International Journal of Engineering and Manufacturing @ijem
Journal articles - International Journal of Engineering and Manufacturing
All articles: 623
A New Automatic Generation Control with Heterogeneous Networks for Smart Grid
Scientific article
Current sensor can measure DC current signal for high frequency (MHz magnitude), which has a very wide frequency range. And its affluent magneto resistance system can meet the needs of all kinds of electric current in the power system monitoring. In this paper, the former measure the performance levels of the network through objective point of view, the latter base on the former to join the subjective demand of distribution communication service, and to compromise subjective and objective decision result which make the business’s decision for choice of network access result more reasonable and more In favor the meet business needs of Cos.
Free
A New Method of Signature Verification Based on Biomimetic Pattern Recognition Theory
Scientific article
Aim at the difficulty and low recognition rate of signature verification, this paper introduces biomimetic pattern recognition theory and applies it to the problem. According to the features of the signature samples, the coverage in the high-dimension feature space is built, one class of samples are all covered with a super-sausage neuron chain. As the radius selection of the super-sausage neurons maybe unreasonable, unwanted area may be covered and correct recognition rate will reduce. So this paper uses the relationship of the distance between the two training samples and the average distance of all the neurons to adjust the radius of the super-sausage neuron automatically. Finally, the experiments show that compared to traditional pattern recognition method, biomimetic pattern recognition theory used in signature verification have a better recognition result and is more effective.
Free
A New Support Vector Machine Optimized by Simulated Annealing for Global Optimization
Scientific article
SA-SVM model was proposed in which parameters were optimized by simulated annealing. Parameter (the kernel function) and C (the error discipline) are the key factors to the precision of SVM. Simulated annealing was used to optimize the key parameters of SVM to make enhancement on the forecasting effect of SVM. By applying this proposed model for several function optimizations, results of which demonstrate the improvement of SA-SVM on the high model accuracy in the optimization searching, and it can overcome the blindness of the model parameters.
Free
Scientific article
Sustainable smart agriculture and climate resilience are significant factors for maintaining food security with environmental management. Existing agricultural systems target predicting and generating reports but lack detailed explanations as to why the phenomenon occurs. The examples of such why are like “Why there is a significant decline in the yield?”, “Why the soil is degrading?”, “Why the level of water is declining?” and so on. To address this challenge, the paper presents a prototype for Explainable LLM based Why-QA framework for sustainable smart agriculture. The implemented prototype integrates domain-enriched LLM with knowledge graph, causal inference engine with explainability layer to provide detailed explanations to complex “why-questions”. Domain-specific LLMs are used to support the domain knowledge with knowledge graph analyzing the sustainable relationships in the answer, causal reasoning to produce the causes of events and explainability module to provide the detailed reasoning supported with benchmark sustainable metrics incorporating the soil, climate and crop data. The prototype implementation of framework is evaluated on a dataset of 500 annotated agricultural why-type questions constructed from FAOSTAT, USDA, and NOAA sources. Results clearly demonstrate promising improvements over five baseline systems developed across causal reasoning and explanation quality metrics, which help validating the architectural feasibility of the proposed framework.
Free
A Novel Genetic Operator for Genetic Folding Algorithm: A Refolding Operator and a New Genotype
Scientific article
Genetic Folding algorithm uses linear chromosomes composed of organized genes in floating-numbers manner, in which each genes chain fold back on themselves to form the final GF chromosome. In this paper, a novel genotype representation and a novel genetic operator were proposed. The paper was applied using MATLAB code to illustrate the beneficiary, flexibility and powerful of the Genetic Folding algorithm solving Santa Fe Trail problem. The problem of programming an artificial ant to follow the Santa Fe Trail is used as an example of program search space. To evaluate the efficiency and feasibility of the proposed methods, a comparison was held between the various types and sizes through the Santa Fe Trail problem. Several test functions along with various levels of difficulty were also conducted. Results of this proposal clearly show significant results of the proposed genotype and the genetic operator also.
Free
A Novel Hand Prosthesis Control Scheme Implementing a Tongue Control System
Scientific article
This paper presents a novel control scheme for new advanced hand prostheses implementing multiple pinches and grasps. The control signals for the hand are determined by myoelectric signals from the arm and volitionally generated signals by tongue through an inductive interface with a mouth piece. The feasibility tests have been performed on an able-bodied subject who controller a virtual reality hand. Results suggest that this hybrid control scheme works well, it is intuitive and the subject learned fast to use it, and what is most important provides many more control channel to advanced hand prostheses. This research is being continued in healthy subjects with the intention to translate the results to patients.
