This paper presents a study of the Smell Agent Symbiotic Organism Search (SASOS) hybrid algorithm. SASOS is developed from bioinspired Smell Agent-Based Optimization(SAO) and Symbiosis Organism Search (SOS) algorithms. Bioinspired algorithms often lack a balance between speed and accuracy to achieve optimal performance efficiency and a global search for the best solution. To address these challenges, the algorithm reduces the imbalance between diversification and intensification in bioinspired algorithms to improve the search for global optima. SASOS performance was evaluated in sixteen selected Congress on Evolutionary Computation (CEC) functions using Aggregative Best Counts (ABC) compared to the regular SAO and SOS algorithms. For an advanced performance comparison, the convergence study was carried out on each CEC function to assess the fitness of the algorithms based on the Desirable Convergence Goal (DCG). Evaluation results using 50 iterations have shown that SASOS performed better withABCof56.25%than the SAO and SOS algorithms with ABC of 28.12% and 15.63%, respectively, in standard benchmark functions. Furthermore, in the convergence study, 1000 iterations were superimposed for each algorithm on the CEC functions. The convergence results showed that SASOS obtained the best DCG of 58.83%compared to SOS and SAO with DCG of 25.00% and 16.67%, respectively. These results made the performance of the hybrid SASOS uniquely different from other similar approaches.This is because the hybrid SASOS satisfactorily balanced the diversification and intensification phases in the bioinspired SAO and SOS algorithms. The eligible characteristics of the hybrid SASOS with respect to ABC and DCG showed its compatibilityand significance forvarious engineering optimizationapplications
{"title":"A Study of Hybridized Smell Agent Symbiotic Organism Search in Congress on Evolutionary Computation Functions","authors":"S. Mohammed","doi":"10.56471/slujst.v6i.350","DOIUrl":"https://doi.org/10.56471/slujst.v6i.350","url":null,"abstract":"This paper presents a study of the Smell Agent Symbiotic Organism Search (SASOS) hybrid algorithm. SASOS is developed from bioinspired Smell Agent-Based Optimization(SAO) and Symbiosis Organism Search (SOS) algorithms. Bioinspired algorithms often lack a balance between speed and accuracy to achieve optimal performance efficiency and a global search for the best solution. To address these challenges, the algorithm reduces the imbalance between diversification and intensification in bioinspired algorithms to improve the search for global optima. SASOS performance was evaluated in sixteen selected Congress on Evolutionary Computation (CEC) functions using Aggregative Best Counts (ABC) compared to the regular SAO and SOS algorithms. For an advanced performance comparison, the convergence study was carried out on each CEC function to assess the fitness of the algorithms based on the Desirable Convergence Goal (DCG). Evaluation results using 50 iterations have shown that SASOS performed better withABCof56.25%than the SAO and SOS algorithms with ABC of 28.12% and 15.63%, respectively, in standard benchmark functions. Furthermore, in the convergence study, 1000 iterations were superimposed for each algorithm on the CEC functions. The convergence results showed that SASOS obtained the best DCG of 58.83%compared to SOS and SAO with DCG of 25.00% and 16.67%, respectively. These results made the performance of the hybrid SASOS uniquely different from other similar approaches.This is because the hybrid SASOS satisfactorily balanced the diversification and intensification phases in the bioinspired SAO and SOS algorithms. The eligible characteristics of the hybrid SASOS with respect to ABC and DCG showed its compatibilityand significance forvarious engineering optimizationapplications","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117131612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Android is an open-source operating system mainly built for smart devices to make them easy to use and user-friendly. Thus, it has immensely engulfed other operating systems in mobile devices, which have become not only a major stakeholder in the market but have also become attractive targets for cyber criminals to lure many Androids malware with the intention of stealing or destroying the user's information without the user knowing. Many traditional signature-based anti-malware efforts have been made to combat malicious apps, but these efforts have been insufficient due to the lack of ability to detect unknown malware. This insufficient effort by traditional signature-based has led to the intervention of researchers to embark upon combating unknown malware using machine learning techniques. This study looks into many existing research papers on malware detection using machine learning in order to determine the significance of feature selection techniques. The comparative analysis examines the importance of feature selection and unselected feature techniques
