Advanced Driver-Assistance Systems (ADAS) help reducing traffic accidents caused by distracted driving. One of the features of ADAS is Forward Collision Warning System (FCWS). In FCWS, car detection is a crucial step....
Advanced Driver-Assistance Systems (ADAS) help reducing traffic accidents caused by distracted driving. One of the features of ADAS is Forward Collision Warning System (FCWS). In FCWS, car detection is a crucial step. this paper explains about car detection system using cascade classifier running on embedded platform. the embedded platform used is NXP SBC-S32V234 evaluation board with 64-bit Quad ARM Cortex-A53. the system algorithm is developed in C++ programming language and used open source computer vision library, OpenCV. For car detection process, object detection by cascade classifier method is used. We trained the cascade detector using positive and negative instances mostly from our self-collected Malaysian road dataset. the tested car detection system gives about 88.3 percent detection accuracy with images of 340 by 135 resolution (after cropped and resized). When running on the embedded platform, it managed to get average 13 frames per second with video file input and average 15 frames per second with camera input.
Magnetic resonance imaging (MRI) is an important medical diagnosis technique in clinical diagnosis, while the quality of MR images is always damaged by the noise which is caused in the image acquisition process. In th...
详细信息
ISBN:
(数字)9781728182063
ISBN:
(纸本)9781728182070
Magnetic resonance imaging (MRI) is an important medical diagnosis technique in clinical diagnosis, while the quality of MR images is always damaged by the noise which is caused in the image acquisition process. In the classic image denoising methods, how to design an excellent regularizer withthe prior knowledge of image is the key to solve the denoising problem. In this work, we introduce the deep neural regularizer for the MRI denoising tasks, the deep neural regularizer is made up of neural network structure and objective function, similar to the classic regularizer, both of these two parts are designed withthe prior knowledge of image. the proposed neural network has three main parts: encoder network, decoder network and skip connections, the encoder network which consists of five down-sampling blocks is enforced to deeply extract low-resolution or highly-abstract MR image features, similar to the encoder network architecture, the decoder network is made up of five up-sampling blocks and is enforced to restore high-resolution MR image features. To generate more finer image features, we also use skip connections to transmit the abstract information from encoder to decoder directly. the objective function consists of data fidelity term and image quality penalty term, specifically, to enforce the capability of data fidelity term, we add the self-designed image structural consistency calculation to data fidelity term besides only calculating the image consistency over image pixels with mean squared error. Meanwhile, to guide the network generate more clearer image and reduce noise information, withthe prior knowledge of image sharpness, an image quality penalty term which calculates the MR image sharpness is also added to the objective function. Experimental results over the simulated MRI data and real clinical data demonstrate the proposed network can achieve superior performance compared with other methods in terms of peak signal to noise ratio, structure simi
Graph databases represent a paradigm shift from relational databases with a strong support for "relationships". As compared to relational databases which compute relationships at runtime, graph databases per...
详细信息
ISBN:
(纸本)9781538646922
Graph databases represent a paradigm shift from relational databases with a strong support for "relationships". As compared to relational databases which compute relationships at runtime, graph databases persist relationships for fast querying and data retrieval. this work presents a recipe recommender as a graph database, Neo4j application. Given any set of ingredients, this application recommends a variety of recipes withthe help of a data set containing thousands of ingredients. Further based on availability of ingredients with a user, this application helps discover the list of possible dishes withthese ingredients. In order to implement this application, ingredients and recipes have been crawled from cookery based websites using Python scripts. the crawled data has been inserted into the Neo4j database and subsequently inter-relationships between ingredients and recipes nodes have been analyzed. Execution of self designed queries has verified the time-efficiency of the proposed approach.
Novel data intensive applications and the diversification of data processing platforms have changed data management significantly over the last decade. In this changed environment, the expressiveness of the traditiona...
详细信息
In a distributed system, programs interact with each other to achieve its functionality. To build a robust system, developers should care about exception handling. this paper propose a dynamic analysis method to explo...
详细信息
ISBN:
(纸本)9781538614457
In a distributed system, programs interact with each other to achieve its functionality. To build a robust system, developers should care about exception handling. this paper propose a dynamic analysis method to explore exception handling strategies of a third-party library without looking code. In result section, we explore an operation which connects to a MySQL server.
