Research Interests:
Forest fires caused by different environmental and human factors are responsible for the extensive destruction of natural and economic resources. Modern machine learning techniques have become popular in developing very accurate and... more
Forest fires caused by different environmental and human factors are responsible for the extensive destruction of natural and economic resources. Modern machine learning techniques have become popular in developing very accurate and precise susceptibility maps of various natural disasters to help reduce the occurrence of such calamities. The present study has applied and tested multiple algorithms to map the areas susceptible to wildfire in the Mediterranean Region of Turkey. Besides, the performance of XGBoost, CatBoost, Gradient Boost, AdaBoost, and LightGBM methods for wildfire susceptibility mapping is also examined. The results have revealed the higher testing accuracy of CatBoost (95.47%) algorithm, followed by LightGBM (94.70%), XGBoost (88.8%), AdaBoost (86.0%), and GBM (84.48%) algorithms. Resultant wildfire susceptibility maps provide proper inventories for forest engineers, planners, and local governments for future policies regarding disaster management in Turkey.
Research Interests:
This research aims to examine the feasibility of adopting a corporate social responsibility strategy that prioritises environmental protection within the food distribution and retail sectors. The environmental strategy involves... more
This research aims to examine the feasibility of adopting a corporate social responsibility strategy that prioritises environmental protection within the food distribution and retail sectors. The environmental strategy involves ecofriendly packaging, streamlined logistics, and conservative energy use. The company Axfood serves as a case study. The study involved public records observation, store visits, and discussions with the managers and head of CSR. The study employed a case study approach, utilising data collected from various sources and analysing it for depth and breadth of understanding to uncover systemic causes of environmental concern at Axfood. Three outcomes were derived from the practical experience gathered from observation, repeated store inspection, interviewing customers and store managers, and five conversations with top management. Recycling and cutting costs through energy efficiency allow businesses to compete based on low prices and high-quality products. It i...
Research Interests:
Energy and security are major challenges in a wireless sensor network, and they work oppositely. As security complexity increases, battery drain will increase. Due to the limited power in wireless sensor networks, options to rely on the... more
Energy and security are major challenges in a wireless sensor network, and they work oppositely. As security complexity increases, battery drain will increase. Due to the limited power in wireless sensor networks, options to rely on the security of ordinary protocols embodied in encryption and key management are futile due to the nature of communication between sensors and the ever-changing network topology. Therefore, machine learning algorithms are one of the proposed solutions for providing security services in this type of network by including monitoring and decision intelligence. Machine learning algorithms present additional hurdles in terms of training and the amount of data required for training. This paper provides a convenient reference for wireless sensor network infrastructure and the security challenges it faces. It also discusses the possibility of benefiting from machine learning algorithms by reducing the security costs of wireless sensor networks in several domains;...
Research Interests:
The use of Sensor-Actor Networks (SANETs) has been applied to surgical training contexts, to illustrate how the Spring Tensor Model (STEM) can be used for laparoscopic end-effector navigation through obstacles and high-risk areas. The... more
The use of Sensor-Actor Networks (SANETs) has been applied to surgical training contexts, to illustrate how the Spring Tensor Model (STEM) can be used for laparoscopic end-effector navigation through obstacles and high-risk areas. The modelling of agents as interactive components of a laparoscopic simulator seeks to emulate the physical environment as a virtualised representation in the integrated SANET infrastructure. Combining SANET middleware framework paradigms to a surgical knowledge-based construct demonstrates how SANETs can enhance medical practice. The architectural hybridisation of the training framework has enabled the adaptation of STEM modelling techniques for a simulated laparoscopic training methodology. The primary benefit of the architecture is that this integration strategy has resulted in a seamless transition of the heuristic framework to be applied to surgical training
Research Interests:
Research Interests:
The report revolve on building construction engineering and management, in which there are a lot of requirements such as well supervision and accuracy and being in position to forecast uncertainties that may arise and mechanisms to solve... more
The report revolve on building construction engineering and management, in which there are a lot of requirements such as well supervision and accuracy and being in position to forecast uncertainties that may arise and mechanisms to solve them. It also focuses on the way the building and construction can minimise the cost of building and wastages of materials. The project will be based of heuristic methods of Artificial Intelligence (AI). There are various evolution methods, but report focus on two experiments Pattern Recognition and Travelling Salesman Problem (TSP). The Pattern Recognition focuses Evolutionary Support Vector Machine Inference System for Construction Management. The construction is very dynamic are has a lot of uncertainties, no exact data this implies that the inference should change according to the environment so that it can fit the reality, therefore there a need of Support Vector Machine Inference System to solve these problems. TSP focus on reducing cost of bu...
