Browse Items (5511 total)
Sort by:
-
An Intelligent Decision Support System to Aid Profit Planning in Manufacturing Companies
In order to assure accuracy in profit planning and decision-making, this study uses an intelligent decision support system to investigate an appropriate approach for calculating the "Break-Even" point in multi-product segments while taking into account the implications for contribution margin, demand, and capacity. The research's methodology and findings may be used to propose new projects, grow businesses, and make decisions in processes that focus on many products. Data are used to illustrate the advanced level of break-even analysis and application, and a description of the convenient and system-generated method of computation is given. A mathematical approach has been used based on actual data to show how to determine the break-even point without sacrificing the influencing aspects such as contribution margin, capacity, product mix, and demand for each. The researchers have created a good system application-oriented platform to make it simple to calculate the break-even point, which will be crucial for decision-making and profit planning even with more than 500 SKU (Stock Keeping Unit). This research evaluated the data and created formulas for actual data structure-based analysis. The study's conclusions have a significant influence on those companies that need to determine the true break-even threshold. The challenge area of concern might be the applicability of this activity for other sectors and other countries as this research was centred on the plastic bag industry in Malaysia. Future research can also analyse other important factors like start-up and semi-variable costs as they are not included in the current study. The identified break-even threshold can still be used effectively given the current market demand and the product's capacity. 2023, Ismail Saritas. All rights reserved. -
An Intelligent Hybrid GA-PI Feature Selection Technique for Network Intrusion Detection Systems
The development of Network Intrusion Detection Systems (NIDS) has become increasingly important due to the growing threat of cyber-attacks. However, with the vast amount of data generated in networks, handling big data in NIDS has become a major challenge. To address this challenge, this research paper proposes an intelligent hybrid GA-PI algorithm for feature selection and classification tasks in NIDS using support vector machines (SVM). The proposed approach is evaluated using two sub-datasets, Analysis and Normal, and Reconnaissance and Normal, which are generated from the publicly available UNSWNB-15 dataset. In this work, instead of considering all possible attacks, the focus is on two attacks, emphasizing the importance of the feature selection agent in determining the optimal features based on the attack type. The experimental results show that the proposed hybrid feature selection approach outperforms existing methodologies in terms of accuracy and execution time. Moreover, the selection of features can be subjective and dependent on the domain knowledge of the researcher. Additionally, the proposed approach requires computational resources for feature selection and classification tasks, which can be a limitation for resource-constrained systems. To be brief, this research paper presents a promising approach for feature selection and classification tasks in NIDS using an intelligent hybrid GA-PI algorithm. While there are some challenges and limitations, the proposed approach has the potential to contribute to the development of effective and efficient NIDS. 2023, Ismail Saritas. All rights reserved. -
An intelligent inventive system for personalised webpage recommendation based on ontology semantics
Owing to the information diversity in the web and its dynamically changing contents, extraction of relevant information from the web is a huge challenge. With the World Wide Web transforming into a more organised semantic web, the incorporation of semantic techniques to retrieve relevant information is highly necessary. In this paper, a dynamic ontology alignment technique for recommending relevant webpages is proposed. The strategy focuses on knowledge tree construction by computing the semantic similarity between the query terms as well as the ontological entities. Furthermore, the semantic similarity is again computed between nodes of the constructed knowledge tree and URLs in the URL repository to recommend relevant webpages. The dynamic ontology alignment by computing their respective semantic similarity constitutes Ontology Semantics. Personalisation is achieved by prioritisation of webpages by content-based analysis of the users web usage data. An overall accuracy of 87.73% is achieved by the proposed approach. Copyright 2019 Inderscience Enterprises Ltd. -
An intelligent web caching system for improving the performance of a web-based information retrieval system
With an increasing number of web users, the data traffic generated by these users generates tremendous network traffic which takes a long time to connect with the web server. The main reason is, the distance between the client making requests and the servers responding to those requests. The use of the CDN (content delivery network) is one of the strategies for minimizing latency. But, it incurs additional cost. Alternatively, web caching and preloading are the most viable approaches to this issue. It is therefore decided to introduce a novel web caching strategy called optimized popularity-aware modified least frequently used (PMLFU) policy for information retrieval based on users' past access history and their trends analysis. It helps to enhance the proxy-driven web caching system by analyzing user access requests and caching the most popular web pages driven on their preferences. Experimental results show that the proposed systems can significantly reduce the user delay in accessing the web page. The performance of the proposed system is measured using IRCACHE data sets in real time. Copyright 2020, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. -
