Image processing in digital computer systems usually considers the visual information as a sequence of frames. These frames are from cameras that capture reality for a short period of time. They are renewed and transm...
详细信息
ISBN:
(纸本)9789898425720
Image processing in digital computer systems usually considers the visual information as a sequence of frames. These frames are from cameras that capture reality for a short period of time. They are renewed and transmitted at a rate of 25-30 fps (typical real-time scenario). Digital video processing has to process each frame in order to obtain a filter result or detect a feature on the input. In stereo vision, existing algorithms use frames from two digital cameras and process them pixel by pixel until it is found a pattern match in a section of both stereo frames. Spike-based processing is a relatively new approach that implements the processing by manipulating spikes one by one at the time they are transmitted, like a human brain. The mammal nervous system is able to solve much more complex problems, such as visual recognition by manipulating neuron's spikes. The spike-based philosophy for visual information processing based on the neuro-inspired Address-Event- Representation (AER) is achieving nowadays very high performances. In this work we study the existing digital stereo matching algorithms and how do they work. After that, we propose an AER stereo matching algorithm using some of the principles shown in digital stereo methods.
The use of simulation tools in the development of new Wireless Sensor Networks protocols and applications should be accompanied by minimisation of redundant code and work, making it possible to seamlessly run the same...
详细信息
ISBN:
(纸本)9789898425690
The use of simulation tools in the development of new Wireless Sensor Networks protocols and applications should be accompanied by minimisation of redundant code and work, making it possible to seamlessly run the same code on simulated and real platforms. This work proposes an architecture for a WSN testing platform that integrates simulation tools in an application-transparent way. The platform will be focused on testing the WSN sink node and providing it with both real and simulated data. The novelty of this approach lies in the use of a flexible network simulation tool not focused on a specific network technology, and the use of generic hardware and open source tools.
There are several dementias but Alzheimer's Disease (AD) is leading cause of dementia in the world. There are an estimated 35.6 million people in the world with dementia and more than 18 million of them have Alzhe...
详细信息
There are several dementias but Alzheimer's Disease (AD) is leading cause of dementia in the world. There are an estimated 35.6 million people in the world with dementia and more than 18 million of them have Alzheimer's disease, which supposes more of the 50% of the total people with dementia. In this paper, intelligent algorithms are designed and implemented in order to manipulate Magnetic Resonance Images (MRI) stored in a big data base of patients, with the main purpose of being able for decision-making in classification task. It will be possible to predict whether the patient is healthy, has Mild Cognitive Impairment (MCI), or already has Alzheimer Disease. We tested our method on data from a large data base (more than 1500 patient were analized), with a sensitivity of and specificity close to 90%which is considerable better the human experts, taking into account that in this paper also MCI is classified. It is noteworthy that with this last study we could offer a tool to assist the early diagnosis of dementia and has the potential to be a useful help for clinicians.
Nowadays, there is an increasing tendency for business applications to collect knowledge and information about their users in order to provide the customers with personalized information. Cross-application user modeli...
详细信息
Uncertainty handling is a major issue for the control of real-world systems. Traditional singleton type-1 Fuzzy Logic Controllers (FLCs) with crisp inputs and precise fuzzy sets cannot fully cope with the high levels ...
详细信息
ISBN:
(纸本)9781612840789
Uncertainty handling is a major issue for the control of real-world systems. Traditional singleton type-1 Fuzzy Logic Controllers (FLCs) with crisp inputs and precise fuzzy sets cannot fully cope with the high levels of uncertainties present in real world environments (e.g. sensor noise, environmental impacts, etc.). While non-singleton type-1 fuzzy systems can provide an additional degree of freedom through non-singleton fuzzification of the inputs, it is unclear how this capability relates to singleton type-1 and specifically interval type-2 FLCs in terms of control performance (also because the application of non-singleton type-1 FLCs is quite rare in the literature). In recent years interval type-2 FLCs employing type-2 fuzzy sets with a Footprint of Uncertainty (FOU) have become increasingly popular. This FOU provides an additional degree of freedom that can enable type-2 FLCs to handle the uncertainties associated with the inputs and the outputs of the FLCs. One of the main criticisms of singleton type-2 FLCs is that they outperform (the usually singleton-) type-1 FLCs because they - respectively their type-2 fuzzy sets, employ extra parameters, thus making improved performance an obvious result. In order to address this criticism, we have implemented a non-singleton type-1 FLC which allows a more direct comparison between the non-singleton type-1 FLC and singleton interval type-2 FLC as the number of parameters for both controllers is very similar. The paper details the implementation details of the FLCs for the application of a nonlinear servo system and provides the experimental simulation results which were performed to study the effect of increasing levels of uncertainty (in the form of input noise) and the capability of the individual FLCs to cope with them. We conclude by providing our interpretation of the results and highlighting the essential differences in the uncertainty handling between the (non-) singleton type-1 and singleton interval type-2 FLC
Today's approaches towards heterogeneous computing rely on either the programmer or dedicated programming models to efficiently integrate heterogeneous components. In this work, we propose an adaptive cost-aware f...
详细信息
ISBN:
(纸本)9781450302418
Today's approaches towards heterogeneous computing rely on either the programmer or dedicated programming models to efficiently integrate heterogeneous components. In this work, we propose an adaptive cost-aware function-migration mechanism built on top of a light-weight hardware abstraction layer. With this mechanism, the highly dynamic task of choosing the most beneficial processing unit will be hidden from the programmer while causing only minor variation in the work and program flow. The migration mechanism transparently adapts to the current workload and system environment without the necessity of JIT compilation or binary translation. Evaluation shows that our approach successfully adapts to new circumstances and predicts the most beneficial processing unit (PU). Through fine-grained PU selection, our solution achieves a speedup of up to 2.27 for the average kernel execution time but introduces only a marginal overhead in case its services are not required. Copyright 2011 ACM.
Four kinds of sequences generated by single cycle triangular function （T-function） are investigated to check the possibility for a single cycle T-function to be a cryptographic component in stream ciphers. Based on ...
详细信息
Four kinds of sequences generated by single cycle triangular function （T-function） are investigated to check the possibility for a single cycle T-function to be a cryptographic component in stream ciphers. Based on the special properties of single cycle T-function and an algorithm due to Wei, linear complexities of these four kinds of sequence are all acquired. The results show that single cycle T-function sequences have high linear complexity. Therefore, T-function satisfies the essential requirements being a basic component of stream cipher.
Contemporary embedded systems are often designed as Multiprocessor System-on-Chips (MPSoC) which include multiple processors and other peripherals on a single chip. In contrast to general purpose multiprocessors, the ...
详细信息
Many present applications usually require high communication throughputs. Multiprocessor nodes and multicore architectures, as well as programmable NICs (Network Interface Cards) provide new opportunities to take adva...
详细信息
The increasing focus on green communications is bringing a fresh attention towards the research works on energy-efficient hybrid routing schemes. The energy-efficient hybrid routing schemes are applied in various type...
详细信息
暂无评论