{"title":"A Comparative Analysis of Android Malware Detection with and without Feature Selection Techniques using Machine Learning","authors":"M. Ibrahim","doi":"10.56471/slujst.v6i.371","DOIUrl":"https://doi.org/10.56471/slujst.v6i.371","url":null,"abstract":"Android is an open-source operating system mainly built for smart devices to make them easy to use and user-friendly. Thus, it has immensely engulfed other operating systems in mobile devices, which have become not only a major stakeholder in the market but have also become attractive targets for cyber criminals to lure many Androids malware with the intention of stealing or destroying the user's information without the user knowing. Many traditional signature-based anti-malware efforts have been made to combat malicious apps, but these efforts have been insufficient due to the lack of ability to detect unknown malware. This insufficient effort by traditional signature-based has led to the intervention of researchers to embark upon combating unknown malware using machine learning techniques. This study looks into many existing research papers on malware detection using machine learning in order to determine the significance of feature selection techniques. The comparative analysis examines the importance of feature selection and unselected feature techniques","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129748621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A 1x4 and 1x8 circular micro strip patch antenna array operating at 2.4GHz are simulated for Industrial Wireless Sensor Network (IWSN) applications using CST studio suite and MATLAB based simulator software. The circular patch antenna designed on a FR4 substrate with dielectric constant of 4.4 and a substrate height of 1.6mm is fed using inset-fed technique. Several antenna characteristics such as return loss, radiation pattern, bandwidth, directivity, antenna gain, radiation efficiency isanalyzed. The compact size and higher directivity help to improve the network performance by alleviating contention, increasing communication range, and mitigating interference of the system. Hence, the advantages gained, make the system more useful for IWSN applications as achieved in this research
利用CST studio suite和基于MATLAB的模拟器软件，对工作频率为2.4GHz的1x4和1x8圆形微带贴片天线阵列进行了工业无线传感器网络(IWSN)应用仿真。在介电常数为4.4、衬底高度为1.6mm的FR4衬底上设计了圆形贴片天线，采用插入馈电技术。分析了天线的回波损耗、辐射方向图、带宽、指向性、天线增益、辐射效率等特性。紧凑的尺寸和更高的指向性有助于通过减少争用、增加通信范围和减少系统干扰来提高网络性能。因此，所获得的优势，使该系统在本研究中实现的IWSN应用中更加有用
{"title":"Design and Analysis of 1x4 and 1x8 Circular Patch Microstrip Antenna Array for IWSN Application","authors":"E. Otsapa","doi":"10.56471/slujst.v6i.365","DOIUrl":"https://doi.org/10.56471/slujst.v6i.365","url":null,"abstract":"A 1x4 and 1x8 circular micro strip patch antenna array operating at 2.4GHz are simulated for Industrial Wireless Sensor Network (IWSN) applications using CST studio suite and MATLAB based simulator software. The circular patch antenna designed on a FR4 substrate with dielectric constant of 4.4 and a substrate height of 1.6mm is fed using inset-fed technique. Several antenna characteristics such as return loss, radiation pattern, bandwidth, directivity, antenna gain, radiation efficiency isanalyzed. The compact size and higher directivity help to improve the network performance by alleviating contention, increasing communication range, and mitigating interference of the system. Hence, the advantages gained, make the system more useful for IWSN applications as achieved in this research","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115064677","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Digital image authentication and security are crucial concerns for the digital revolution since any image may be readily tampered with. Digital watermarking schemes