Research Interests:
Wireless Sensor Networks (WSNs) are the core of the Internet of Things (IoT) technology, as they will be used in various applications in the near future. The issue of security and power consumption is still one of the most important... more
Wireless Sensor Networks (WSNs) are the core of the Internet of Things (IoT) technology, as they will be used in various applications in the near future. The issue of security and power consumption is still one of the most important challenges facing this type of network. 6LoWPAN protocol was developed to meet these challenges in networks with limited power and resources. The 6LoWPAN uses a hierarchical topology and the traditional method of encryption and key management, keeping power consumption levels high. Therefore, in this paper, a technique has been developed that helps in balancing security and energy consumption by exploiting the Trust technique between low-cost WSN nodes called Trust-Cluster Head (Trust-CH). Trust between nodes is built by monitoring the behavior of packet transmission, the number of repetitions and the level of security. The Trust-CH model provides a dynamic multi-level encryption system that depends on the level of Trust between WSN nodes. It also propos...
Research Interests:
Research Interests:
Steganography is the process of concealing data to protect the carrier file data from intruders. One of the main challenges of steganography is to maintain optimum visual quality while increasing hiding capacity. This can be resolved by... more
Steganography is the process of concealing data to protect the carrier file data from intruders. One of the main challenges of steganography is to maintain optimum visual quality while increasing hiding capacity. This can be resolved by incorporating the human visual systems weaknesses in steganography, which results in a good quality of the algorithm. Additionally, steganography is considered as an optimization problem to obtain optimum embedding rate. For this reason, this paper presents a novel method aimed towards a selection of perceptual embedding threshold in Discrete Wavelet Transform using human visual system characteristics and Genetic Algorithm. This method included an introduction of an optimization model by maintaining a correlation between neighboring areas of the image and the different parts of the object. The results of the experiment involving a variety of two thousand images show the differences between the various methods and the HVS in relation to accuracy. Furt...
Research Interests:
Efficient solutions for the purpose of delivery of information are called for by the revolution of internet. However concerns and problems over security, distribution of digital content and encapsulation of media artifacts have arisen as... more
Efficient solutions for the purpose of delivery of information are called for by the revolution of internet. However concerns and problems over security, distribution of digital content and encapsulation of media artifacts have arisen as a result of these phenomenal developments. Hence, it has become necessary to seek capabilities to transport and secure multimedia with its meta-data in a safe way. Steganography has evolved as an enabler of multimedia applications keeping secret communication and embedded captioning secure. There is a tolerable outcome that occurs between imperceptibility and steganographic capacity that fit right into the mix. For instance, the more subtle elements are hidden within the cover object having higher capacity, the more degradation is exhibited towards the carrier file, resulting in an increase in the distortion attributed to the information being concealed and at the same time, decreasing the stego file quality. Suitable use of Evolutionary Algorithm a...
Research Interests:
With the advent of smartphones, many people have the ability to take a photo and upload it to the internet whenever they want. Most smartphones will include basic metadata in the image file; however, this is usually limited to information... more
With the advent of smartphones, many people have the ability to take a photo and upload it to the internet whenever they want. Most smartphones will include basic metadata in the image file; however, this is usually limited to information about the camera itself, and not the content of the photo. This data is also easy to access, as there are many websites and applications that will extract the metadata from an image, thus it is unsuitable for personal information.While there are many applications out there which will allow a user to take and upload photos for their friends or the public to view, such as Facebook or Instagram, these applications rely on information provided along side the image for privacy settings, commenting, and image searching. Other search engines would have difficulty categorising the pictures they find on various sites, and if the image is saved and re-uploaded somewhere else, the information about them would likely be lost.Steganography provides a feasible a...
