Fusion: Practice and Applications

This paper suggests a novel fusion approach of combining Analytic Hierarchy Process (AHP) and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to enhance multi-criteria decision-making for energy management. In this way, by integrating the two powerful methodologies, the fusion approach is enabled that allows for dealing with the complex and highly dynamic character of energy management decisions for which there is required the careful consideration of many conflicting criteria. The method uses A to derive weightings for each decision criterion via AHP based on expert judgments, ensuring all relevant factors are systematically considered proportionately. Subsequently, TOPSIS is applied to evaluate and rank the alternatives such that the most effective energy solutions close to the ideal solution are identified. This integration of AHP with TOPSIS leads to comprehensive analysis that draws both the strengths of these techniques and provides a powerful tool to make informed and balanced decisions in the energy sector. The effectiveness of this fusion method, when applied, could then lead to the attainment of subtler findings and dependable suggestions, making it a beneficial contribution to this field of energy management.

For Internet of Things (IoT)-based on healthcare systems to autonomously monitor patients, radio frequency identification, or RFID, its essential. It is difficult to guarantee complete coverage throughout sizable healthcare facilities with a small number of RFID readers, though Software for RFID network planning must be optimized. The purpose of this paper is about optimizing related software and suggest a topological RFID network planning strategy that will minimize reader interference while deploying the fewest possible readers. The best location for RFID tags on patients as well as readers depends on the layout of the institution and how the patients move. To dependably scan tags across a variety of locations, RFID network design software precisely calculates the number and positions of readers using algorithms. Software features and network planning goals are developed to efficiently track patient status by automating the gathering of medical data. in this paper to find the optimal number of RFID readers required and their location in the system. After the algorithm was tested, it was found that the algorithm can determine the true effectiveness of the coverage and reduce the area of interference between the areas of coverage of RFID readers. PSO is a superior algorithm for solving difficult problems (NP). The PSO algorithm has shown a high efficiency in finding the optimal solution, with some of weakness in the performance of the algorithm, represented in finding functional boundaries that serve the research problem. By providing constant access to health information, this plan raises the standard of care.

The IoT can be defined as a system of various types of computing and digital devices, machines, objects, animals, and humans that are connected through networks to send data without the need for direct person-to-person or computer-to-person interfaces. Every component in this structure is given a unique identity. While under the domain of IoT, WSN serves as a wireless sensor network that does not have an established infrastructure but consists of many wireless sensors for surveillance over systems, the environment, and the physical world. Because of its versatile usage like surveillance and environmental monitoring, Wireless Sensor Networks (WSNs) are vital in many applications. The performance of these networks is largely dependent on how sensor nodes are distributed across the area to provide good coverage and connectivity. In this paper, we propose a new method for node placement optimization in WSNs, which tries to solve the problem of coverage holes at the stage of initial deployment. Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) are implemented using MATLAB to deal with the problem's complex and non-linear nature. These algorithms help find optimal node positions, thus improving coverage while ensuring no coverage gaps occur. A way to achieve this is through iterations, which involve fitness evaluation, selection of promising solutions, and genetic operators like crossover and mutation or position updates for PSO to investigate and improve the final solution. The simulation results mentioned in this paper demonstrate the usefulness of those methods, displaying major increases in coverage and the removal of all gaps that could appear in the initial deployment. This research contributes to the field of wireless sensor network optimization, specifically addressing coverage issues using GA and PSO algorithms …

