Sinarwati Mohamad Suhaili | Universiti Malaysia Sarawak (UNIMAS) (original) (raw)

Papers by Sinarwati Mohamad Suhaili

Mağallaẗ baġdād li-l-ʿulūm, Feb 25, 2024

International Journal of Advanced Computer Science and Applications

During emergency operations in Disaster Management System (DMS) for natural and man-made disaster... more During emergency operations in Disaster Management System (DMS) for natural and man-made disasters, any breakdown in the existing information and communication technology will affect the aspect of effectiveness and efficiency on an emergency response task. For Vehicular Ad-hoc Sensor Network (VASNET), the limitation in terms of infrastructure that consists of RSU (Roadside Sensor Unit) may partially or fully destroy the post-disaster scenario. As such, performance degradation of VASNET affects the network infrastructure on high packet loss, delay, and produce a huge amount of energy consumption in DMS. Thus, modification of VASNET and integrate with Internet of Thing (IoT) technology is a must to improve and solving the current problem on VASNET technology. Therefore, the main objective of this study was to investigate the performance of the proposed modified VASNET framework integrated with IoT at DMS in terms of energy consumption and packet loss. A suggested node in the proposed framework was introduced to implement low data rate and high data rate in evaluating the proposed framework using LTE and LTE-A transmission protocol. It was found that LTE-A contributes more energy by 25.33 (mJ/Byte) compared to LTE on 20 (mJ/Byte) on a high data rate. On the other hand, in terms of low data rate, LTE-A influences the most on the proposed framework by recording 19.82(mJ/Byte), LTE only 19.33 (mJ/Byte). For packet loss, LTE shows a high packet loss rate by contributing 11.39% compared to LTE-A, which is 8.0% in terms of low data rate, and 14.80% compared to LTE-A, only 11.97% for high data rate. Consequently, LTE-A on high data rate contributes more energy consumption and LTE in packet loss on same data rate.

2018 IEEE Conference on Wireless Sensors (ICWiSe)

The use of low power sensor nodes to collect useful sensing information effectively is critical f... more The use of low power sensor nodes to collect useful sensing information effectively is critical for any wireless sensor network (WSN) application to last longer. To increase network lifetime, energy consumption is considered as one of an essential performance metric. Most of the current proposed routing protocols proposed to reduce the amount of energy consumed and to increase the network lifetime. The common pioneer hierarchical routing protocol for wsn such as Low Energy Adaptive Cluster Hierarchical Routing (LEACH) is also proposed to improve the energy efficiency of WSN. LEACH is a cluster based routing protocol in which sensor nodes are combined together to form separate clusters and every cluster has a leader node named cluster head (CH). In this paper, we have done the analytical study of LEACH protocol to identify to what extent LEACH protocol can perform in terms of average energy consumption and packet loss for different data rate.

The design of any routing protocols for Mobile Ad-hoc Sensor Networks (MASNETs) is a complex issu... more The design of any routing protocols for Mobile Ad-hoc Sensor Networks (MASNETs) is a complex issue because of the diversity of their potential applications that are constrained by power sources and dynamic mobile networks. These characteristics impose a new demand on the routing protocol which is a consequence of the mobile nodes. A mobile node can change position quite frequently, which means that we need a routing protocol that quickly adapts to topology changes. Using AODV routing protocol in MASNETs’ application shows degradation in network performance due to high density and speed of mobile nodes. In this paper, through extensive simulation we evaluated the capability of Ad-hoc On-Demand Distance Vector (AODV) routing protocol on how far it can react to network topology change in MASNETs. We present the analysis of the impact of mobile nodes on the average percentage of packet loss with different speed, density and route update interval (RUI) of mobile nodes. Our performance st...