were since been utilized to tackle a range of problems over time and involving the verification of digital images and copyright protection. In a real-world setting, watermarked contents are frequently subject to a succession of assaults which makes it necessary to strike a balance between resilience and imperceptibility in the face of attacks. There are numerous hazards to this, and numerous watermarking techniques have been created to counter them. Data with less perceptual distortion should be able to be included in a real watermarking technique in addition to restoring the original cover content. As a result, robustness, imperceptibility, and security are three crucial criteria for digital content'sauthentication and copyrightpreservation. This study therefore presents a careful review of some cutting-edge watermarking technologies used for copyright protection and authentication so as to identify their strengths and limitations. For clarity, this study shall explain some basic concepts of digital watermarking as well as the various forms of attacks on watermarks. The contributions from this work will be useful to researchers aim at developing efficient watermarking techniques
{"title":"Robust Watermarking Techniques for the Authentication and Copyright Protection of Digital Images: A Survey","authors":"Godwin Ugwu Onoja","doi":"10.56471/slujst.v6i.366","DOIUrl":"https://doi.org/10.56471/slujst.v6i.366","url":null,"abstract":"Digital image authentication and security are crucial concerns for the digital revolution since any image may be readily tampered with. Digital watermarking schemes were since been utilized to tackle a range of problems over time and involving the verification of digital images and copyright protection. In a real-world setting, watermarked contents are frequently subject to a succession of assaults which makes it necessary to strike a balance between resilience and imperceptibility in the face of attacks. There are numerous hazards to this, and numerous watermarking techniques have been created to counter them. Data with less perceptual distortion should be able to be included in a real watermarking technique in addition to restoring the original cover content. As a result, robustness, imperceptibility, and security are three crucial criteria for digital content'sauthentication and copyrightpreservation. This study therefore presents a careful review of some cutting-edge watermarking technologies used for copyright protection and authentication so as to identify their strengths and limitations. For clarity, this study shall explain some basic concepts of digital watermarking as well as the various forms of attacks on watermarks. The contributions from this work will be useful to researchers aim at developing efficient watermarking techniques","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133112548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Heavy metals persistence in water brings about undesirable effect on man and animal because they are not degradable like other organic pollutants. Carbonized Avocado Pear seed (CAPS) as well as carbonized orange peel (COP) was impregnated with Potassium hydroxide (KOH) in ratio 1:1 for 48 hours. The KOH impregnated CAPS and COP was separately washed and oven dried at 10 for 6 hours and thereafter heated in a muffle furnace (Carbolite AAF1100) at 2500C for 1 hour. The activated carbonized pear seed (ACAPS) and activated carbonized orange peel (ACOP) obtained was physicochemically described with SEM and FTIR. The adsorption route of Pb2+ ion on top of ACAPS as well as ACOP was examined by means of batch adsorption isotherm investigation. The Pb2+ ion adsorption pattern was assessed with Langmuir, DRK, Freundlich, Tempkin and Flory-Huggin isotherm models. The SEM photograph, disclosed that ACAPS posessed numerous openings of different dimensions whereas ACOP possessed less openings of lesser dimensions. R2 worth ranging from 0.92 to 1.00 was got, indicating that the whole isotherm models were capable of elucidating the connection in the figures got. The Pb2+ ion had a firmer attraction and adsorption capacity for ACAPS. On the overall, ACAPS was a superior adsorbent likened with ACOP for effectual elimination of Pb2+ ion owing to a blend of its numerous pores of different dimensions and it surface functional groups with a qm worth of 23.10 and 6.06mg/g in that order.
