Papers by Muhammad Faizan
A lane departure warning system (LDWS) has significant potential to reduce crashes on roads. Most... more A lane departure warning system (LDWS) has significant potential to reduce crashes on roads. Most existing commercial LDWSs use some kind of image processing techniques with or without Global Positioning System (GPS) technology and/or high-resolution digital maps to detect unintentional lane departures. However, the performance of such systems is compromised in unfavorable weather or road conditions, e.g., fog, snow, or irregular road markings. Previously, we proposed and developed an LDWS using a standard GPS receiver without any highresolution digital maps. The previously developed LDWS relies on a road reference heading (RRH) of a given road extracted from an opensource, low-resolution mapping database to detect an unintentional lane departure. This method can detect true lane departures accurately but occasionally gives false alarms, i.e., it can issue lane departure warnings even when a vehicle is within its lane. The false alarms occur due to the inaccuracy of how the RRH originated from an inherent lateral error in open-source, low-resolution maps. To overcome this problem, we proposed and developed a novel algorithm to generate an accurate RRH for a given road using a vehicle's past trajectories on that road. The newly developed algorithm that generates an accurate RRH for any given road has been integrated with the previously developed LDWS and extensively evaluated in the field for detection of unintentional lane departures. The field test results showed that the newly developed RRH Generation algorithm significantly improved the performance of the previously developed LDWS by accurately detecting all true lane departures while practically reducing the frequency of false alarms to zero.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
To date, the amount of data collected are significant and the growth is exponential in various fi... more To date, the amount of data collected are significant and the growth is exponential in various fields over the last decades. Most companies typically address the issue of storage system capacities and therefore such situation creates the issue handling "big data." However, most companies sometimes may find it a challenge to obtain useful knowledge from a large amount of information. As such, numerous organizations are expected to tackle the data-related difficulties. In contrast, there is a necessity to improve and support business processes in progressively changing conditions. Generally, it is possible to analyses the available data and propose improvements because some tools and methods exist to facilitate such cause. Process mining may offer effective approaches to complement the business process. Process mining allows organizations to take advantage of the information within the systems, but can also be used to check process conformance, predict execution challenges, and identify bottlenecks. For instance, healthcare has rapidly changed over decades of research and development. Through scientific discovery, more diseases can be treated. However, it also affects the feasibility of health institutions to accommodate more complicated health treatment processes and systems effectively. Indeed, many solutions exist to cure a particular disease, since machines are becoming further complex, requiring medical staff to be equipped with necessary training. Also, it significantly increases the cost of health care. This paper presents the insights of process mining, highlighting the possible approaches used to gather and analyses the data using feasible method in process mining including real discovery processes. The paper also discusses the challenges of process mining.
Asian Journal of Research in Computer Science, 2020
Data Science emerged as an important discipline and its education is essential for success in alm... more Data Science emerged as an important discipline and its education is essential for success in almost every aspect of life. Here comes the age of Big data. Big data impacts all aspects of our lives and society is admitting it. Data processing and other techniques are combined to convert abundant data into valuable information for society, organizations, and people. Specific strategies and approaches are needed to provide better to educate future data scientists to overcome the challenges of Big data. In this paper, we discussed the general concept of data science, Big data, and areas of Big data computing.
Journal of Network and Computer Applications, 2019
Energy efficient transmission rate regulation of wireless sensing nodes, is a critical issue when... more Energy efficient transmission rate regulation of wireless sensing nodes, is a critical issue when operating in an energy harvesting (EH) enabled environment. In this work, we view the energy management problem as a queue control problem where the objective is to regulate transmission such that the energy level converges to a reference value. We employ a validated non-linear queuing model to derive two non-linear robust throughput controllers. A notable feature of the proposed scheme is its capability of predicting harvest-able energy. The predictions are generated using the proposed Accurate Solar Irradiance prediction Model (ASIM) whose effectiveness in generating accurate both long and short term predictions is demonstrated using real world data. The stability of the proposed controllers is established analytically and the effectiveness of the proposed strategies is demonstrated using simulations conducted on the Network Simulator (NS-3). The proposed policy is successful in guiding the energy level to the reference value, and outperforms the Throughput Optimal (TO) policy in terms of the throughput achieved.
International Journal of Advanced Computer Science and Applications, 2020
In modern scientific research, data analyses are often used as a popular tool across computer sci... more In modern scientific research, data analyses are often used as a popular tool across computer science, communication science, and biological science. Clustering plays a significant role in the reference composition of data analysis. Clustering, recognized as an essential issue of unsupervised learning, deals with the segmentation of the data structure in an unknown region and is the basis for further understanding. Among many clustering algorithms, "more than 100 clustering algorithms known" because of its simplicity and rapid convergence, the K-means clustering algorithm is commonly used. This paper explains the different applications, literature, challenges, methodologies, considerations of clustering methods, and related key objectives to implement clustering with big data. Also, presents one of the most common clustering technique for identification of data patterns by performing an analysis of sample data.
Catalysis Letters
Vanadium phosphorus oxide (VPO) catalysts promoted by phosphorus-based ionic liquids (ILs) as str... more Vanadium phosphorus oxide (VPO) catalysts promoted by phosphorus-based ionic liquids (ILs) as structure directing agent and promoters have been innovatively synthesized and investigated for selective oxidation of n-butane to maleic anhydride (MA). The catalytic performances showed that the IL addition notably improved the n-butane conversion and MA selectivity, during which the optimized 3%IL-VPO catalyst exhibited the maximum MA yield of 59.2% that is much better than that of blank VPO with 49.4% MA yield under the same reaction conditions. XRD, FI-IR, Raman, SEM, TG, BET, XPS and H2-TPR techniques were utilized combinatorically to elaborate the synergistic effect of cations and anions of ILs. Results demonstrated that IL-cations oriented synthesis of VPO precursor showing a vertically intercrossed slice structure morphology having smaller lamellar thickness. Correspondingly, it notably enhanced the specific surface area of the VPO catalysts and exposed the more active surface of (...
Uploads
Papers by Muhammad Faizan