An internet of health things-driven deep learning framework for detection and classification of skin cancer using transfer learning
As specified by World Health Organization, the occurrence of skin cancer has been growing over the past decades. At present, 2 to 3 million nonmelanoma skin cancers and 132 000 melanoma skin cancers arise worldwide annually. The detection and classification of skin cancer in early stage of development allow patients to have proper diagnosis and treatment. The goal of this article is to present a novel deep learning internet of health and things (IoHT) driven framework for skin lesion classification in skin images using the concept of transfer learning. In proposed framework, automatic features are extracted from images using different pretrained architectures like VGG19, Inception V3, ResNet50, and SqueezeNet, which are fed into fully connected layer of convolutional neural network for classification of skin benign and malignant cells using dense and max pooling operation. In addition, the proposed system is fully integrated with an IoHT framework and can be used remotely to assist medical specialists in the diagnosis and treatment of skin cancer. It has been observed that performance metric evaluation of proposed framework outperformed other pretrained architectures in term of precision, recall, and accuracy in detection and classification of skin cancer from skin lesion images. 2020 John Wiley & Sons, Ltd. -
An Introduction to ?Agile for HR Through? the Development of ?an Agile Operating ?Mindset
An understanding of Agile principles and a readiness mindset for human resources professionals play a crucial role in determining the application of Agile for HR in an organisational context. With the rise in extended and non-linear workforce configurations and geo-neutral team arrangements, Agile organisations necessitate that the nature of the HR function evolve from working through traditional architectural models and quickly adopting Agile models of functional excellence. The dearth of literature on understanding and implementing Agile practices in the HR function within enterprises requires a clear examination of the advantages of going Agile for HR. This essay explores the intuitive concept of Agile HR and operating schema, which can develop as a starting point in examining an understanding of how Agile practices in HR can evolve for sustainable enterprises and some challenges that are encountered. The Author(s) 2024. -
An Intrusion Detection Model Based on Hybridization of S-ROA in Deep Learning Model for MANET
A kind of wireless network called a mobile ad hoc network (MANET) can transfer data without the aid of any infrastructure. Due to its short battery life, limited bandwidth, reliance on intermediaries or other nodes, distributed architecture, and self-organisation, the MANET node is vulnerable to many security-related attacks. The Internet of Things (IoT), a more modern networking pattern that can be seen as a superset of the paradigms discussed above, has recently come into existence. It is extremely difficult to secure these networks due to their scattered design and the few resources they have. A key function of intrusion detection systems (IDS) is the identification of hostile actions that impair network performance. It is extremely important that an IDS be able to adapt to such difficulties. As a result, the research creates a deep learning-based feature extraction to increase the machine learning technique's classification accuracy. The suggested model uses outstanding network-constructed feature extraction (RNBFE), which pulls structures from a deep residual network's many convolutional layers. Additionally, RNBFE's numerous parameters cause a lot of configuration issues because they require manual parameter adjustment. Therefore, the integration of the Rider Optimization Algorithm (ROA) and the Spotted Hyena Optimizer (SHO) to frame the new algorithm, Spotted Hyena-based Rider Optimization (S-ROA), is used to adjust the RNBFEs settings. Attack classification is performed on the resulting feature vectors using fuzzy neural classifiers (FNC). The experimental analysis uses two datasets that are publicly accessible. The Author(s), under exclusive licence to Shiraz University 2024. -
An investigation and analysis on automatic speech recognition systems
A crucial part of a Speech Recognition System (SRS) is working on its most fundamental modules with the latest technology. While the fundamentals provide basic insights into the system, the recent technologies used on it would provide more ways of exploring and exploiting the fundamentals to upgrade the system itself. These upgrades end up in finding more specific ways to enhance the scope of SRS. Algorithms like the Hidden Markov Model (HMM), Artificial Neural Network (ANN), the hybrid versions of HMM and ANN, Recurrent Neural Networks (RNN), and many similar are used in accomplishing high performance in SRS systems. Considering the domain of application of SRS, the algorithm selection criteria play a critical role in enhancing the performance of SRS. The algorithm chosen for SRS should finally work in hand with the language model conformed to the natural language constraints. Each language model follows a variety of methods according to the application domain. Hybrid constraints are considered in the case of geography-specific dialects. 2024 by author(s). -
