Browsing by Author "Kashem, Mohammod Abul"

Now showing 1 - 13 of 13

A Modified Throttled Load Balancing Algorithm To Accelerate Cloud System by Reducing Response Time
(Daffodil International University, 23-07-01) Islam, MD. Toufecul; Kashem, Mohammod Abul; Jahan, Tanjina
The load balancing becomes an important factor in maintaining system stability and performance. As an effect, a strategy for improving system performance by balancing workload across Virtual Machines (VMs) is required. To accomplish load balancing and Quality of Service, scheduling algorithms are utilized. The Modified Throttled Load Balancing Algorithm (MTLBA) reduces response time as well as manages and balances load amongst virtual machines. Here used the Cloud Analysts simulation toolkit to test the modified technique. The results of our MTLBA were likened to the existing Throttled Load Balancing Algorithm. The results demonstrated that the suggested MTLBA outperforms existing Throttled algorithms.
A Novel Hybrid Evolutionary Mating Algorithm for Covid19 Confirmed Cases Prediction based on Vaccination
(IEEE, 2023-05-01) Ahmed, Marzia; Mohamad, Ahmad Johari; Rahman, Mostafijur; Sulaiman, Mohd Herwan; Kashem, Mohammod Abul
Microorganisms may cause illness when they enter the body, multiply, and spread to other parts. The rapid spread of COVID-19 to neighboring countries is examined in this research. Anticipating a positive COVID-19 occurrence helps in determining risks and creating countermeasures. As a result, developing robust mathematical models with small error margins for predictions is crucial. Based on these findings, a combined method of evaluating confirmed cases of COVID-19 with universal immunization is recommended. First, the best hyperparameter values of the RBF kernel-based LSSVM (least square support vector machine) were determined using the most recent Evolutionary Mating Algorithm (EMA). After that, LSSVM will complete the task of prediction. This hybrid method has been utilized for time series forecasting in Malaysia since the country's immunization program against COVID-19 got underway. We evaluate our results next to those of well-known methodologies in nature-inspired metaheuristics.
A Proportional Scheduling Protocol for the OFDMA-Based Future Wi-Fi Network
(Daffodil International University, 2022-05-05) Islam, Gazi Zahirul; Kashem, Mohammod Abul
The IEEE 802.11ax (Wi-Fi 6) and IEEE 802.11be (Wi-Fi 7) adopt the OFDMA technology to provide high-speed and uninterrupted communications in the dense network. Until the advent of IEEE 802.11ax standard, Wireless LAN (WLAN) predominantly uses the Random Access (RA) mechanism to access the network. IEEE 802.11ax and IEEE 802.11be (proposed) provide another access mechanism for WLAN (i.e., Wi-Fi), which is known as Scheduled Access (SA). This mechanism utilizes the OFDMA technology to provide high- speed and smooth communications in congested areas. By the way, the performance of the OFDMA-based wireless LAN largely depends on the scheduling protocol. Many researchers propose RA and SA protocols independently, which do not consider the simultaneous implementation of both mechanisms. This paper proposes a Proportional Resource Scheduling (PRS) scheme for the OFDMA-based wireless LAN that simultaneously implements RA and SA mechanisms for data transmission. We design two algorithms for the resource scheduling for the PRS protocol. Algorithm 1 provides the initial scheduling information, which is received by Algorithm 2 as the input. After performing revision, Algorithm 2 provides the final scheduling information to the access point. The PRS distributes the channel resources proportionally to the stations according to their available loads. Thus, it utilizes the resources efficiently and increases the throughput and fairness in accessing the channel. We construct analytical models both for the SA and RA mechanisms and conduct rigorous simulations to measure the efficiency of the PRS protocol. The analyses validate the robustness of the proposed protocol in throughput, goodput, fairness, and retransmissions. The main contribution of the proposed protocol is that it provides a framework for simultaneous implementation of RA and SA mechanisms for the future wireless LAN
An adaptive replication model for heterogeneous systems
(IEEE Xplore, 2015-01-22) Nader-Uz-Zaman, M.; Kashem, Mohammod Abul; Ahmad, R. Badlishah; Rahman, Mostafijur
Data replication is an increasingly important topic as databases are more and more deployed over distributed systems, grid community and clustering systems. The performance, reliability and portability of entire database may possible by using replication technique. Replication may be considered as a data backup policy. Replication in homogeneous system is common practice in real life, but replication in heterogeneous system is quite challenging, because of the dissimilar computing environment. Since the computer environment porn to be heterogeneous, hence it's a promising field for researchers to consider replication in heterogeneous environment. In our research a persistence layer has been proposed for replication in heterogeneous systems. This persistence layer work on asynchronous model, hence it may call as asynchronous replication model. The model works implements multi threading technique for creating parallel connection with peer servers. The main server and replicated server are connected with a common interface. The interface is a replication engine, which intelligently holds data and makes decision depending on different factors for sending data to smoothen the replication process. The whole structure follows the rules of SOA (Service oriented architecture) thus, modification of replication servers do not affect the main server. Finally the architecture of this concept builds on different configurable files. These files help us in system up-gradation without shutting down the system. At the end, some experiments have been carried out and the results have been analyzed. Full Text Link: doi.org/10.1109/ICED.2014.7015771
