Browsing by Author "Ahmed, Md. Razu"

Now showing 1 - 13 of 13

An Automated Embedded Detection and Alarm System for Preventing Accidents of Passengers Vessel Due to Overweight
(Scopus, 2019-10-23) Shamrat, F. M. Javed Mehedi; Ahmed, Md. Razu; Nobel, Naimul Islam; Tasnim, Zarrin
One of the prominent transport system in Bangladesh is rivers and seas. Vessel overloading is found in Bangladesh as the main cause of accidents on the rivers and seas. Therefore, there must be a role to play in ensuring passenger safety on the vessels. In Bangladesh, the researchers are more focusing on the data collection related to vessel overloading and sinking. However, there is a need to overcome vessel overloading. This paper design and develop an embedded automated system which able to identify overweight and detect the location of a vessel. The proposed system segregated into three modules such as, the Location Detection Module (LDM) always tracks the current location of the vessel for monitoring; the Overweight Detection Module (ODM) measure the exceed water level of the vessel to identify the overweight issue; the Notification Module (NM) is responsible for generating message service (SMS) to notify nearby coast guard to stop the vessel. The result shows the successful overweight detection, location tracking, and instant notification send up-to-the-10 seconds. It can be noted that our proposed prototype can be embedded with any type of vessels including passenger vessel, general cargo vessel, etc.
Computational Intelligence Approaches for Prediction of Chronic Kidney Disease
(Springer, 2022-01-01) Ahmed, Md. Razu; Ali, Md. Asraf; Ahmed, Nasim; Bhuiyan, Touhid
Over the past few decades, it has been observed that there is a growing interest in the area of intelligence systems, such as Machine Learning. Machine learning has been extensively used in order to support medical specialists and clinicians in the help of forecast and diagnosis of various diseases. The aim of this study is to compare the performance of six supervision-based Machine Learning techniques, which are used in the prediction and detection of the chronic kidney disease outbreak. Machine learning techniques are used to solve clinical problems and medical diagnosis’ which have recently been developed. Hence, it is essential to have a framework that can instantly recognize the prevalence of kidney disease in thousands of samples. This research uses the chronic kidney disease dataset that contains 400 Kidney patient’s data including 25 parameters. Moreover, we evaluated the performance of six supervision-based machine learning classification techniques, which are: KNN, Support Vector Machine, Decision Tree, Random Forest, Naïve Bayes and Logistics Regression. The performance of the supervised machine learning classification techniques was validated with sensitivity, specificity, f1 measure and accuracy. In this experiment, NB and RF outperformed, they were found to be at 100% accuracy, whereas the DT achieved 98% accuracy. Moreover, the KNN, SVM, LR classification techniques achieved 96% accuracy. Our findings showed that both the Random Forest and Naïve Bayes classification techniques outperformed as compared to other classification techniques used to predict kidney disease of the patients tested. In summary, our study has emphasized the research trends and scope in relation to Chronic Kidney Disease and as well as clinical research areas by machine learning techniques, which have had an effective impact in biomedical fields.
Computational Intelligence Techniques for Disease Prediction
(Daffodil International University, 2018-12-18) Ahmed, Md. Razu
Objective: The aim of the study is to examine the performance of six Machine Learning algorithms for reducing the complexity and cost of chronic disease diagnosis by prediction. Methods: I used six machine learning techniques for the classification of chronic disease datasets including Breast Cancer, Chronic Kidney Disease and Liver Patient datasets. SVM, NB, KNN, RF, DT and LR were used for prediction and diagnosis of chronic disease. The performance of the used techniques was evaluated with sensitivity, specificity, f 1 measure and total accuracy. Results: All the machine learning classifiers show the accuracy level above 95% for both of the kidney disease and breast cancer prediction. Hence, the accuracy level nearly of 75% for liver disease prediction using all classification classifiers. In Kidney disease datasets, NB and RF has achieved the best performance than the other classification techniques in terms of accuracy by obtaining the highest accuracy as 100% respectively. The performance of analyzing breast cancer datasets, SVM achieved the highest performance with maximum classification accuracy of 97.07% while second highest classification accuracy is achieved by NB and RF (97%). Moreover, in the terms of accuracy for analyzing liver disease datasets, LR achieved the highest accuracy (i.e. 0.75%) and NB achieved the worst performance (i.e. 0.53%). Conclusion: My findings showed that the NB, RF outperformed for analyzing the kidney datasets. NB, RF, SVM achieves best performance for performing experiment on breast cancer. In addition, LR have shown the utmost performance on liver disease datasets. In summary, our study has emphasized the research trends and scope in relation to chronic disease and clinical research fields by machine learning techniques, which has an effective impact in bio-medical fields.