An Investigation into the Role of AI-Based Innovation in Supporting the Next Generation of Startup Entrepreneurs
The advent of Artificial Intelligence (AI) has revolutionized various industries, offering unprecedented opportunities for innovation and entrepreneurship. This investigation delves into the pivotal role of AI-based innovation in nurturing and empowering the next generation of startup entrepreneurs.AI technologies, including machine learning, natural language processing, and computer vision, have significantly augmented the capabilities of startups across diverse sectors. This study aims to elucidate the multifaceted ways in which AI fosters entrepreneurial endeavors, from ideation to market penetration.AI algorithms enable startups to analyze vast datasets swiftly, extracting valuable insights that inform strategic decision-making and product development. Through predictive analytics and trend forecasting, entrepreneurs can anticipate market demands, optimize resource allocation, and mitigate risks, thereby enhancing the viability and competitiveness of their ventures.AI facilitates personalized customer experiences, driving customer engagement and retention for startups. By leveraging AI algorithms to analyze user behavior and preferences, entrepreneurs can deliver tailored products, services, and marketing campaigns, fostering brand loyalty and customer satisfaction.The integration of AI into startup ecosystems also presents various challenges, including ethical considerations, data privacy concerns, and regulatory complexities. Therefore, this investigation also explores the ethical implications and regulatory frameworks surrounding AI-based entrepreneurship, advocating for responsible innovation practices and stakeholder collaboration. 2024, Collegium Basilea. All rights reserved. -
An Investigation of Complex Interactions Between Genetically Determined Protein Expression and the Metabolic Phenotype of Human Islet Cells Using Deep Learning
The relationship between gene modules and several genome-scale metrics was examined, including heterozygosity that caused type 2 diabetes due to insulin deuteration, differential expression, genotyping association, methylation, and copy number changes. This work investigates the complex relationships between protein expression, genetic polymorphisms, and metabolic properties of human islet cells using expression quantitative trait loci (eQTL) detection. We looked at the genomic, transcriptomic, and proteomic information from islet cells in persons with type 2 diabetes. From the information from different levels, we noticed novel eQTLs that regulate crucial metabolic and signaling pathways in islet cells. Our study highlights the importance of a systems-level approach in understanding the complicated biological processes by highlighting the complexity of the link between genetic variants, protein expression, and metabolic abnormalities using the PIMA Indian dataset. Our findings provide novel insights into the molecular mechanisms behind islet cell failure in type 2 diabetes, potential targets for emerging treatment strategies, and the genomic implications of variations in gene expression, mutations, and other factors. To accomplish this purpose, we proposed a novel BLB model and obtained 99.89%. 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. -
An investigation of the business level strategies in Zimbabwe food manufacturing sector (2006 -2013) /
International Journal Of Science And Research, Vol.3, Issue 6, pp.1052-1063, ISSN No: 2319-7064. -
An Investigation of the Effects of Chronic Stress on Attention in Parents of Children with Neurodevelopmental Disorders
Prolonged exposure to stress can cause impairments in various brain functions including cognition. Attention is one such important cognitive function that is required for our daily life and work-related activities. Chronic stress can have an impact on attention networks such as alerting, executive control, and orienting. The effects of naturalistic, persistent psychosocial stress on several attention networks were explored in this study. Parents of children with neurodevelopmental disorders (NDD) and parents of children with typical development (TD) were given an attention network test (ANT). Overall the stressed group (M= 564.623, SD= 75.484) was found to have a quicker reaction time in all the target and cue conditions whencompared to the non-stressed group (M= 588.874, SD= 101.575). Both groups had similar accuracy in all the conditions. When comparing the three attention network scores, no significantdifference was found in either group. However, in the stressed group, there was a significant beneficial relationship between the alerting and orienting networks (p=.006) and a high negative correlation between the alerting and executive control networks (p=.028). No significant correlation was found between the attention networks in the non-stressed group. Copyright2024 by authors, all rights reserved. -
An investigation on structural and optical properties of reduced graphene oxide-tin oxide nanocomposite
