Full-screen magnification for windows using DirectX Overlays.

The design of hardware-friendly architectures with low computational overhead is desirable for low latency realization of CNN on resource-constrained embedded platforms. In this work, we propose CAxCNN, a Canonic Sign Digit (CSD) based approximation methodology for representing the filter weights of pre-trained CNNs.The proposed CSD representation allows the use of multipliers with reduced computational complexity. The technique can be applied on top of state-of-the-art CNN quantization schemes in a complementary manner. Our experimental results on a variety of CNNs, trained on MNIST, CIFAR-10 and ImageNet datasets, demonstrate that our methodology provides CNN designs with multiple levels of classification accuracy, without requiring any retraining, and while having a low area and computational overhead. Furthermore, when applied in conjunction with a state-of-art quantization scheme, CAxCNN allows the use of multipliers, which offer 77% logic area reduction, as compared to their accurate counterpart, while incurring a drop in Top-1 accuracy of just 5.63% for a VGG-16 network trained on ImageNet.

A hybrid scheme for multicast authentication over lossy networks

Embedded systems require even more flexibility. Several system permits on-the-market software updates. However these updates must be reliable, otherwise, the results can be catastrophic. Device drivers may have any updates and they are very vulnerable to this problem, requiring mechanisms that are able to capture errors arising from updates at runtime. This work proposes an approach for runtime errors checking in the driver when accessing the device, allowing detecting bugs throughout the lifetime of the embedded system. The proposed mechanism for capturing errors is composed of two modules: Monitor of Device/Driver Communication (MDDC) and the set of FSM. Both modules can be synthesized from a device description at a high-level of abstraction. When connected to a hardware platform in a FPGA they are able to check if the driver operations will lead to a correct state of operation. Thus, the designer can be sure that the updated device driver is reliable. To validate the technique, drivers for an Ethernet controller and a serial port were developed. Results show the effectiveness in finding device driver errors during runtime, as well low MDDC's overhead about 1.5% in terms of performance and footprint area of the system FPGA prototype.

Problem statement: The heterogeneity in the choice of simulation platforms for real time scheduling stands behind the difficulty of developing a common simulation environment. A Discrete Event Simulation (DES) for a real time scheduling domain encompassing event definition, time advancing mechanism and scheduler has yet to be developed. Approach: The study focused on the proposed and the development of an event based discrete event simulator for the existing General Utility Scheduling (GUS) to facilitate the reuse of the algorithm under a common simulation environment. GUS is one of the existing TUF/UA scheduling algorithms that consider the Time/Utility Function (TUF) of the executed tasks in its scheduling decision. The scheduling optimality criteria are based on maximizing accrued utility accumulated from execution of all tasks in the system. These criteria are named as Utility Accrual (UA). The TUF/ UA scheduling algorithms are design for adaptive real time system environment. The developed GUS simulator has derived the set of parameter, events, performance metrics and other unique TUF/UA scheduling element according to a detailed analysis of the base model. Results: The Accrued Utility Ratio (AUR) is investigated and compared to the benchmark of the modeled domain. Successful deployment of the GUS simulator was proven by the generated results. Conclusion: Extensive performance analysis of GUS simulator can be deployed using the developed simulator with low computational overhead. Further enhancements were to extend the developed GUS simulator with detail performance metrics together with a fault tolerance mechanism to support a reliable real time application domain.

Wireless Sensor Networks have been an active area of research owing to its myriad range of applications. Traditional security protocols are not feasible for such networks due to their resource constraint nature. However, ECC has been considered as a viable cryptographic technique due to its low computational overhead. In this paper study and application of ECC on a popular WSN operating system, TinyOS, has been carried out. Practical implementation of the ECC operations has been performed using TinyECC library. TinyECC has been used to develop custom security protocols on TinyOS. The performance benchmarking of the proposed protocols has also been carried out. The developed protocol has been fused on the MicaZ Motes.

