Dr Kavi Kumar Khedo is an Associate Professor at the Faculty of Information, Communication and Digital Technologies at the University of Mauritius. He has a PhD in Computer Science and has more than 18 years of teaching and research experience in the field of computer science. He has occupied several senior leadership positions at the University of Mauritius and has made significant contributions in curriculum development and high impact research activities in the area of computing. Dr. Khedo is a Fellow of the Institute of Engineering and Technology (IET) and a Senior Member of the Institute of Electrical and Electronics Engineers (IEEE). He is currently leading the Internet of Things Research Group and the Health Informatics Research Group at the University of Mauritius. He has carried out applied research that have led to innovative and practical solutions to problems of national interest with real societal and environmental impacts. Dr. Khedo was a research scholar at the University of Lancaster UK and a Fulbright research scholar at the University of Massachusetts USA. He has published over 60 research papers in the areas of ubiquitous computing, health informatics, and wireless sensor networks in renowned journals and conference proceedings. He has also served on numerous review panels and editorial boards of distinguished international journals such as IEEE Internet of Things Journal, IEEE Sensors, SAGE Health Informatics Journal, IET Wireless Sensor Systems, SPRINGER Health and Technology Journal.
Based on the proliferation of smartphones, a new type of social networking called Proximity based... more Based on the proliferation of smartphones, a new type of social networking called Proximity based Social Networking (PBSN) was emerged based on the geo-locations of users in the vicinity. However, many concerns have been reported recently on PBSN applications where user information is intercepted and misused, specifically locations of users which are sensitive data. In this paper, a secure PBSN application called MobiShop has been designed and implemented for the largest shopping mall in Mauritius. Users can receive advertisements or coupons from shops when they are approaching those shops, buy cinema tickets and place orders in the food court using the MobiShop application. The payment is then done directly at the counters when they receive their tickets or food by using a transaction ID. Different security measures have been integrated in the application to secure the information and communication of the users. The AllJoyn framework is used to implement the discovery process and the chat system. All messages exchanged are encrypted using the RSA cryptographic algorithm and the passwords of the users are encrypted using the SHA-512 Hash algorithm. Evaluation tests have shown that MobiShop offers a secure platform for the Mauritian shoppers where integrity of the system is ensured and attacks such as man-in-the-middle attacks are prevented.
The development of the Proximity based Mobile Social Networking (PMSN) has been growing exponenti... more The development of the Proximity based Mobile Social Networking (PMSN) has been growing exponentially with the adoption of smartphones and introduction of Wi-Fi hotspots in public and remote areas. Users present in the vicinity can interact with each other using the embedded technologies in their mobile devices such as GPS, Wi-Fi and Bluetooth. Due to its growing momentum, this new social networking has also aroused the interest of business people and advertisers. However, due to a lack of security in these networks, several privacy concerns were reported. Users are more reluctant to share their locations and to address this issue, some initial solutions to preserve location privacy were implemented. The aim of this paper is to present a clear categorization of the different privacy threats in PMSN. Moreover, the location privacy enforcement policies and techniques used to ensure privacy are outlined and some solutions employed in existent systems are presented and discussed. To the best of our knowledge, this is the first study done outlining several categories of PMSN privacy challenges and their solutions in this new type of social networking services. Finally, some privacy research challenges and future perspectives are proposed.
Advances in intelligent systems and computing, 2019
Augmented Reality (AR) is an emerging technology that is currently revolutionising the worldly ac... more Augmented Reality (AR) is an emerging technology that is currently revolutionising the worldly activities. The evolution of mobile devices has pioneered AR as a state-of-the-art technology in the last decade giving rise to more and more Location-Based Mobile AR (LBMAR) systems. This technology is widely been used by heritage industry to create the missing sparks from their static environment thus making it livelier and entertaining. Yet, current systems have not exploited the emerging sensory technologies in smartphones which led to low-quality AR experiences. In this work, we will model a real-time Mobile AR system for a cultural site in Mauritius that will both promote the cultural tourism and enhance the visiting experience. Moreover, the proposed prototype will also attract historians and students so that they can carefully study those heritage aspects that were not accessible before.
