Proposed System Architecture Research Articles

Smart Collection of Waste Bread in Algeria Using the Internet of Things

Algerians are among the largest consumers of bread throughout the year and produce large amounts of bread waste. As bread is made from imported wheat, these losses on currency are a heavy loss for the national economy. To minimize these losses, Algeria needs to encourage the recycling of stale bread to minimize the cost of importing soft wheat and valorize it for farmers. This paper presents a framework based on the Internet of Things (IoT) to monitor and collect waste bread from recycling bins. This system could assist Small and Medium Enterprises (SMEs) in Algeria in bread waste collection, by monitoring the level of filling of the outdoor waste bins. The proposed system's architecture used a Mega 2560 microcontroller, HC-SR04 ultrasonic sensors, and SIM 808/900 modules.

Modular Stacked Multiport Wireless Energy Interconnection System With Virtual AC Bus and Its Power Flow Control Strategy

This article proposes a modular stacked multiport wireless energy interconnection (WEI) system with a virtual ac bus for multisource and multiload wireless power transfer (WPT) applications, which has the following advantages. 1) It can serve as an interface for WPT among multiple sources and loads. 2) Bipolar coils are adopted to eliminate the undesired cross-coupling among multiple coils, which simplifies the complexity of system modeling and power flow control. 3) The relay coil with constant current characteristics is introduced as a virtual ac bus, from which the derived multicoil structure provides the bidirectional channel for power transfer between any two ports. 4) System applicability and scalability are greatly enhanced due to the modularization of coils, power converters, and compensation circuits. For power flow control, the hybrid phase-shifted control method matched with the WEI system is applied, in which the power flow direction is determined by the external phase-shifted angles between ports, whereas the power values are regulated by the internal phase-shifted angles. Furthermore, the peak value of the current of the virtual ac bus, as an intermediate control variable, is controlled to be constant; thus, distributed control can be further realized. Finally, a four-port experimental prototype was built and experiments were carried out under different operating conditions. The efficiency curves and loss distribution, as well as the tolerance analysis of coil misalignments, are given. From the experimental results, the effectiveness of the proposed system architecture and its power flow control strategy is verified.

Computational and Mathematical Methods in Medicine Glioma Brain Tumor Detection and Classification Using Convolutional Neural Network.

The classification of the brain tumor image is playing a vital role in the medical image domain, and it directly assists the clinicians to understand the severity and to take an appropriate solution. The magnetic resonance imaging tool is used to analyze the brain tissues and to examine the different portion of brain circumstance. We propose the convolutional neural network database learning along with neighboring network limitation (CDBLNL) technique for brain tumor image classification in medical image processing domain. The proposed system architecture is constructed with multilayer-based metadata learning, and they have integrated with CNN layer to deliver the accurate information. The metadata-based vector encoding is used, and the type of coding estimation for extra dimension is known as sparse. In order to maintain the supervised data in terms of geometric format, the atoms of neighboring limitation are built based on a well-structured k-neighbored network. The resultant of the proposed system is considerably strong and subjective for classification. The proposed system used two different datasets, such as BRATS and REMBRANDT, and the proposed brain MRI classification technique outcome is more efficient than the other existing techniques.

Siamese Temporal Convolutional Networks for Driver Identification Using Driver Steering Behavior Analysis

Driver identification has shown sustainable development in recent years in a wide variety of applications including but not limited to security, personalization, fleet management, insurance telematics, or ride-hailing. However, the current progress suffers from several challenges such as costly data collections and the need for a huge amount of data from each individual for both driver identification and impostor detection. Therefore, more novel and efficient solutions are required to mitigate the existing challenges. In this paper, we address driver identification and impostor detection tasks using driving behavior analysis of the drivers. We design a deep learning-based system architecture that analyzes windows of 30 seconds of driving data to capture the unique underlying characteristics of the individuals steering behavior based on which it further distinguishes the drivers. We also develop a novel strategy to tackle driver verification and impostor detection tasks based on the combination of the proposed system architecture and Siamese networks concepts. We map the steering behavior of the drivers into latent representations which can be later used to train a similarity function. The performance of the proposed systems is tested over a real-world dataset of 95 drivers. The evaluation results indicate that our system outperforms well-established benchmarks and baseline methodologies.

