- All articles 732
-
International Journal of Information Engineering and Electronic Business @ijieeb
Journal articles - International Journal of Information Engineering and Electronic Business
All articles: 732
IoT-Enabled Estrus Detection in Dairy Cattle Using Machine Learning Technique
Scientific article
In the dairy industry, optimizing reproductive management is crucial for sustainable operations and enhancing animal welfare. The traditional manual detection methods usually miss many of the estrus incidences and hence have resulted in a 20-30% decline in conception rates and further massive economic losses.This paper presents an advanced framework integrating machine learning and Internet of Things (IoT) technologies to improve estruses detection in dairy cattle, thereby supporting efficient herd management and productivity. The proposed solution leverages a stacking model of Random Forest and Gradient Boosting Machine (GBM) algorithms to accurately identify estruses events, providing a reliable method for reproductive monitoring. The experimental evaluation yields accuracies of 92.1 % using RF, 92.3 % using GBM, and an improved 93.19 % when the stacking model is applied, along with improvements in precision of 94 and an F1-score of 94 %, reflecting its strength in complex behavioral pattern recognition. Rigorous evaluation across key performance metrics confirms the model’s high accuracy, underscoring its suitability for practical deployment. The system employs IoT-enabled smart collars equipped with temperature sensors, accelerometers, GPS, and RFID to gather real-time data on cattle health and reproductive status. By analyzing this data, the system delivers precise and timely insights into estruses cycles, enabling targeted breeding interventions and enhanced reproductive management. Data collected through the smart collars is securely stored in Google Firebase, facilitating efficient data archiving and rapid access via a user-friendly web application. The proposed integration of IoT, machine learning, and cloud computing presents a holistic, scalable, and economically viable solution for enhancing reproductive efficiency, animal welfare, and sustainable dairy management.
Free
Scientific article
Precision agriculture transform the agricultural sector by integrating advanced technologies to enhance productivity and sustainability. In crop farming, precision agriculture can significantly improve practices through precise monitoring and data-driven decision-making, addressing challenges such as optimizing resource usage and improving crop health. This study presents the development and implementation of an IoT-based Crop Recommendation System designed to optimize farming practices through a mobile application. This system uses different sensors to continuously extract data regarding the temperature, pH, NPK value and other relevant parameters. These parameters can be analyzed in real-time to help farmers make informed decisions on irrigation, fertilization, and crop selection, tailored to specific field conditions. This information is stored to create individual datasets, offering researchers valuable insights into optimal conditions for various crops. This can improve yield and promote sustainable farming practices. In this study, we evaluated a series of machine learning algorithms for their ability to predict an optimal crop based on environmental parameters. Among these algorithms, Naive Bayes demonstrated superior performance, achieving an accuracy of 99.55%, precision of 99.58%, recall of 99.55%, and F1-score of 99.54%. These findings highlight the effectiveness of our approach in integrating machine learning with the IoT for precise crop management. Implemented through a user-friendly mobile application, the proposed system enhances accessibility and usability for farmers.
Free
Irregular Function Estimation with LR-MKR
Scientific article
Estimating the irregular function with multi-scale structure is a hard problem. The results achieved by the traditional kernel learning are often unsatisfactory, since underfitting and overfitting cannot be simultaneously avoided, and the performance relative to boundary is often unsatisfactory. In this paper, we investigate the data-based local reweighted regression model under kernel trick and propose an iterative method to solve the kernel regression problem, local reweighted multiple kernel regression (LR-MKR). The new framework of kernel learning approach includes two parts. First, an improved Nadaraya-Watson estimator based on blockwised approach is constructed to organize a data-driven localized reweighted criteria; Second, an iterative kernel learning method is introduced in a series decreased active set. Experiments on simulated and real data sets demonstrate the proposed method can avoid under fitting and over fitting simultaneously and improve the performance relative to the boundary effetely.