Journal of Telecommunication, Electronic and Computer Engineering, 2017

Mobile ad-hoc and sensor network (MASNET) is a collection of mobile sensor nodes connected via wi... more Mobile ad-hoc and sensor network (MASNET) is a collection of mobile sensor nodes connected via wireless links which can dynamically establish a temporary network of their own, when required, without relying on pre-existing infrastructure. However, mobility of the nodes poses some substantial threats in the network such as power draining and frequent change of the network topology. Due to the dynamic nature of this network, routing of packets is very challenging. Keeping this in mind, we have carried out an extensive survey on various state-of-the-art cluster based routing techniques for MASNET .In this paper, a comprehensive survey on cluster based routing protocols in MASNET are presented with focus on the advantages and disadvantages of each routing protocol. Energy consumption, end-to-end delay, throughput, and packet delivery ratio are some of the parameters that play a significant role in determining whether a routing protocol is efficient or not.

Advanced Science Letters, 2017

Mobile Ad-hoc and Sensor Networks (MASNETs) are energy constrained networks which have been the f... more Mobile Ad-hoc and Sensor Networks (MASNETs) are energy constrained networks which have been the focus of many recent research and development efforts. In MASNETs, the network topologies are frequently change due to the moving sensor nodes that have low radio frequency coverage which make the design and implementation of a routing protocol in this networks very challenging. Thus, the Dynamic Energy Savvy (DES-AODV) routing algorithm is proposed to enhance the performance of Ad-hoc On Demand Distance Vector (AODV) by changing the routing metric from hop count to estimated distance that is based on the Received Signal Strength Indicator (RSSI) values. The performance of DES-AODV is evaluated and compared with the existing AODV in terms of the average percentage of packet loss and energy consumption with the density of mobile nodes. The simulation results show that the proposed DES-AODV outperforms the existing AODV in both percentage of packet loss and energy consumption. © 2017 American Scientific Publishers All rights reserved.

2015 9th International Conference on IT in Asia (CITA), 2015

The rapid development of wireless communication technologies and portable mobile devices such as ... more The rapid development of wireless communication technologies and portable mobile devices such as laptops, PDAs, smart phones and wireless sensors brings the best out of mobile computing particularly mobile ad-hoc and sensor networks. Nowadays, most of researchers working on Wireless Sensor Networks (WSNs) focus on Mobile Ad-hoc and Sensor Networks (MASNETs) due to their wide range of potential applications ranging from underwater monitoring to search and rescue mobile robotics applications. In this research work, through extensive simulation, we have evaluated the capability of Ad-hoc On Demand Distance Vector (AODV) routing protocol on how far it can react to different mobility duration of mobile nodes in MASNETs. The performance of AODV is investigated in terms of the average percentage of packet loss and energy consumption. The initial performance study demonstrates that the performance of AODV is signicantly decreased in mobile environment due to the frequent topology change in MASNETs. Therefore, in order to enhance the performance of AODV in MASNETs, the new routing algorithm based on the estimated distance is proposed to replace the hop count for the selection of next node during the packet transmission. The estimated distance is computed based on the Received Signal Strength Indicator (RSSI) values that are collected during the communication between the sensor nodes. The performance of the proposed solution is also further evaluated and compared with the existing AODV routing protocol in term of their energy consumption and percentage of packet loss. Our study demonstrates that the proposed solution outperform the existing AODV in MASNETs.

2015 9th International Conference on IT in Asia (CITA), 2015

IET International Conference on Wireless Communications and Applications (ICWCA 2012), 2012

Saving energy is a very critical issue in wireless sensor networks (WSNs) because sensor nodes ha... more Saving energy is a very critical issue in wireless sensor networks (WSNs) because sensor nodes have a severe resource constraints such as lack of processing power and limited in power supply. Since the communication is the most energy consuming activities in WSNs, the power use for transmission or reception of packet should be managed properly. Transmission power control (TPC) technique is one of the techniques to reduce energy consumption which has been widely studied in mobile ad-hoc networks (MANETs). This technique is implemented by adjusting the transmission power in communication between nodes. However, as mobile wireless sensor networks (MWSNs) applications emerge, the unique characteristics of this network such as severe resource constraints and frequent topology change suggest that TPC might be useful to reduce energy consumption in MWSN. Therefore, we investigate the impact of TPC on Ad hoc On-Demand Distance Vector (AODV) routing protocol for MWSNs. AODV is used as a medium of communication to assist the investigation of the effects of TPC in multihop communication in MWSNs. The simulation results show that the implementation of TPC technique has some impact on MWSNs in respect to transmission energy consumption and transmission power level required at low node mobility.