Research Interests:
As security violations increase, cybersecurity is a critical issue for any area of cyberspace. A large number of zero-day attacks are taking place on a continuous basis due to the inclusion of several protocols. Most of these attacks are... more
As security violations increase, cybersecurity is a critical issue for any area of cyberspace. A large number of zero-day attacks are taking place on a continuous basis due to the inclusion of several protocols. Most of these attacks are minor variations of cyberattacks that have been carried out previously. This shows that problems are faced by even the most sophisticated methods, such as conventional machine learning systems, when identifying these minor variations in attacks over time. By considering a few challenges in the existing intrusion detection methods, an effective semisupervised technique is presented in this paper to decrease the false alarm rate and enhance the detection rate for intrusion detection systems (IDSs). The proposed approach proposes an IDS utilizing k-nearest neighbor hyperparameter tuning with fivefold cross-validation on semisupervised learning. For each unlabeled data point, its k-nearest neighbors in the training set are first identified. After that, ...
With the advent of smartphones, we have the ability to take a photo and upload it to the internet whenever we desire. Hence, it may be of key importance to include metadata of the image for heritage preservation. This project focuses on... more
With the advent of smartphones, we have the ability to take a photo and upload it to the internet whenever we desire. Hence, it may be of key importance to include metadata of the image for heritage preservation. This project focuses on heritage concepts and their importance in every evolving and changing digital domain where system solutions have to be sustainable, sharable, efficient and suitable to the basic user needs. Steganography provides a feasible and viable solution to ensure secure heritage preservation of the multimedia content. By embedding information directly into the image, the information about the image will never be lost, as it is not separated from its original source. The aim of the paper is to demonstrate this aspect via an image sharing app that allows users to exchange messages and personalized information that is embedded in the image such that it is inaccessible without knowing their keys.
Hiding of information is a great significance in information security. For information security and intellectual property, effective methods are required. Steganography is the art of hiding information in such a way that it cannot produce... more
Hiding of information is a great significance in information security. For information security and intellectual property, effective methods are required. Steganography is the art of hiding information in such a way that it cannot produce distrust about its presence. In this way only the sender and recipient are aware of hidden information. There are two critical characteristics of steganography which are as stego image imperceptibility and payload capacity. Recently, many edge detection based steganogaphy approaches have been developed to provide high imperceptibility of the stego image. However, the capacity of these approaches can be limited. This paper presents an effective edge detection method based on gradient, 9x9 mask of LOG and zero crossing in combination with clustering to classify the image to edge and non-edge regions. Different amount of secret message will be hidden in each cluster after the detection of the edge regions. It declares the stability between stego image...
Steganography is the art of writing concealed information in a way that it cannot arouse suspicion about its existence. The hidden data must not raise the attention of attackers to the existence of secret information in the host image.... more
Steganography is the art of writing concealed information in a way that it cannot arouse suspicion about its existence. The hidden data must not raise the attention of attackers to the existence of secret information in the host image. Therefore, ensuring high imperceptibility of the steganography is very essntial. Imperceptibility evaluation of the stego file can be determined by subjective or objective evaluation. Subjective evaluation is based on human judgment and opinion determining visual quality. This kind of evaluation, is not efficient as it is expensive, time consuming, and in any way cannot be referred to as an automatic system. On the other hand, objective metrics are based on mathematical concepts and might have poor correlation with subjective evaluation. This paper focuses on predicting the subjective quality using anticipatory objective Image Quality metric (IQM). The primary objective of this paper is to develop a systematic method of using HVS for image quality ass...