Analyzing the Quality of Water and Predicting the Suitability for Fish Farming Based on IOT in the Context of Bangladesh
(2019 International Conference on Sustainable Technologies for Industry 4.0 (STI), IEEE, 2019-12) Ahmed, Marzia; Rahaman, Md. Obaidur; Rahman, Mostafijur; Kashem, Mohammod Abul
Nearly 5.3% of the national income of Bangladesh comes from fish. Fishes are the significant natural essentials that help to grow national income, nutrition, reduce the unemployment problem of a country and also earn foreign currency. Furthermore, it's a great source of low cost, high protein and other health beneficiary nutrients comparative to red meat. Nonetheless, to fulfill the expected demand for fish, the existing system and conventional fish farming has been failed to raise the amount of fish needed for the growing population. This paper analyzed the water quality parameters standards for the suitability of fish farming and the causes of fish diseases affected by the parameters through collected ponds data from the different areas of Bangladesh. Several machine learning algorithms have been compared for accuracy for the significance water level and error rate. Logistic regression has been fitted better to train and test part. The prediction has been done to find out whether the new pond's water quality is suitable for fish farming with respect to the value of quality parameters. An empirical IOT based system design has been given to comparing the prediction in the future. Moreover, this research also analyzed the feasible environment parameter and standards for fish growth, the reason, and risk for fish death as well as the growth rate of fish by monitoring the quality parameters of water for fish.
Efficient Resource Allocation in the IEEE 802.11ax Network Leveraging OFDMA Technology
(Daffodil International University, 2022-10-31) Zahirul Islam, Gazi; Kashem, Mohammod Abul
The IEEE 802.11ax pave the way to deliver the high-speed communications in the Wi-Fi network even in the dense areas. In this regard, the most challenging task is to enhance the throughput as IEEE 802.11ax standard promises to provide four times improvement in average throughput per station. Unfortunately, none of the existing protocols could satisfy the demand of the standard yet. The performance of the IEEE 802.11ax protocol largely depends on the efficient and wise scheduling of resource units to the stations. The uplink scheduling is more challenging than the downlink since in the uplink path many stations send data to the access point where the stations must be synchronized for the OFDMA transmissions. This paper innovates an uplink scheduling protocol named Efficient Resource Allocation (ERA) that promises to provide a high-throughput to the Wireless LAN along with the reduction of retransmissions of the packets. The simulations and analyses show that the proposed protocol would be a robust one to satisfy the promises of the latest IEEE 802.11ax standard. To the best of our knowledge, the proposed protocol is the unique one of its kind where the resource units are distributed to the stations according to their available loads.
Efficient Resource Allocation in the IEEE 802.11ax Network Leveraging OFDMA Technology
(Journal of King Saud University - Computer and Information Sciences, 2020-10-31) Islam, Gazi Zahirul; Kashem, Mohammod Abul
The IEEE 802.11ax pave the way to deliver the high-speed communications in the Wi-Fi network even in the dense areas. In this regard, the most challenging task is to enhance the throughput as IEEE 802.11ax standard promises to provide four times improvement in average throughput per station. Unfortunately, none of the existing protocols could satisfy the demand of the standard yet. The performance of the IEEE 802.11ax protocol largely depends on the efficient and wise scheduling of resource units to the stations. The uplink scheduling is more challenging than the downlink since in the uplink path many stations send data to the access point where the stations must be synchronized for the OFDMA transmissions. This paper innovates an uplink scheduling protocol named Efficient Resource Allocation (ERA) that promises to provide a high-throughput to the Wireless LAN along with the reduction of retransmissions of the packets. The simulations and analyses show that the proposed protocol would be a robust one to satisfy the promises of the latest IEEE 802.11ax standard. To the best of our knowledge, the proposed protocol is the unique one of its kind where the resource units are distributed to the stations according to their available loads.
