Stevens Institute of Technology

About: Stevens Institute of Technology is a education organization based out in Hoboken, New Jersey, United States. It is known for research contribution in the topics: Cognitive radio & Wireless network. The organization has 5440 authors who have published 12684 publications receiving 296875 citations. The organization is also known as: Stevens & Stevens Tech.

Asynchronous Online Federated Learning for Edge Devices with Non-IID Data

Abstract: Federated learning (FL) is a machine learning paradigm where a shared central model is learned across distributed devices while the training data remains on these devices. Federated Averaging (FedAvg) is the leading optimization method for training non-convex models in this setting with a synchronized protocol. However, the assumptions made by FedAvg are not realistic given the heterogeneity of devices. First, the volume and distribution of collected data vary in the training process due to different sampling rates of edge devices. Second, the edge devices themselves also vary in latency and system configurations, such as memory, processor speed, and power requirements. This leads to vastly different computation times. Third, availability issues at edge devices can lead to a lack of contribution from specific edge devices to the federated model. In this paper, we present an Asynchronous Online Federated Learning (ASO-Fed) framework, where the edge devices perform online learning with continuous streaming local data and a central server aggregates model parameters from clients. Our framework updates the central model in an asynchronous manner to tackle the challenges associated with both varying computational loads at heterogeneous edge devices and edge devices that lag behind or dropout. We perform extensive experiments on a benchmark image dataset and three real-world datasets with non-IID streaming data. The results demonstrate ASO-Fed converging fast and maintaining good prediction performance.

Optimizing the secure evaluation of twig queries

Abstract: The rapid emergence of XML as a standard for data exchange over the Web has led to considerable interest in the problem of securing XML documents. In this context, query evaluation engines need to ensure that user queries only use and return XML data the user is allowed to access. These added access control checks can considerably increase query evaluation time. In this paper, we consider the problem of optimizing the secure evaluation of XML twig queries. We focus on the simple, but useful, multi-level access control model, where a security level can be either specified at an XML element, or inherited from its parent. For this model, secure query evaluation is possible by rewriting the query to use a recursive function that computes an element's security level. Based on security information in the DTD, we devise efficient algorithms that optimally determine when the recursive check can be eliminated, and when it can be simplified to just a local check on the element's attributes, without violating the access control policy. Finally, we experimentally evaluate the performance benefits of our techniques using a variety of XML data and queries.

Leadership Skills Development for Engineers

Abstract: :Leadership must be a key element advancing for the engineering profession to remain relevant and connected in an era of heightened outsourcing and global competition Companies intent on m

Securing Data in Internet of Things (IoT) Using Cryptography and Steganography Techniques

Abstract: Internet of Things (IoT) is a domain wherein which the transfer of data is taking place every single second. The security of these data is a challenging task; however, security challenges can be mitigated with cryptography and steganography techniques. These techniques are crucial when dealing with user authentication and data privacy. In the proposed work, the elliptic Galois cryptography protocol is introduced and discussed. In this protocol, a cryptography technique is used to encrypt confidential data that came from different medical sources. Next, a Matrix XOR encoding steganography technique is used to embed the encrypted data into a low complexity image. The proposed work also uses an optimization algorithm called Adaptive Firefly to optimize the selection of cover blocks within the image. Based on the results, various parameters are evaluated and compared with the existing techniques. Finally, the data that is hidden in the image is recovered and is then decrypted.