International Journal of Informatics and Communication Technology (IJ-ICT)
Not a member yet
494 research outputs found
Sort by
Design of a 175 GHz SiGe-based voltage-controlled oscillator with greater than 7.6 dBm power
Get PDFIn this research, we present a low phase noise (PN) and wide tuning range 175 GHz inductors and capacitors (LC) voltage-controlled oscillator (VCO) based on a differential Colpitts oscillator that was designed using a 0.13 μm bipolar complementary metal oxide semiconductor (BiCMOS) and simulated. The square of the tank Q-factor and the square of the oscillation amplitude were both maximized to reduce PN. With an extensive examination of parasitic, mathematical analysis of load impedances, and implementation of differential design, the PN was reduced, and the output power was enhanced. Using a supply voltage of 1.6 V, the VCO consumes 41.9 mA, resulting in a total power usage of 67 mW to prevent undesirable PN deterioration, an inter-stage LC filter at the VCO-buffer interface increases the swing at the buffer input. To make a better output, a buffer is used to isolate the load from the VCO core. In addition, the VCO has a high linearity and the overall, the VCO presented in this study demonstrates excellent performance and has the potential to be used in a wide range of applications that require a high-performance, low-power VCO
Machine learning techniques for plant disease detection: an evaluation with a customized dataset
Get PDFDiseases in edible and industrial plants remains a major concern, affecting producers and consumers. The problem is further exacerbated as there are different species of plants with a wide variety of diseases that reduce the effectiveness of certain pesticides while increasing our risk of illness. A timely, accurate and automated detection of diseases can be beneficial. Our work focuses on evaluating deep learning (DL) approaches using transfer learning to automatically detect diseases in plants. To enhance the capabilities of our approach, we compiled a novel image dataset containing 87,570 records encompassing 32 different plants and 74 types of diseases. The dataset consists of leaf images from both laboratory setups and cultivation fields, making it more representative. To the best of our knowledge, no such datasets have been used for DL models. Four pre[1]trained computer vision models, namely VGG-16, VGG-19, ResNet-50, and ResNet-101 were evaluated on our dataset. Our experiments demonstrate that both VGG-16 and VGG-19 models proved more efficient, yielding an accuracy of approximately 86% and a f1-score of 87%, as compared to ResNet-50 and ResNet-101. ResNet-50 attains an accuracy and a f1-score of 46.9% and 45.6%, respectively, while ResNet-101 reaches an accuracy of 40.7% and a f1-score of 26.9%
Comparative performance study of HC-12, nRF24L01, and XBee for vehicular communication
Get PDFIn recent times, the volume of traffic congestion has been rapidly growing on roads. These days the necessity of having safe transportation and journey is essential. Thus, vehicle communication could be a possible solution to enhance safe transit. Vehicular communications provide a wide range of applications with different characteristics, namely vehicle and vehicle (V2V) communications. Every year, traffic accidents kill many people worldwide, and many people have been injured. V2V communication enables vehicles to communicate with each other to provide safety and convenience to drivers. Therefore, this paper explores a direction to develop a conceptual approach to V2V communication with HC-12, nRF24L01, and XBee. The study aims to analyze and evaluate the communication range that may contribute to the future road transportation system
Architectural pattern for service collaboration
Get PDFThe aim of this paper is to propose a modeling framework, tailored to build efficient, elastic and autonomous applications from tasks and services. It includes integrated services to develop the software products, reusing on demand in-house services with specific requirements and flexible the representational state transfer (REST) services. The idea is to decouple authorization for reduced service dependency and to provide a possibility for developing the whole application by increasing the existing application flexibility. Based on the fact that there are different web application platforms that serve to offer services to users but they are not integrated; we propose a framework with high flexibility degree, especially integrating the most used services such: e-learning, administrative, and library services, as University services are concern
180 nm NMOS voltage-controlled oscillator for phase-locked loop applications
Get PDFThe voltage-controlled oscillator (VCO) is the primary device in the phase-locked loop (PLL) to produce the local oscillator frequency. The excessive phase noise of VCOs is the primary cause of PLL performance loss. This paper proposes the design and optimization of low phase noise and low power consumption for a 180 nm N-channel metal-oxide semiconductor NMOS VCO for PLL applications with P-channel metal-oxide semiconductor PMOS varactors and spiral inductors. At 2 V supply voltage, the optimized NMOS VCO has a power consumption of 21 mW, a phase noise of -130 dBc/Hz at 1 MHz offset and a total harmonic distortion (THD) of 3.9%. The proposed design is verified by PSpice simulations. A new criterion is proposed for optimizing NMOS LC oscillators
Evaluating the level of inteference in UMTS/LTE heterogeneous network system