Diabetes Mellitus (DM) is one of the leading health complication around the world causing nationa... more Diabetes Mellitus (DM) is one of the leading health complication around the world causing national economic burden and low quality of life. This increases the need to focus on prevention and early detection to improve the management and treatment of diabetes. The aim of this paper is to present a comprehensive critical review focusing on recent glucose prediction models and a best fit model is proposed based on the evaluation to perform data analytics in a wireless body area network system. The proposed glucose prediction algorithm is based on autoregressive (ARX) model which consider exogenous inputs such as CGM data, blood pressure (BP), total cholesterol (TC), low-density lipoprotein cholesterol (LDL), high density lipoproteins (HDL). A dataset of 442 diabetic patients is used to evaluate the performance of the algorithm through mean absolute error (MAE), root-mean-square error (RMSE), and coefficient of determination (R2). The experimental results demonstrate that the proposed prediction algorithm can improve the prediction accuracy of glucose. Potential research work and challenges are pointed out for further development of glucose prediction models.
Environmental monitoring is the most popular application of wireless sensor networks (WSNs). At p... more Environmental monitoring is the most popular application of wireless sensor networks (WSNs). At present, WSNs have been used for a number of applications such as soil moisture monitoring, solar radiation mapping, aquatic monitoring, glacial control and climate change, and forest fire alarm. The ability to place autonomous and low cost nodes in large harsh environments without communication infrastructure enables accurate data collection directly observed from interested areas. In this paper, the use of WSNs for realtime monitoring of the hydrological conditions of rivers for flood forecasting and prompt warnings is investigated. This paper describes the design and deployment of a real-time flood monitoring system (RTFMS). The system performs flood forecasting based on readily available data to provide an indication of likely flood behaviour. RTFMS intends to predict flood in rivers using simple and fast calculations, to provide real-time results and save the lives of people who may be affected by the flood.
Technical advances of Online Social Networking (OSN) have promoted new types of social interactio... more Technical advances of Online Social Networking (OSN) have promoted new types of social interactions such as Proximity Based Social Networking (PBSN) where proximate users interact with each other using their mobile devices. However, personal details users share on these networks are not secured and messages exchanged are prone to different attacks and eavesdropping. Qualcomm introduces AllJoyn, which eases the development of such applications discovering with nearby devices and establishing a secure communication. In this paper, a secure device and service discovery protocol is introduced leveraging the AllJoyn framework. It allows mobile users to perform secure device advertising and discovery, authentication, encryption and decryption of exchanged messages. The security and performance of the proposed architecture are thoroughly analyzed and evaluated by using penetration tools and scenarios. Results showed that exchanged messages could not be captured and the system is not prone to attacks such as man-in-the-middle attacks.
The advancement of virtual reality has sharpened the concept of augmented reality (AR) to new dim... more The advancement of virtual reality has sharpened the concept of augmented reality (AR) to new dimension of perceptions of seeing, hearing and immersing in a real world. The evolution of mobile devices has pioneered AR as a state-of-the-art technology in the last decade giving rise to more and more location-based mobile AR (LBMAR) systems. However, notably there are very limited review studies that have focused on investigating factors such as: growth, types, characteristics, features, sensors, application domains and their respective challenges. This study presents a systematic review on location-based mobile augmented reality (LBMAR) system. A total of 35 studies published between the years 2013 and 2018 in top six most popular indexed databases are reviewed. The systematic review has been conducted using Kitchenham method, and the analysis of the findings was carried out using the PRISMA method. This chapter provides a major review of the current state of LBMAR system and outlines the research issues that require more investigation.
International Journal of Advanced Research in Computer Science, 2010
High precision and real-time communications are increasingly becoming important in Wireless Senso... more High precision and real-time communications are increasingly becoming important in Wireless Sensor Networks as such networks are required to support highly time-critical applications. The sensor nodes need to communicate data to each other at the correct time. However, the clocks of sensor nodes run at different speed and very often drift from the real time value. In this paper we are proposing EETS, an energy efficient time synchronization algorithm. Energy efficiency is achieved by synchronizing only nodes that are communicating with each other when an event occurs. EETS is performed in two phases namely the Level discovery phase and the Synchronization phase. A simulation study has been carried out and the results shows that EETS is more energy efficient than other existing algorithms. Particularly, EETS has been compared to Network Wide Time Synchronization (NWTS) which is a widely used algorithm for time synchronization in WSN. Simulation results have shown that NWTS uses about...