{"title":"Adsorptive Potency of Activated Carbonized Avocado Pear Seeds (Persea Americana) and Activated Carbonized orange peels (Citrus Sinensis) in Eliminating Pb2+ ions in Contaminated Water.","authors":"O. Moses","doi":"10.56471/slujst.v5i.253","DOIUrl":"https://doi.org/10.56471/slujst.v5i.253","url":null,"abstract":"Heavy metals persistence in water brings about undesirable effect on man and animal because they are not degradable like other organic pollutants. Carbonized Avocado Pear seed (CAPS) as well as carbonized orange peel (COP) was impregnated with Potassium hydroxide (KOH) in ratio 1:1 for 48 hours. The KOH impregnated CAPS and COP was separately washed and oven dried at 10 for 6 hours and thereafter heated in a muffle furnace (Carbolite AAF1100) at 2500C for 1 hour. The activated carbonized pear seed (ACAPS) and activated carbonized orange peel (ACOP) obtained was physicochemically described with SEM and FTIR. The adsorption route of Pb2+ ion on top of ACAPS as well as ACOP was examined by means of batch adsorption isotherm investigation. The Pb2+ ion adsorption pattern was assessed with Langmuir, DRK, Freundlich, Tempkin and Flory-Huggin isotherm models. The SEM photograph, disclosed that ACAPS posessed numerous openings of different dimensions whereas ACOP possessed less openings of lesser dimensions. R2 worth ranging from 0.92 to 1.00 was got, indicating that the whole isotherm models were capable of elucidating the connection in the figures got. The Pb2+ ion had a firmer attraction and adsorption capacity for ACAPS. On the overall, ACAPS was a superior adsorbent likened with ACOP for effectual elimination of Pb2+ ion owing to a blend of its numerous pores of different dimensions and it surface functional groups with a qm worth of 23.10 and 6.06mg/g in that order.","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"325 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115965498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The study examined information and communication technology training and job performances of library professionals in Rivers State University and University of Port Harcourt. Descriptive survey design was adopted for the study. The population of the study comprised all library professionals and para-professionals from both universities understudy. Purposive sampling was used to select 51 library staff. A structured questionnaire was used as instrument for data collection. The data was analyzed using descriptive statistics. The hypothesis was tested using Pearson Product-Moment Correlation Coefficient. The study however found that ICT trainings significantly impact on Job performances of library professionals. The types of ICT training significant are on the use of computer/internet, OPAC, ILMS, emails, smartphones, databases and networking sites. The trainings are mostly received through conferences, workshops and personal training scheme. The study also found that there is non-frequent ICT training scheme as most schemes are held once in every two years in the academic libraries studied, and this is insufficient to guarantee effective job performances and staff productivity at all times. Therefore to keep abreast with the constantly evolving communication technologies, the study recommends a regular capacity building for at least twice a year. Also, library professionals should be encouraged to attend ICT seminars, workshops, conferences within and outside the library, and also engage in personal training scheme to develop themselves more.
{"title":"Information and Communication Technology Training and Job Performances of Library Professionals in Academic Libraries in Rivers State: A case study of Rivers State University and University of Port Harcourt","authors":"H. I. Wiche","doi":"10.56471/slujst.v5i.256","DOIUrl":"https://doi.org/10.56471/slujst.v5i.256","url":null,"abstract":"The study examined information and communication technology training and job performances of library professionals in Rivers State University and University of Port Harcourt. Descriptive survey design was adopted for the study. The population of the study comprised all library professionals and para-professionals from both universities understudy. Purposive sampling was used to select 51 library staff. A structured questionnaire was used as instrument for data collection. The data was analyzed using descriptive statistics. The hypothesis was tested using Pearson Product-Moment Correlation Coefficient. The study however found that ICT trainings significantly impact on Job performances of library professionals. The types of ICT training significant are on the use of computer/internet, OPAC, ILMS, emails, smartphones, databases and networking sites. The trainings are mostly received through conferences, workshops and personal training scheme. The study also found that there is non-frequent ICT training scheme as most schemes are held once in every two years in the academic libraries studied, and this is insufficient to guarantee effective job performances and staff productivity at all times. Therefore to keep abreast with the constantly evolving communication technologies, the study recommends a regular capacity building for at least twice a year. Also, library professionals should be encouraged to attend ICT seminars, workshops, conferences within and outside the library, and also engage in personal training scheme to develop themselves more.","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"566 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133679325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the rapid development of technology today, lots of technological advancements are on the high increase. Information storage for individual and organizations including educational sector is taking another dimension. Harnessing cloud computing in educational sector will definitely lead to the adoption of Cloud Computing in the sector. Cloud Computing is everything that could answer the challenges of ICT in educational sector and the ability to make ICT resources cheaper and it gives great flexibility for expansion, but suffered a lot of setbacks when it comes to security and privacy concerns. Since, it is where software applications, data storage and processing capacity are accessed over the internet. This paper will study the benefit of harnessing cloud computing in Educational Sector and give recommendations for adopting the new technology which can be accessed through public, private, community and hybrid cloud based technologies.
