EMITTER - International Journal of Engineering Technology
Not a member yet
261 research outputs found
Sort by
Estimation of Confidence in the Dialogue based on Eye Gaze and Head Movement Information
Full text linkIn human-robot interaction, human mental states in dialogue have attracted attention to human-friendly robots that support educational use. Although estimating mental states using speech and visual information has been conducted, it is still challenging to estimate mental states more precisely in the educational scene. In this paper, we proposed a method to estimate human mental state based on participants’ eye gaze and head movement information. Estimated participants’ confidence levels in their answers to the miscellaneous knowledge question as a human mental state. The participants’ non-verbal information, such as eye gaze and head movements during dialog with a robot, were collected in our experiment using an eye-tracking device. Then we collect participants’ confidence levels and analyze the relationship between human mental state and non-verbal information. Furthermore, we also applied a machine learning technique to estimate participants’ confidence levels from extracted features of gaze and head movement information. As a result, the performance of a machine learning technique using gaze and head movements information achieved over 80 % accuracy in estimating confidence levels. Our research provides insight into developing a human-friendly robot considering human mental states in the dialogue
Automating Test Case Generation for Android Applications using Model-based Testing
Full text linkTesting of mobile applications (apps) has its quirks as numerous events are required to be tested. Mobile apps testing, being an evolving domain, carries certain challenges that should be accounted for in the overall testing process. Since smartphone apps are moderate in size so we consider that model-based testing (MBT) using state machines and statecharts could be a promising option for ensuring maximum coverage and completeness of test cases. Using model-based testing approach, we can automate the tedious phase of test case generation, which not only saves time of the overall testing process but also minimizes defects and ensures maximum test case coverage and completeness. In this paper, we explore and model the most critical modules of the mobile app for generating test cases to ascertain the efficiency and impact of using model-based testing. Test cases for the targeted model of the application under test were generated on a real device. The experimental results indicate that our framework reduced the time required to execute all the generated test cases by 50%. Experimental setup and results are reported herein
Investigation in Gas-Oil Two-Phase Flow using a Differential Pressure Transducer and Wire Mesh Sensor in Vertical Pipes
Full text linkThe current study is performed to identify the flow regimes of oil-gas two-phase flow experimentally in a vertical pipe has an internal diameter of 6.7 cm. It also aims to provide more details about the possibility of using Differential Pressure Transducers (DPT) for indicating flow patterns. A flow development of oil and gas has been investigated in a vertical pipe of 6 m in length and operated at atmospheric pressure. A series of experiments have been run to cover a range of inlet oil superficial velocities from 0.262 to 0.419 m/s, and inlet gas superficial velocities from 0.05 to 4.7 m/s. Wire Mesh Sensors (WMS) have been used to collect the obtained void fraction values of the flow. The Differential Pressure Transducer (DPT) is utilized to measure the pressure drop values of a one-meter along the pipe. The flow patterns are classified according to the analysis of void fractions, pressure gradients regarding time series, tomographic images, probability density functions of the void fractions, and pressure gradients. A bubbly flow is observed at low superficial velocities of gas and liquid, slug flow is observed at the lower flow rate of liquid and moderate flow rates of gas, while the churn flow pattern is recognized at the higher rates of liquid and gas. Also, the result has revealed the possibility of using Differential Pressure Transducers (DPT) to classify the gas-oil flow patterns in vertical pipes
Rapid Control Prototyping of Five-Level MMC based Induction Motor Drive with different Switching Frequencies
Full text linkIn this paper, Rapid Control Prototyping (RCP) of five-level Modular Multilevel Converter (MMC) based Induction Motor (IM) drive performance is observed with different switching frequencies. The Semikron based MMC Stacks with two half-bridge each are tested with the switching logic generated by phase and level shifted based Sinusoidal Pulse Width Modulation (SPWM) technique. The switching logic is generated by the Typhoon Hardware in Loop (HIL) 402. The disadvantages of Multilevel Converter like not so good output quality, less modularity, not scalable and high voltage and current rating demand for the power semiconductor switches can be overcome by using MMC. In this work, the IM drive is fed by MMC and the experimentally the performance is observed. The performance of the Induction Motor in terms of speed is observed with different switching frequencies of 2.5kHz, 5kHz, 7.5kHz, 10kHz, 12.5kHz and the results are tabulated in terms of Total Harmonic Distortion (THD) of input voltage and current to the Induction Motor Drive. The complete model is developed using Typhoon HIL 2021.2 Version Real-Time Simulation Software
Towards Improvement of LSTM and SVM Approach for Multiclass Fall Detection System
Full text linkTelemonitoring of human physiological data helps detect emergency occurrences for subsequent medical diagnosis in daily living environments. One of the fatal emergencies in falling incidents. The goal of this paper is to detect significant incidents such as falls. The fall detection system is essential for human body movement investigation for medical practitioners, researchers, and healthcare businesses. Accelerometers have been presented as a practical, low-cost, and dependable approach for detecting and predicting outpatient movements in the user. The accurate detection of body movements based on accelerometer data enables the creation of more dependable systems for incorporating long-term development in physiological remarks. This research describes an accelerometer-based platform for detecting users' body movement when they fall. The ADXL345, MMA8451q, and ITG3200 body sensors capture activity data, subsequently classified into 15 fall incident classes based on SisFall dataset. Falling incidents classification is performed using Long Short-Term Memory results in best AUC-ROC value of 97.7% and best calculation time of 6.16 seconds. Meanwhile, Support Vector Machines results in the best AUC-ROC value of 98.5% and best calculation times of 17.05 seconds