Procedia Engineering, 2012

Preserving energy is a very critical issue in mobile ad-hoc sensor networks (MASNETs) because sen... more Preserving energy is a very critical issue in mobile ad-hoc sensor networks (MASNETs) because sensor nodes have a severe resource constraints due to their lack of processing power and limited in power supply. Since the communication is the most energy consuming activities in MASNETs, the power use for transmission or reception of packet should be managed as much as possible. One way to reduce energy consumption is by applying transmission power control (TPC) technique to adjust the transmission power in communication between nodes. This technique has been widely studied in MASNETs. However, as MASNET applications emerge, the unique characteristics of this network such as severe resource constraints and frequent topology change suggest that TPC might be useful to reduce energy consumption in MASNETs. Therefore, we investigate different effects of TPC on Ad hoc On-Demand Distance Vector (AODV) routing protocols for MASNETs. AODV is used as a medium of communication to assist the investigation of the effects of TPC in multihop communication in this networks with Random Way Point (RWP) mobility model. Our simulation results show a noticeable effects of TPC implementation technique on MASNETs in respect to transmission energy consumption and packet received ratio at low node mobility. These results support the use of TPC technique to enhance the performance of multihop AODV routing protocol in MASNETs.

International Journal of Advanced Computer Science and Applications

Companies constantly rely on customer support to deliver pre-and post-sale services to their clie... more Companies constantly rely on customer support to deliver pre-and post-sale services to their clients through websites, mobile devices or social media platforms such as Twitter. In assisting customers, companies employ virtual service agents (chatbots) to provide support via communication devices. The primary focus is to automate the generation of conversational chat between a computer and a human by constructing virtual service agents that can predict appropriate and automatic responses to customers' queries. This paper aims to present and implement a seq2seq-based learning task model based on encoder-decoder architectural solutions by training generative chatbots on customer support Twitter datasets. The model is based on deep Recurrent Neural Networks (RNNs) structures which are uni-directional and bi-directional encoder types of Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU). The RNNs are augmented with an attention layer to focus on important information between input and output sequences. Word level embedding such as Word2Vec, GloVe, and FastText are employed as input to the model. Incorporating the base architecture, a comparative analysis is applied where baseline models are compared with and without the use of attention as well as different types of input embedding for each experiment. Bilingual Evaluation Understudy (BLEU) was employed to evaluate the model's performance. Results revealed that while biLSTM performs better with Glove, biGRU operates better with FastText. Thus, the finding significantly indicated that the attention-based, bi-directional RNNs (LSTM or GRU) model significantly outperformed baseline approaches in their BLEU score as a promising use in future works.

This research project is about the innovation of a teaching and learning approach with the integr... more This research project is about the innovation of a teaching and learning approach with the integration of augmented reality as the tool and the subject, named design-based learning (DBL), aimed to empower pre-university students’ learning performance and motivation. Across three lecture groups (n1 = 114, n2 = 98, n3 = 95), there is an increased in mean marks between two tests conducted prior to and post of DBL. The mean scores for learning motivation captured using instructional materials motivation survey (IMMS) for attention, relevance, confidence and satisfaction model are all above average of 3 out of 5