{"title":"Harnessing Cloud Computing in Nigerian Educational Sector","authors":"Salim M. Ahmad","doi":"10.56471/slujst.v5i.251","DOIUrl":"https://doi.org/10.56471/slujst.v5i.251","url":null,"abstract":"Due to the rapid development of technology today, lots of technological advancements are on the high increase. Information storage for individual and organizations including educational sector is taking another dimension. Harnessing cloud computing in educational sector will definitely lead to the adoption of Cloud Computing in the sector. Cloud Computing is everything that could answer the challenges of ICT in educational sector and the ability to make ICT resources cheaper and it gives great flexibility for expansion, but suffered a lot of setbacks when it comes to security and privacy concerns. Since, it is where software applications, data storage and processing capacity are accessed over the internet. This paper will study the benefit of harnessing cloud computing in Educational Sector and give recommendations for adopting the new technology which can be accessed through public, private, community and hybrid cloud based technologies.","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120809955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Credit loans are considered most essential aspect of most financial institutions. All loan mortgagees or lenders are demanding to identify out effective commercial and business approaches to encourage customers to apply their credit loans. There are numerous business patrons who act negatively after their requests got approval. To avert this condition, lenders have to discover some techniques to forecast customer’s behaviors. This resulted to the usage of machine learning algorithms by the financial lending institutions for accessing loan applicants. Despite advancements in automating decision-based loan systems, most existing models do not consider the “early loan repayment” attribute as a factor in resolving this prediction error. In reality, the amendment for preliminary loan reimbursement in model building is obligatory, since a larger numbers of timely loan reimbursement observed during the loan period, reduces default rate. For effective model’s comparison based on accuracy and minimum errors of prediction, six supervised machine learning algorithms i.e. Random Forest, Artificial Neural Network, Classification and Regression Tree, Support Vector Machine, Logistic Regression, and Naïve Bayes were adopted to develop a default prediction models which include the early loan repayment attribute. The models were trained and tested on a loan dataset consisting of attributes with, and without early loan repayment attribute and were evaluated using five performance metrics. The results of the performance evaluation show that models that account for early loan repayment have higher accuracy, recall, precision, Root Mean Square Error and Receiver Operative Characteristics curve values than models trained without the early loan repayment attribute. The Random forest model proofed to be the best predictive model having 93% accuracy, 11% RMSE, 90% precision, 89% recall and 81% ROC value over others models.
{"title":"Default Prediction for Loan Lenders Using Machine Learning Algorithms","authors":"Awuza Abdulrashid Egwa","doi":"10.56471/slujst.v5i.222","DOIUrl":"https://doi.org/10.56471/slujst.v5i.222","url":null,"abstract":"Credit loans are considered most essential aspect of most financial institutions. All loan mortgagees or lenders are demanding to identify out effective commercial and business approaches to encourage customers to apply their credit loans. There are numerous business patrons who act negatively after their requests got approval. To avert this condition, lenders have to discover some techniques to forecast customer’s behaviors. This resulted to the usage of machine learning algorithms by the financial lending institutions for accessing loan applicants. Despite advancements in automating decision-based loan systems, most existing models do not consider the “early loan repayment” attribute as a factor in resolving this prediction error. In reality, the amendment for preliminary loan reimbursement in model building is obligatory, since a larger numbers of timely loan reimbursement observed during the loan period, reduces default rate. For effective model’s comparison based on accuracy and minimum errors of prediction, six supervised machine learning algorithms i.e. Random Forest, Artificial Neural Network, Classification and Regression Tree, Support Vector Machine, Logistic Regression, and Naïve Bayes were adopted to develop a default prediction models which include the early loan repayment attribute. The models were trained and tested on a loan dataset consisting of attributes with, and without early loan repayment attribute and were evaluated using five performance metrics. The results of the performance evaluation show that models that account for early loan repayment have higher accuracy, recall, precision, Root Mean Square Error and Receiver Operative Characteristics curve values than models trained without the early loan repayment