International Journal of Engineering and Manufacturing @ijem
Journal articles - International Journal of Engineering and Manufacturing
All articles: 649
Artifacts Removal of EEG Signals By the Application of ICA and Double Density DWT Algorithm
Scientific article
Independent Component Analysis is used for the automation and detection of brain artifacts. The Independent Component Analysis (ICA) here is used for the segmentation of artifact peaks in the signal. Then the Discrete Wavelet Transform is applied for multi-level transfer of signal data until the reception of significant result. We have extended our search and applied the Double Density Algorithm for the multi-level transfer. The results obtained were analyzed from the data set of EEG signals taken with a outsource reference. Since the method is parameter free implementations in clinical settings are imaginable.
Free
Scientific article
This study proposes an optimized Multi-Histogram Equalization (OMHE) technique for contrast enhancement while preserving the brightness of an input image. The objective of this study is to improve the visual interpretability or perception of information among color images. In this technique, input image histogram is partitioned into multiple sub-histograms and then classical histogram equalization process is applied to each one. Values of t threshold points for dividing the image histogram into t+1 sub-histograms are optimized using Artificial Bee Colony, a swarm intelligence-based optimization algorithm. A new fitness function for evaluating the contrast of enhanced image is proposed here that will guide the Artificial Bee colony algorithm into finding the optimal threshold values. AMBE (Absolute Mean Brightness Error), PSNR (Peak signal to noise ratio), SSIM (Structural Similarity Index) and Entropy are computed for quantitative analysis of the performance of the proposed method with existing methods. Comparisons show that proposed method performs better than other present approaches by enhancing the contrast well while preserving the brightness of the input image.
Free
Artificial neural networks based approach for predicting LVDT output characteristics
Scientific article
This paper presents a novel approach for training and output prediction of data of a Linear variable differential transformer (LVDT). LVDT is a commonly used device used in laboratories for measuring linear displacements in specific situations. This article considers application of Artificial Neural Networks (ANNs) for learning and output estimation of LVDT. Real-time experiments were conducted and results were collected for training of ANNs. The Regression results and outputs verified the learning and prediction capability of ANNs.
Free
Scientific article
To improve surveillance, the proposed patrolling security system employs autonomous mobile robots outfitted with low-cost night vision cameras. Regular patrols, which are essential for discouraging criminal behavior, are typically conducted by security or law enforcement officers with the use of pricey CCTV equipment. The goal of using autonomous robots is to save expenses while enhancing the quality of patrols in particular regions. Using a night vision camera, the late-night guarding robot detects human movement within its assigned zone while following a random path. Its obstacle-detecting sensors help to prevent crashes and guarantee secure navigation. The robot records incidences, takes pictures with its mounted camera, and carefully scans regions for probable incursions. It then sends the data to the user as quickly as it can. This project's primary goal is to draw attention to suspicious activity in hidden areas.
Free
Scientific article
The determination of strength properties i.e compressive strength, flexural strength and splitting tensile strength is essential to estimate the load at which the concrete members may crack especially in aggressive environment. The paper reports an experimental investigation on deterioration of used engine oil (UEO) soaked flyash concrete with respect to its strength properties and effective automation of classification of data sets returned by the SEM test on the same set of samples. In the former part, concrete cube ,beam and cylinder specimens with fly ash admixture as partial replacement of cement by 0%, 5%, 10%, 15%, 20%, 25%, 30%, 35% and 40% were subjected to water curing and then to UEO soaking. Gradual decrease in the strength properties of concrete specimens with respect to time was observed. An attempt has been made to study the permeation properties like soroptivity with the addition of fly ash in concrete. The SEM analysis of test results was in good agreement to this. An attempt was made to automate this analysis phase using correlation coefficient and Support Vector Machines (SVM). It was found that the latter achieved better results in terms of performance.