Chatbot is an artificial intelligent application that can converse with a user through textual or... more Chatbot is an artificial intelligent application that can converse with a user through textual or auditory method. The chatbot can give a response according to their characteristic and domain knowledge. This study aims to evaluate the use of chatbot named eLVA among students at the Centre for Pre University Studies. A series of 10 questions was distributed to 40 students to evaluate the use of eLVA after they have experienced it. The results indicated that chatbot are most likely to be very helpful in teaching and learning because it has helped students getting an instant response. However, results showed that the main reason for students to stop using chatbot involved getting incorrect information and worried about Chatbot making mistakes. The result further show that there is no significant difference in the use of eLVa between male and female students. The study also found that there is no significant correlation between study program (Physical Sciences/Life Sciences) towards the...

Expert Systems with Applications

2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), 2014

2012 International Conference on Advanced Computer Science Applications and Technologies (ACSAT), 2012

Mobile ad-hoc sensor networks (MASNETs) have recently become an important area of research for Mo... more Mobile ad-hoc sensor networks (MASNETs) have recently become an important area of research for Mobile adhoc networks (MANETs) researchers. The increasing capabilities and the decreasing costs of sensors make MASNETs applications possible to be deployed in real world. However, before such application can be deployed, their performance need to be measured first. But, the use of real-world measurement is costly and time consuming. Therefore, it is more economical and practical to use simulation tools to simulate MASNETs applications. Although, there are many existing simulation tools for MANETs, most of them are not suitable for MASNETs due to resource-constraint of such networks. Therefore, it is essential to have a survey of the existing simulation tools for MASNETs. In this paper, the comparative study on different simulation tools is conducted to identify the most appropriate tool for MASNETs.

2013 1st International Conference on Artificial Intelligence, Modelling and Simulation, 2013

In recent years, extensive research has been conducted on Wireless Sensor Networks (WSNs) due to ... more In recent years, extensive research has been conducted on Wireless Sensor Networks (WSNs) due to their wide range of potential applications ranging from commercial to critical military and health care applications. For most of these applications, security is an important requirement. However, security mechanisms in WSNs differ from traditional ad-hoc networks due to their energy and resource constraints. Due to these constraints, the sensor nodes are vulnerable to security threats because the traditional security measures are not enough to protect these nodes during information dissemination in WSNs. Thus, in this paper we have studied TinySec security measures; Authentication-only (TinySec-Auth) and Authentication Encryption (TinySec-AE) in order to evaluate the suitability of these security measures for WSN applications. We have evaluated these TinySec mechanisms in terms of packet transmission time, average number of packet received and energy consumption. The simulation results show that TinySec-AE consumed more energy and required more time to transmit packet in comparing to TinySec-Auth due to higher computational time and longer packet size for extra encryption mechanism.

2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), Dec 1, 2014

Recently, the increasing number of chemical com pound datasets to be screened has been growing ra... more Recently, the increasing number of chemical com pound datasets to be screened has been growing rapidly due to the fast developments of high-throughput screening in drug discovery. These compound datasets requires compound selection methods which have become one of the main technique in drug discovery especially in drug lead identification process. Thus, finding the best method in compound selection is needed to the pharmaceutical industry to ensure the accurate results of this process. One of most used compound selection method is cluster based compound selection, which involves subdividing a set of compounds into clusters and choosing one compound or a small number of compounds from each cluster. In this cluster-based compound selection, non-overlapping methods such as Ward's, Group Average, Jarvis Patrick's and K-means are preferred methods to cluster the diverse set of compounds. However, there are little study on overlapping method such as fuzzy c mean (FCM) and fuzzy c-varieties (FCV) clustering algorithms. Therefore, these two clustering algorithms are applied and their performance is compared based on the effectiveness of the clustering results in terms of separation between actives and inactives (Pa) into different clusters and mean intercluster molecular dissimilarity (MIMDS). The analysis shows FCM gives the best results compare to FCV in terms of Pa indicating that FCM has a promising use in compound selection algorithms. But, FCV is perform better than the FCM in term of MIMDS when a higher number of compounds and higher fuzziness index value are concerned.

