Search

Your search keyword '"Razzaque, Md. Abdur"' showing total 331 results
Start Over Author "Razzaque, Md. Abdur"
331 results on '"Razzaque, Md. Abdur"'

1. Optimizing UAV-UGV Coalition Operations: A Hybrid Clustering and Multi-Agent Reinforcement Learning Approach for Path Planning in Obstructed Environment

Author

Brotee, Shamyo, Kabir, Farhan, Razzaque, Md. Abdur, Roy, Palash, Mamun-Or-Rashid, Md., Hassan, Md. Rafiul, and Hassan, Mohammad Mehedi

Subjects
Computer Science - Robotics, Computer Science - Multiagent Systems
Abstract

One of the most critical applications undertaken by coalitions of Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) is reaching predefined targets by following the most time-efficient routes while avoiding collisions. Unfortunately, UAVs are hampered by limited battery life, and UGVs face challenges in reachability due to obstacles and elevation variations. Existing literature primarily focuses on one-to-one coalitions, which constrains the efficiency of reaching targets. In this work, we introduce a novel approach for a UAV-UGV coalition with a variable number of vehicles, employing a modified mean-shift clustering algorithm to segment targets into multiple zones. Each vehicle utilizes Multi-agent Deep Deterministic Policy Gradient (MADDPG) and Multi-agent Proximal Policy Optimization (MAPPO), two advanced reinforcement learning algorithms, to form an effective coalition for navigating obstructed environments without collisions. This approach of assigning targets to various circular zones, based on density and range, significantly reduces the time required to reach these targets. Moreover, introducing variability in the number of UAVs and UGVs in a coalition enhances task efficiency by enabling simultaneous multi-target engagement. The results of our experimental evaluation demonstrate that our proposed method substantially surpasses current state-of-the-art techniques, nearly doubling efficiency in terms of target navigation time and task completion rate.

Published
2024

12. A Gray Box Interpretable Visual Debugging Approach for Deep Sequence Learning Model

Author

Islam, Md Mofijul, Debnath, Amar, Sayeed, Tahsin Al, Setu, Jyotirmay Nag, Rahman, Md Mahmudur, Sakib, Md Sadman, Razzaque, Md Abdur, Khan, Md. Mosaddek, and Shatabda, Swakkhar

Subjects
Computer Science - Machine Learning, Computer Science - Human-Computer Interaction, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Deep Learning algorithms are often used as black box type learning and they are too complex to understand. The widespread usability of Deep Learning algorithms to solve various machine learning problems demands deep and transparent understanding of the internal representation as well as decision making. Moreover, the learning models, trained on sequential data, such as audio and video data, have intricate internal reasoning process due to their complex distribution of features. Thus, a visual simulator might be helpful to trace the internal decision making mechanisms in response to adversarial input data, and it would help to debug and design appropriate deep learning models. However, interpreting the internal reasoning of deep learning model is not well studied in the literature. In this work, we have developed a visual interactive web application, namely d-DeVIS, which helps to visualize the internal reasoning of the learning model which is trained on the audio data. The proposed system allows to perceive the behavior as well as to debug the model by interactively generating adversarial audio data point. The web application of d-DeVIS is available at ddevis.herokuapp.com.

Published
2018

20. Development and assessment of a fast pyrolysis reactor for bio-oil, syngas and bio-char production from biomass residues