A Novel Power Processing Unit (PPU) System Architecture Based on HFAC Bus for Electric Propulsion Spacecraft

This article proposes a novel power processing unit (PPU) system architecture based on the high-frequency alternating current (HFAC) bus for electric propulsion spacecraft. The proposed PPU system architecture takes the HFAC output of the inverter network in the main load power supply as the bus while supplying power for other low-power supplies. Compared with the conventional PPU system architecture, the number of transistors is significantly reduced, and the outputs of low-power supplies are regulated with nonisolated controllers, leading to a lower cost, more compact size, and higher reliability. Moreover, the redundancy design and the fault mode analysis are introduced, which greatly improve the flexibility of the fault operation strategies. Finally, the test on the electrical characteristic of the HFAC bus in the experimental prototype proves the feasibility and stability of the proposed system architecture. The obvious performance enhancement is further demonstrated through a systematic comparison with the conventional PPU system architecture.

Deep Learning Approach for the Detection of Noise Type in Ancient Images

Recent innovations in digital image capturing techniques facilitate the capture of stationary and moving objects. The images can be easily captured via high-end digital cameras, mobile phones and other handheld devices. Most of the time, captured images vary compared to actual objects. The captured images may be contaminated by dark, grey shades and undesirable black spots. There are various reasons for contamination, such as atmospheric conditions, limitations of capturing device and human errors. There are various mechanisms to process the image, which can clean up contaminated image to match with the original one. The image processing applications primarily require detection of accurate noise type which is used as input for image restoration. There are filtering techniques, fractional differential gradient and machine learning techniques to detect and identify the type of noise. These methods primarily rely on image content and spatial domain information of a given image. With the advancements in the technologies, deep learning (DL) is a technology that can be trained to mimic human intelligence to recognize various image patterns, audio files and text for accuracy. A deep learning framework empowers correct processing of multiple images for object identification and quick decision abilities without human interventions. Here Convolution Neural Network (CNN) model has been implemented to detect and identify types of noise in the given image. Over the multiple internal iterations to optimize the results, the identified noise is classified with 99.25% accuracy using the Proposed System Architecture (PSA) compared with AlexNet, Yolo V5, Yolo V3, RCNN and CNN. The proposed model in this study proved to be suitable for the classification of mural images on the basis of every performance parameter. The precision, accuracy, f1-score and recall of the PSA are 98.50%, 99.25%, 98.50% and 98.50%, respectively. This study contributes to the development of mural art recovery.

Recursive LSTM for the Classification of Named Entity Recognition for Hindi Language

NER assumes a key part in Information Extraction from reports (for example email), conversational information, and so forth. Many tongue handling applications, for example, data recovery, question responding to, and machine interpretation, depend on NER. It tends to be challenging to determine the ambiguities of lexical components utilized in a text arrangement. There is too much work has been already done in English language but there is a need to improve accuracy for the NER in Hindi language. In this research researcher are minimize chances of misclassification by using different classifier namely location, name, weather etc. BiLSTM Development of a NER framework for Indian languages is a similarly troublesome task. In this paper, Researcher have done the different research to contrast the aftereffects of NER and typical implanting and quick text implanting layers to examinations the exhibition of word installing with various bunch sizes to prepare the profound learning models. In this paper, Researcher have done the different examinations to contrast the consequences of NER and typical implanting and quick text installing layers to investigations the presentation of word inserting with various group sizes to prepare the profound learning models. The value of the precision of proposed system architecture is 76.13% which is way more than other system architectures. Also, the value of recall and F1-score of proposed system architecture is 71.49 and 74.26 respectively. So, by comparing proposed system architecture with existing SpaCy, CoreNLP and NLTK it is easy to conclude that proposed system architecture is reliable in all the sense.