Free
Isochronous and Anisochronous Modulation Schemes in Wireless Optical Communication Systems
Scientific article
The choice of the modulation format is one of the principle factors in realizing a high performance wireless optical communication system at a reasonable cost and acceptable complexity. The purpose of this paper is to make a comparison between isochronous and anisochronous modulation scheme categories from Discrete (digital) pulse time modulations (PTM) through the simplest scheme in each family; PPM and DPIM respectively, in term of bandwidth requirement, power efficiency and transmission capacity. This is done to give a wider view on the performance of such schemas under wide range of design parameters. In this paper, the properties of PPM and DPIM have been analyzed, from this analysis it has been shown that DPIM or anisochronous modulation schemes in general are strong candidates when synchronization and transmission capacity are taken into account, and when it comes to power performance PPM or isochronous modulations are better.
Free
Iterative Shrinkage Operator for Direction of Arrival Estimation
Scientific article
In this correspondence we present the application of iterative shrinkage (IS) operator to the DOA estimation task. In particular we focus our attention to Stage wise Orthogonal Matching Pursuit (StOMP) algorithm. We compare StOMP against MUSIC, which is state of the art in DOA estimation. StOMP belongs to compressive sensing regime where as MUSIC is parametric technique based upon sub-space processing. To best of our knowledge IS operators have not been analyzed for DOA estimation. The comparison is performed using extensive numerical simulations.
Free
Scientific article
The growing need for accessible websites cannot be overemphasized as it has posed a major challenge in the world of Information and Communication Technology (ICT). Most businesses have gone online in order to improve their market value; the banking sector is not an exception. In an attempt to satisfying customers, websites developers have violated most of the websites standards. The banking sector is one area that carries out most of its activities online. Therefore, it is important that their websites be accessible to all especially people with visually impaired disability and more so, regardless of the browsing technology being used. This study evaluates the accessibility and usability of Nigeria banking websites using some automated tools and manual inspection method. This is done in order to know the conformance of the banking websites with standard as specified by Web Accessibility Initiate (WAI). Results from the study indicate that some of the websites do not conform to the expected standard. Hence, there is need for substantial improvements on most bank websites in Nigeria
Free
Knowledge Template Based Multi-perspective Car Recognition Algorithm
Scientific article
In order to solve the problem due to the vehicle-oriented society such as traffic jam or traffic accident, intelligent transportation system(ITS) is raised and become scientist’s research focus, with the purpose of giving people better and safer driving condition and assistance. The core of intelligent transport system is the vehicle recognition and detection, and it’s the prerequisites for other related problems. Many existing vehicle recognition algorithms are aiming at one specific direction perspective, mostly front/back and side view. To make the algorithm more robust, our paper raised a vehicle recognition algorithm for oblique vehicles while also do research on front/back and side ones. The algorithm is designed based on the common knowledge of the car, such as shape, structure and so on. The experimental results of many car images show that our method has fine accuracy in car recognition.
Free
Knowledge Transfer and Innovation through University - Industry Collaboration
Scientific article
University–industry collaboration (UIC) has become an essential mechanism for fostering innovation and transferring knowledge across institutional boundaries. It is a powerful driver for innovation and sustainable economic development. This study investigates the role of UIC in facilitating knowledge transfer and its impact on innovation outcomes within industries. The study also identifies barriers such as organizational misalignment, lack of trust, and limited funding. A conceptual model is proposed to demonstrate the dynamics of UIC. Recommendations include policy reforms, structured collaboration frameworks, and enhanced R&D investments. Drawing from both qualitative and quantitative methods, the study investigates the nature of UIC, the influencing factors, and its outcomes in terms of innovation capabilities. The findings underscore the importance of trust, absorptive capacity, and aligned goals in enhancing knowledge transfer. The study also identifies critical enablers and barriers, offering strategic insights for optimizing collaborative frameworks.