Secure Real-time Data Transmission for Drone Delivery Services using Forward Prediction Scheduling SCTP
Full text linkDrone technology is considered the most effective solution for the improvement of various industrial fields. As a delivery service, drones need a secure communication system that is also able to manage all of the information data in real-time. However, because the data transmission process occurs in a wireless network, data will be sent over a channel that is more unstable and vulnerable to attack. Thus, this research, purposes a Forward Prediction Scheduling-based Stream Control Transmission Protocol (FPS-SCTP) scheme that is implemented on drone data transmission system. This scheme supports piggybacking, multi-streaming, and Late Messages Filter (LMF) which will improve the real-time transmission process in IEEE 802.11 wireless network. Meanwhile, on the cybersecurity aspect, this scheme provides the embedded option feature to enable the encryption mechanism using AES and the digital signatures mechanism using ECDSA. The results show that the FPS-SCTP scheme has better network performance than the default SCTP, and provides full security services with low computation time. This research contributes to providing a communication protocol scheme that is suitable for use on the internet of drones’ environment, both in real-time and reliable security levels
Density-based Clustering for 3D Stacked Pipe Object Recognition using Directly-given Point Cloud Data on Convolutional Neural Network
Full text linkOne of the most commonly faced tasks in industrial robots is bin picking. Much work has been done in this related topic is about grasping and picking an object from the piled bin but ignoring the recognition step in their pipeline. In this paper, a recognition pipeline for industrial bin picking is proposed. Begin with obtaining point cloud data from different manner of stacking objects there are well separated, well piled, and arbitrary piled. Then followed by segmentation using Density-based Spatial Clustering Application with Noise (DBSCAN) to obtain individual object data. The systems then use Convolutional Neural Network (CNN) that consume raw point cloud data. Performance of the segmentation reaches an impressive result in separating objects and network is evaluated under the varying style of stacking objects and give the result with average Accuracy, Recall, Precision, and F1-Score on 98.72%, 95.45%, 99.39%, and 97.33% respectively. Then the obtained model can be used for multiple objects recognition in one scene
Classification Method in Fault Diagnosis of Oil-Immersed Power Transformers by Considering Dissolved Gas Analysis
Full text linkFault detection in the incipient stage is necessary to avoid hazardous operating conditions and reduce outage rates in transformers. Fault-detected dissolved gas analysis is widely used to detect incipient faults in oil-immersed transformers. This paper proposes fault diagnosis transformers using an artificial neural network based on classification techniques. Data on the condition of transformer oil is assessed for dissolved gas analysis to measure the dissolved gas concentration in the transformer oil. This type of disturbance can affect the gas concentration in the transformer oil. Fault diagnosis is implemented, and fault reference is provided. The result of the NN method is more accurate than the Tree and Random Forest method, with CA and AUC values 0.800 and 0.913. This classification approach is expected to help fault diagnostics in power transformers
A Machine learning Classification approach for detection of Covid 19 using CT images
Full text linkCoronavirus disease 2019 popularly known as COVID 19 was first found in Wuhan, China in December 2019. World Health Organization declared Covid 19 as a transmission disease. The symptoms were cough, loss of taste, fever, tiredness, respiratory problem. These symptoms were likely to show within 11 –14 days. The RT-PCR and rapid antigen biochemical tests were done for the detection of COVID 19. In addition to biochemical tests, X-Ray and Computed Tomography (CT) images are used for the minute details of the severity of the disease. To enhance efficiency and accuracy of analysis/detection of COVID images and to reduce of doctors' time for analysis could be addressed through Artificial Intelligence. The dataset from Kaggle was utilized to analyze. The statistical and GLCM features were extracted from CT images for the classification of COVID and NON-COVID instances in this study. CT images were used to extract statistical and GLCM features for categorization. In the proposed/prototype model, we achieved the classification accuracy of 91%, and 94.5% using SVM and Random Forest respectively
Hardware Trojan Detection and Mitigation in NoC using Key authentication and Obfuscation Techniques
Full text linkToday's Multiprocessor System-on-Chip (MPSoC) contains many cores and integrated circuits. Due to the current requirements of communication, we make use of Network-on-Chip (NoC) to obtain high throughput and low latency. NoC is a communication architecture used in the processor cores to transfer data from source to destination through several nodes. Since NoC deals with on-chip interconnection for data transmission, it will be a good prey for data leakage and other security attacks. One such way of attacking is done by a third-party vendor introducing Hardware Trojans (HTs) into routers of NoC architecture. This can cause packets to traverse in wrong paths, leak/extract information and cause Denial-of-Service (DoS) degrading the system performance. In this paper, a novel HT detection and mitigation approach using obfuscation and key-based authentication technique is proposed. The proposed technique prevents any illegal transitions between routers thereby protecting data from malicious activities, such as packet misrouting and information leakage. The proposed technique is evaluated on a 4x4 NoC architecture under synthetic traffic pattern and benchmarks, the hardware model is synthesized in Cadence Tool with 90nm technology. The introduced Hardware Trojan affects 8% of packets passing through infected router. Experimental results demonstrate that the proposed technique prevents those 10-15% of packets infected from the HT effect. Our proposed work has negligible power and area overhead of 8.6% and 2% respectively