Free
Scientific article
Kidney abnormalities, when detected late, can develop into chronic conditions such as kidney tumors and cardiorenal syndrome. Recently, there has been a move toward automation, especially as it pertains to developing a framework for advanced preprocessing, feature fusion, and hybrid spatial-temporal learning for the detection of the abnormalities in question. For example, Non-Local Means (NLM) filtering for noise reduction, image quality improvements through U-Net kidney segmentation and deep learning-based text annotation removal, as well as robust training through data augmentation and preprocessing ends up facilitating the process. The combination of classical texture and shape descriptors and deep embeddings from a Vision Transformer (ViT) through an attention mechanism allows the model to pinpoint where clinically relevant focus should be. A hybrid CNN-LSTM framework attends to spatial and temporal feature extraction, while attention modules receive the classification output to refine it. The incorporation of weighted binary cross-entropy for handling class imbalance, and of explainable AI, is demonstrated through Integrated Gradients. Experimental results for VATLA show it used advanced algorithms and automation principles in developing systems for all previous performance indicators, while providing evidence of scoring 0.94 in accuracy, 0.92 in precision, 0.95 in recall, and 0.96 in AUC, or area under the curve.
Free
Attention-Guided Deep Learning Framework for Ovarian Cancer Subtype Classification
Scientific article
Ovarian cancer histotype classification is challenging because of substantial morphological heterogeneity and subtle subtype-specific features. This work presents a controlled evaluation of high-resolution pathology representations and slide-level aggregation methods for automated classification of five ovarian cancer subtypes from whole-slide histopathology images. Precomputed CONCH patch embeddings were aggregated using mean pooling, max pooling, gated attention-based multiple-instance learning, and a max-pooling cascade. The models were evaluated on 513 non-TMA whole-slide images from UBC-OCEAN using leakage-controlled five-fold cross-validation, with each slide receiving exactly one out-of-fold prediction. Gated ABMIL achieved a balanced accuracy of 81.39% and a macro-F1 score of 81.96%. Max pooling produced the highest numerical performance, with a balanced accuracy of 81.44%, macro-F1 of 82.59% (95% CI: 78.84-86.26%), macro-AUROC of 96.99%, and macro-AUPRC of 90.79%. However, paired slide-level bootstrap comparisons found no statistically significant differences among the CONCH aggregation strategies after Holm correction. Compared with the EfficientNet-B0 thumbnail baseline, CONCH max pooling improved macro-F1 by 30.30 percentage points and balanced accuracy by 25.70 percentage points, with both paired bootstrap confidence intervals excluding zero. Attention weights enabled visualization of influential patches, although these regions were not independently validated by pathologists. The findings show that high-resolution pathology foundation-model representations support ovarian cancer subtyping, while greater aggregation complexity does not necessarily improve performance. External multi-institutional validation is required before clinical generalizability can be established.
Free
Scientific article
Android's widespread adoption and open ecosystem make it a primary target for malware, a challenge exacerbated by internet fragmentation resulting in non-stationary data distributions across regions. This work presents AuthProtect, a scalable malware detection framework based on incremental learning and a novel permission-to-exploitation mapping approach that links 135 permissions to 25 malware development techniques. The system is validated on a balanced dataset of 82,704 benign and 82,704 malicious applications, partitioned into three geographic regions to assess robustness to distribution shifts. A similarity-based selective training strategy improves computational efficiency by training only on novel samples (cosine similarity < threshold τ), while a test-then-train mechanism enhances robustness by sequentially processing samples to avoid data exposure bias. Evaluation on four benchmark datasets (Naticusdroid, Malgenome, CICMalDroid 2020, Android Malware Dataset) demonstrates accuracy ranging from 0.9573 to 0.9992, with a maximum accuracy of 0.9982 on real-world data. We provide a comparative analysis against state-of-the-art methods and ablation studies quantifying the contribution of each component. Limitations include dependency on the completeness of permission-technique mapping and computational overhead for real-time deployment on resource-constrained devices.