A low-cost pavement-rating system, based on machine learning, utilising smartphone sensors

One of the key innovations of this study is the development of a cost-efficient approach for pavement monitoring. This work aims to develop a system that evaluates roadway pavement surface conditions with improved frequency by utilising unsupervised machine learning algorithms and smartphone sensors. The evaluation of roadways utilising complex contemporary data sets is currently conducted periodically because of the high cost of collection methods. For this purpose, the study presents a data-driven framework on the use of a vehicle, a smartphone, an on-board diagnostic device and machine learning for the rating of pavement surfaces, while statistical features are considered in both time- and frequency-domain forms. The selection of features is performed utilising unsupervised classification algorithms. Moreover, the proposed system architecture has been field-tested for the detection of pavement anomalies and the classification of five rating categories. Furthermore, the proposed system may provide daily information on roadway pavement surface conditions, which can be used by agencies for automating the planning of pavement maintenance operations and for improving driving safety.

Physical layer protection for ADS-B against spoofing and jamming

Automatic Dependent Surveillance-Broadcast (ADS-B) is a widely used secondary surveillance radar standard for aviation and is a significant component in ensuring air traffic safety. Unfortunately, it has been demonstrated that ADS-B has security flaws. This paper addresses some of these issues by proposing a method and system architecture for verification of received signal authenticity on ADS-B In enabled aircraft. The method is based on physical layer signal analysis, i.e. estimation of signal source range and direction-of-arrival. Proposed system architecture includes a directional slotted antenna system and multi-channel receiver on ADS-B In side, but requires no change to existing ADS-B protocol. The proposed techniques provide security against message injection attacks, such as spoofing, and partial security against jamming. We assess estimation of error bounds and performance of the proposed techniques in simulated use-case scenarios.

Autonomous Robotic Manipulation: Real-Time, Deep-Learning Approach for Grasping of Unknown Objects

Recent advancement in vision-based robotics and deep-learning techniques has enabled the use of intelligent systems in a wider range of applications requiring object manipulation. Finding a robust solution for object grasping and autonomous manipulation became the focus of many engineers and is still one of the most demanding problems in modern robotics. This paper presents a full grasping pipeline proposing a real-time data-driven deep-learning approach for robotic grasping of unknown objects using MATLAB and convolutional neural networks. The proposed approach employs RGB-D image data acquired from an eye-in-hand camera centering the object of interest in the field of view using visual servoing. Our approach aims at reducing propagation errors and eliminating the need for complex hand tracking algorithm, image segmentation, or 3D reconstruction. The proposed approach is able to efficiently generate reliable multi-view object grasps regardless of the geometric complexity and physical properties of the object in question. The proposed system architecture enables simple and effective path generation and a real-time tracking control. In addition, our system is modular, reliable, and accurate in both end effector path generation and control. We experimentally justify the efficacy and effectiveness of our overall system on the Barrett Whole Arm Manipulator.

MM-Wave HetNet in 5G and beyond Cellular Networks Reinforcement Learning Method to improve QoS and Exploiting Path Loss Model

