Dereje Regassa

Dr. Dereje Regassa


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 November 2023 in Sensors
Verified
Journal Article
Open access
PDF file
ENEric Nizeyimana
Eric Nizeyimana
DHDamien Hanyurwimfura
Damien Hanyurwimfura
JHJunseok Hwang
Junseok Hwang
JNJimmy Nsenga
Jimmy Nsenga
DRDereje Regassa
Dereje Regassa
Air pollution is a critical problem in densely populated urban areas, with traffic significantly contributing. To mitigate the adverse effects of air pollution on public health and the environment, there is a growing need for the real-time monitoring and detection of pollution spikes in transportation. This paper presents a novel approach to using Internet of Things (IoT) edge networks for the real-time detection of air pollution peaks in transportation, specifically designed for innovative city applications. The proposed system uses IoT sensors in buses, cabs, and private cars. These sensors are equipped with air quality monitoring capabilities, including the measurement of pollutants such as particulate matter (PM2.5 and PM10), nitrogen dioxide (NO2), ozone (O3), sulfur dioxide (SO2), and carbon dioxide (CO2). The sensors continuously collect air quality data and transmit them to edge devices within the transportation infrastructure. The data collected by these sensors are analyzed, and alerts are generated when pollution levels exceed predefined thresholds. By deploying this system within IoT edge networks, transportation authorities can promptly respond to pollution spikes, improving air quality, public health, and environmental sustainability. This paper details the sensor technology, data analysis methods, and the practical implementation of this innovative system, shedding light on its potential for addressing the pressing issue of transportation-related pollution. The proposed IoT edge network for real-time air pollution spike detection in transportation offers significant advantages, including low-latency data processing, scalability, and cost-effectiveness. By leveraging the power of edge computing and IoT technologies, smart cities can proactively monitor and manage air pollution, leading to healthier and more sustainable urban environments.

27 March 2023
Verified
Conference Paper
Open access
DRDereje Regassa
Dereje Regassa
DSDongkyu Sung
Dongkyu Sung
SKSunggon Kim
Sunggon Kim
HYHeonyoung Yeom
Heonyoung Yeom
YSYongseok Son
Yongseok Son
This paper presents an efficient hashing scheme called EHS to improve the performance and space efficiency on PM. In our scheme, we delay expensive rehashing operations by using the free space in buckets maximally. To do this, 1) we search and utilize the available spaces in all the buckets 2) we devise metadata of the bucket to manage and track the available spaces in all the buckets. This scheme enables to delay the full table rehashing and use the full space in the hash table efficiently. We implement and evaluate EHS on a real device such as Intel Optane® DC Persistent Memory (DCPMM). The experiment result shows EHS improves the performance by up to 53% and 14% in the case of insert operation compared with state-of-art schemes such as CCEH and Dash, respectively. It also improves the load factor by up to 91.8% and 87% compared with CCEH and Dash, respectively.

19 May 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DRDereje Regassa
Dereje Regassa
HYHeonyoung Yeom
Heonyoung Yeom
YSYongseok Son
Yongseok Son
Distributed supercomputing is becoming common in different companies and academia. Most of the parallel computing researchers focused on harnessing the power of commodity processors and even internet computers to aggregate their computation powers to solve computationally complex problems. Using flexible commodity cluster computers for supercomputing workloads over a dedicated supercomputer and expensive high-performance computing (HPC) infrastructure is cost-effective. Its scalable nature can make it better employed to the available organizational resources, which can benefit researchers who aim to conduct numerous repetitive calculations on small to large volumes of data to obtain valid results in a reasonable time. In this paper, we design and implement an HPC-based supercomputing facility from commodity computers at an organizational level to provide two separate implementations for cluster-based supercomputing using Hadoop and Spark-based HPC clusters, primarily for data-intensive jobs and Torque-based clusters for Multiple Instruction Multiple Data (MIMD) workloads. The performance of these clusters is measured through extensive experimentation. With the implementation of the message passing interface, the performance of the Spark and Torque clusters is increased by 16.6% for repetitive applications and by 73.68% for computation-intensive applications with a speedup of 1.79 and 2.47 respectively on the HPDA cluster. We conclude that the specific application or job could be chosen to run based on the computation parameters on the implemented clusters.

20 October 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
DRDereje Regassa
Dereje Regassa
HYHeonyoung Yeom
Heonyoung Yeom
JHJunseok Hwang
Junseok Hwang
Recent advancements in memory technology have opened up a wealth of possibilities for innovation in data structures. The emergence of byte-addressable persistent memory (PM) with its impressive capacity and low latency has accelerated the adoption of PM in existing hashing-based indexes. As a result, several new hashing schemes utilizing emulators have been proposed. However, these schemes have proven to be suboptimal, lacking scalability when implemented on real devices. Only a handful of hash table designs have successfully addressed critical properties such as load factor, scalability, efficient memory utilization, and recovery. One of the main challenges in redesigning data structures for an effective hashing scheme in PM is minimizing the overhead associated with dynamic hashing operations in the hash table. To tackle this challenge, this paper introduces ESH, an efficient and scalable hashing scheme that significantly improves memory efficiency, scalability, and overall performance on PM. The ESH scheme maximizes the utilization of the hash table’s available space, thus reducing the frequency of full-table rehashing and improving performance. Consequently, this scheme achieves a high load factor while minimizing the need for rehashing. To evaluate the effectiveness of the ESH scheme, we compare it to widely used dynamic hashing schemes employing similar techniques on Intel Optane® DC persistent memory (DCPMM). The experimental results demonstrate that ESH outperforms CCEH and Dash in terms of data insertion performance, exhibiting a 30% improvement over CCEH and a 4% improvement over Dash. Furthermore, ESH improves the lookup operation by nearly 10% compared to Dash, while achieving a load factor of up to 91%, surpassing its competitors.