attribute. The Random forest model proofed to be the best predictive model having 93% accuracy, 11% RMSE, 90% precision, 89% recall and 81% ROC value over others models.","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125321617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The rapid advancement and development in high performance computing, ultrafast computing, autonomous technologies and complexity of biomedical data for visualization and image guidance play a significant role in modern surgery to help surgeons perform their surgical procedures. Brain tumour diagnosis requires an enhanced, effective as well as accurate 3-D visualization system for navigation, reference, diagnosis as well as documentation. The automatic and effective 3-D high performance artificial intelligence-enabled medical visualization framework was designed and implemented using automated machine learning (AutoML) to take the advantage of complexity in the underlying datasets to help specialists in identifying the most appropriate regions of interest and their associated hyper parameters for optimizing performance, whilst simultaneously attempting to maximize the reliability of resulting predictions. C# and Compute Unified Device Architecture (CUDA) in Microsoft.NET environment in comparison side by side with visual basic studio was used for the implementation. The framework was evaluated for rendering processing speed with brain datasets obtained from the department of surgery, University of North Carolina, United States. Interestingly, our framework achieves 3-D visualization of the human brain, reliable enough to detect and locate possible brain tumor with high interactive speed and accuracy.
{"title":"Automated Medical Visualization Application of Supervised Learning to Clinical Diagnosis, Disease and Therapy Management.docx","authors":"A. Adeshina","doi":"10.56471/slujst.v5i.311","DOIUrl":"https://doi.org/10.56471/slujst.v5i.311","url":null,"abstract":"The rapid advancement and development in high performance computing, ultrafast computing, autonomous technologies and complexity of biomedical data for visualization and image guidance play a significant role in modern surgery to help surgeons perform their surgical procedures. Brain tumour diagnosis requires an enhanced, effective as well as accurate 3-D visualization system for navigation, reference, diagnosis as well as documentation. The automatic and effective 3-D high performance artificial intelligence-enabled medical visualization framework was designed and implemented using automated machine learning (AutoML) to take the advantage of complexity in the underlying datasets to help specialists in identifying the most appropriate regions of interest and their associated hyper parameters for optimizing performance, whilst simultaneously attempting to maximize the reliability of resulting predictions. C# and Compute Unified Device Architecture (CUDA) in Microsoft.NET environment in comparison side by side with visual basic studio was used for the implementation. The framework was evaluated for rendering processing speed with brain datasets obtained from the department of surgery, University of North Carolina, United States. Interestingly, our framework achieves 3-D visualization of the human brain, reliable enough to detect and locate possible brain tumor with high interactive speed and accuracy.","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121654825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We propose some fixed duration pursuit differential game problems of l-catch in a Hilbert space. Players' motions obey ordinary differential equations and the control functions of players are subjected to either integral or geometric constraints. Pursuit is said to be completed in l-catch sense if the distance between the players with conicting goals are less than a fixed constant l. In this sense, we obtain sufficient conditions for the completion of the pursuit and construct a strategy for the pursuer in each of the four different problems considered. Furthermore, we give examples to support our theoretical findings
{"title":"Pursuit Differential Game Problems of L-Catch in A Hilbert Space","authors":"Yunusa Aliyu Hadejia","doi":"10.56471/slujst.v5i.282","DOIUrl":"https://doi.org/10.56471/slujst.v5i.282","url":null,"abstract":"We propose some fixed duration pursuit differential game problems of l-catch in a Hilbert space. Players' motions obey ordinary differential equations and the control functions of players are subjected to either integral or geometric constraints. Pursuit is said to be completed in l-catch sense if the distance between the players with conicting goals are less than a fixed constant l. In this sense, we obtain sufficient conditions for the completion of the pursuit and construct a strategy for the pursuer in each of the four different problems considered. Furthermore, we give examples to support our theoretical findings","PeriodicalId":299818,"journal":{"name":"SLU Journal of Science and Technology","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134541121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：