Free
LDASpike for Recognizing Epileptic Spikes in EEG
Scientific article
Manual processing of recorded EEG data for characteristics like epileptic spikes is very time consuming since the recording of EEG for a longer duration producing enormous amount of data. Therefore, automated systems are required to speed up the processing. In the current work, a classification method has been proposed for detecting the epileptic spikes in the recorded EEG data by using Linear Discriminant Analysis (LDA) and has been named LDASpike. The prerecorded EEG data files were used as input to LDASpike and the output produced was the total number of spikes present in each EEG file. The proposed method results on an average sensitivity 100% and selectivity 95.38%, when the training and testing data were same. However, with four fold cross-validation applied in this work, the sensitivity and selectivity were achieved as 98.45% and 96.06%, respectively, on an average. Though a little time initially is spent to train the system but the result produced by the system is very promising and can be compared with the existing standard methods. This system can also works with the real time recording and processing for a clinical setup.
Free
Lessons Towards Developing An Integrated Tool-support for Small Team Meetings
Scientific article
Teams within organisations meet regularly to review their progress and engage in collaborative activities within a team setting. However, the uptake of tools to support their activities within team meetings is limited. Research efforts on understanding the reasons for low rates of tool adoption and learning lessons in developing tools that could be readily adopted by team members within team meetings are largely unexplored. This qualitative study focuses on learning lessons towards developing an integrated tool-support for small team meetings within organisations using focus groups. Discussions were based on a tool-kit framework generated by observing their team meetings in an earlier study. The discussions were recorded and the transcripts were analysed using grounded theory approach to generate stories on team processes and potential tools that could assist team members during each process. The lessons derived from the study were based on three aspects of tool-support namely the potential users of the proposed tool-kit, processes within the team meetings that would be influenced by the introduction of the tool-kit and the technological aspects of the tool-kit.
Free
Lightweight Cryptographic Protocol for Resource-Constrained IoT Devices in Smart Healthcare
Scientific article
IoT healthcare devices often lack resources, and encrypting patient data flows securely is an active area of research. Current cryptographic solutions are typically too computationally and energy intensive to be used on constrained IoT devices. In this work we introduce HealthCrypt: an authenticated encryption scheme for smart IoT deployments in healthcare on highly-constrained microcontrollers. It consists of a novel compact SP-network paired with native authenticated encryption, removing the need to have a separate MAC pass and minimizing total cycle cost. We implement HealthCrypt on an ARM Cortex-M0 running at 48 MHz with the FELICS benchmark suite. Results show HealthCrypt uses only 90 bytes of RAM, only requires 1,620 gate equivalents (under the proposed IoT limit of 2,000 GE) of hardware area, and only uses 5.93 nJ of energy per block encryption. Measurements of its statistical security show it has an almost perfect avalanche of 0.5026, Shannon entropy only 0.0094 bits/byte away from the ideal, and good key sensitivity of 0.4949. Against competitors like PRESENT-80, SPECK-64/128, and SIMON-64/128, HealthCrypt has been rated to have the best overall IoT Healthcare Suitability Score of 79.23.
Free
Linear antenna array pattern synthesis using elephant swarm water search algorithm
Scientific article
Linear antenna array pattern synthesis using computational method is an important task for the electronics engineers and researchers. Suitable optimization techniques are required for solving this kind of problem. In this work, Elephant Swarm Water Search Algorithm (ESWSA) has been used for efficient and accurate designing of linear antenna arrays that generate desired far field radiation pattern by optimizing amplitude, phase and distance of the antenna elements. ESWSA is inspired by water resource search procedure of elephants during drought. Two different fitness functions for two different benchmark problem of linear antenna array have been tested for validation of the proposed methodology. During optimization, three types of synthesis have been used namely: amplitude only, phase only and position only control for all cases antenna array. The results show that ESWSA is very efficient process for achieving desired radiation pattern while amplitude only control performed better compare to the others two controlling process for all benchmark problems.
Free
M-Commerce in Bangladesh –Status, Potential and Constraints
Scientific article
Mobile Commerce often referred to as "M-Commerce" or "mCommerce" is a new dimension or extension of e-Commerce that is performed by mobile devices and Personal Digital Assistants (PDA) using mobile phone networks. As the number of mobile users is increasing dramatically the prospect of m-commerce is also increasing day by day in developing countries like Bangladesh. Though there are a lot of researchers has written about the prospect and adoption of M-commerce but in my research, I tried to find out the statistical analysis of mobile users, mobile internet users; M-commerce current status in Bangladesh. Research also has been done for a number of visitors of stakeholder's site, using the ranking tools, uses of mobile apps by customers and limitation of mobile commerce adoption in Bangladesh those were not discussed earlier. Here, I collected data through web and phone call from various stakeholders, in the top line m-commerce business, studied and identified the problem, shown the current status and major barriers of M-commerce and suggested a methodological framework.