This paper presents High density heterogeneous networks (HetNet) which are the most promising technology for the fifth generation (5G) cellular network. Since 5G will be available for a long time, previous generation networking systems will need customization and updates. We examine the merits and drawbacks of legacy and Q-Learning (QL)-based adaptive resource allocation systems. Furthermore, various comparisons between methods and schemes are made for the purpose of evaluating the solutions for future generation. Microwave macro cells are used to enable extra high capacity such as Long-Term Evolution (LTE), eNodeB (eNB), and Multimedia Communications Wireless technology (MC), in which they are most likely to be deployed. This paper also presents four scenarios for 5G mm-Wave implementation, including proposed system architectures. The WL algorithm allocates optimal power to the small cell base station (SBS) to satisfy the minimum necessary capacity of macro cell user equipment (MUEs) and small cell user equipment (SCUEs) in order to provide quality of service (QoS) (SUEs). The challenges with dense HetNet and the massive backhaul traffic they generate are discussed in this study. Finally, a core HetNet design based on clusters is aimed at reducing backhaul traffic. According to our findings, MM-wave HetNet and MEC can be useful in a wide range of applications, including ultra-high data rate and low latency communications in 5G and beyond. We also used the channel model simulator to examine the directional power delay profile with received signal power, path loss, and path loss exponent (PLE) for both LOS and NLOS using uniform linear array (ULA) 2X2 and 64x16 antenna configurations at 38 GHz and 73 GHz mmWave bands for both LOS and NLOS (NYUSIM). The simulation results show the performance of several path loss models in the mmWave and sub-6 GHz bands. The path loss in the close-in (CI) model at mmWave bands is higher than that of open space and two ray path loss models because it considers all shadowing and reflection effects between transmitter and receiver. We also compared the suggested method to existing models like Amiri, Su, Alsobhi, Iqbal, and greedy (non adaptive), and found that it not only enhanced MUE and SUE minimum capacities and reduced BT complexity, but it also established a new minimum QoS threshold. We also talked about 6G researches in the future. When compared to utilizing the dual slope route loss model alone in a hybrid heterogeneous network, our simulation findings show that decoupling is more visible when employing the dual slope path loss model, which enhances system performance in terms of coverage and data rate.

Multi-Sensor Surveillance System Based on Integrated Video Analytics

Image-based sensing is a powerful source of information for a wide range of applications such as surveillance, monitoring, and automation. The volume of data collected by surveillance devices is enormous; therefore, images are processed to extract application-driven data, moreover, centralized processing is unfeasible when several cameras are distributed across broad geographical regions. In such scenario, with processing limitations and bandwidth availability being important restrictions, an automated process is required for extracting meaningful information from the collected data during surveillance process and reducing operator fatigue. The proposed design, which continuously processes the image stream to meet real-time requirements, provides integrated video analytics with enhancement, panoramic views, and automated motion detection. This system enhances pictorial information for human interpretation and analyzes scene data using machine-vision modules. These features aid in the use of surveillance system for continuous monitoring of border areas without the need for human intervention under adverse-weather conditions. The proposed system architecture is based on distributed video-analytics using visual and infrared-band sensors. The system has a visual detection range of 5 km with 80% detection probability for a 2.3 m X 2.3 m target under standard clear visibility conditions. The preliminary results indicate that the system is capable of processing up to 25 video frames per second. Additionally, the implemented system records data for post-analysis and uses video analytics to reduce the bandwidth requirement of communication link. Finally, this system can be distinguished because it is flexible, compact, affordable, and scalable, and therefore, can be considered for monitoring and surveillance.

Exploring the Impact of Parallel Architecture on Improving Adaptable Neuro-Fuzzy Inference Systems for Gas-Insulated Switch Defect Recognition

Gas-insulated switchgear malfunctions during power system operation may occur due to electrical, thermal, or human errors in the manufacturing process. The leading causes of insulation deterioration of gas-insulated switchgear are discharging along the surface caused by dirt on the insulating material, internal discharge caused by impurities and cavities in the insulating material, corona discharge caused by poor assembly or construction at the site, and electric tree channel discharge caused by the intense internal discharge. Since different defects produce different partial discharge characteristics, the operating power equipment can be analyzed using measurement instruments to detect partial discharge for preventive equipment fault diagnosis, avoiding unnecessary power outages and losses; therefore, evaluating the defects in gas-insulated switchgear is essential. In this study, three gas-insulated switchgears were prefabricated with different defects before encapsulation, and the partial discharge data of each defect were measured by applying different test voltages. The adaptive neuro-fuzzy inference system (ANFIS) input data were used to evaluate the recognition effect, showing that the average recognition rate of the core for all defects was over 90%. The proposed system architecture can continuously accumulate the defect measurement database of gas-insulated switchgear and be used as a reference for constructing electrical equipment defect recognition systems.