Mağallaẗ baġdād li-l-ʿulūm, Feb 25, 2024

International Journal of Advanced Computer Science and Applications

During emergency operations in Disaster Management System (DMS) for natural and man-made disaster... more During emergency operations in Disaster Management System (DMS) for natural and man-made disasters, any breakdown in the existing information and communication technology will affect the aspect of effectiveness and efficiency on an emergency response task. For Vehicular Ad-hoc Sensor Network (VASNET), the limitation in terms of infrastructure that consists of RSU (Roadside Sensor Unit) may partially or fully destroy the post-disaster scenario. As such, performance degradation of VASNET affects the network infrastructure on high packet loss, delay, and produce a huge amount of energy consumption in DMS. Thus, modification of VASNET and integrate with Internet of Thing (IoT) technology is a must to improve and solving the current problem on VASNET technology. Therefore, the main objective of this study was to investigate the performance of the proposed modified VASNET framework integrated with IoT at DMS in terms of energy consumption and packet loss. A suggested node in the proposed framework was introduced to implement low data rate and high data rate in evaluating the proposed framework using LTE and LTE-A transmission protocol. It was found that LTE-A contributes more energy by 25.33 (mJ/Byte) compared to LTE on 20 (mJ/Byte) on a high data rate. On the other hand, in terms of low data rate, LTE-A influences the most on the proposed framework by recording 19.82(mJ/Byte), LTE only 19.33 (mJ/Byte). For packet loss, LTE shows a high packet loss rate by contributing 11.39% compared to LTE-A, which is 8.0% in terms of low data rate, and 14.80% compared to LTE-A, only 11.97% for high data rate. Consequently, LTE-A on high data rate contributes more energy consumption and LTE in packet loss on same data rate.

2018 IEEE Conference on Wireless Sensors (ICWiSe)

The use of low power sensor nodes to collect useful sensing information effectively is critical f... more The use of low power sensor nodes to collect useful sensing information effectively is critical for any wireless sensor network (WSN) application to last longer. To increase network lifetime, energy consumption is considered as one of an essential performance metric. Most of the current proposed routing protocols proposed to reduce the amount of energy consumed and to increase the network lifetime. The common pioneer hierarchical routing protocol for wsn such as Low Energy Adaptive Cluster Hierarchical Routing (LEACH) is also proposed to improve the energy efficiency of WSN. LEACH is a cluster based routing protocol in which sensor nodes are combined together to form separate clusters and every cluster has a leader node named cluster head (CH). In this paper, we have done the analytical study of LEACH protocol to identify to what extent LEACH protocol can perform in terms of average energy consumption and packet loss for different data rate.

The design of any routing protocols for Mobile Ad-hoc Sensor Networks (MASNETs) is a complex issu... more The design of any routing protocols for Mobile Ad-hoc Sensor Networks (MASNETs) is a complex issue because of the diversity of their potential applications that are constrained by power sources and dynamic mobile networks. These characteristics impose a new demand on the routing protocol which is a consequence of the mobile nodes. A mobile node can change position quite frequently, which means that we need a routing protocol that quickly adapts to topology changes. Using AODV routing protocol in MASNETs’ application shows degradation in network performance due to high density and speed of mobile nodes. In this paper, through extensive simulation we evaluated the capability of Ad-hoc On-Demand Distance Vector (AODV) routing protocol on how far it can react to network topology change in MASNETs. We present the analysis of the impact of mobile nodes on the average percentage of packet loss with different speed, density and route update interval (RUI) of mobile nodes. Our performance st...