Free
Machine Learning and Software Quality Prediction: As an Expert System
Scientific article
To improve the software quality the number of errors from the software must be removed. The research paper presents a study towards machine learning and software quality prediction as an expert system. The purpose of this paper is to apply the machine learning approaches, such as case-based reasoning, to predict software quality. The main objective of this research is to minimize software costs. Predict the error in software module correctly and use the results in future estimation. The novel idea behind this system is that Knowledge base (KBS) building is an important task in CBR and the knowledge base can be built based on world new problems along with world new solutions. Second, reducing the maintenance cost by removing the duplicate record set from the KBS. Third, error prediction with the help of similarity functions. In this research four similarity functions have been used and these are Euclidean, Manhattan, Canberra, and Exponential. We feel that case-based models are particularly useful when it is difficult to define actual rules about a problem domain. For this purpose we have developed a case-based reasoning model and have validated it upon student data. It was observed that, Euclidean and Exponential both are good for error calculation in comparison to Manhattan and Canberra after performing five experiments. In order to obtain a result we have used indigenous tool. For finding the mean and standard deviation, SPSS version 16 and for generating graphs MATLAB 7.10.0 version have been used as an analyzing tool.
Free
Machine learning based business forecasting
Scientific article
The business sectors directly contribute to the growth of any nation. Moreover, the business is an activity of producing, buying, and selling the goods and services to generate the money. The business directly involves in the gross domestic product (GDP). The business forecasting is the activity of predicting or estimating the feature position of the sales, expenditures, and profits of any business. However, the business forecasting helps to the business sectors for planning, decision making, resource utilization, business success, etc. Therefore, business forecasting is a pressing need for the growth of any business. In recent past, many researches attempt to carry out the business forecasting using different tools. However, this paper presents the business forecasting for sales data using machine learning technique and the obtained results are presented and discussed..
Free
Scientific article
Malware classification has already been a prominent concern for decades, and malware attacks have proliferated at an astounding rate, constituting a significant threat to cyberspace. Deep learning (DL) and malware image approaches are becoming more prevalent in the field of malware analysis, with spectacular results. This work focuses on the challenge of classifying malware variants that are represented as images. This study employs visualization and proposes a convolutional neural network (CNN) based DL model to effectively and accurately classify malware. The proposed model is trained and tested on a very challenging and heterogeneous dataset, and it achieves accuracy of 98.179%, precision of 97.39%, a F1-score of 97.70%, and a fast classification speed (3 seconds needed to test 934 unseen malware). This demonstrates the proposed model's incredibly quick, effective and accurate performance. The proposed model outperformed existing traditional DL models in terms of various performance measures and demonstrated its usefulness in classifying malware families through visualization. This study and experimental results reveal that small-scale malware images and a simple CNN architecture alone are capable of accurately classifying malware families with high classification accuracy.
Free
Scientific article
The study observes the metadata identification and analysis for Document, Audio, Image, and Videos. The process uses MapReduce and Match Aggregate Pipeline to identify, classify, and categories for identification purposes. The inputs are FITS array results and processed in form of XML. The works consist of the extraction process, identification and analysis, classification, and metadata information. The objective is establishing the file information based on volume, variety, veracity, and velocity criteria as part of task identification component in Self-Assignment Data Management. Testing is done for all file types with the number of files and the size of the file according to the grouping. The results show that there is a pattern where the match-aggregate-pipeline has a longer processing time than MapReduce on a small block size, shown in a block size of 64 Mb, 128 Mb, and 256 Mb. But once the block size is magnified the match-aggregate-pipeline has faster processing time at 1024 Mb and 2048 Mb. The results have a contribution in the metadata processing for large files can be done by arranging the block sizes in Match Aggregate Pipeline.