Designing of a Novel Neural Network Model for Classification of Music Genre

Music genre classification is an important task that entails classifying music genres based on aural data. Music genre classification is widely used in the field of music information retrieval. Data preparation, feature extraction, and classification are the three primary processes in the proposed system. New neural network is used to classify music genres. To categorize songs into respective music genres, the proposed system leverages feature values from spectrograms created from slices of songs as input to a proposed system architecture. Extensive tests on the GTZAN dataset demonstrate the efficacy of the proposed approach in comparison to existing methods. The proposed system architecture is also tested on Indian rhythms. This paper consists of the comparison of proposed system architecture with existing algorithms.

An IoT-Based Treatment Optimization and Priority Assignment Using Machine Learning

In India, the resources availability with respect to demand has a larger gap in reality. For data analytics and resource scheduling for optimized access using the Internet of Things (IoT) as a data frontend collector, a machine learning technique is discussed in this paper. Telemedicine was initially considered "futuristic" and "experimental," but telemedicine is the need of this time. Telemedicine applies in a number of fields: patient care, education, science, management, and public health. The present study describes launchpad's for patient compliance. The proposed approach is aimed at achieving an integrated IoT Unit, Machine Learning Unit, and Broadcasting Unit treatment platform using an interface medium. Methods: The proposed system is designed for data collection using MSP430 and RL200 Launchpads at the patient side under sensory operations. The processed data is extracted to servers for processing and thus providing an optimized machine learning technique for resource sharing, such as drug distribution, instrumental enhancement, and appointment allocation. Novelty: The proposed system architecture utilizes user group from various locations under both rural and urban categories installing the monitoring application as discussed under the IoT unit of for data acquisition and transmission. The hardware kit is aided with MSP430 and supporting Wi-Fi for connectivity to cloud servers. Findings: In the future stage of experiment and setup, MSP430 was replaced by RL200 with a built-in Wi-Fi module for easy connectivity and achieve compactness. The proposed technique has achieved satisfactory results for open datasets under the Hadoop environment.

Middleware to Address Heterogeneity Problem in IoT

The Internet of Things (IoT) envisions a future in which digital and physical things or products (e.g., smartphones, TVs, cars) can be linked through the use of appropriate data. to enable a variety of applications using information and communication technology as well as products and services The characteristics of the Internet of Things include an ultra-large scale network of things, as well as device and network-level heterogeneity and a high number of unintentionally created occurrences things like this will make developing a wide range of applications and services a difficult endeavor. In general, middleware can make a process easier. Integration of heterogeneous computing and development process promoting interoperability within telecommunication equipment a wide range of applications and services. In this paper, we will discuss Smart System for Device Interoperability was offered as a solution. It serves as a hub, allowing disparate devices to communicate with one another. Regardless of their differences, they can communicate through it. Protocols and other forms of communication Detailed. The proposed system's architecture is presented, as well as each of its component is well explored.

Flow rule‐based routing protocol management system in software‐defined IoT sensor network for IoT applications

SummaryIn this article, a software‐defined (SDN)‐based Internet of things (IoT) sensor network (S‐ISN) architecture is proposed to fulfill the IoT applications in real time. The proposed system's architecture contains three planes, namely, data plane, control plane, and application plane, to enrich SDN in IoT applications. An IoT application‐based SDN controller is designed exclusively with two management rules—IoT application device management and IoT application‐based topology management. IoT application device management engages in controlling the functions of physical devices that lie on the data plane—path formation of the sensor (proactive, reactive, and hybrid) and reporting scheme management (query, time, and event) of the IoT sensor node. Likewise, IoT application topology management facilitates controlling network topology‐related issues using network structure management (data, location, group, and hierarchical) and next‐hop selection management (broadcast, location, and probabilistic) of the IoT sensor network. The above said management policies are achieved in real time to meet the applications of IoT. Hence, this S‐ISN scheme focuses on IoT application‐related issues with great flexibility in real time. Experimental results show that the network metrics have been improved by the proposed approach as compared with existing methods.