Author

Razzaque, Md Abdur

Subjects
660
Abstract

Design, development and assessment of a Fluidized Bed Reactor (FBR) is a very complex process, where enormous empirical correlations; charts and graphs; lot of parameters, assumptions, unit operations are involved, straight forward design equations and design data are limited, and generally the operation of the system requires many adjustments. The improved design of FBR with high coefficient of performance (COP), low energy consumption, high yield and environmentally friendly (low emission) is the target. The scope of the study is to design and fabrication of a lab scale fluidized bed fast pyrolysis system with throughput capacity of 1 kg of dry biomass per hour which includes a bubbling fluidized bed reactor, 2 cyclone separators in series, 4 condensers in series operating between temperatures of 600-300; 300-200; 200-125 and 125-40˚C to selectively condense alkanes, phenols, aromatics, indene, methyl-indene, benzene, toluene, methyl–naphthalene, esters, acids, alcohols, ketones; 2 heaters (1 pre- and 1 primary), an auger feeder with hopper and controller, blowers and rig structure. A 3-D simulation was performed to facilitate the mounting of different unit operations, instruments and control panels with sufficient maintenance and manoeuvring accessibilities yet compact structure with low structural footprints. The rig is having the dimensions of 2204X2750X1100mm (L x H x W) and suitable for batch operation to produce about 650 gm bio-oil, 150 gm non-condensable and 200 gm bio-char from 1kg of dry biomass pyrolysis. The rig is manually operated, however the data acquisition and logging systems are digital and has provision of scrubbing exhaust gas, and an online analyser has been installed to measure and monitor lower hydrocarbons including hydrogen concentrations and Lower Explosive Limit (LEL) in the exhaust gas. Four types of biomass such as Empty fruit bunch (EFB), Urban tree shavings (UTS), Saw dust Broga (SDB) and Saw dust Semenyih (SDS) were pre-treated with aqueous acidic (H2SO4) and alkaline (NaOH) solutions to find the percentage of solids extraction with varying liquid-solid ratios, acid/alkali concentrations, reaction temperatures and retention time. For pyrolysis operation, UTS was selected among the four biomass samples with a set of pre-treatment parameters (4.81 wt. % H2SO4, 15:1 liquid-solid ratio, 4hr retention time, 70˚C, 100rpm agitation speed) that maximizes bio-oil production. Pyrolysis in a batch tubular furnace at 600˚C with nitrogen flowrate of 30 ml/min resulted in bio-oil yield of 39.43% and 27.67%, and char yield of 38.07% and 30.73% from raw and pre-treated UTS respectively. The semi-batch pyrolysis results were compared with biomass pyrolysis results from the batch pyrolysis rig operations. The catalytic upgrading of the bio-oil to liquid fuel in a batch reactor is ongoing research work. The contribution of this research can be summarised as the successful design, fabrication, testing and operation of a Fluidized Bed System to produce fuel from biomass in batch pyrolysis. Characterization of the feedstock to get the optimum operation condition of the designed FBR to get the best yield out of the system and evaluation of the performance characteristics (Mass and Energy Balance) of the system. Characterization of the products (bio-oil, bio-char and syngas) following standard methods having results comparable with literature.

Published
2016

40. Data security in smart devices: Advancement, constraints and future recommendations.

Author

Wenhua, Zhang, Kamrul Hasan, Mohammad, Ismail, Ahmad Fadzil, Yanke, Zhang, Razzaque, Md Abdur, Islam, Shayla, and Anil kumar, Budati

Subjects
DATA security, COMPUTER network protocols, COMPUTER network security, SECURITY systems, DATA security failures, DATA privacy, SMART devices, COMPUTER networks
Abstract

Network security protocols are implemented to address network security challenges. Computer networks and applications have advanced and developed significantly in recent years, but consumers 'excitement for network technology and high‐tech devices has been dampened by continual exposure to data security vulnerabilities. As of now, some individuals refuse to use smart devices due to concerns about the authenticity, confidentiality and integrity of data security leaks. This not only prompts Internet service providers to follow market protection mechanisms but also requires software developers to apply appropriate security protocols to protect computer network security. These applications' dependability and integrity are dependent not just on the effectiveness of cryptographic algorithms, but also on key management protocols. Understanding network security protocols and implementing high‐quality standards to govern the transmission of data in the network are critical components of guaranteeing network security. The article explores data security, primarily at the application layer, various attack methods for different network security protocols and highlights the potential security implications. The study also looks at the corresponding, practical security measures and future research prospects for certain kinds of attacks. Finally, some technical challenges that remain unsolved at the time of writing are summarised, and future trends in cybersecurity are discussed. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

44. A Hyper Heuristic Algorithm for Efficient Resource Allocation in 5G Mobile Edge Clouds

Author

Laboni, Nadia Motalib, Safa, Sadia Jahangir, Sharmin, Selina, Razzaque, Md. Abdur, Rahman, Md. Mustafizur, and Hassan, Mohammad Mehedi

Abstract

Emergence of intelligent devices and mobile edge clouds (MECs) in 5G networks has exponentially increased the number of applications that demand low latency services. However, their resource heterogeneity, limited computing power and storage including congestion in the ultra-dense 5G network, make the real-time services challenging. Existing works are limited either by addressing application delay requirements or computational load balancing. This article develops an efficient resource allocation framework for selecting optimal servers and routing paths in the 5G MEC network by jointly optimizing latency, computational, and network load variances. First, we formulate the above multi-objective problem as a mixed-integer non-linear programming problem. Further, we adopt a hyper-heuristic (AWSH) algorithm by leveraging the combined powers of Ant Colony, Whale, Sine-Cosine, and Henry Gas Solubility Optimization algorithms. The proposed AWSH algorithm works at the higher level, and it explores and exploits one of the three lower-level heuristics in each iteration to efficiently capture the dynamically varying environmental parameters and thereby address the resource allocation problem. Their collaborative effort helps to achieve a global optimum in allocating resources of 5G MEC network. Simulation results prove the superiority of the AWSH algorithm compared to state-of-the-art solutions in terms of service latency, successful offloading ratio, and load balancing.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results