Design of Microstrip Patch Antenna to Deploy Unmanned Aerial Vehicle as UE in 5g Wireless Network
(International Journal of Electrical and Computer Engineering, 2021) Md. Imran, Abu Zafar; Hakim, Mohammad Lutful; Ahmed, Md. Razu; Islam, Mohammad Tariqul; Hossain, Elias
The use of unmanned aerial vehicle (UAV) has been increasing rapidly in the civilian and military applications, because of UAV's high-performance communication with ground clients, especially for its intrinsic properties such as adaptive altitude, mobility, and flexibility. UAV deployment can be monitored and controlled through 5G wireless network as user equipment (UE) along with other devices. A highly directive microstrip patch antenna (MPA) could establish long-distance communication by overcoming air attenuation and reduce co-channel interference in the limited region if UAV uses a specifically dedicated band, which might enhance spatially reuse of the spectrum. Also, MPA is highly recommended for UAV because of its low weight, low cost, compact size, and flat shape. In this paper, we have designed a highly directive single-band 2×2 and 4×4 antenna array for 5.8 GHz and 28 GHz frequency respectively for UAV application in a focus to deploy UAV through 5G wireless network. Here, The Roger RT5880 (lossy) material utilize as a substrate due to its lower dielectric constant which achieves higher directivity and good mechanical stability. Inset feed technique used to feed antenna for lowering input impedance which provides higher antenna efficiency. The results show a wider bandwidth of 702 MHz and 1.596 GHz for 5.8 GHz and 28 GHz antenna array correspondingly with a compact size.
Design of Microstrip Patch Antenna to Deploy Unmanned Aerial Vehicle as Ue in 5g Wireless Network
(International Journal of Electrical and Computer Engineering,, 2021-03-21) Md. Imran, Abu Zafar; Hakim, Mohammad Lutful; Ahmed, Md. Razu; Islam, Mohammad Tariqul; Hossain, Elias
The use of unmanned aerial vehicle (UAV) has been increasing rapidly in the civilian and military applications, because of UAV's high-performance communication with ground clients, especially for its intrinsic properties such as adaptive altitude, mobility, and flexibility. UAV deployment can be monitored and controlled through 5G wireless network as user equipment (UE) along with other devices. A highly directive microstrip patch antenna (MPA) could establish long-distance communication by overcoming air attenuation and reduce co-channel interference in the limited region if UAV uses a specifically dedicated band, which might enhance spatially reuse of the spectrum. Also, MPA is highly recommended for UAV because of its low weight, low cost, compact size, and flat shape. In this paper, we have designed a highly directive single-band 2×2 and 4×4 antenna array for 5.8 GHz and 28 GHz frequency respectively for UAV application in a focus to deploy UAV through 5G wireless network. Here, The Roger RT5880 (lossy) material utilize as a substrate due to its lower dielectric constant which achieves higher directivity and good mechanical stability. Inset feed technique used to feed antenna for lowering input impedance which provides higher antenna efficiency. The results show a wider bandwidth of 702 MHz and 1.596 GHz for 5.8 GHz and 28 GHz antenna array correspondingly with a compact size.
Empirical Study of Computational Intelligence Approaches for the Early Detection of Autism Spectrum Disorder
(Scopus, 2021) Khatun, Mst. Arifa; Ali, Md. Asraf; Ahmed, Md. Razu; Noori, Sheak Rashed Haider; Sahayadhas, Arun
The objective of the research is to develop a predictive model that can significantly enhance the detection and monitoring performance of Autism Spectrum Disorder (ASD) using four supervised learning techniques. In this study, we applied four supervised-based classification techniques to the clinical ASD data obtained from 704 patients. Then, we compared the four machine learning (ML) algorithms performance across tenfold cross-validation, ROC curve, classification accuracy, F1 measure, precision, recall, and specificity. The analysis findings indicate that Support Vector Machine (SVM) achieved the uppermost performance than the other classifiers in terms of accuracy (85%), f1 measure (87%), precision (87%), and recall (88%). Our work presents a significant predictive model for ASD that can effectively help the ASD patients and medical practitioners.