Journal of Telecommunication, Electronic and Computer Engineering, 2017

Mobile ad-hoc and sensor network (MASNET) is a collection of mobile sensor nodes connected via wi... more Mobile ad-hoc and sensor network (MASNET) is a collection of mobile sensor nodes connected via wireless links which can dynamically establish a temporary network of their own, when required, without relying on pre-existing infrastructure. However, mobility of the nodes poses some substantial threats in the network such as power draining and frequent change of the network topology. Due to the dynamic nature of this network, routing of packets is very challenging. Keeping this in mind, we have carried out an extensive survey on various state-of-the-art cluster based routing techniques for MASNET .In this paper, a comprehensive survey on cluster based routing protocols in MASNET are presented with focus on the advantages and disadvantages of each routing protocol. Energy consumption, end-to-end delay, throughput, and packet delivery ratio are some of the parameters that play a significant role in determining whether a routing protocol is efficient or not.

Advanced Science Letters, 2017

Mobile Ad-hoc and Sensor Networks (MASNETs) are energy constrained networks which have been the f... more Mobile Ad-hoc and Sensor Networks (MASNETs) are energy constrained networks which have been the focus of many recent research and development efforts. In MASNETs, the network topologies are frequently change due to the moving sensor nodes that have low radio frequency coverage which make the design and implementation of a routing protocol in this networks very challenging. Thus, the Dynamic Energy Savvy (DES-AODV) routing algorithm is proposed to enhance the performance of Ad-hoc On Demand Distance Vector (AODV) by changing the routing metric from hop count to estimated distance that is based on the Received Signal Strength Indicator (RSSI) values. The performance of DES-AODV is evaluated and compared with the existing AODV in terms of the average percentage of packet loss and energy consumption with the density of mobile nodes. The simulation results show that the proposed DES-AODV outperforms the existing AODV in both percentage of packet loss and energy consumption. © 2017 American Scientific Publishers All rights reserved.

2015 9th International Conference on IT in Asia (CITA), 2015

The rapid development of wireless communication technologies and portable mobile devices such as ... more The rapid development of wireless communication technologies and portable mobile devices such as laptops, PDAs, smart phones and wireless sensors brings the best out of mobile computing particularly mobile ad-hoc and sensor networks. Nowadays, most of researchers working on Wireless Sensor Networks (WSNs) focus on Mobile Ad-hoc and Sensor Networks (MASNETs) due to their wide range of potential applications ranging from underwater monitoring to search and rescue mobile robotics applications. In this research work, through extensive simulation, we have evaluated the capability of Ad-hoc On Demand Distance Vector (AODV) routing protocol on how far it can react to different mobility duration of mobile nodes in MASNETs. The performance of AODV is investigated in terms of the average percentage of packet loss and energy consumption. The initial performance study demonstrates that the performance of AODV is signicantly decreased in mobile environment due to the frequent topology change in MASNETs. Therefore, in order to enhance the performance of AODV in MASNETs, the new routing algorithm based on the estimated distance is proposed to replace the hop count for the selection of next node during the packet transmission. The estimated distance is computed based on the Received Signal Strength Indicator (RSSI) values that are collected during the communication between the sensor nodes. The performance of the proposed solution is also further evaluated and compared with the existing AODV routing protocol in term of their energy consumption and percentage of packet loss. Our study demonstrates that the proposed solution outperform the existing AODV in MASNETs.

2015 9th International Conference on IT in Asia (CITA), 2015

IET International Conference on Wireless Communications and Applications (ICWCA 2012), 2012

Saving energy is a very critical issue in wireless sensor networks (WSNs) because sensor nodes ha... more Saving energy is a very critical issue in wireless sensor networks (WSNs) because sensor nodes have a severe resource constraints such as lack of processing power and limited in power supply. Since the communication is the most energy consuming activities in WSNs, the power use for transmission or reception of packet should be managed properly. Transmission power control (TPC) technique is one of the techniques to reduce energy consumption which has been widely studied in mobile ad-hoc networks (MANETs). This technique is implemented by adjusting the transmission power in communication between nodes. However, as mobile wireless sensor networks (MWSNs) applications emerge, the unique characteristics of this network such as severe resource constraints and frequent topology change suggest that TPC might be useful to reduce energy consumption in MWSN. Therefore, we investigate the impact of TPC on Ad hoc On-Demand Distance Vector (AODV) routing protocol for MWSNs. AODV is used as a medium of communication to assist the investigation of the effects of TPC in multihop communication in MWSNs. The simulation results show that the implementation of TPC technique has some impact on MWSNs in respect to transmission energy consumption and transmission power level required at low node mobility.