Summary This paper presents a novel protocol, SENCAST, a scalable protocol for large ad hoc emerg... more Summary This paper presents a novel protocol, SENCAST, a scalable protocol for large ad hoc emergency network for unicasting and multicasting. SENCAST is scalable to a very large ad hoc network and adheres to emerging communication scenarios in emergency systems where mobile nodes typically work as a group and are involved in a collaborative manner. SENCAST not only distributes real-time information efficiently in such an environment, but the paths are discovered with low overheads by limiting the scope of route discovery packets to a region of potential paths creation. SENCAST uses context information like bandwidth available and location. Route reconfigurations are localised and thus limiting the sending of control packets to a specific region. The resiliency of the SENCAST is improved with multiple routes. Moreover, based on the movement of the source or the destination, routes may be extended in a localised manner or new routes being discovered in other areas while stale ones ar...
The aim of ubiquitous computing, as envisioned by Mark Weiser, is to provide various services any... more The aim of ubiquitous computing, as envisioned by Mark Weiser, is to provide various services anywhere and at anytime by making multiple computers available throughout the physical space while in effect making them invisible to the user. As a stimulating new paradigm and the ...
2017 1st International Conference on Next Generation Computing Applications (NextComp), 2017
Evolution of mobile technologies and widespread adoption of mobile devices in learning today is m... more Evolution of mobile technologies and widespread adoption of mobile devices in learning today is momentous. Mobile learning refers to the use of portable devices to study independent of location and time. To allow flexible learning to occur, content adaptation is necessary. Content-adaptation aims at delivering the most suitable learning elements in dynamic conditions using different contextual information from various sources in order to enhance the learners' experiences. This paper describes our ongoing research project, the context-aware mobile learning application, Mobiware that makes use of contextual data in mobile learning for content-adaptation. Important information was gathered from individual learners, the device used and the surrounding to give rise to independent customized learning materials. The aim of developing this mobile application is to set a dynamic system, which instantly acknowledges different user situations, and deliver the best-adapted learning content to the learner. Details about the current trends in mobile learning are reported which leads to the proposed context-aware mobile learning application.
Mobile technologies nowadays contribute to greater options to how learners can enhance their lear... more Mobile technologies nowadays contribute to greater options to how learners can enhance their learning styles, leaving behind the traditional learning setup. Indeed mobile learning has become an integral part of our everyday life. Mobile learning refers to the use of mobile devices whereby learning is supported independent of the location and activity of the learner. This learning concept considers continual changes of contexts such as locations and the time available to learn within the mobile environment. Given that the current state of the use of contextual information in mobile learning is not extended, this paper put forward a context aware mobile learning system upon which parameters such as intrinsic and extrinsic context are used in order to improve mobile learning experience of the users. This work aims to synthesize a context-aware mobile learning system using dynamic content adaptation to establish personalized learning contents delivery on portable devices.
2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC), 2018
This work is a continuation of a larger research work which advocates that Distance Education (DE... more This work is a continuation of a larger research work which advocates that Distance Education (DE) through audio-only learning mode can be developed into a full fledge audio-MOOC. Audio MOOC framework is an innovative framework which enables learning through mere phone calls. It has been conceived to digitally include low literate population in the education process by opening up access to learning materials to the unreached and the have-nots usually hindered by barriers such as language, literacy, culture, connectivity and distance which existing MOOCs have failed to address. This work demonstrates how our proposed framework is used to connect to a remote island lost in the middle of the Indian Ocean with limited maritime and air access but which since some few years back can be connected via basic phones through voice calls. Agalega is an ideal test case scenario for our research since it characterizes remoteness, limited connectivity, semi-literate population with limited access to education which our research aims at addressing. A group of 50 Fishermen was identified from both the Agalega islands. The course was of 9 days duration from 15 to 23 September 2017. The system was conducted live over the telephony network making use of our GSM gateway. The specificity of the system was that our GSM gateway resided in Mauritius connected to a cloud server, while the course was delivered to people of Agalega 1100 Km far from Mauritius over the sea. Nevertheless, our system performed as expected and proved to be a success.