Mango is one of the important commercial crop in the world. It provides nutritional and financial support to human life. Different diseases of leaves impact the health of the mango crops. The early and proper pest control measurement can prevent large output losses. We propose an automated inspection and classification of disease-affected mango leaves that uses Deep Learning (DL) model. Our DL model-empowered Convolutional Neural Network (CNN) architecture is trained with an extensive image dataset of mango leaves portraying a variety of disease indications at both low and high-resolution images. The objective is to be able to identify accurately the disease type on mango leaves including Bacterial Canker, Powdery mildew, Anthracnose, Gall midge, and Sooty mould. Crops can develop gradual immunity with reasonable pest control and can purposively shaped them against constantly evolving environment. The proposed system will be effective and it will definitely prove a facile system to be used as a key component of a novel precision agriculture system as will be presented in our future work. The performance of the proposed system is augmented through the utilization of transfer learning techniques and pre-trained models, including VGG-16, MobileNet, Googlenet, YoloV8, and EfficientNet. These Deep Learning models not only offer an accurate and efficient approach for classifying diseases in mango leaves but also provide valuable insights into the severity of the identified diseases. Utilizing this information to support farmers and agricultural professionals in making informed decisions pertaining to disease management and treatment strategies can significantly contribute to the sustainable growth of mango crops. The development and implementation of such automated technologies have the potential to revolutionize the monitoring of mango crop health, enabling early disease detection and enhancing crop yields.

The pedagogical of computer programming education is being enriched and improved through the interactive learning material. Visualization, modeling, and internet platforms for developing interactive visual skills are only a few examples of the types of specialized learning material currently accessible for use in a wide range of computing classes. There are some specific challenges related to the implementation of active learning, such as insufficient time for class, an increase in preparation, implementing students' engagement in extensive courses, and a lack of necessary materials, technology, or supplies. Computer vision is a subfield of AI that allows machines to learn from visual data (such as photos, movies, and other digital media) and then act on or offer solutions to problems. To enhance the efficiency of intelligent interactive learning and practice, this article incorporates a visual machine vision analytical framework under the guidance of Artificial intelligence to create a Machine-Vision-based Smart Education Assistance System (MV-SEAS). Visualization speeds up and simplifies regular communication by consolidating several forms of information into a single visual representation. This study discusses how visualizing information is crucial for students' initial knowledge acquisition and continued education and development. The seamless amalgamation of automated innovative education analyses and interactive visualizations is emphasized. The paper aimed to identify and characterize the technical challenges mentioned above must be surmounted to make it simpler for computer educators to discover, adopt, and tailor intelligent learning materials. The study concludes by proposing an MV-SEAS for storing, integrating, and disseminating smart educational data. It investigates whether it can be done using existing standards and guidelines. In the end, this essay combines trials to prove the effectiveness of the proposed smart education method. The findings demonstrate that interactive visualization of AI-assisted smart education may effectively combine subject experts' information with educators' experience to produce more powerful and easily intelligible machine intelligence.

In smart cities, the widespread adoption of Information and Communication Technologies (ICTs) presents both opportunities and challenges for security. While ICTs enable increased productivity, data sharing, and improved citizen services, they also create new vulnerabilities for malicious actors to exploit. This necessitates robust host-based security solutions to protect critical infrastructure and data. This paper proposes a novel multi-level fusion approach for enhanced host-based malware detection in ICT-enabled smart cities. By leveraging diverse data sources and employing advanced fusion techniques, our approach achieves significant improvements in malware detection accuracy, network evaluation, and security analysis compared to existing methods. Specifically, our proposed approach demonstrates a 72.1% malware detection rate across various attack scenarios, 69.7% accuracy in host network evaluation, 82.8% reduction in security analysis error, 75.4% accuracy in network probability detection, and an overall accuracy of 67.2%. These results showcase the potential of multi-level fusion for strengthening host-based security in smart cities. This approach offers several advantages over traditional host-based security solutions. Firstly, it provides more comprehensive threat detection by utilizing multiple data sources. Secondly, it reduces the burden on IT administrators by automating security analysis and decision-making. Finally, it enables continuous improvement through adaptive learning and feedback mechanisms. Overall, our multi-level fusion approach represents a promising advancement in host-based security for ICT-enabled smart cities. It offers significant improvements in accuracy and efficiency, paving the way for a more secure and resilient urban environment.