In this paper, we address the camera selection problem by fusing the performance of multiple trackers. Currently, all the camera selection/hand-off approaches largely depend on the performance of the tracker deployed to decide when to hand-off from one camera to another. However, a slight inaccuracy of the tracker may pass the wrong information to the system such that the wrong camera may be selected and error may be propagated. We present a novel approach to use multiple state-of-the-art trackers based on different features and principles to generate multiple hypotheses and fuse the performance of multiple trackers for camera selection. The proposed approach has very low computational overhead and can achieve real-time performance. We perform experiments with different numbers of cameras and persons on different datasets to show the superior results of the proposed approach. We also compare results with a single tracker to show the merits of integrating results from multiple trackers.

We describe the design and implementation of public key infrastructure for the Bristol University Cyberjacket and three initial applications. The first one removes the need for the user to remember passwords, the second application provides an authentic record that a meeting took place, the third provides an authentic record of a conversation. The wearable public key infrastructure (WPKI) we develop uses very small communication, whilst also providing a balanced and low computational overhead on both the 'client' and 'server' sides.

Secret sharing (SS) technology is widely used in multi-party computation (MPC) because of its simple secret structure and low computational overhead. Aiming at solving the problem that the existing SS-MPC scheme cannot solve the collusion of all computing parties to recover the original data, this work designs a practical SS-MPC for collusion whole (PSCW) scheme. Through the negotiation of redundant computing nodes and redundant security parameters between computing parties, PSCW scheme can ensure that original data cannot be recovered even if all computing nodes collude to obtain all secret shares, which guarantees the confidentiality of the scheme. At the same time, with the addition of redundant computing nodes, PSCW scheme can correctly realize computing requirements of users and ensure the correctness of the calculation results. Compared with the existing SS-MPC scheme, PSCW scheme has higher security and higher application value in real scenes.

In this paper, a user selection problem for multiuser multiple-input multiple-output systems in the general wireless environment with full-rank and rank-deficient channel users is investigated. It is demonstrated that the maximum number of simultaneously supportable users is elastic, and the spatial resources occupied by each user can be squeezed in the rank-deficient environment. Therefore, a user selection algorithm is then proposed with relatively low computational overhead. The data rate requirement distinctions of different services are considered in the user selection criterion, and the resources occupied by real-time service users are primarily squeezed since they do not need extremely high data rate. Numerical results show that the effective throughput and the number of selected users achieved by the proposed user selection algorithm are larger than that of exiting researches.

The Extensible Markup Language (XML) rapidly establishes itself as the de facto standard for presenting, storing, and exchanging data on the Internet. However, querying large volume of XML data represents a bottleneck for several computationally intensive applications. A fast and accurate selectivity estimation mechanism is of practical importance because selectivity estimation plays a fundamental role in XML query performance. Recently proposed techniques are all based on some forms of structure synopses that could be time-consuming to build and not effective for summarizing complex structure relationships. To overcome this limitation, we propose an innovative selectivity estimation algorithm, which consists of (1) the path tree synopsis data structure, a succinct description of the original document with low computational overhead and high accuracy for processing tasks like selectivity estimation, (2) a streaming selectivity estimation algorithm which is efficient for path tree traversal. Extensive experiments on both real and synthetic data sets show that our technique achieves better accuracy and less construction time than existing approaches.

This paper presents improved methods to detect cracks and thermal leakage in building envelopes using unmanned aerial vehicles (UAV) (i.e., drones) with video camcorders and/or infrared cameras. Three widely used contour detectors of Sobel, Laplacian, and Canny algorithms were compared to find a better solution with low computational overhead. Furthermore, a scheme using frame-based location identification was developed to effectively utilize the existing approach by finding the current location of the drone-assisted image frame. The results showed a simplified drone-assisted scheme along with automation, higher accuracy, and better speed while using lower battery energy. Furthermore, this paper found that the cost-effective drone with the attached equipment generated accurate results without using an expensive drone. The new scheme of this paper will contribute to automated anomaly detection, energy auditing, and commissioning for sustainably built environments.

