摘要 :
Securing user identity from data breach in a web server is one of the major concerns for the users of the web applications. Similarly, protecting user access pattern from unauthorized access should be taken seriously, because the ...
展开
Securing user identity from data breach in a web server is one of the major concerns for the users of the web applications. Similarly, protecting user access pattern from unauthorized access should be taken seriously, because the potential threats such attacks may pose, are huge. However, these security measures should not be adopted at the expense of user experience and convenience. Nevertheless, any extra overhead in the form of security measures introduced in a distributed system results in significant performance declination. The target of a secured framework for a distributed system like web application should be a reasonable trade-off between security and user experience. Thus, in this work, we present a framework that ensures security for the user identity along with keeping the online activities of the users anonymous while ensuring scalability of the system. Our framework is designed in a scalable form that can work with other distributed architectures that provide security to user data and identities. To ensure all these measures, our proposal includes the implementation of Forward Secrecy using Diffie-Hellman Key exchange protocol where the server cannot remember a user's history after a session ends. In addition, we present our own mechanism to hide logical data sharing strategies to protect users against selective DoS attacks. Moreover, we implemented a modified version of bloom filter to safeguard user access pattern in a compromised server. Our proposed implementation of bloom filter also ensures that the scalability of distributed system is preserved even with little infrequent overhead in the server because of security measures proposed in this work. Finally, we implemented different modules of our framework using both Web Socket and Long Polling transport protocols and recorded the time required to perform various tasks. Web socket protocol took less time to perform each task than the long polling protocol, which is convincing enough to suggest that web socket performs better than long polling in the given scenarios.
收起
摘要 :
Alzheimer's disease has become a major concern in the healthcare domain as it is growing rapidly. Much research has been conducted to detect it from MRI images through various deep learning approaches.However, the problems of the ...
展开
Alzheimer's disease has become a major concern in the healthcare domain as it is growing rapidly. Much research has been conducted to detect it from MRI images through various deep learning approaches.However, the problems of the availability of medical data and preserving the privacy of patients still exists. To mitigate this issue in Alzheimer's disease detection, we implement the federated approach, which is found to be more efficient, robust, and consistent compared with the conventional approach. For this, we need deep excavation on various orientations of MRI images and transfer learning architectures. Then, we utilize two publicly available datasets (OASIS and ADNI) and design various cases to evaluate the performance of the federated approach. The federated approach achieves better accuracy and sensitivity compared with the conventional approaches in most of the cases. Moreover, the robustness of the proposed approach is also found to be better than the conventional approach. In our federated approach, MobileNet, a low-cost transfer learning architecture, achieves the highest 95.24%, 81.94%, and 83.97% accuracy in the OASIS, ADNI, and merged (ADNI + OASIS) test sets, which is much higher than the achieved performance in the conventional approach. Furthermore, in the proposed approach, only the weights of the model are shared, which keeps the original MRI images in their respective hospital or institutions, preserving privacy in the healthcare domain.
收起
摘要 :
This paper presents an algorithm to extract symbolic rules from trained artificial neural networks (ANNs), called ERANN. In many applications, it is desirable to extract knowledge from ANNs for the users to gain a better understan...
展开
This paper presents an algorithm to extract symbolic rules from trained artificial neural networks (ANNs), called ERANN. In many applications, it is desirable to extract knowledge from ANNs for the users to gain a better understanding of how the networks solve the problems. Although ANN usually achieves high classification accuracy, the obtained results sometimes may be incomprehensible, because the knowledge embedded within them is distributed over the activation functions and the connection weights. This problem can be solved by extracting rules from trained ANNs. To do so, a rule extraction algorithm has been proposed in this paper to extract symbolic rules from trained ANNs. A standard three-layer feedforward ANN with four-phase training is the basis of the proposed algorithm. Extensive experimental studies on a set of benchmark classification problems, including breast cancer, iris, diabetes, wine, season, golfplaying, and lenses classification, demonstrates the applicability of the proposed method. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and the rules accuracy. The proposed method achieved accuracy values 96.28%, 98.67%, 76.56%, 91.01%, 100%, 100%, and 100% for the above problems, respectively. It has been seen that these results are one of the best results comparing with results obtained from related previous studies.