Free
Map-Reduce based Multiple Sub-Graph Enumeration Using Dominating-Set Graph Partition
Scientific article
The purpose of this paper is to find all the instances of a given set of pattern graphs (sub-graphs) in a large data graph using a single round of Map-Reduce. For the simplest pattern graphs like a triangle and rectangle we propose the solution. This paper enumerates complex pattern graphs using the enumeration of simple pattern graphs. We proposed Dominating set based graph partition, it generates non-overlapped sub-graphs. Each sub-graph is processed by one machine in the cluster. We analyze both the communication cost and the total computational cost. Communication cost is reduced by using Map-Reduce based dominating set graph partition. At the same time Multiple pattern (sub-graphs) graphs can be enumerated with the same communication cost. The proposed method is not always superior to the conventional sub-graph enumeration, but in some cases involving large-scale data where this method wins, including (1) Adjacency list representation of the graph is the input (2) Number of partitions are decided based on the graph size. We experimentally show that our approach decreases significantly the computation cost, communication cost and scales the enumeration process with a large graph database.
Free
Mathematical Model of Strategic Diagnostics of Enterprise in the Circular Economy Adaptation Process
Scientific article
The article considers the development of strategic diagnostics of an enterprise in the condition of adaptation to a circular economy. In the context of global economic and environmental changes, strategic diagnostics is an important tool for assessing the effectiveness of the implemented changes and adapting to new challenges. The authors emphasize the importance of implementing the principles of a circular economy, which involve minimizing waste and reusing resources. It is obvious that in the process of adapting an enterprise to the conditions of a circular economy, strategic diagnostics plays an important role, which allows assessing the enterprise readiness to transition to a new economic model, determining its competitive advantages and developing effective development strategies. A set of strategic diagnostics tools with their adaptation to the conditions of a circular economy is systematized. It is substantiated that the proposed tools allow enterprises to effectively adapt to the conditions of a circular economy, reduce environmental impact, increase competitiveness, and find new opportunities for sustainable economic development. An algorithm for using strategic diagnostics of the enterprise in the context of adaptation to circular economy is developed. The presented algorithm allows enterprises to effectively adapt to the conditions of the circular economy, increase competitiveness, and ensure long-term business sustainability.
Free
Scientific article
In this article, practical issues are considered at the complex level, in the field of realizing mathematical modelling of the assessment of the potential of the Ukrainian IT industry in the conditions of global challenges. The purpose of the study is to analyze modern approaches to evaluating this potential using advanced mathematical methods, such as multifactorial regression, cluster analysis and factor analysis. The work describes in detail the methods that allow you to evaluate the relationships between the main economic, technological and social indicators that influence the globalized development of the modern IT sector in Ukraine. The study emphasizes the strategic importance of assessing the capabilities of the IT sector to solve modern economic and technological tasks. Within mathematical modeling in the work, an improved model of evaluation of the above potential is proposed in which the combination of considered methods with the combination of the principles of Bayesian data analysis is combined. This approach allows you to more accurately take into account the uncertainty and variability inherent in modern economic and technological conditions. Usage of the Bayesian approach makes it possible to get a more flexible and adaptive model that better reflects dynamic processes that affect the development of IT industry in Ukraine in global challenges. The analysis begins with multifactorial regression, which examines the relationship between economic, technological and infrastructure factors that influence the development of the IT sector. The next stage is a cluster analysis that allows you to distinguish regional IT-hubs, comparing their effectiveness and revealing differences in Ukraine. With the help of factor analysis, we reveal the hidden variables that have a significant impact on the development of the industry. We also compare the results of each of the models to identify common trends and differences, which allows not only to identify opportunities for development, but also to indicate problems that need attention. Based on the results obtained, we offer specific recommendations for improving the competitiveness and stability of the Ukrainian IT industry. Our conclusions emphasize the importance of using innovative approaches to achieve more efficient development of this field.
Free