Free
Scientific article
Multi CNN has recently gained popularity in image classification applications. In particular, Computer vision has acquired a lot of attraction due to its numerous potential uses in food quality management. Among all the dry fruits available in India, the cashew nut is a significant crop. Specifically high-quality cashew nuts are quite popular on the worldwide market. Although there are a variety of approaches for automatically identifying cashew nuts, the majority of them concentrate on a single view image of the cashew nut. The fundamental issue with current methods for recognizing whole and split cashew nuts is that a single view image of a cashew nut cannot encompass the entire view of a cashew nut, resulting in low classification accuracy. We proposed Multi-view CNN to provide a novel framework for classifying three types of cashew nuts. Images of the sample cashew nuts are taken from three distinct angles (top, left, and right) and fed into the proposed modified CNN architecture. For categorization, the modified CNN extracts and combines many elements from these three images and obtains the accuracy of 98.87%.
Free
Scientific article
Accurate registration of PET and CT images is an important component in oncology, so we aim to develop an automated registration algorithm for PET and CT images acquired by different system. These two modalities offer affluent complementary information: CT provides specificity to anatomic findings, and PET provides precise localization of metabolic activity. In this paper, we proposed an improved registration method that can accurately align PET and CT images. This registration algorithm includes two stages. The first stage is to deform PET image based on B-Spline Free Form Deformations (FFD). It is consists of three independent steps. After the feature points of PET and CT images have been extracted in the preprocessing step. As a next step, the PET image is deformed by B-Spline Free Form Deformations (FFD) with feature points of CT images. The second stage is to register PET and CT images based on Mutual Information (MI) of feature points combined with Particle Swarm Optimization (PSO) algorithm and Powell algorithm that are used to search the optimal registration parameters.
Free
Scientific article
One of the main goals for designing database is minimize the data redundancy. Literature shows that there is several approach have been used to minimize the data redundancy, such as converting an Entity Relational Diagram (ERD) scheme according to steps of an algorithm for ER-to-relational mapping, and applying the normalization rules. These techniques have improved the database design quality, reduced the data redundancy, and omitted from a large proportion of repetition. However, there are still a big proportion of duplicated values especially for the huge database as some attribute are related to each other and may have the same data, such as the attributes of first_name, middle_name, and family_name. These attributes cannot be called as the multivalued attribute as these values belong to variety of entities or relations. Therefore, we propose a novel normalization forms for relational database design that match the related data attribute. This proposed approach called Matching Related Data Attribute Normal Form (MRDANF). A civil registration database system is used as a case study to validate the proposed approach. The results show that using our proposed approach has the positive impact on database quality and performance as the data redundancy will be reduced.
Free
Scientific article
The Internet of Things (IoT) has ushered in significant advancements in networked technologies, yet it simultaneously raises concerns about the security and privacy of connected devices. Traditional authentication methods based on cryptographic protocols are increasingly vulnerable to attacks as the number of devices grows and attackers develop more sophisticated strategies. In this paper, we propose a novel quantum-based authentication method using Quantum Physical Unclonable Functions (QPUFs) to address the security challenges in IoT devices. Quantum PUFs exploit the inherent quantum properties of devices to generate unique, unclonable responses to challenges, providing a high level of security and resilience against attacks such as cloning, spoofing, and interception. We present the architecture of the proposed quantum authentication system, discuss the challenge-response protocol, and evaluate the system’s performance. Experimental results show that this approach offers strong security guarantees with minimal computational overhead. We Evaluate the Security, Scalability of our approach in simulated adverse IoT environment.