收起
摘要 :
Fair scheduling is an ideal candidate for fair bandwidth sharing and thereby achieving fairness among the contending flows in a network. It is particularly challenging for ad hoc networks due to infrastructure free operation and l...
展开
Fair scheduling is an ideal candidate for fair bandwidth sharing and thereby achieving fairness among the contending flows in a network. It is particularly challenging for ad hoc networks due to infrastructure free operation and location dependent contentions. As there is no entity to serve coordination among nodes, we need a mechanism to overcome inherent unreliability of the network to provide reduced collision and thereby higher throughput and adequate fair allocation of the shared medium among different contending flows. This paper proposes a flow rank based probabilistic fair scheduling technique. The main focus is to reduce the collision probability among the contending flows while maintaining the prioritized medium access for those flows, which ensures a weighted medium access control mechanism based on probabilistic round robin scheduling. Each flow maintains a flow-table upon which the rank is calculated and backoff value is assigned according to the rank of the flow, i.e., lower backoff interval to lower ranked flow. However, flow-table instability due to joining of a new flow, partially backlogged flow, hidden terminal and partially overlapped region exhibits a challenging problem that needs to be mitigated for our mechanism to work
properly. We take appropriate measures to make the flow-table stabilized under such scenarios. Results show that our mechanism achieves better throughput and fairness compared to IEEE 802.11 MAC and existing ones.
收起
摘要 :
In this paper, we present a throughput-maximizing routing metric, referred to as expected forwarding time (EFT), for IEEE 802.11s-based wireless mesh networks. Our study reveals that most of the existing routing metrics select the...
展开
In this paper, we present a throughput-maximizing routing metric, referred to as expected forwarding time (EFT), for IEEE 802.11s-based wireless mesh networks. Our study reveals that most of the existing routing metrics select the paths with minimum aggregate transmission time of a packet. However, we show by analyses that, due to the shared nature of the wireless medium, other factors, such as transmission time of the contending nodes and their densities and loads, also affect the performance of routing metrics. We therefore first identify the factors that hinder the forwarding time of a packet. Furthermore, we add a new dimension to our metric by introducing traffic priority into our routing metric design, which, to the best of our knowledge, is completely unaddressed by existing studies. We also show how EFT can be incorporated into the hybrid wireless mesh protocol (HWMP), the path selection protocol used in the IEEE 802.11s draft standard. Finally, we study the performance of EFT through simulations under different network scenarios. Simulation results show that EFT outperforms other routing metrics in terms of average network throughput, end-to-end delay, and packet loss rate.
收起
摘要 :
Broadband wireless access networks are promising technology for providing better end user services. For such networks, designing a scheduling algorithm that fairly allocates the available bandwidth to the end users and maximizes t...
展开
Broadband wireless access networks are promising technology for providing better end user services. For such networks, designing a scheduling algorithm that fairly allocates the available bandwidth to the end users and maximizes the overall network throughput is a challenging task. In this paper, we develop a centralized fair scheduling algorithm for IEEE 802.16 mesh networks that exploits the spatio-temporal bandwidth reuse to further enhance the network throughput. The proposed mechanism reduces the length of a transmission round by increasing the number of non-contending links that can be scheduled simultaneously. We also propose a greedy algorithm that runs in polynomial time. Performance of the proposed algorithms is evaluated by extensive simulations. Results show that our algorithms achieve higher throughput than that of the existing ones and reduce the computational complexity.
收起
摘要 :
In recent years, wireless sensor networks have been a very popular research topic, offering a treasure trove of systems, networking, hardware, security, and application-related problems. Distributed nature and their deployment in ...