Recent advancements in deep learning have shown that multimodal inference can be particularly useful in tasks like autonomous driving, human health, and production line monitoring. However, deploying state-of-the-art multimodal models in distributed IoT systems poses unique challenges since the sensor data from low-cost edge devices can get corrupted, lost, or delayed before reaching the cloud. These problems are magnified in the presence of asymmetric data generation rates from different sensor modalities, wireless network dynamics, or unpredictable sensor behavior, leading to either increased latency or degradation in inference accuracy, which could affect the normal operation of the system with severe consequences like human injury or car accident. In this paper, we propose PATCH, a framework of speculative inference to adapt to these complex scenarios. PATCH serves as a plug-in module in the existing multimodal models, and it enables speculative inference of these off-the-shelf deep learning models. PATCH consists of 1) a Masked-AutoEncoder-based cross-modality imputation module to impute missing data using partially-available sensor data, 2) a lightweight feature pair ranking module that effectively limits the searching space for the optimal imputation configuration with low computation overhead, and 3) a data alignment module that aligns multimodal heterogeneous data streams without using accurate timestamp or external synchronization mechanisms. We implement PATCH in nine popular multimodal models using five public datasets and one self-collected dataset. The experimental results show that PATCH achieves up to 13% mean accuracy improvement over the state-of-art method while only using 10% of training data and reducing the training overhead by 73% compared to the original cost of retraining the model.

Numerical simulations of cardiac electrophysiology are now considered a valuable tool for medical research. To study and explore the cardiac electrical propagation, it is essential to develop and study techniques that allow efficient simulation as well as retain accuracy. The finite difference method has been a popular method for solving the governing equation in the monodomain model of cardiac propagation due to its simplicity and low computational overhead. The inhomogeneous and anisotropic conductive anatomy of the three-dimensional cardiac tissue represents a complex system which involves spatial and temporal derivatives as well as a nonlinear ionic current term. This makes the simulation computationally intensive, and consequently, the development of an efficient computational technique is required to improve the accuracy and efficiency of the simulations. In this paper, a model order reduction technique has been developed which provides low-dimensional approximations for the full-dimensional cardiac monodomain system by using dynamic mode decomposition method. Numerical results show that the reduced order approximations reduce the CPU time by a factor of 5.9, while its RMS difference with original model is 0.9443 mV.

This paper presents a lightweight and adaptive object detection framework tailored for night-time drone surveillance using thermal-RGB fusion. The proposed system integrates a dual-branch CNN backbone to extract modality-specific features, followed by a mid-level fusion strategy that combines thermal and RGB representations into a unified feature map. A real-time adaptive sensor selection mechanism dynamically adjusts the contribution of each modality based on scene context, enhancing robustness under varying illumination conditions. The architecture employs YOLOv5-Nano as a compact feature extraction backbone, supported by quantization and pruning for real-time deployment. Extensive experiments conducted on publicly available datasets, demonstrate superior accuracy and efficiency compared to single-modality and non-adaptive baselines. Ablation studies validate the contribution of each component. The results highlight the system’s capability to achieve high detection performance with low computational overhead, offering a practical and scalable solution for intelligent aerial surveillance in complex night-time environments

Aiming at increasing the satellite link performance, advanced modulation techniques have been thoroughly studied. On the other hand, reliable transmission techniques with a low computational overhead are pursued for many applications in critical scenarios such as: control operation of a satellite while it is placed into its orbit, the disposal of a satellite at the end of its life or the deep-space missions. In these specific mission critical scenarios, fast and correct data reception is even more important than high channel capacity. An unknown and fast variable channel state condition, with large Doppler shifts and low available power require incoherent and light computationally modulation techniques. This paper introduces a whole digital implementation of a receiver, based on the Double Differential PSK (DD-PSK) modulation, that is perfectly compliant with these requirements.