International Journal of Reconfigurable and Embedded Systems (IJRES)
Not a member yet
454 research outputs found
Sort by
FPGA-based fault analysis for 7-level switched ladder multi-level inverter using decision tree algorithm
Get PDFThe proposed method involves the fault analysis of the inverter switches present in the multi-level inverter (MLI) circuitry. The decision tree machine learning algorithm is incorporated for the fault analysis of the inverter switches. The multi-level inverter utilized in this work is a 7-level switched ladder multi-level inverter. There is 4 number of switches in the design of a 7-level inverter driven by the non-carrier digital pulse width modulation signals. The non-carried-based digital pulse-width modulator (DPWM) generation is generated using the event angle for the 7-level of the switched ladder inverter. The proposed method investigates the stuck-at-fault occurrences of the 4 switches in the inverter by manipulating the decision tree parameters such as entropy, information gain, and decision tree. Based on the decision tree, the very high-speed integrated circuit hardware description language (VHDL) code is developed by making use of the behavioral modeling and validated for the power, area in the Xilinx Vivado tool. The real-time feasibility is verified for the proposed method by synthesizing the developed VHDL code in the field programmable gate array (FPGA) device
Comparative study of single precision floating point division using different computational algorithms
Get PDFThis paper presents different computational algorithms to implement single precision floating point division on field programmable gate arrays (FPGA). Fast division computation algorithms can apply to all division cases by which an efficient result will be obtained in terms of delay time and power consumption. 24-bit Vedic multiplication (Urdhva-Triyakbhyam-sutra) technique enhances the computational speed of the mantissa module and this module is used to design a 32-bit floating point multiplier which is the crucial feature of this proposed design, which yields a higher computational speed and reduced delay time. The proposed design of floating-point divider using fast computational algorithms synthesized using Verilog hardware description language has a 32-bit floating point multiplier module unit and a 32-bit floating point subtractor module unit. Xilinx Spartan 6 SP605 evaluation platform is used to verify this proposed design on FPGA. Synthesis results provide the device utilization and propagation delay parameters for the proposed design and a comparative study is done with previous work. Input to the divider is provided in IEEE 754 32-bit formats
Route optimization via improved ant colony algorithm with graph network
Get PDFRoute optimization problem using vehicle routing problem (VRP) and time window constraint is explained as finding paths for a finite count of vehicles to provide service to a huge number of customers and hence, optimizing the path in a given duration of the time window. The vehicles in the loop have restricted intake of capacity. This path initiates from the depot, delivers the goods, and stops at the depot. Each customer is to serve exactly once. If the arrival of the vehicle is before the time window “opens” or when the time window “closes,” there will be waiting for cost and late cost. The challenge involved over here is to scheduling visits to customers who are only available during specific time windows. Ant colony optimization (ACO) algorithm is a meta-heuristic algorithm stimulated by the growing behaviour of real ants. In this paper, we combine the ACO algorithm with graph network henceforth increasing the number of vehicles in a particular depot for increasing the efficiency for timely delivery of the goods in a particular time width. This problem is solved by, an efficient technique known as the ACO+graph algorithm
Energy-efficient routing protocol for wireless sensor networks based on progressive and concentric clusters
Get PDFSmart parking is common in contemporary cities. These smart parking lots are outfitted mostly with wireless sensor networks (WSNs), which are used to detect, monitor, and collect data on the availability status of all existing parking spaces in a given area. Sensors make up WSN, which may gather, process, and transmit informations to the sink. However, the power and communication limitations of the sensors have an effect on the performance and quality of the WSNs. The decrease in the battery and the energy of the nodes causes a decrease in the life of the nodes and also of the entire WSN network. In this article, we present a routing protocol that implements an efficient and robust algorithm allowing the creation of clusters so that the base station can receive data from the entire WSN network. This protocol adopts a reliable and efficient algorithm allowing to minimize the energy dissipation of the sensors and to increase the lifetime of the WSN. In comparison to alternative parking lot management protocols already in use, the simulation results of the proposed protocol are effective and robust in terms of power consumption, data transmission reliability, and WSN network longevity
People identification via tongue print using fine-tuning deep learning
Get PDFMany person-verification systems are critical in security systems for verifying passage through doors opened to specific people using various techniques. People can use electronic payment methods and security apps to generate codes for quick, remote financial transactions. Older systems required precision and speed. Many alternative methods were developed by technology and artificial intelligence to make such operations simple and quick. The identification of tongue prints is discussed in this paper. Tongue prints, like fingerprints, are unique to each individual. The tongue was used in this study because it is unique among such organs. The tongue is protected by the lips. This guards against taking a tongue print by force. Some people distort their fingerprints, making fingerprint recognition systems unable to recognize them. Car accidents cause facial distortion, which distorts the system and prevents it from distinguishing facial prints, so the tongue was used as a fingerprint in this study. A database of 1,104 images for 138 Mustansiriyah University College of Science students yielded an average of eight images per individual. VGG16 was implemented for transfer learning and fine-tuning. In comparison to previous studies, the accuracy achieved was more than 91%