Research Interests:
Information security is considered one of the most important issues in various infrastructures related to the field of data communication where most of the modern studies focus on finding effective and low-weight secure approaches.... more
Information security is considered one of the most important issues in various infrastructures related to the field of data communication where most of the modern studies focus on finding effective and low-weight secure approaches. Digital watermarking is a trend in security techniques that hides data by using data embedding and data extraction processes. Watermarking technology is integrated into different frames without adding an overheard as in the conventional encryption. Therefore, it is efficient to be used in data encryption for applications that run over limited resources such as the Internet of Things (IoT). In this paper, different digital watermarking algorithms and approaches are presented. Additionally, watermarking requirements and challenges are illustrated in detail. Moreover, the common architecture of the watermarking system is described. Furthermore, IoT technology and its challenges are highlighted. Finally, the paper provides the motivations, objectives and appl...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Software-defined networking (SDN) is an innovative architecture that separates the control plane from the data plane to simplify and speed up the management of large networks. This means the control logic has been moved from the network... more
Software-defined networking (SDN) is an innovative architecture that separates the control plane from the data plane to simplify and speed up the management of large networks. This means the control logic has been moved from the network hardware level to the centralized control management level. Therefore, the use of the OpenFlow Discovery Protocol (OFDP) is one of the most common protocols used to discover the network topology in a data plane and then transmit it to the control plane for management. However, OFDP has various shortcomings in its performance such as exchanging too many messages between both levels (control and data), which in turn increases the load on the SDN-Controller. Additionally, since the application layer depends entirely on the network topologies plotted in the control plane, it is very important to obtain accurate network topology information from data plane. Therefore, after providing background on topology discovery protocols to the reader, we will concen...
Research Interests:
Identity theft is a serious crime where the criminals steal user's identity to access their bank accounts, personal hospital records and etc. The usage of cloud storage has allowed the hackers to attack the victims easily by accessing... more
Identity theft is a serious crime where the criminals steal user's identity to access their bank accounts, personal hospital records and etc. The usage of cloud storage has allowed the hackers to attack the victims easily by accessing the victim's data stored in a remote location. Cloud storage may be convenient to allow users to store any data files and access those files from different devices and in different locations around the world. However, it can still pose security threats as with a lot of important data stored in one location is very appealing to cunning hackers. The solution of using image steganography application to hide important data or documents under an image before uploading them to the cloud storage will avoid the risks of attracting hackers or outsiders to discover the importance of the data hidden. The application uses one of simplest image steganography approach 'LSB algorithm' to achieve best quality of encoded image/stego-image. Besides, the application can be deployed via offline or online depending whether they want to upload the encoded image/stego-image to the cloud storage.
Research Interests:
Research Interests:
Wireless Sensor Networks (WSNs) continue to face two major challenges: energy and security. As a consequence, one of the WSN-related security tasks is to protect them from Denial of Service (DoS) and Distributed DoS (DDoS) attacks.... more
Wireless Sensor Networks (WSNs) continue to face two major challenges: energy and security. As a consequence, one of the WSN-related security tasks is to protect them from Denial of Service (DoS) and Distributed DoS (DDoS) attacks. Machine learning-based systems are the only viable option for these types of attacks, as traditional packet deep scan systems depend on open field inspection in transport layer security packets and the open field encryption trend. Moreover, network data traffic will become more complex due to increases in the amount of data transmitted between WSN nodes as a result of increasing usage in the future. Therefore, there is a need to use feature selection techniques with machine learning in order to determine which data in the DoS detection process are most important. This paper examined techniques for improving DoS anomalies detection along with power reservation in WSNs to balance them. A new clustering technique was introduced, called the CH_Rotations algor...
Research Interests:
Computer scientists and engineers work with increasing amounts of information. These data are used for knowledge retrieval, data management decision support and so on. Sorting algorithms are important procedures that if efficiently... more
Computer scientists and engineers work with increasing amounts of information. These data are used for knowledge retrieval, data management decision support and so on. Sorting algorithms are important procedures that if efficiently composed and implemented can increase speed of data processing and decision correctness. Many various sorting algorithms and their modifications are applicable in large computer systems. However, as the computer architectures are more efficient with each release and the software is more complex with each version there is need to improve sorting methods applied for big data computation.
The main goal of hiding data is to conceal the very existence of the hidden information, therefore there is a significant demand for steganographic approaches that can ensure imperceptibility of such infromation. However, there is a... more
The main goal of hiding data is to conceal the very existence of the hidden information, therefore there is a significant demand for steganographic approaches that can ensure imperceptibility of such infromation. However, there is a limited corresponding evaluation parameters available. Most of the studies use the Peak Signal to Noise Ratio (PSNR) as a metric for imperceptibility evaluation, although it could provide less accurate results than the Human Visual System (HVS) evaluation. This paper provides a review of the existent evaluation metrics that are used to assess the quality of steganography. The examination of the correlation between the existing objective and subjective metrics is also conducted. Pixel differences metrics have a poor correlation with the subjective metrics, hence the HSV based metrics have better correlation than pixel metrics.