Free
A Novel Resource and Distribution Aware Random Forest for Agricultural Productivity Prediction
Scientific article
Agriculture has continued being one of the economic powerhouses of India, but then the productivity is usually compromised due to the poor utilization of soil and environment data. This paper is a proposal of a new framework named Distribution and Resource Aware Random Forest (DRARF) to be used in smart farming applications. The strategy combines IoT-ready soil data that comprises of moisture, temperatures, humidity, pH, and NPK that are monitored via different sources and used to make crop-specific decisions. The DRARF presents two important novel features to traditional Random Forests: (i) distribution-aware threshold selection, which guarantees statistical meaningful data partition and (ii) resource-aware feature selection, which gives more predictive power without the expense of buying sensors in the IoT. It assessed the framework using soil and environmental data of wheat and rice. The comparative tasks performed using Logistic Regression, Support Vector Machine, Naïve Bayes, and the classical random Forest have shown that DRARF not only provides a better accuracy, precision, recall and F1-scores, but it also minimizes sensor redundancy. Its potential depends on its scalability, efficiency, and reliability as a precision agricultural decision-support system and this, as well as the remaining results, are reflected in the results. The given approach with machine learning and IoT-facilitated sensing source-based solutions can bring the advancements in the sphere of smart farming technologies to help increase the yield of crops and resources and improve long-term food security.
Free
A Novel Spiking Cortical Model based Filter for Impulse Noise Removal
Scientific article
A novel spiking cortical model based switching mean filter for removing impulse noise is presented. In the proposed filter, the noise detector using spiking cortical model is first adopted to identify the pixels that are likely to be corrupted by impulse noise. Then the detected impulses are removed by the weighted mean filter while the noise-free pixels are left unaltered. Extensive simulations show that the proposed filter outperforms a number of existing decision-based filters due to its excellent performance in terms of effectiveness in image restoration. Because of its outstanding restoration performance, the proposed filter can be used for noise removal in numerous consumer electronics products such as digital camera and digital television.
Free
A Parameter Free Iterative Method for Solving Projected Generalized Lyapunov Equations
Scientific article
This paper is devoted to the numerical solution of projected generalized continuous-time Lyapunov equations with low-rank right-hand sides. Such equations arise in stability analysis and control problems for descriptor systems including model reduction based on balanced truncation. A parameter free iterative method is proposed. This method is based upon a combination of an approximate power method and a generalized ADI method. Numerical experiments presented in this paper show the effectiveness of the proposed method.
Free
A Participatory System to Sense the Road Conditions
Scientific article
The monitoring of road conditions and surface anomalies such as potholes, bumps etc., has shown a great importance in the safety and comfort of road users from pedestrian to drivers. Detection and identification of such road anomalies not only reduces the causes of road accidents but also avoid vehicle damages. This can provision the management authorities to keep a track of road conditions along with maintenance of roads. Monitoring the road conditions is a challenging task and potholes detection plays an important role in the repairing of asphalt road surface. Many approaches exist to collect data about road surface conditions, however most of these approaches are low-speed human visual inspection or approaches that uses advanced and costly measuring equipments. Therefore, there is a need to develop a cost effective system that can manages these kind of issues. In this paper, a Participatory Sensing system based on raspberry pi is designed and developed to detect and record road surface anomalies that are measured by the inertial measurement unit (IMU) and GPS sensor. An android application is also designed and developed to alert the user from an upcoming high-intensity rough area on the road. Message Queuing Telemetry Transport (MQTT) protocol is used to publish and subscribe data from raspberry pi to data servers.
Free
A Probability Model for Occurrences of Large Forest Fires
Scientific article
Forest fires occur at various spots and various times all around the world. One of major efforts in forest fire management is to estimate the probability of occurrence of fires so that people would be better prepared to control those fires. In this paper, we establish a probability model and a numerical procedure for estimating probability of occurrences of large forest fires. A simulated numerical experiment is also presented to illustrate the application of the probability model and the numerical procedure.
Free
A Real-time Light-weight Computer Vision Application for Driver’s Drowsiness Detection
Scientific article
The issue of drowsiness while operating a motor vehicle is an increasingly common occurrence that has been found to contribute significantly to a substantial number of fatal accidents annually. The urgency of the current situation necessitates implementing a solution to mitigate accidents and fatalities. The present study aims to investigate a less intricate and less expensive but remarkably efficient approach for detecting drowsiness in drivers, in contrast to the existing complex systems developed for this purpose. This paper focuses on developing a simple drowsy driver detection system utilizing the Python programming language and integrating the OpenCV and Dlib models. The shape detector provided by Dlib is employed to accurately determine the spatial coordinates of the facial landmarks within the given video input. This enables the detection of drowsiness by monitoring various factors such as the aspect ratios of the eyes, mouth, and the angle of head tilt. The performance evaluation of the system under consideration is conducted through the utilization of standardized public datasets and real-time video footage. When tested with dataset image inputs, the system showed exceptional recognition accuracy. The performance comparison is done to show the efficacy of the proposed approach. Traveling can be made safer and more effective by combining the proposed system with additional safety features and automation technology in cars.