The research article "Harnessing the Power of Machine Learning to Refine Data Fusion Processes for Better Accuracy and Speed" proposes integrating different machine learning methods to improve data fusion. The suggested method uses an ensemble learning strategy, a deep learning-based fusion model, SVMs for data combining, CNNs for image and time-series data combining, and RNNs for time-series data combining. For best efficiency, each algorithm is carefully constructed utilizing mathematical concepts. Deep learning shines on complicated datasets, whereas the ensemble approach, which uses several models, is more accurate. CNN handles visual data better than RNN does sequence data. However, SVM shines in multidimensional domains. These reliable and adaptive solutions can tackle various data fusion difficulties. This approach outperforms others in processing speed, accuracy, precision, memory, and F1-score. Finding a balance between computer complexity and human satisfaction enhances dependability, data duplication, and quality. This novel technique transforms machine learning-powered data fusion. Another benefit is better data integration in complicated systems.

Human Activity Recognition (HAR) is one of the most important modern research fields concerned with studying and analyzing human actions and behaviors. Human activity recognition applications offer great potential for a wide range of applications in various fields that enhance health, safety, and efficiency. Due to the diversity of human activities and the way people carry out these activities, it is difficult to recognize human activity. The amazing capabilities provided By Artificial Intelligence (AI) tools in analyzing and understanding hidden patterns in complex data can greatly facilitate the HAR process. There has been a huge trend in the past 10 years to use Machine Learning (ML) and Deep Learning (DL) techniques to analyze and understand big data for HAR. Although there are many studies using these techniques, their accuracy still needs to be further improved due to several challenges: Data complexity, class imbalance, determining the appropriate feature selection technique with ML technique, and tuning the hyperparameters of the used ML technique. To overcome these challenges, this study proposes an effective framework based on two stages: a data preprocessing procedure that includes data balance and data normalization. Then, a hybrid CNN-XGB model combining Convolutional Neural Network (CNN) and a fine-tuned XGBoost (XGB) classifier is developed for accurate HAR. The CNN-XGB model achieved excellent results in HAR when trained and tested on the HCI-HAR dataset, achieving an accuracy of up to 99.0%. Effectively HAR provides the opportunity to apply many applications that contribute to improving the quality of life in various areas of our daily lives.

Recently, wireless sensor networks on several challenging topics have piqued researchers’ attention. Maximising a network's lifetime requires just the right combination of cluster size and number of nodes. Data transmission from nodes to cluster leaders is energy intensive, even for a modest number of clusters. If there are several clusters, many leaders will be chosen, and many nodes will rely on long-distance transmission to communicate with the home base. Therefore, in order to maximise efficiency, it is necessary to strike a balance between these two factors. WSN's major challenge is improving its energy efficiency. This is because their energy consumption defines their lifespan, and it is difficult, if not impossible, to recharge their batteries. Therefore, it is crucial to develop algorithms that consume as little energy as possible in order to maximise the network's potential. The perfect clusters are essential for the longevity of the network. Therefore, an algorithm called statistical centre energy efficient clustering approach (SEECA) is presented to increase the network's lifetime while decreasing its energy consumption. The experimental findings show that the proposed methodology SCEECA outperforms the LEACH method by a wide margin, with gains of 32% in Residual energy, 16% in Network Lifetime, and 12% in Throughput.

We have discovered five novel strategies to enhance data fusion in complex systems. This page provides a comprehensive explanation of these five methodologies. Data may be combined with a list. Examples of techniques include entropy-based data selection and parameter optimization for data fusion. This technique effectively resolves all problems related to merging records. Accurate, rapid, and easily expandable. Ablation studies assess the effectiveness of various techniques. Every process is crucial; omitting anyone would adversely affect the mix. This approach may integrate data from several sources to guarantee accuracy and utility. This facilitates the use of intricate technologies, hence enhancing data integration. The study promotes further inquiry and implementation. These results indicate that using this method might enhance the process of combining data.