Graphene-metal oxide composites have attracted tremendous research interest in recent days due to their unique and fascinating properties. In the present study, rGO and SnO2 were synthesized separately by modified Hummers' method and nitrate-citrate gel combustion technique respectively. One step hydrothermal method was used to prepare reduced graphene oxide-tin oxide nanocomposite of various concentrations of rGO and SnO2.The obtained samples were characterized by XRD, FTIR, Raman Spectroscopy, UV-Vis spectroscopy, SEM and TEM. The results of different characterization techniques showed the successful formation of SnO2, rGO and SnO2-rGO composites. X-ray analysis pattern indicates formation of the SnO2 nanoparticles in the graphene matrix. The size of the particles prepared is in nanoscale and was found to be 10-20 nm range. TEM images reveal the incorporation of crystalline SnO2 nanoparticles in graphene layers. Upon incorporation of tin oxide to graphene matrix, one could easily tailor the energy gap of the composite matrix. 2020 World Research Association. All rights reserved. -
An investigation on structural, electrical and optical properties of GO/ZnO nanocomposite
Coupling of graphene oxide with metal oxide is an effective way to enhance the opto-electric properties of the composite. Herein, a hybrid structure of graphene oxide (GO) -Zinc oxide (ZnO) nanostructure was successfully designed and fabricated with varying concentrations of ZnO. The GO and ZnO nanoparticles were synthesized through Hummer's and simple precipitation method respectively. Structural and physiochemical properties were examined via X-ray powder diffraction, FTIR and UV-Vis spectroscopy. The XRD results of GO showed a peak at 2? of 12.02 with particles of size 6nm and inter layer spacing 0.87 nm. The XRD patterns of ZnO nanoparticles showed a hexagonal unit cell structure and the average dimension of the sample was calculated to be 15 nm. The band gap of the synthesized GO is found to be 5.1 eV and that of ZnO to be 3.07 eV with the help Tauc plot. The dependence of various concentration of ZnO on the electrical behaviour is discussed by an impedance analyzer in the frequency range 100Hz to 1MHz. The ZnO/GO composite with best results have been obtained for 20% and 60 % ratios of ZnO. The composite has high dielectric permittivity and low loss tangent values and is identified as a promising candidate for energy storage applications. 2019 The Authors. -
An IoT-based agriculture maintenance using pervasive computing with machine learning technique
Purpose: In cultivation, early harvest offers farmers an opportunity to increase production while decreasing the chances of lower crop production rates, ensuring that the economy remains balanced. The significant reason is to predict the disease in plants and distinguish the type of syndrome with the help of segmentation and random forest optimization classification. In this investigation, the accurate prior phase of crop imagery has been collected from different datasets like cropscience, yesmodes and nelsonwisc. In the current study, the real-time earlier state of crop images has been gathered from numerous data sources similar to crop_science, yes_modes, nelson_wisc dataset. Design/methodology/approach: In this research work, random forest machine learning-based persuasive plants healthcare computing is provided. If proper ecological care is not applied to early harvesting, it can cause diseases in plants, decrease the cropping rate and less production. Until now different methods have been developed for crop analysis at an earlier stage, but it is necessary to implement methods to advanced techniques. So, the detection of plant diseases with the help of threshold segmentation and random forest classification has been involved in this investigation. This implemented design is verified on Python 3.7.8 software for simulation analysis. Findings: In this work, different methods are developed for crops at an earlier stage, but more methods are needed to implement methods with prior stage crop harvesting. Because of this, a disease-finding system has been implemented. The methodologies like Threshold segmentation and RFO classifier lends 97.8% identification precision with 99.3% real optimistic rate, and 59.823 peak signal-to-noise (PSNR), 0.99894 structure similarity index (SSIM), 0.00812 machine squared error (MSE) values are attained. Originality/value: The implemented machine learning design is outperformance methodology, and they are proving good application detection rate. 2021, Emerald Publishing Limited. -
AN IOT-BASED COMPUTATIONAL INTELLIGENCE MODEL TO PERFORM GENE ANALYTICS IN PATERNITY TESTING AND COMPARISON FOR HEALTH 4.0
Parental comparison and parenthood testing are essential in various legal and medical scenarios. The accuracy and reliability of these tests heavily rely on the gene analysis algorithms used. However, analyzing the quality of succession data are quite challenging due to the presence of detrimental characteristics. To address this issue, we propose using machine learning-based algorithms such as clustering (Correlation-based) and Classification (Modified Naive Bayesian) to separate these characteristics from the parent-child gene array. This progression helps to identify, validate, and select tools, techniques for scrutinizing indecent sequences, leading to accurate and reliable results. In this paper, we present an IoT-based intelligence tool for parental comparison that uses a secure gene analysis algorithm. The model employs multiple sensors and devices to collect genetic data, which is then securely processed and analyzed using contemporary algorithms. The suggested model uses advanced techniques such as encryption and decryption to ensure the privacy and confidentiality of the genetic information. Our experimental consequences reveal that the proposed model is reliable, secure, and provides accurate results. The model has the potential to be used in various legal and medical contexts where the security and reliability of genetic data are critical. 2023 Little Lion Scientific. -