Over the last decade, there has been a tremendous growth in the amount and diversity of electroni... more Over the last decade, there has been a tremendous growth in the amount and diversity of electronic health-related data, such as patient records, drug information, drug–disease associations, medical resource allocations, and clinical experiments’ results, altogether referred to as medical big data. Health data analytics refers to the proper exploitation of medical big data in view of getting better understandings that can drive health research, which may ultimately accelerate advancements in biomedicine, enhance patient outcomes, and reduce overall healthcare costs. This chapter provides an extensive review of the application areas that can benefit from health data analytics, namely drug–disease association, disease outbreak detection and surveillance, pharmacovigilance, healthcare management, clinical research, and clinical practice. A variety of tools and platforms have been developed to support health data analytics, each dealing with different application areas and diverse data t...
Based on the proliferation of smartphones, a new type of social networking called Proximity based... more Based on the proliferation of smartphones, a new type of social networking called Proximity based Social Networking (PBSN) was emerged based on the geo-locations of users in the vicinity. However, many concerns have been reported recently on PBSN applications where user information is intercepted and misused, specifically locations of users which are sensitive data. In this paper, a secure PBSN application called MobiShop has been designed and implemented for the largest shopping mall in Mauritius. Users can receive advertisements or coupons from shops when they are approaching those shops, buy cinema tickets and place orders in the food court using the MobiShop application. The payment is then done directly at the counters when they receive their tickets or food by using a transaction ID. Different security measures have been integrated in the application to secure the information and communication of the users. The AllJoyn framework is used to implement the discovery process and the chat system. All messages exchanged are encrypted using the RSA cryptographic algorithm and the passwords of the users are encrypted using the SHA-512 Hash algorithm. Evaluation tests have shown that MobiShop offers a secure platform for the Mauritian shoppers where integrity of the system is ensured and attacks such as man-in-the-middle attacks are prevented.
The development of the Proximity based Mobile Social Networking (PMSN) has been growing exponenti... more The development of the Proximity based Mobile Social Networking (PMSN) has been growing exponentially with the adoption of smartphones and introduction of Wi-Fi hotspots in public and remote areas. Users present in the vicinity can interact with each other using the embedded technologies in their mobile devices such as GPS, Wi-Fi and Bluetooth. Due to its growing momentum, this new social networking has also aroused the interest of business people and advertisers. However, due to a lack of security in these networks, several privacy concerns were reported. Users are more reluctant to share their locations and to address this issue, some initial solutions to preserve location privacy were implemented. The aim of this paper is to present a clear categorization of the different privacy threats in PMSN. Moreover, the location privacy enforcement policies and techniques used to ensure privacy are outlined and some solutions employed in existent systems are presented and discussed. To the best of our knowledge, this is the first study done outlining several categories of PMSN privacy challenges and their solutions in this new type of social networking services. Finally, some privacy research challenges and future perspectives are proposed.
Advances in intelligent systems and computing, 2019
Augmented Reality (AR) is an emerging technology that is currently revolutionising the worldly ac... more Augmented Reality (AR) is an emerging technology that is currently revolutionising the worldly activities. The evolution of mobile devices has pioneered AR as a state-of-the-art technology in the last decade giving rise to more and more Location-Based Mobile AR (LBMAR) systems. This technology is widely been used by heritage industry to create the missing sparks from their static environment thus making it livelier and entertaining. Yet, current systems have not exploited the emerging sensory technologies in smartphones which led to low-quality AR experiences. In this work, we will model a real-time Mobile AR system for a cultural site in Mauritius that will both promote the cultural tourism and enhance the visiting experience. Moreover, the proposed prototype will also attract historians and students so that they can carefully study those heritage aspects that were not accessible before.
Diabetes Mellitus (DM) is one of the leading health complication around the world causing nationa... more Diabetes Mellitus (DM) is one of the leading health complication around the world causing national economic burden and low quality of life. This increases the need to focus on prevention and early detection to improve the management and treatment of diabetes. The aim of this paper is to present a comprehensive critical review focusing on recent glucose prediction models and a best fit model is proposed based on the evaluation to perform data analytics in a wireless body area network system. The proposed glucose prediction algorithm is based on autoregressive (ARX) model which consider exogenous inputs such as CGM data, blood pressure (BP), total cholesterol (TC), low-density lipoprotein cholesterol (LDL), high density lipoproteins (HDL). A dataset of 442 diabetic patients is used to evaluate the performance of the algorithm through mean absolute error (MAE), root-mean-square error (RMSE), and coefficient of determination (R2). The experimental results demonstrate that the proposed prediction algorithm can improve the prediction accuracy of glucose. Potential research work and challenges are pointed out for further development of glucose prediction models.