Empirical Study of Computational Intelligence Approaches for the Early Detection of Autism Spectrum Disorder
(Springer, 2020-09-30) Khatun, Mst. Arifa; Ali, Md. Asraf; Ahmed, Md. Razu; Noori, Sheak Rashed Haider; Sahayadhas, Arun
The objective of the research is to develop a predictive model that can significantly enhance the detection and monitoring performance of Autism Spectrum Disorder (ASD) using four supervised learning techniques. In this study, we applied four supervised-based classification techniques to the clinical ASD data obtained from 704 patients. Then, we compared the four machine learning (ML) algorithms performance across tenfold cross-validation, ROC curve, classification accuracy, F1 measure, precision, recall, and specificity. The analysis findings indicate that Support Vector Machine (SVM) achieved the uppermost performance than the other classifiers in terms of accuracy (85%), f1 measure (87%), precision (87%), and recall (88%). Our work presents a significant predictive model for ASD that can effectively help the ASD patients and medical practitioners.
FIR filter design using modified lanczos window function
(© 2012 Advanced Materials Research, 2012) Samad, Md. Abdus; Uddin, Jia; Ahmed, Md. Razu
Attenuated side lobe peak in the range of around ~-45dB is required in many applications of signal processing and measurements. However, the problem is usual window based FIR filter design lies in its side lobes amplitudes that are higher than the requirement of application. We propose a modified Lanczos window function by heuristic by examining the Lanczos window, which has better performance like equiripple, minimum side lobe compared to the several commonly used windows. The proposed window has slightly larger main lobe width of the commonly used Hamming window, while featuring 5.1-18.5 dB smaller side lobe peak. The proposed modified Lanczos window maintains its maximum side lobe peak about -55.2-51.9 dB compared to -39-36.7 dB of Hamming window for M= 10-14, while offering roughly equal main lobe width. Our simulated results also show significant performance upgrading of the proposed modified Lanczos window compared to the Kaiser, Gaussian, and Lanczos windows. The proposed modified Lanczos window also shows better performance than Dolph-Chebyshev window. Finally, the example of designed low pass FIR filter confirms the efficiency of the proposed modified Lanczos window.
FIR filter design using modified lanczos window function
(© 2012 Advanced Materials Research, 2012) Samad, Md. Abdus; Uddin, Jia; Ahmed, Md. Razu
Attenuated side lobe peak in the range of around ~-45dB is required in many applications of signal processing and measurements. However, the problem is usual window based FIR filter design lies in its side lobes amplitudes that are higher than the requirement of application. We propose a modified Lanczos window function by heuristic by examining the Lanczos window, which has better performance like equiripple, minimum side lobe compared to the several commonly used windows. The proposed window has slightly larger main lobe width of the commonly used Hamming window, while featuring 5.1-18.5 dB smaller side lobe peak. The proposed modified Lanczos window maintains its maximum side lobe peak about -55.2-51.9 dB compared to -39-36.7 dB of Hamming window for M= 10-14, while offering roughly equal main lobe width. Our simulated results also show significant performance upgrading of the proposed modified Lanczos window compared to the Kaiser, Gaussian, and Lanczos windows. The proposed modified Lanczos window also shows better performance than Dolph-Chebyshev window. Finally, the example of designed low pass FIR filter confirms the efficiency of the proposed modified Lanczos window.
Improved Variable Step Length a Search Algorithm for Path Planning of Mobile Robots
(2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), IEEE, 2021-06-03) Hasan, Md. Hasibul; Ahmed, Md. Razu
The use of Mobile Robots in diverse sectors are increasing day by day. Nowadays, mobile robots are widely used in industrial sectors, but real-time path planning and collision free path tracking raises more challenging issues. A good path planning process for these mobile robots is needed in order for them to perform better. In path planning problems, the A∗ algorithm has been widely investigated and applied, but the cost and efficiency of the path is not completely taken into consideration. This algorithm has been tweaked and improved in a number of ways to facilitate path planning. Taking into account the variable-step-length A∗ search algorithm, which can take steps longer than one. This method uses a fixed step length and produces a better path than the A∗ Search algorithm. However, if the step length can be modified in the process as required, a more optimal direction can be obtained. As a result, this paper proposes an improved updated variable-step-length based A∗ algorithm that can update or change step length. This algorithm will efficiently find a path with a shorter length. In order to check the feasibility and efficiency of the proposed system, simulation and practical experiments are carried out. The findings show that the improved A∗ algorithm will increase the planned route’s safety and efficiency while also reducing the robot’s movement time in difficult terrain.