Internet of Things (IoT) based ECG System for Rural Health Care
(Scopus, 2021) Rahman, Md. Obaidur; Kashem, Mohammod Abul; Nayan, Al-Akhir; Akter, Most. Fahmida; Rabbi, Fazly; Ahmed, Marzia; Asaduzzaman, Mohammad
Nearly 30% of the people in the rural areas of Bangladesh are below the poverty level. Moreover, due to the unavailability of modernized healthcare-related technology, nursing and diagnosis facilities are limited for rural people. Therefore, rural people are deprived of proper healthcare. In this perspective, modern technology can be facilitated to mitigate their health problems. ECG sensing tools are interfaced with the human chest, and requisite cardiovascular data is collected through an IoT device. These data are stored in the cloud incorporates with the MQTT and HTTP servers. An innovative IoT-based method for ECG monitoring systems on cardiovascular or heart patients has been suggested in this study. The ECG signal parameters P, Q, R, S, T are collected, pre-processed, and predicted to monitor the cardiovascular conditions for further health management. The machine learning algorithm is used to determine the significance of ECG signal parameters and error rate. The logistic regression model fitted the better agreements between the train and test data. The prediction has been performed to determine the variation of PQRST quality and its suitability in the ECG Monitoring System. Considering the values of quality parameters, satisfactory results are obtained. The proposed IoT-based ECG system reduces the health care cost and complexity of cardiovascular diseases in the future.
Internet of Things Based Electrocardiogram Monitoring System Using Machine Learning Algorithm
(Daffodil International University, 2022-08-08) Rahman, Md. Obaidur; Shamrat, F. M. Javed Mehedi; Kashem, Mohammod Abul; Akte, Most. Fahmida; Chakraborty, Sovon; Ahmed, Marzia; Mustary, Shobnom
In Bangladesh’s rural regions, almost 30% of the population lives in poverty. Rural residents also have restricted access to nursing and diagnostic services due to obsolete healthcare infrastructure. Consequently, as cardiac failure occurs, they usually fail to call the services and adopt the facilities. The internet of things (IoT) offers a massive advantage in addressing cardiac problems. This study proposed a smart IoT-based electrocardiogram (ECG) monitoring systemfor heart patients. The system is divided into several parts: ECG sensing network (data acquisition), IoT cloud (data transmission), result analysis (data prediction) and monetization. P, Q, R, S, and T are ECG signal properties fetched, pre-processed, analyzed and predicted to age level for future health management. ECG data are saved in the cloud and accessible via message queuing telemetry transport (MQTT) and hypertext transfer protocol (HTTP) servers. The linear regression method is utilized to determine the impact of electrocardiogram signal characteristics and error rate. The prediction was made to see how much variation there was in PQRST regularity and its sufficiency to be utilized in an ECG monitoring device. Recognizing the quality parameter values, acceptable outcomes are achieved. The proposed system will diminish future medical costs and difficulties for heart patients.
Internet of Things in Pregnancy Care Coordination and Management: A Systematic Review
(MDPI Publications, 2023-11-23) Hossain, Mohammad Mobarak; Kashem, Mohammod Abul; Islam, Md. Monirul; Sahidullah, Md.; Mumu, Sumona Hoque; Uddin, Jia; Aray, Daniel Gavilanes; Diez, Isabel de la Torre; Ashraf, Imran; Samad, Md Abdus
The Internet of Things (IoT) has positioned itself globally as a dominant force in the technology sector. IoT, a technology based on interconnected devices, has found applications in various research areas, including healthcare. Embedded devices and wearable technologies powered by IoT have been shown to be effective in patient monitoring and management systems, with a particular focus on pregnant women. This study provides a comprehensive systematic review of the literature on IoT architectures, systems, models and devices used to monitor and manage complications during pregnancy, postpartum and neonatal care. The study identifies emerging research trends and highlights existing research challenges and gaps, offering insights to improve the well-being of pregnant women at a critical moment in their lives. The literature review and discussions presented here serve as valuable resources for stakeholders in this field and pave the way for new and effective paradigms. Additionally, we outline a future research scope discussion for the benefit of researchers and healthcare professionals.