Free
Automated Roof Top Plant Growth Monitoring System in Urban Areas
Scientific article
Innovation is progressing at a quick pace so it is required to utilize it in an each fields to have the coveted and appropriate yield. Present day's robots are winding up plainly more well-known and are progressively depend upon embrace schedule, regularly dull errands which are costly to do utilizing generously compensated labor. Because of the expanded populace and urbanization less space found for cultivating particularly in urban regions. There is a need of self-creating of slightest individual prerequisites. To fulfill ordinary demand in green vegetables and love towards their indoor and outside plants can be expert through urban rooftop gardening. This paper clarifies essential assignments of checking and detailing the development status of plants in urban rooftop gardening. We execute the customary checking of plants development. Height of the plant is one of the parameter to decide the growth of the plant. The tallness of the plant is more than the predetermined typical height in the program; robot shows that as overgrown, if there is no development discovered robot will show that as vacant slot. For identifying the development of the plant we utilize Sharp GP2D12 sensor, three white line sensors of ATMEGA 2560 FIREBIRD V to take after the arena of cultivation slots.
Free
Automated Wall Painting Robot for Mixing Colors based on Mobile Application
Scientific article
The final stage, which is the building paint or the adopted design, is where most real estate developers and constructors struggle. Where extensive painting is required, which takes a lot of time, effort, and accuracy from the firm doing the work. Additionally, it might be challenging to decide on the precise color grades for the design and calculate the right amount of paint to use for the job. Where these activities are extremely expensive, and the complex implementation is accompanied by worries and skepticism. These are the motivations behind the development of painting machines that blend colors. Artificial intelligence is used in the machine's design to make it efficient and quick at what it does. High accuracy is needed when selecting the proper colors, and this machine is distinguished by its ability to select the proper color tone. The color sensor (TCS34725 RGB) determines the relevance and accuracy of the desired color by comparison with the system database with the assistance of the light sensor (STM32), which measures the degree of illumination of the chosen place. By combining basic colors, this technique saves the customer the hassle of looking at specialized stores for the level of color they require. By giving the system the codes assigned to each color, it may also blend colors. The system also has the feature of controlling the machine remotely via smart phone application by enabling bluetooth and wifi features.
Free
Automatic IoT based plant monitoring and watering system using Raspberry Pi
Scientific article
The main objective of this proposed work is to develop an Embedded System for plant monitoring and watering system using Internet of Things, Raspberry Pi as Processor, and sensors for sensing environmental conditions. In this work, IoT concept is introduced to connect devices through Internet and facilitate information access by the users. The system can obtain accurate perception of Environmental information in agriculture field and then transmit the same to users. The system monitors different parameters like Temperature, Humidity, Soil Moisture and Intensity of light. IR sensor is fixed to check any external object entry into the field, in case of intruder detection buzzer will turn on for few seconds. The Motor fixed in the field operates both manually and automatically depending upon Moisture sensor results in soil. Motor automatically switches between on and off stage of pumping action. Results are observed either in web app and monitor.
Free
Automatic System Recognition of License Plates using Neural Networks
Scientific article
The urgency to increase the efficiency of recognition of car number plates on images with a complex background need the development of methods, algorithms and programs to ensure high efficiency, To solve the task the author has used the methods of the artificial Intelligence, identification and pattern recognition in images, theory of artificial neural networks, convolution neural networks, evolutionary algorithms, mathematical modeling and models characters were then statistics by using feed forward back propagated multi layered perception neural networks.. The proposed this work is to show a system that solves the practical problem of car identification for real scenes. All steps of the process, from image acquisition to optical character recognition are considered to achieve an automatic identification of plate.
Free
Automatic plant Irrigation Control System Using Arduino and GSM Module
Scientific article
The evolving information technology abridges the hardship in the daily life of consumers all over the world, hence the application of this knowledge in the irrigation field is necessary nowadays. The exponential growth of demand in food is due to the ever-evolving population of the world, thus it becomes necessary to expand the present area of cultivation. Considering the present situation of weather change due to global warming as a result of industrial activities, farming via irrigation is the reliable process of food production. Water remains the only source for survival for crop production, thus optimal management and proper use of water become pertinent with the ever-increasing land for irrigation. Arduino based automatic plant irrigation control system; provides a simple approach to automated irrigation. This work makes use of the GSM module for the notification of the user about the situation in the farm, this project aims to design and implement an automatic plant irrigation control system using Arduino and GSM module. In this proposed system, there are two main parts hardware and software units. Mechanical units which are the hardware unit comprises of instrumentation systems and watering irrigation systems. The equipment system is based on microcontroller, flow meter, moisture sensor, LCD, and GSM module. The software part comprises of C++ code, this is to enable the linkage between various modules. The main control of this system is the microcontroller unit that serves as the brain for coordinating control for various modules of the system, it synchronizes and operates the watering system and notifies the user about the condition of the field and watering section via GSM module. Implementation of this project will significantly help in a water-saving of about 30 – 50% as compared to the conventional watering system like the sprinkler, improve growth and discourage weeds because water will only be served to the needed area, simple method and timer-based system for automatic watering can be incorporated for efficiency.