Machine Learning Techniques for Predicting Surface EMG Activities on Upper Limb Muscle
(Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, Springer, 2020-07-30) Roy, Joy; Ali, Md. Asraf; Ahmed, Md. Razu; Sundaraj, Kenneth
The aim of this review study is to analyze the techniques for predicting the surface EMG activities on upper limb muscles using different machine learning algorithms. In this study, we followed a systematic searching procedure to select articles from four different online databases, i.e. PubMed, Science Direct, IEEE Xplore and Biomed Central (published years between 2010 and 2018). In our searching procedure, we searched by characteristically with two keywords (“EMG” and “Machine Learning”) in the above four listed databases to find the related articles in the field of machine learning techniques for predicting surface EMG activities on upper limb muscles. From the searching of this review, we selected total 25 articles for predicting surface EMG signals on upper limb muscles, where 10 articles are provided most efficient and effective classifier of surface EMG signals, 11 articles described different hand gesture recognition using machine learning algorithms, 2 articles explained that the importance of muscles selection, 1 article presented the natural pinching technique and 1 article focus on evaluation error rate of movements. This review presents not only the machine learning techniques for prediction of surface EMG activities on upper limb muscles but also it focuses on the challenge of the machine learning techniques for predicting surface EMG data. In addition, we believe that this review also provides muscle related issues that will impact the prediction of surface EMG activities on muscle.
Publishing CSV Data as Linked Data on the Web
(Scopus, 2020) Mahmud, S. M. Hasan; Hossin, Md. Altab; Hasan, Md. Rezwan; Jahan, Hosney; Noori, Sheak Rashed Haider; Ahmed, Md. Razu
The majority of datasets on Open Government Data (OGD) portals are stored in comma-separated values (CSV) file. Publishing CSV data as a Linked Open Data (LOD) on the Web is an active field of research. However, there are very few effective applications have been developed with this purpose. Linked Data refer many ways for connecting and publishing structured data to data consumers, but available datasets are in CSV format. Therefore, publishing the CSV model on the webpage, it is needed to change CSV in RDF file format. Many methods and tools have been proposed for data mapping and publishing, however, most of them are not followed by the W3C recommendations rules. The contribution and goal of this paper are to develop a Semantic approach that can effectively convert CSV data into RDF data with rich semantics and release RDF data on the web using LOD principles. We utilize Semantic Web resources and W3C recommendation rules in automatic data publishing method, which enables distributed system for scalability. We apply the proposed method to existing CSVW Implementation Report-W3C and U.S Government’s application (data.gov). Our experimental results indicate that the proposed approach successfully converts CSV to RDF data and publish those RDF as LOD on the Web, with adequate performance on any sized datasets.
The Impact of Software Fault Prediction in Real-World Application
(Scopus, 2020) Ahmed, Md. Razu; Ali, Md. Asraf; Ahmed, Nasim; Zamal, Md. Fahad Bin; Shamrat, F.M. Javed Mehedi
Software fault prediction and proneness has long been considered as a critical issue for the tech industry and software professionals. In the traditional techniques, it requires previous experience of faults or a faulty module while detecting the software faults inside an application. An automated software fault recovery models enable the software to significantly predict and recover software faults using machine learning techniques. Such ability of the feature makes the software to run more effectively and reduce the faults, time and cost. In this paper, we proposed a software defect predictive development models using machine learning techniques that can enable the software to continue its projected task. Moreover, we used different prominent evaluation benchmark to evaluate the model's performance such as ten-fold cross-validation techniques, precision, recall, specificity, f 1 measure, and accuracy. This study reports a significant classification performance of 98-100% using SVM on three defect datasets in terms of f1 measure. However, software practitioners and researchers can attain independent understanding from this study while selecting automated task for their intended application.