Procedia Engineering, 2012

Preserving energy is a very critical issue in mobile ad-hoc sensor networks (MASNETs) because sen... more Preserving energy is a very critical issue in mobile ad-hoc sensor networks (MASNETs) because sensor nodes have a severe resource constraints due to their lack of processing power and limited in power supply. Since the communication is the most energy consuming activities in MASNETs, the power use for transmission or reception of packet should be managed as much as possible. One way to reduce energy consumption is by applying transmission power control (TPC) technique to adjust the transmission power in communication between nodes. This technique has been widely studied in MASNETs. However, as MASNET applications emerge, the unique characteristics of this network such as severe resource constraints and frequent topology change suggest that TPC might be useful to reduce energy consumption in MASNETs. Therefore, we investigate different effects of TPC on Ad hoc On-Demand Distance Vector (AODV) routing protocols for MASNETs. AODV is used as a medium of communication to assist the investigation of the effects of TPC in multihop communication in this networks with Random Way Point (RWP) mobility model. Our simulation results show a noticeable effects of TPC implementation technique on MASNETs in respect to transmission energy consumption and packet received ratio at low node mobility. These results support the use of TPC technique to enhance the performance of multihop AODV routing protocol in MASNETs.

International Journal of Advanced Computer Science and Applications

Companies constantly rely on customer support to deliver pre-and post-sale services to their clie... more Companies constantly rely on customer support to deliver pre-and post-sale services to their clients through websites, mobile devices or social media platforms such as Twitter. In assisting customers, companies employ virtual service agents (chatbots) to provide support via communication devices. The primary focus is to automate the generation of conversational chat between a computer and a human by constructing virtual service agents that can predict appropriate and automatic responses to customers' queries. This paper aims to present and implement a seq2seq-based learning task model based on encoder-decoder architectural solutions by training generative chatbots on customer support Twitter datasets. The model is based on deep Recurrent Neural Networks (RNNs) structures which are uni-directional and bi-directional encoder types of Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU). The RNNs are augmented with an attention layer to focus on important information between input and output sequences. Word level embedding such as Word2Vec, GloVe, and FastText are employed as input to the model. Incorporating the base architecture, a comparative analysis is applied where baseline models are compared with and without the use of attention as well as different types of input embedding for each experiment. Bilingual Evaluation Understudy (BLEU) was employed to evaluate the model's performance. Results revealed that while biLSTM performs better with Glove, biGRU operates better with FastText. Thus, the finding significantly indicated that the attention-based, bi-directional RNNs (LSTM or GRU) model significantly outperformed baseline approaches in their BLEU score as a promising use in future works.

This research project is about the innovation of a teaching and learning approach with the integr... more This research project is about the innovation of a teaching and learning approach with the integration of augmented reality as the tool and the subject, named design-based learning (DBL), aimed to empower pre-university students’ learning performance and motivation. Across three lecture groups (n1 = 114, n2 = 98, n3 = 95), there is an increased in mean marks between two tests conducted prior to and post of DBL. The mean scores for learning motivation captured using instructional materials motivation survey (IMMS) for attention, relevance, confidence and satisfaction model are all above average of 3 out of 5

Chatbot is an artificial intelligent application that can converse with a user through textual or... more Chatbot is an artificial intelligent application that can converse with a user through textual or auditory method. The chatbot can give a response according to their characteristic and domain knowledge. This study aims to evaluate the use of chatbot named eLVA among students at the Centre for Pre University Studies. A series of 10 questions was distributed to 40 students to evaluate the use of eLVA after they have experienced it. The results indicated that chatbot are most likely to be very helpful in teaching and learning because it has helped students getting an instant response. However, results showed that the main reason for students to stop using chatbot involved getting incorrect information and worried about Chatbot making mistakes. The result further show that there is no significant difference in the use of eLVa between male and female students. The study also found that there is no significant correlation between study program (Physical Sciences/Life Sciences) towards the...