This study investigated the experimental work of titanium alloy in the die-sinking electrical discharge (EDM) machining process to enhance surface integrity (surface roughness) by applying regression-based modeling. Furthermore, a multiple polynomial regression (MPR) model was developed to predict surface roughness responses under optimized conditions. The effects of EDM parameters, such as pulse-on time (ON), pulse-off time (OFF), peak current (IP), and servo voltage (SV), on surface roughness were studied. The experiment was conducted using a two-level full factorial design with four center points. Roughness was measured using a surface roughness tester (Formtracer SJ-301). The significant cutting parameters for surface roughness were determined using analysis of variance (ANOVA). The results showed that increasing the servo voltage significantly reduced the surface roughness by 46.48%. The developed model also predicted surface roughness values lower than those observed in the experimental data, with an R2 value of 0.608.

In today’s competitive markets, it is crucial to render personalized assistance tailored to unique individual’s needs. To accomplish this goal, a recommender system represents a noteworthy progression in collaborative filtering recommender systems. This shift highlights a broader research focus that extends beyond algorithms to encompass a diverse array of questions related to the functionality of the recommender. The identification accuracy must be assessed as a function of how well the suggested approach fits with a user's wants and needs, particularly in the context of collaborative constraint-based functions. The next phase of research must focus on defining parameters for assessment which may be used to compare the performance of constraint-based algorithms across a wide variety of diverse issues. It is currently necessary to design, or at criteria for assessment for constraint-based algorithms. We have addressed key research challenges related to the following topics: constraint-aware machine learning, understanding parameters in solution spaces, metrics for assessing constraint-based systems, algorithm selection, machine learning considerations, and investigating constraint-based platforms, and elucidations. 

This study explores the enhancement of accuracy in Indonesian sentiment analysis by incorporating text segmentation features during the pre-processing phase. One of the most important steps in creating a high-quality Bag of Words is to separate Indonesian sentences with no spacing, which is made possible by the created text segmentation algorithm. Through the conducted observations and analyses, it was observed that text comments from social media frequently exhibit connected sentences without spacing. The segmentation process was developed through a matching model utilizing a standard Indonesian word dictionary. Implementation involved testing Indonesian text data related to COVID-19 management, resulting in a substantial increase of 3,036 features. The Bag of Words was then constructed using the Term Frequency-Inverse Document Frequency method. Subsequently, sentiment analysis classification testing was conducted using both deep learning and machine learning models to assess data quality and accuracy. The sentiment analysis accuracy for applying Deep Learning, Support Vector Machine and Naive Bayes is 86.46%, 88.02% and 86.19% respectively.

Recently, the popularity of online games has risen drastically due to the latest technology that can connect players globally. League of Legends (LoL) holds the title of being the most extensively played Multiplayer Online Battle Arena (MOBA) game globally. This issue compels a substantial volume of preceding research that still analyzes and predicts the game outcomes with traditional methods that can be inaccurate and imprecise. Furthermore, these methods are frequently associated with the high rates of both false positive and false negative results. Hence, this paper presents a weighted-based feature predictor model to enhance the prediction accuracy. The approach predicts the game outcome of League of Legends matches in the Latin America North (LAN) and North America (NA) regions. We utilize player mastery and win rate for each summoner as the features. The data preparation process includes a weighted algorithm calculation and then evaluation using Naïve Bayes and Support Vector Machine algorithm. The outcomes illustrate that the weight-based feature approach can predict the outcome of LoL matches with an average accuracy of over 97 percent. This approach can be a valuable technique for players, teams, and coaches to analyze their performance and make strategic decisions.

The knowledge of courses can be represented by using ontology to create intelligent educational systems. This study proposes the Onto-Linking model as a knowledge framework that expresses the knowledge of the inputted schema to investigate the schema linking problem of the Text-to-SQL model. It combines the ontology with the structure of the schema. The proposed ontology is utilized to encapsulate the semantics of the intellectual elements of the schema, such as the table names, column names, foreign/primary key restrictions, and information about the probing schema connection. Therefore, the model makes it easier to accurately translate natural language questions into SQL queries. It improves query creation, helps with error handling, and supports query validation by helping the model better grasp the query's intent. The outcomes of the pedagogically oriented model aimed at guiding learners to comprehend the process of reasoning to attain the respective solution.