展开
In recent years, wireless sensor networks have been a very popular research topic, offering a treasure trove of systems, networking, hardware, security, and application-related problems. Distributed nature and their deployment in remote areas, these networks are vulnerable to numerous security threats that can adversely affect their proper functioning. The problem is more critical if its purpose is for some mission-critical applications such as in a tactical battlefield. This paper presents a security scheme for group-based distributed wireless sensor networks. Our first goal is to devise a group-based secure wireless sensor network. We exploit the multi-line version of matrix key distribution technique and Gaussian distribution to achieve this goal. Secondly, security mechanisms are proposed for such a group-based network architecture in which sensed data collected at numerous, inexpensive sensor nodes are filtered by local processing on its way through more capable and compromise-tolerant reporting nodes. We address the upstream requirement that reporting nodes authenticate data produced by sensors before aggregating and the downstream requirement that sensors authenticates commands disseminated from reporting nodes. Security analysis is presented to quantify the strength of the proposed scheme against security threats. Through simulations, we validate the analytical results.
收起
摘要 :
Due to the half-duplex property of the sensor radio and the broadcast nature of wireless medium, limited bandwidth remains a pressing issue for wireless sensor networks (WSNs). The design of multi-channel MAC protocols has attract...
展开
Due to the half-duplex property of the sensor radio and the broadcast nature of wireless medium, limited bandwidth remains a pressing issue for wireless sensor networks (WSNs). The design of multi-channel MAC protocols has attracted the interest of many researchers as a cost effective solution to meet the higher bandwidth demand for the limited bandwidth in WSN. In this paper, we present a scheduled-based multi-channel MAC protocol to improve network performance. In our protocol, each receiving node selects (schedules) some timeslot(s), in which it may receive data from the intending sender(s). The timeslot selection is done in a conflict free manner, where a node avoids the slots that are already selected by others in its interference range. To minimize the conflicts during timeslot selection, we propose a unique solution by splitting the neighboring nodes into different groups, where nodes of a group may select the slots allocated to that group only. We demonstrate the effectiveness of our approach thorough simulations in terms of performance parameters such as aggregate throughput, packet delivery ratio, end-to-end delay, and energy consumption.
收起
摘要 :
Though plenty of research works have been done on stop word/phrase detection, there is no work done on Bengali stop words
and stop phrases. This research innovates the definition and classification of Bengali stop words and phras...
展开
Though plenty of research works have been done on stop word/phrase detection, there is no work done on Bengali stop words
and stop phrases. This research innovates the definition and classification of Bengali stop words and phrases and implements
two approaches to identify them. First one is a corpus-based approach, while the second one is based on the finite-state
automaton. Performance of both approaches is measured and compared. Result analysis shows that corpus-based method
outperforms the finite-state automaton-based method. The corpus-based and finite-state automaton-based method shows 90%
and 80% of accuracy, respectively, for stop word detection and 80% and 70% accuracy, respectively, for stop phrase detection.
收起
摘要 :
Wireless Sensor Network (WSN) is highly budgeted by energy since sensor nodes are mostly battery-powered and deployed in hard-to-reach area for prolonged duration. Moreover radio communication is very expensive for WSN. At the sam...
展开
Wireless Sensor Network (WSN) is highly budgeted by energy since sensor nodes are mostly battery-powered and deployed in hard-to-reach area for prolonged duration. Moreover radio communication is very expensive for WSN. At the same time, a substantial portion WSN applications require periodic data collection. In this paper we investigate this issue in depth and present a solution architecture: 2PDA, that eliminates repeated transmission. The solution is founded upon temporal linear correlation among sensor data. Instead of sending each data packet we model them using method of least square that exploits temporal correlation among sensor data. 2PDA observes sensor data and performs operation parameterized by application-precision. After successful computation only the parameters of the model are sent over the radio to the application-end or sink. 2PDA was implemented in TinyOS. Implementation showed a significant improvement (i.e. 80%) for the node's life-time. Rigorous numerical analysis was done on various sensor data which indicated its modest efficiency under different scenario. Effects of various parameters such as type of sensory information, time and place of data collection were assessed. Finally a network simulation was carried out to evaluate its scalability.
收起