Automated ventilator prototype for COVID-19 patient treatment: the design and development of the electronic system
Get PDFThe coronavirus disease 2019 (COVID-19) pandemic has created an urgent global demand for ventilators, respirators and various resuscitation devices. Various research and development organizations, private companies and individual engineers have collaborated and carried out the development of low-cost ventilation prototypes. In turn, doctors and nurses are collapsed due to the exponential increase in COVID-19 cases. This scenario worsens more when the tasks are manual in nature. The article`s objective to describe the electronic system designed, developed and implemented in a functional prototype of an automatic ventilator in order to be evaluated by a team of health professionals to be later used in cases of health emergencies. This system automates the manual ventilation task aided by a few medical resources in a scenario of scarce resources and is a temporary solution when a respirator is not available
Efficient content-based image retrieval using integrated dual deep convolutional neural network
Get PDFContent-based image retrieval (CBIR) uses the content features for retrieving and searching the images in a given large database. Earlier, different hand feature descriptor designs are researched based on cues that are visual such as shape, colour, and texture used to represent these images. Although, deep learning technologies have widely been applied as an alternative to designing engineering that is dominant for over a decade. The features are automatically learnt through the data. This research work proposes integrated dual deep convolutional neural network (IDD-CNN), IDD-CNN comprises two distinctive CNN, first CNN exploits the features and further custom CNN is designed for exploiting the custom features. Moreover, a novel directed graph is designed that comprises the two blocks i.e. learning block and memory block which helps in finding the similarity among images; since this research considers the large dataset, an optimal strategy is introduced for compact features. Moreover, IDD-CNN is evaluated considering the two distinctive benchmark datasets the oxford dataset considering mean average precision (mAP) metrics and comparative analysis shows IDD-CNN outperforms the other existing model
Gym training muscle fatigue monitoring using EMG myoware and arduino with envelope and sliding window methods
Get PDFMuscles are an important organ in the movement of the body's skeleton to carry out sports activities. Measurement of muscle activity during the exercise process can be done using electromyography (EMG). This research uses Myoware muscle sensor (AT-04-001) which is integrated with Arduino Uno and Xbee to monitor biceps brachii muscle fatigue wirelessly. Fatigue data processing is carried out objectively using the envelope and sliding window method and subjectively verbally from the respondents. From this study, it was found that muscle fatigue can be measured using the method objectively when there is an increase in EMG amplitude with a window size of 5 s. The indication of biceps brachii muscle fatigue for the right arm is stronger to withstand the load during exercise with the average duration of the measurement of the right arm is 41.87 s from 69.67 s; 53.53 s from 98.90 s and 76.87 s from 98.80 s with the ratio of the left arm tending to fatigue more quickly is 23.53 s from 42.13 s; 41.87 s from 51.60 s and 23.53 s from 44.73 s
Design and development frequency reconfigurable microwave filter for wireless application
Get PDFThis paper presents a novel reconfigurable bandpass filter with three reconfigurable states used for C band wireless applications. The frequency reconfigurable is achieved using the combination of a different microstrip coupled resonator structure and switching device as PIN diodes. The open-loop filter structure provides three narrow band states at 5.1, 5.2, and 5.8 GHz. The frequency reconfiguration is obtained without compromising performances. The compact size of the proposed designed along with the targeted frequency bands at lower wireless local area network (WLAN) (5.1, 5.2 GHz), and worldwide interoperability for microwave access (WiMAX) (5.8 GHz) applications. The prototype is constructed on an RT duroid 5880 substrate and tested for validation in vector network analyzer (VNA). The designed filter provides excellent selectivity and good rejection at desired resonant frequencies
Emotion classification for musical data using deep learning techniques
Get PDFThis research is done based on the identification and thorough analyzing musical data that is extracted by the various method. This extracted information can be utilized in the deep learning algorithm to identify the emotion, based on the hidden features of the dataset. Deep learning-based convolutional neural network (CNN) and long short-term memory-gated recurrent unit (LSTM-GRU) models were developed to predict the information from the musical information. The musical dataset is extracted using the fast Fourier transform (FFT) models. The three deep learning models were developed in this work the first model was based on the information of extracted information such as zero-crossing rate, and spectral roll-off. Another model was developed on the information of Mel frequencybased cepstral coefficient (MFCC) features, the deep and wide CNN algorithm with LSTM-GRU bidirectional model was developed. The third model was developed on the extracted information from Mel-spectrographs and untied these graphs based on two-dimensional (2D) data information to the 2D CNN model alongside LSTM models. Proposed model performance on the information from Mel-spectrographs is compared on the F1 score, precision, and classification report of the models. Which shows better accuracy with improved F1 and recall values as compared with existing approaches