Machine learning has opened up the opportunity for understanding how the brain works. In this paper, functional magnetic resonance imaging (fMRI) data are analyzed with reduced dimension. We have carried out a perform...
详细信息
ISBN:
(纸本)9781728129723
Machine learning has opened up the opportunity for understanding how the brain works. In this paper, functional magnetic resonance imaging (fMRI) data are analyzed with reduced dimension. We have carried out a performance comparison of random projection (RP) and principal component analysis (PCA) with different number of components of fMRI data. In addition to that, six different types of machine learning algorithm have been used. In particular, the Haxby dataset is chosen for our experiment. the dataset comprises 9 classes for object recognition. 10-fold cross validation step has been employed. We have discovered that RP outperforms PCA when the former is paired with logistic regression, Gaussian Naive Bayes and linear support vector machine. the best pair for this study was found to be PCA and k-nearest neighbors. Nevertheless, each algorithm was found to have its own strengths for fMRI classification approach.
Drivers can easily be distracted by their handheld devices while they are driving and this ultimately contributed to the increase of road accidents. this work proposed a steering wheel cover that is designed using an ...
详细信息
the key to any nameless representation of syntax is how it indicates the variables we choose to use and thus, implicitly, those we discard. Standard de Bruijn representations delay discarding maximally till the leaves...
the key to any nameless representation of syntax is how it indicates the variables we choose to use and thus, implicitly, those we discard. Standard de Bruijn representations delay discarding maximally till the leaves of terms where one is chosen from the variables in scope at the expense of the rest. Consequently, introducing new but unused variables requires term traversal. this paper introduces a nameless 'co-de-Bruijn' representation which makes the opposite canonical choice, delaying discarding minimally, as near as possible to the root. It is literate Agda: dependent types make it a practical joy to express and be driven by strong intrinsic invariants which ensure that scope is aggressively whittled down to just the support of each subterm, in which every remaining variable occurs somewhere. the construction is generic, delivering a universe of syntaxes with higher-order meta variables, for which the appropriate notion of substitution is hereditary. the implementation of simultaneous substitution exploits tight scope control to avoid busywork and shift terms without traversal. Surprisingly, it is also intrinsically terminating, by structural recursion alone.
the Smith-Waterman algorithm is very sensitive but computationally intensive on general purpose CPUs. On the other hand, the FPGA has proven to be an excellent platform for accelerating the algorithm in addition to it...
详细信息
ISBN:
(纸本)9781538642337
the Smith-Waterman algorithm is very sensitive but computationally intensive on general purpose CPUs. On the other hand, the FPGA has proven to be an excellent platform for accelerating the algorithm in addition to its low cost and power consumption. this paper therefore proposes the use of the parallelism and carry-free propagation properties of Residue Number Systems (RNS) to accelerate the algorithm on an FPGA;a deviation from the usual binary/decimal implementations. Compared to the only previous known work that uses RNS for this task, our implementation is (1) the first to employ the use of Linear Systolic Arrays (LSA), (2) avoid the use of Lookup Tables, (3) has a larger dynamic range and (4) aligns long sequences. Implemented on a modest hardware and on a Kintex7 FPGA, we achieved a performance improvement of 169 times over the general-purpose processor implementation. this result was obtained using the naive implementation of LSAs, indicating the positive effects of using RNS.
functional Dependency extraction is a useful way to find inherent rules that apply in a given dataset. However, not all of such rules are exact, datasets comprised of real-world measurements can often contain rules th...
ISBN:
(数字)9781728156255
ISBN:
(纸本)9781728156262
functional Dependency extraction is a useful way to find inherent rules that apply in a given dataset. However, not all of such rules are exact, datasets comprised of real-world measurements can often contain rules that are supported by a significant portion of the dataset (so-called Approximate functional Dependencies), with only a few exceptions. Extracting such rules is also very beneficial, e.g. for estimating the achievable classification precision on a dataset. Sequential Indexing Tables (SITs) are an extended version of Lookup Tables, in which multidimensional problem space is broken down to a sequence of 1D and 2D lookup tables, where each member of the sequence forms a layer and processes the values of one given attribute. In this paper, a SIT -based dependency extractor is proposed that can be used to extract Approximate functional Dependencies from datasets.
暂无评论