Environmental monitoring is the most popular application of wireless sensor networks (WSNs). At p... more Environmental monitoring is the most popular application of wireless sensor networks (WSNs). At present, WSNs have been used for a number of applications such as soil moisture monitoring, solar radiation mapping, aquatic monitoring, glacial control and climate change, and forest fire alarm. The ability to place autonomous and low cost nodes in large harsh environments without communication infrastructure enables accurate data collection directly observed from interested areas. In this paper, the use of WSNs for realtime monitoring of the hydrological conditions of rivers for flood forecasting and prompt warnings is investigated. This paper describes the design and deployment of a real-time flood monitoring system (RTFMS). The system performs flood forecasting based on readily available data to provide an indication of likely flood behaviour. RTFMS intends to predict flood in rivers using simple and fast calculations, to provide real-time results and save the lives of people who may be affected by the flood.
Technical advances of Online Social Networking (OSN) have promoted new types of social interactio... more Technical advances of Online Social Networking (OSN) have promoted new types of social interactions such as Proximity Based Social Networking (PBSN) where proximate users interact with each other using their mobile devices. However, personal details users share on these networks are not secured and messages exchanged are prone to different attacks and eavesdropping. Qualcomm introduces AllJoyn, which eases the development of such applications discovering with nearby devices and establishing a secure communication. In this paper, a secure device and service discovery protocol is introduced leveraging the AllJoyn framework. It allows mobile users to perform secure device advertising and discovery, authentication, encryption and decryption of exchanged messages. The security and performance of the proposed architecture are thoroughly analyzed and evaluated by using penetration tools and scenarios. Results showed that exchanged messages could not be captured and the system is not prone to attacks such as man-in-the-middle attacks.
The advancement of virtual reality has sharpened the concept of augmented reality (AR) to new dim... more The advancement of virtual reality has sharpened the concept of augmented reality (AR) to new dimension of perceptions of seeing, hearing and immersing in a real world. The evolution of mobile devices has pioneered AR as a state-of-the-art technology in the last decade giving rise to more and more location-based mobile AR (LBMAR) systems. However, notably there are very limited review studies that have focused on investigating factors such as: growth, types, characteristics, features, sensors, application domains and their respective challenges. This study presents a systematic review on location-based mobile augmented reality (LBMAR) system. A total of 35 studies published between the years 2013 and 2018 in top six most popular indexed databases are reviewed. The systematic review has been conducted using Kitchenham method, and the analysis of the findings was carried out using the PRISMA method. This chapter provides a major review of the current state of LBMAR system and outlines the research issues that require more investigation.
International Journal of Advanced Research in Computer Science, 2010
High precision and real-time communications are increasingly becoming important in Wireless Senso... more High precision and real-time communications are increasingly becoming important in Wireless Sensor Networks as such networks are required to support highly time-critical applications. The sensor nodes need to communicate data to each other at the correct time. However, the clocks of sensor nodes run at different speed and very often drift from the real time value. In this paper we are proposing EETS, an energy efficient time synchronization algorithm. Energy efficiency is achieved by synchronizing only nodes that are communicating with each other when an event occurs. EETS is performed in two phases namely the Level discovery phase and the Synchronization phase. A simulation study has been carried out and the results shows that EETS is more energy efficient than other existing algorithms. Particularly, EETS has been compared to Network Wide Time Synchronization (NWTS) which is a widely used algorithm for time synchronization in WSN. Simulation results have shown that NWTS uses about...
Summary This paper presents a novel protocol, SENCAST, a scalable protocol for large ad hoc emerg... more Summary This paper presents a novel protocol, SENCAST, a scalable protocol for large ad hoc emergency network for unicasting and multicasting. SENCAST is scalable to a very large ad hoc network and adheres to emerging communication scenarios in emergency systems where mobile nodes typically work as a group and are involved in a collaborative manner. SENCAST not only distributes real-time information efficiently in such an environment, but the paths are discovered with low overheads by limiting the scope of route discovery packets to a region of potential paths creation. SENCAST uses context information like bandwidth available and location. Route reconfigurations are localised and thus limiting the sending of control packets to a specific region. The resiliency of the SENCAST is improved with multiple routes. Moreover, based on the movement of the source or the destination, routes may be extended in a localised manner or new routes being discovered in other areas while stale ones ar...