Get PDFThe study evaluated interference in a dense heterogeneous network using third-generation universal mobile telecommunication systems (UMTS) and fourth-generation long term evolution (LTE) networks LTE. The UMTs/LTE heterogeneous network determines the level of interference when the two communication systems coexist and how to improve the network by migrating from UMTs to LTE, which has a faster download speed and larger capacity. Techno lite 8 on third generation (3G) and Infinix Pro 6 on fourth generation (4G) were used to measure network the received signal strength (RSS) during site investigation. UE interference was detected and traced using a spectrum analyzer. UMTS and LTE path loss exponents are 2.6 and 3.2. Shannon's capacity theorem calculated LTE and UMTS capacity. When signal to interference and noise ratio (SINR) was used as a quality of service (QoS) indicator, MATLAB channel capacity plots did not match Shannon's due to neighboring interference. UMTS had an R2 of 0.54 and LTE 0.57 for the Shannon channel capacity equation. Adjacent channel interference (ACI) user devices reduce network capacity, lowering QoS for other customers
Novel DV-hop algorithm-based machines learning technics for node localization in rang-free wireless sensor networks
Get PDFLocalization is a critical concern in many wireless sensor network (WSN) applications. Furthermore, correct information regarding the geographic placements of nodes (sensors) is critical for making the collected data valuable and relevant. Because of their benefits, such as simplicity and acceptable accuracy, the based connectivity algorithms attempt to localize multi-hop WSN. However, due to environmental factors, the precision of localisation may be rather low. This publication describes an Extreme Learning Machine (ELM) technique for minimizing localization error in range-free WSN. In this paper, we propose a Cascade Extreme Learning Machine (Cascade-ELM) to increase localization accuracy in Range-Free WSNs. We tested the proposed approaches in a variety of multi-hop WSN scenarios. Our research focused on an isotropic and irregular environment. The simulation results show that the proposed Cascade-ELM algorithm considerably improves localization accuracy when compared to previous algorithms derived from smart computing approaches. When compared to previous work, isotropic environments show improved localization results
Automated machine learning for analysis and prediction of vehicle crashes
Get PDFThis work discusses the study and development of a graphical interface and implementation of a machine learning model for vehicle traffic injury and fatality prediction for a specified date range and for a certain zip (US postal) code based on the New York City's (NYC) vehicle crash data set. While previous studies focused on accident causes, little insight has been offered into how such data may be utilized to forecast future incidents, Studies that have historically concentrated on certain road segment types, such as highways and other streets, and a specific geographic region, this study offers a citywide review of collisions. Using cutting-edge database and networking technology, a user-friendly interface was created to display vehicle crash series. Following this, a support vector machine learning model was built to evaluate the likelihood of an accident and the consequent injuries and deaths at the zip code level for all of NYC and to better mitigate such events. Using the visualization and prediction approach, the findings show that it is efficient and accurate. Aside from transportation experts and government policymakers, the machine learning approach deliver useful insights to the insurance business since it quantifies collision risk data collected at specific places
A comprehensive survey of automatic dysarthric speech recognition
Get PDFThe need for automated speech recognition has expanded as a result of significant industrial expansion for a variety of automation and human-machine interface applications. The speech impairment brought on by communication disorders, neurogenic speech disorders, or psychological speech disorders limits the performance of different artificial intelligence-based systems. The dysarthric condition is a neurogenic speech disease that restricts the capacity of the human voice to articulate. This article presents a comprehensive survey of the recent advances in the automatic dysarthric speech recognition (DSR) using machine learning (ML) and deep learning (DL) paradigms. It focuses on the methodology, database, evaluation metrics, and major findings from the study of previous approaches. From the literature survey it provides the gaps between exiting work and previous work on DSR and provides the future direction for improvement of DSR. The performance of the various machine and DL schemes is evaluated for the DSR on UASpeech dataset based on accuracy, precision, recall, and F1-score. It is observed that the DL based DSR schems outperforms the ML based DSR schemes
CNN inference acceleration on limited resources FPGA platforms_epilepsy detection case study
Get PDFThe use of a convolutional neural network (CNN) to analyze and classify electroencephalogram (EEG) signals has recently attracted the interest of researchers to identify epileptic seizures. This success has come with an enormous increase in the computational complexity and memory requirements of CNNs. For the sake of boosting the performance of CNN inference, several hardware accelerators have been proposed. The high performance and flexibility of the field programmable gate array (FPGA) make it an efficient accelerator for CNNs. Nevertheless, for resource-limited platforms, the deployment of CNN models poses significant challenges. For an ease of CNN implementation on such platforms, several tools and frameworks have been made available by the research community along with different optimization techniques. In this paper, we proposed an FPGA implementation for an automatic seizure detection approach using two CNN models, namely VGG-16 and ResNet-50. To reduce the model size and computation cost, we exploited two optimization approaches: pruning and quantization. Furthermore, we presented the results and discussed the advantages and limitations of two implementation alternatives for the inference acceleration of quantized CNNs on Zynq-7000: an advanced RISC machine (ARM) software implementation-based ARM, NN, software development kit (SDK) and a software/hardware implementation-based deep learning processor unit (DPU) accelerator and DNNDK toolkit