Free
Automatically Extracting Name Alias of User from Email
Scientific article
Mining user identity information from emails is an important research topic in email mining. Most approaches extract an email user's name only from the header of an email, but there are often many name information in the body of emails, which are usually more suitable for representing the sender's or recipient's identity. This paper focuses on the problem of extracting email users' name aliases in the body of plain-text emails. After locating and extracting salutation and signature blocks from email bodies, we can identify the potential aliases in the salutation and signature lines, which can be directly related with the email addresses in email headers, by using named entity recognition(NER) tools. To verify and amend the potential aliases that were identified by NER tools, we propose a novel approach to extract aliases in the salutation and signature lines based on name boundary word template built on the characteristics of alias neighboring words. Results on the public subset of the Enron corpus indicate that the approaches presented in this paper can efficiently extract user's aliases from email bodies.
Free
Battery Management System for Solar Power Plants in Uganda: An IoT-Driven Approach
Scientific article
In Uganda, the efficiency and reliability of solar power plants are often compromised due to inadequate battery management, leading to reduced battery lifespan and suboptimal performance. To address this challenge, this project develops and prototypes a smart Battery Management System (BMS) tailored for solar power plants. The system continuously monitors key battery parameters, including voltage, load current, and temperature, while leveraging Internet of Things (IoT) technology for real-time data transmission and remote monitoring. Intelligent algorithms autonomously regulate charging and discharging cycles to prevent overcharging and deep discharge, optimizing battery performance. Testing demonstrated that the BMS significantly improved battery lifespan and energy efficiency by disconnecting charging at 100% and isolating the load at 10% discharge to prevent battery degradation. Additionally, the system disconnects power when battery temperature exceeds 30°C (ambient temperature: 25°C) and detects abnormal current levels above 0.16A to mitigate faults such as short circuits. These automated protections enhance battery reliability and longevity. By implementing proactive battery management strategies, the developed BMS contributes to more efficient and resilient energy storage systems, promoting sustainable energy development in Uganda.
Free
Behavioral Compatibility Analysis of Component-based Real-time System
Scientific article
For verification of component behavior compatibility in component-based real-time system, we make use of the timed automata to formally describe the component. In this way, the problem of component behavior compatibility is equivalent to whether the complementary actions can really synchronize over common channels on the system’s TA models. We then use the verification function of UPPAAL to automatically generate result, and finally conduct a case study to demonstrate how our technique works.
Free
Benchmarking Linear, Ensemble, and Neural Models for Entity-Level Sentiment Analysis on Twitter Data
Scientific article
Social media streams reflect opinion of public in real-time, but short and noisy tweets make it hard to attribute sentiment to entities and this paper introduces an AI/ML pipeline to classify the sentiment towards the referenced entities in twitter messages. Using the Twitter Entity Sentiment Analysis benchmark (twitter_training.csv and twitter_validation.csv), the tweets are normalized (lowercasing, punctuation, platform specific artifacts, tokenization, stop word filtering and lemmatization) and represented using TF-IDF (Term Frequency–Inverse Document Frequency) features with a maximum of 5000 terms. Machine learning models including Logistic Regression, linear SVM, Multinomial Naive Bayes, and ensemble and neural methods such as Random Forest, XGBoost, and Multilayer Perceptron (MLP) are trained on the training split and evaluated on the validation split using macro-averaged precision, recall, F1-score, and confusion matrix analysis. The results show that linear discriminative models are well suited to sparse TF-IDF spaces, with SVM and Logistic Regression providing balanced class-wise behaviour and Naive Bayes offering a computationally efficient baseline. XGBoost delivers moderate improvements over simple probabilistic models, while Random Forest achieves substantial gains through ensemble learning. The best overall performance is obtained by MLP, demonstrating that non-linear neural modeling more effectively captures complex feature interactions and entity-relevance patterns. Misclassifications are focused on the Neutral - Irrelevant boundary, resulting in instances of relevance ambiguity at the entity level in the case of sentiment and driving future extensions with context aware deep architectures and entity conditioned representations. These baselines provide support for monitoring purposes for brands and public figures as well as expose the limits of non-contextual features for sarcasm and implicit targets in Twitter discourse.