Free
A Reinforcement Learning-based Offload Decision Model (RL-OLD) for Vehicle Number Plate Detection
Scientific article
Vehicle license number plate detection is essential for road safety and traffic management. Many existing systems have been proposed to achieve high detection precision without optimization of computer resources. Existing models have not preferred to use devices like smartphones or surveillance cameras because of high latency, data loss, bandwidth costs, and privacy. In this article, we propose a model of unloading decisions based on reinforcement learning (RL-OLD) for recognition and detection of vehicle license plates for high precision with optimization of computer resources. The proposed model detected different categories of vehicle registration plates by effectively utilizing edge computing. Our model can choose either the compute-intensive model of the cloud or the lightweight model of the local system based on the properties of the number plate. This approach has achieved high accuracy, limited data loss, and limited latency.
Free
A Review on Stabilization of Soft Soils with Geopolymerization of Industrial Wastes
Scientific article
Geopolymers are inorganic aluminosilicate polymers that solidify into ceramic-like substances at tempera-tures close to ambient. The elements in silicate oxide (SiO2) and aluminum oxide (Al2O3) are essential for the hardening of geopolymers because they combine with other elements to create N-A-S-H formation, which gives the material its distinctive strength. Geopolymers based on industrial wastes are increasingly being used to stabilize soft soils. Fly ash, GGBS, metakaolin, glass powders, and others are a few of the industrial wastes that aid in synthesizing geopolymers. Several experimental studies were carried out to determine the mechanical strength, durability, and microstructure im-provement of soft soils stabilized with geopolymers. Some of the experiments include X-ray diffraction (XRD), scan-ning electron microscopy (SEM), unconfined compression testing (UCS), and durability testing. The main objective of this review was to assess the different types of binders, binder ratios, alkali activator types, alkali activator concentra-tions, and other parameters used in synthesizing geopolymers. The binder's proportion varies between 5% and 30% of the soil's dry weight. Researchers commonly use sodium silicate (Na2SiO3) and sodium hydroxide (NaOH) solution for the alkali activator. Since the unconfined compression test is one of the quickest and least expensive ways to determine shear strength, most researchers were used to measure stabilized soils' mechanical strength. This paper highlights the most frequently used industrial wastes used to synthesize geopolymers. The review enables researchers to acquire es-sential and complementary inputs for future research.
Free
A Review: DWT-DCT Technique and Arithmetic-Huffman Coding based Image Compression
Scientific article
Nowadays, the volume of the data is increasing with time which generates a problem in storage and transfer. To overcome this problem, the data compression is the only solution. Data compression is the science (or an art) of representing information in compact form. This is an active research area. Compression is to save the hardware storage space and transmission bandwidth by reducing the redundant bits. Basically, lossless & lossy are two types of data compression technique. In lossless data compression, original data is similar to decompressed or decoded data, but in lossy technique is not same. In this paper, Study lossless image compression technique. The purpose of image compression is to maximum bandwidth utilization and reduces storage capacity. This technique is beneficial to image storage and transfer. At the present time, Mostly image compression research have focused on the wavelet transform due to better performance over another transform. The performance is evaluated by using MSE & PSNR. DWT, quantization, Arithmetic, Huffman coding and DCT techniques are briefly introduced. After decompression, the quality of image is evaluated using PSNR parameter between original & decoded image. Compression ratio (CR) parameter is calculated to measure how many times image compressed.
Free
A Scheme of IBE Key Issuing Protocol Based on Identity-password Pair
Scientific article
To avoid the impersonation attack, an efficient and secure key issuing protocol based on identity-password pair is proposed, in which an additional identity-password pair issued by KGC and KPAs is used to authenticate a user’s identity. In this protocol we use a simple blinding technique to eliminate the of secure channel and multiple authorities approach to avoid the key escrow problem. Our protocol solves the key-escrow problem successfully and saves at least 4n pairing and 2n Hash operations in comparison to Lee B et al’s protocol.
Free