Expert Systems with Applications

2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), 2014

2012 International Conference on Advanced Computer Science Applications and Technologies (ACSAT), 2012

Mobile ad-hoc sensor networks (MASNETs) have recently become an important area of research for Mo... more Mobile ad-hoc sensor networks (MASNETs) have recently become an important area of research for Mobile adhoc networks (MANETs) researchers. The increasing capabilities and the decreasing costs of sensors make MASNETs applications possible to be deployed in real world. However, before such application can be deployed, their performance need to be measured first. But, the use of real-world measurement is costly and time consuming. Therefore, it is more economical and practical to use simulation tools to simulate MASNETs applications. Although, there are many existing simulation tools for MANETs, most of them are not suitable for MASNETs due to resource-constraint of such networks. Therefore, it is essential to have a survey of the existing simulation tools for MASNETs. In this paper, the comparative study on different simulation tools is conducted to identify the most appropriate tool for MASNETs.

2013 1st International Conference on Artificial Intelligence, Modelling and Simulation, 2013

In recent years, extensive research has been conducted on Wireless Sensor Networks (WSNs) due to ... more In recent years, extensive research has been conducted on Wireless Sensor Networks (WSNs) due to their wide range of potential applications ranging from commercial to critical military and health care applications. For most of these applications, security is an important requirement. However, security mechanisms in WSNs differ from traditional ad-hoc networks due to their energy and resource constraints. Due to these constraints, the sensor nodes are vulnerable to security threats because the traditional security measures are not enough to protect these nodes during information dissemination in WSNs. Thus, in this paper we have studied TinySec security measures; Authentication-only (TinySec-Auth) and Authentication Encryption (TinySec-AE) in order to evaluate the suitability of these security measures for WSN applications. We have evaluated these TinySec mechanisms in terms of packet transmission time, average number of packet received and energy consumption. The simulation results show that TinySec-AE consumed more energy and required more time to transmit packet in comparing to TinySec-Auth due to higher computational time and longer packet size for extra encryption mechanism.

2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), Dec 1, 2014

Recently, the increasing number of chemical com pound datasets to be screened has been growing ra... more Recently, the increasing number of chemical com pound datasets to be screened has been growing rapidly due to the fast developments of high-throughput screening in drug discovery. These compound datasets requires compound selection methods which have become one of the main technique in drug discovery especially in drug lead identification process. Thus, finding the best method in compound selection is needed to the pharmaceutical industry to ensure the accurate results of this process. One of most used compound selection method is cluster based compound selection, which involves subdividing a set of compounds into clusters and choosing one compound or a small number of compounds from each cluster. In this cluster-based compound selection, non-overlapping methods such as Ward's, Group Average, Jarvis Patrick's and K-means are preferred methods to cluster the diverse set of compounds. However, there are little study on overlapping method such as fuzzy c mean (FCM) and fuzzy c-varieties (FCV) clustering algorithms. Therefore, these two clustering algorithms are applied and their performance is compared based on the effectiveness of the clustering results in terms of separation between actives and inactives (Pa) into different clusters and mean intercluster molecular dissimilarity (MIMDS). The analysis shows FCM gives the best results compare to FCV in terms of Pa indicating that FCM has a promising use in compound selection algorithms. But, FCV is perform better than the FCM in term of MIMDS when a higher number of compounds and higher fuzziness index value are concerned.