseline difference (88.92% and 79.26%, respectively). The validation of PCA results was performed using a Backpropagation Neural Network (BPNN). The highest accuracy, 97.44%, was obtained from the global autoscaling method, followed by global normalization, local normalization, logarithm, and baseline difference, with an accuracy level of 94.87%, 92.31%, 89.74%, and 82.05%, respectively. This demonstrates that the selection of the feature extraction method can affect the classification results and improve e-nose performance
Investigation of Structural Parameter Variation on Extended Gate TFET for Bio-Sensor Applications
Get PDFTraditional Gate engineered Metal Oxide Semiconductor (MOS) technology faced serious challenges in terms of greater sensitivity for target biomolecules and to be utilized as the state-of-the-art Nano-recognition tool. Research on a tunnel field-effect transistor (TFET) started with the aim to achieve fast detection, low power consumption, and its potential for on-chip integration capability. Dielectric Modulated TFET (DMTFET) has established itself to be a primary candidate for sensing both charged and charge-neutral species with volumetric sensitivity. As extended gate DMTFET happens to be inferior to its short gate counterpart, we have devised ways to achieve superior performance only by making variations over structural electrostatics. With the incorporation of most possible ways of modulation, we present two orders of magnitude on-current increment and a considerable percentage of sensitivity improvement over the conventional one. Future scopes having noteworthy diversifications have also been analyzed with proper justification
Practical application of IOT and its implications on the existing software
Get PDFThe data management from end-to-end level is done by cloud-assisted IOT for its users and they keep a goal in increasing their number of users with the course of time. From saving the infiltration of data from both internal and external threats to the system, IOT is the best-proposed method used for securing the database. Connecting objects/individuals with the Internet via safe interaction is the main objective of IOT. It can assemble all the hardware devices that are designed to store data for an individual or an organization. The associated applications and the way in which it can be deployed in the present organization in order to optimize the current working system. This paper focuses on providing an overall systematic secured data sharing portal that is devoid of threats from internal as well as external entities. By using CIBPRE data encryption a major security reform is introduced by IOT in storing and sharing of data on a regular basis