Free
Scientific article
Laser micromachining has become an essential tool in precision manufacturing due to its non-contact nature, high spatial resolution, and capability to produce intricate micro-features. However, identifying the optimal combination of process parameters remains challenging because of the nonlinear and interdependent effects of laser power, scanning speed, and pulse frequency on cut quality. In this study, a comparative framework is presented that benchmarks the Taguchi Design of Experiments (DoE) against a Deep Neural Network (DNN) model to predict and optimize the micromachining performance of stainless steel. A unified Cut Quality Index (CQI) was developed by combining three critical responses kerf width, heat-affected zone (HAZ), and edge chipping into a single measure of overall cut integrity. A physics-consistent dataset of 75 samples, comprising 20 literature-based and 55 synthetically generated data points, was constructed to ensure both experimental realism and statistical diversity. The Taguchi analysis using an L18 orthogonal array identified the optimal parameters as 80 W laser power, 250 mm/s scanning speed, and 60 kHz pulse frequency, corresponding to the highest signal-to-noise ratio and thermally balanced operation. The DNN model achieved strong predictive accuracy (R² ≈ 0.92–0.94), effectively capturing nonlinear parameter interactions without overfitting. The results demonstrate that while the Taguchi method efficiently identifies robust process windows with minimal experimentation, the DNN extends predictive capability across continuous, untested regions of the process space. Collectively, these findings establish a physics-informed, data-driven comparative framework for intelligent optimization of laser micromachining, with direct relevance to aerospace, biomedical, and precision micro-engineering applications.
Free
Beyond the grid, the Symbiosis of Virtual Power Plants and Communication Networks: A review
Scientific article
Virtual power plants (VPPs) are smart energy systems that aggregate geographically distributed energy resources (DERs), including renewable and non-renewable energy sources, energy storage devices, and controllable loads, into a single virtual plant. These plants are integrated into distribution networks to enhance grid stability and reliability. VPPs require a two-way communication framework to monitor and control all generation sources and loads, ensuring a balance between supply and demand while providing services to distribution or transmission network operators. In VPPs, various applications are used, each with specific communication quality requirements, such as reliability, latency, and bandwidth. Therefore, selecting communication technologies and protocols that meet these requirements and deliver optimal performance for each application is essential. This research paper presents a comprehensive review of the literature on VPPs, exploring their applications, communication requirements, and structural frameworks. It also examines the protocols and standards necessary to ensure reliability, security, and communication quality. Finally, the paper summarizes the global development and implementation of VPPs over the past two decades.
Free
Big Data in Cyber-Physical Systems, Digital Manufacturing and Industry 4.0
Scientific article
A cyber physical system (CPS) is a complex system that integrates computation, communication, and physical processes. Digital manufacturing is a method of using computers and related technologies to control an entire production process. Industry 4.0 can make manufacturing more efficient, flexible, and sustainable through communication and intelligence; therefore, it can increase the competitiveness. Key technologies such as the Internet of Things, cloud computing, machine-to-machine (M2M) communications, 3D printing, and Big Data have great impacts on Industry 4.0. Big Data analytics is very important for cyber-physical systems (CPSs), digital manufacturing, and Industry 4.0. This paper introduces technology progresses in CPS, digital manufacturing, and Industry 4.0. Some challenges and future research topics in these areas are also presented.
Free