An IoT-based tracking application to monitor goods carrying vehicle for public distribution system in India
Designing a secured transportation system to handover food items to various fair price shops is one of the objectives of smart city development in India. In this paper, an IoT-based tracking solution for moving goods carrying vehicle is proposed. A hardware prototype model is developed using different sensors with GPS/GPRS tracking module and is attached to the vehicle. An alarm is raised to make decision in case of trouble or malfunction. The data generated by the model during the movement of vehicle is encrypted using RSA algorithm and sent to cloud for monitoring by an application developed using PHP and analysis using MapReduce programming model. Experiments are conducted to study the feasibility of the developed model during deployment. From the experiment it is observed that, the developed hardware model and the application meet the objective of monitoring vehicle, safer recovery in case of malfunction and secured delivery of items. Copyright 2021 Inderscience Enterprises Ltd. -
An Objective Evaluation of Harris Corner and FAST Feature Extraction Techniques for 3D Reconstruction of Face in Forensic Investigation
3d reconstructed face images are the volumetric data from two dimensions, it can provide geometric information, which is very helpful for different application like facial recognition, forensic analysis, animation. Reconstructed face images can provide better visualization, than a two dimensional image can provide. For a proper 3d reconstruction one of primary step is feature extraction. The objective of this study is to conduct a comprehensive evaluation of two prominent traditional feature extraction techniques, namely Harris Corner and FAST (Features from Accelerated Segment Test), for the purpose of 3D reconstruction of face images in forensic analysis. In this research paper feature extraction was carried out using the Harris corner detection and FAST Feature technique. 3D reconstruction is completed using the retrieved features. In this study a comparative analysis was conducted assessing the aspect ratio, depth resolution. The results of the assessment provide valuable insights into the strengths and limitations of both techniques, aiding researchers and practitioners in selecting the most suitable method for 3D face image reconstruction applications. 2023, Ismail Saritas. All rights reserved. -
An objective function based technique for devignetting fundus imagery using MST
Fundus photography is a powerful imaging modality that is utilized for detecting macular degeneration, retinal neoplasms, choroid disturbances, glaucoma and diabetic retinopathy. As the illumination source in fundus imaging is situated at the center of the fundus camera, the illumination at the peripheral regions of the images would be relatively less than the center, which is termed vignetting. Vignetting adversely affects the performance of computerized methods for analyzing fundus imagery. A devignetting method for fundus imagery based on the Modified Sigmoid Transform (MST) is proposed in this paper. Gain (A) and centering parameter (?) of MST have a crucial influence on its performance. For low values of the gain, local contrast is penalized, and the overall dynamic range is compressed. When the value of gain is very high, the images after the illumination correction will have a washed out appearance. The optimum value of gain is determined in this paper from an objective method based on two statistical indices, Average Gradient of Illumination Component (AGIC) and Error of Enhancement (EME). MST with gain value defined via objective methods is able to correct the uneven illumination in fundus images without penalizing the local contrast. The proposed method is compared with illumination equalization model, homomorphic filtering and Adaptive Gamma Correction (AGC) and was found to be superior in terms of naturality uniformity of background illumination, and computational speed. 2018 -
AN OPTIMIZATION AND PREDICTIVE MODELING TO ENHANCE THE WEAR AND MECHANICAL PERFORMANCE OF Al 5054 ALLOY FOR DEFENSE APPLICATIONS WITH TiO2 NANOPARTICLES
This study examines the effects of 2%, 4%, and 6% additions of TiO2 nanoparticles on the wear and mechanical characteristics of Al 5054 alloy reinforcement. The results demonstrate that the addition of TiO2 nanoparticles considerably increases the alloys tensile and impact strengths. Tensile strength reaches a peak of 221 MPa at 6% reinforcement and it rises gradually as the percentage of TiO2 reinforcement increases. Similarly, impact strength rises with time and, with TiO2 reinforcement, it reaches a maximum of 63 Joules at 6%. Wear analysis using Taguchi-based design determines the optimal combination of composition, disc rotation speed, load, and sliding distance to minimize a given wear rate and friction force. The SEM analysis validates that the composites exhibit enhanced wear resistance due to the uniform distribution of TiO2 nanoparticles. An Artificial Neural Network (ANN) model is also developed to predict the responses, and it achieves an overall accuracy of 83.549%. The mechanical properties and wear resistance of TiO2-reinforced Al 5054 composites can be enhanced, as it is demonstrated by these results. This information is crucial for material design and optimization across a range of engineering applications. 2024, Scibulcom Ltd.. All rights reserved.