Extending MQTT with Real-Time Communication Services Based on SDN.

MQTT is one of the most popular application-layer protocols used in the scope of the Internet-of-Things (IoT) and Industrial-Internet-of-Things (IIoT), given its suitability for resource-constrained embedded systems. However, MQTT Quality-of-Service policies do not support timeliness requirements, which is common in IIoT. The literature reports several research works that address this limitation, but they are limited in scope (e.g., improvements in the broker’s internal operation, control of the publisher’s data rate, and path optimizations). Conversely, this paper presents a comprehensive architectural approach, proposing a set of extensions to the MQTT protocol that allow applications to explicitly specify real-time requirements and instantiate corresponding network reservations to enforce the desired temporal behavior. Such reservations are enforced via Software Defined Networking, specifically the OpenFlow protocol, but other protocols that allow bandwidth reservations, e.g., TSN, can also be used. This paper presents the proposed system architecture together with extensive emulation and implementation results that validate the feasibility of the approach, showing that time-sensitive MQTT traffic can be effectively segregated and prioritized to meet application-defined real-time requirements. Using several combinations of network topologies and load levels and comparing to the absence of the proposed real-time mechanisms, both average and worst-case latencies of the time-sensitive traffic decreased to approximately half, while for the normal traffic, they increased by approximately 10%.

One-bit DACs precoding for massive MU-MIMO systems based on antenna selection architecture

In massive multi-user multiple-input multiple-output (MU-MIMO) communication systems, the utilization of one-bit digital-to-analog converters (DACs) in the base station (BS) radio frequency (RF) chains can significantly reduce the power consumption of the system. This study proposes a low-cost precoding architecture for massive MU-MIMO systems to alleviate multi-user interference (MUI). By including a selection structure, the architecture decreases the power consumption of typical one-bit precoding architecture. Based on this structure, we investigate the antenna selection-aided one-bit DACs precoding problem. However, jointly identifying the precoding factor and the precoding vector of the proposed precoding architectures is intractable because they are coupled together. We address this issue by utilizing an alternating direction multiplication method (ADMM) framework. The antenna selection strategy and the implementation of the non-convex approximate projection operator are given in detail. In addition, the power consumption of the proposed system architecture is analyzed. Simulation results reveal that the proposed precoding algorithm can successfully activate the antenna subset and ensure the performance of the system. Moreover, the hardware complexity and power consumption of the proposed precoding architectures are considerably lower than those of previous one-bit DACs precoding architectures.

3D Printing in the Context of Cloud Manufacturing

3D printing has drawn tremendous attention in Industry 4.0. Nowadays, with the ever-increasing consumers’ requests for 3D printing services, there lies a big challenge to eliminate the unbalanced demands and supplies of 3D printing resources in a geographically distributed environment. Cloud manufacturing, as a newly emerged service-oriented manufacturing paradigm, provides a promising way to overcome the challenge by integrating 3D printing into the cloud-based context, which may flourish the development of smart networks of virtual 3D printing cloud and also promote a novel 3D printing service business model to achieve mass customization. This paper presents a comprehensive study of 3D printing in cloud manufacturing environment. Two typical models of 3D printing, i.e. primary 3D printing cloud model and advanced 3D printing cloud model are presented and compared. The system architecture design of a 3D printing cloud platform is proposed to support the latter model. Furthermore, a series of key enabling technologies are presented based on the proposed system architecture. Finally, a prototype of 3D printing cloud platform is deployed with a case study of an aircraft engine part. The research will provide valuable theoretical and practical references to the future development of 3D printing clouds.