The aim of ubiquitous computing, as envisioned by Mark Weiser, is to provide various services any... more The aim of ubiquitous computing, as envisioned by Mark Weiser, is to provide various services anywhere and at anytime by making multiple computers available throughout the physical space while in effect making them invisible to the user. As a stimulating new paradigm and the ...
2017 1st International Conference on Next Generation Computing Applications (NextComp), 2017
Evolution of mobile technologies and widespread adoption of mobile devices in learning today is m... more Evolution of mobile technologies and widespread adoption of mobile devices in learning today is momentous. Mobile learning refers to the use of portable devices to study independent of location and time. To allow flexible learning to occur, content adaptation is necessary. Content-adaptation aims at delivering the most suitable learning elements in dynamic conditions using different contextual information from various sources in order to enhance the learners' experiences. This paper describes our ongoing research project, the context-aware mobile learning application, Mobiware that makes use of contextual data in mobile learning for content-adaptation. Important information was gathered from individual learners, the device used and the surrounding to give rise to independent customized learning materials. The aim of developing this mobile application is to set a dynamic system, which instantly acknowledges different user situations, and deliver the best-adapted learning content to the learner. Details about the current trends in mobile learning are reported which leads to the proposed context-aware mobile learning application.
Mobile technologies nowadays contribute to greater options to how learners can enhance their lear... more Mobile technologies nowadays contribute to greater options to how learners can enhance their learning styles, leaving behind the traditional learning setup. Indeed mobile learning has become an integral part of our everyday life. Mobile learning refers to the use of mobile devices whereby learning is supported independent of the location and activity of the learner. This learning concept considers continual changes of contexts such as locations and the time available to learn within the mobile environment. Given that the current state of the use of contextual information in mobile learning is not extended, this paper put forward a context aware mobile learning system upon which parameters such as intrinsic and extrinsic context are used in order to improve mobile learning experience of the users. This work aims to synthesize a context-aware mobile learning system using dynamic content adaptation to establish personalized learning contents delivery on portable devices.
2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC), 2018
This work is a continuation of a larger research work which advocates that Distance Education (DE... more This work is a continuation of a larger research work which advocates that Distance Education (DE) through audio-only learning mode can be developed into a full fledge audio-MOOC. Audio MOOC framework is an innovative framework which enables learning through mere phone calls. It has been conceived to digitally include low literate population in the education process by opening up access to learning materials to the unreached and the have-nots usually hindered by barriers such as language, literacy, culture, connectivity and distance which existing MOOCs have failed to address. This work demonstrates how our proposed framework is used to connect to a remote island lost in the middle of the Indian Ocean with limited maritime and air access but which since some few years back can be connected via basic phones through voice calls. Agalega is an ideal test case scenario for our research since it characterizes remoteness, limited connectivity, semi-literate population with limited access to education which our research aims at addressing. A group of 50 Fishermen was identified from both the Agalega islands. The course was of 9 days duration from 15 to 23 September 2017. The system was conducted live over the telephony network making use of our GSM gateway. The specificity of the system was that our GSM gateway resided in Mauritius connected to a cloud server, while the course was delivered to people of Agalega 1100 Km far from Mauritius over the sea. Nevertheless, our system performed as expected and proved to be a success.
Over the last decade, there has been a tremendous growth in the amount and diversity of electroni... more Over the last decade, there has been a tremendous growth in the amount and diversity of electronic health-related data, such as patient records, drug information, drug–disease associations, medical resource allocations, and clinical experiments’ results, altogether referred to as medical big data. Health data analytics refers to the proper exploitation of medical big data in view of getting better understandings that can drive health research, which may ultimately accelerate advancements in biomedicine, enhance patient outcomes, and reduce overall healthcare costs. This chapter provides an extensive review of the application areas that can benefit from health data analytics, namely drug–disease association, disease outbreak detection and surveillance, pharmacovigilance, healthcare management, clinical research, and clinical practice. A variety of tools and platforms have been developed to support health data analytics, each dealing with different application areas and diverse data t...
Uploads
Papers by Kavi Khedo