IOT Based Risk Level Prediction Model for Maternal Health Care in the Context of Bangladesh
(2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI), IEEE, 2020-12) Ahmed, Marzia; Kashem, Mohammod Abul
Internet of Things (IoT), a new paradigm has the extensive applicability including healthcare and numerous areas. In this research, a system has been developed for effective monitoring and predicting risk level of a pregnant women, in the context of Bangladesh. This system will analyzed the health data and risk factors of pregnant women to identify the risk intensity level. The United Nations goal is primarily concern about improving maternal health, reducing maternal and child mortality by 2030; however the rate is not declining up to the indication. This research intended to use respective analytical tools and machine learning algorithms for discovering the risk level on the basis of risk factors in pregnancy. In this research, a maternal health data set has been prepared from different sources (IoT device, Web portal, Hospitals in Bangladesh). This data set been also stored in the local server and as usual as in the cloud server as CSV(comma-separated value). For the analysis of risk factors, categorize and classifying approaches has been used according to the intensity of risk. After comparing among some groups of the machine learning algorithm, in case of classification and prediction of the risk level shows that Modified Decision Tree Algorithm gives the highest accuracy and the numeric value of this accuracy is 97%. A web application has also been developed as a crowd sourced platform to get feedback on different important suggestions and recommendations from corresponding stakeholders, which can also create as test data for further use.
Monitoring Water Quality Metrics of Ponds With IoT Sensors and Machine Learning To Predict Fish Species Survival
(Elsevier, 2023-10-15) Islam, Md. Monirul; Kashem, Mohammod Abul; Alyami, Salem A.; Moni, Mohammad Ali
Aquaculture involves cultivating various marine and freshwater aquatic creatures within regulated environments. Monitoring the aquatic environmental conditions in real-time is crucial for successful fish farming. The Internet of Things (IoT) offers significant potential for real-time monitoring, and this paper introduces an IoT framework designed for efficient monitoring and effective control of various water-related aquatic environmental parameters. The proposed system is implemented as an embedded system utilizing sensors and an Arduino microcontroller. In cultivating pond water, diverse sensors such as pH, temperature, and turbidity sensors are deployed, with each sensor connected to an Arduino Uno-based microcontroller board. These sensors collect data from the water, which is then stored as a CSV file in an IoT cloud platform called ThingSpeak through the Arduino microcontroller. To gather data for analysis, we conducted measurements across five ponds, varying in size and environmental conditions. After getting the real-time data, we compared our experimental results with the standard reference values. As a result, we could take the decision of whether a pond is suitable for cultivating fish or not. After that, we labeled the data with 11 fish categories: Katla, sing, prawn, shrimp, rui, tilapia, pangas, karpio, magur, silver carp, and koi. The data was analyzed using 10 machine learning (ML) algorithms, including J48, Random Forest, K Nearest Neighbors (K-NN), K*, Logistic Model Tree (LMT), Reduced Error Pruning Tree (REPTree), Jumping Rule Inference with Pruned Search (JRIP), Partial Decision Trees (PART), Decision Table, and Logit boost. After experimental analyses, it was discovered that only three of the five ponds were ideal for fish farming, and those three ponds only met the required standards for pH, Temperature, Turbidity, and Conductivity. Among the state-of-art machine learning algorithms, Random Forest achieved the highest score of performance metrics as accuracy 94.42%, kappa statistics 93.5%, and Avg. TP Rate 94.4%. In addition, we calculated the Biochemical Oxygen Demand (BOD), Chemical Oxygen Demand (COD), and Dissolved Oxygen (DO) for one scenario. This study includes prototype hardware details of the proposed IoT system.
Review and Analysis of Risk Factor of Maternal Health in Remote Area Using the Internet of Things (IoT)
(Scopus, 2020) Ahmed, Marzia; Kashem, Mohammod Abul; Rahman, Mostafijur; Khatun, Sabira
IoT is the greatest ingenious innovation in the modern era, which can exploit also in mission-critical like the healthcare industry. This paper demonstrates effective monitoring of pregnant women mostly in a rural area of a developing country, with the help of wearable sensing enabled technology, which also notifies the pregnant women and her family about the health conditions. There are many researchers have been researched to reduce the maternal and fetal mortality but the mortality rate is not reducing, where it should be in zero tolerance. This research intended to use machine learning algorithms for discovering the risk level on the basis of risk factors in pregnancy. In this research, an existing dataset (Pima-Indian-diabetes dataset) has been used for the analysis of risk factor and comparison of some machine learning algorithm shows that Logistic Model Tree (LMT) gives the highest accuracy in case of classification and prediction of the risk level. Regardless, few selected pregnant women’s data has been collected (through IoT enabled devices) and the same process also applied for this dataset also by using LMT. Comparison results show that the prediction of risks is the same for the existing and real dataset.