教学课程资源库 更多>>

关键词： Genomics   Bioinformatics   Sequential analysis   Feature extraction   Computer science   Sensitivity   Tools   Novel sequence insertions   insertion contents   genotypes   next-generation sequencing   extended reference  

摘要： Next generation sequencing technology has led to the development of methods for the detection of novel sequence insertions (nsINS). Multiple signatures from short reads are usually extracted to improve nsINS detection performance. However, characterization of nsINSs larger than the mean insert size is still challenging. This article presents a new method, ERINS, to detect nsINS contents and genotypes of full spectrum range size. It integrates the features of structural variations and mapping states of split reads to find nsINS breakpoints, and then adopts a left-most mapping strategy to infer nsINS content by iteratively extending the standard reference at each breakpoint. Finally, it realigns all reads to the extended reference and infers nsINS genotypes through statistical testing on read counts. We test and validate the performance of ERINS on simulation and real sequencing datasets. The simulation experimental results demonstrate that it outperforms several peer methods with respect to sensitivity and precision. The real data application indicates that ERINS obtains high consistent results with those of previously reported and detects nsINSs over 200 base pairs that many other methods fail. In conclusion, ERINS can be used as a supplement to existing tools and will become a routine approach for characterizing nsINSs.

关键词： Computer science  

摘要： With the extensive use of biometrics for authenticating users, the need to ensure privacy of biometric data is greater than ever before. Biometric authentication systems are vulnerable to attacks and the loss of biometric data will lead to loss of privacy of an individual. Multibiometrics refers to the use of multiple biometric modalities simultaneously in order to perform matching. In this work, we introduce a multibiometric fusion technique which can be used to ensure that the original raw biometric data are unlikely to be compromised and, at the same time, recognition can be performed. The face and the iris biometric modalities are fused at the feature-level to produce discriminative embeddings that can be used for recognition. The original face or the iris cannot be retrieved from the combined representation, thus preserving the privacy of the individual. We present the results of this approach, provide analysis, discuss the challenges, and list possible future directions.

关键词： Training   Feature extraction   Redundancy   Quantization (signal)   Computer science   Amplitude modulation   Cameras   Person re-identification   hashing   self distillation   mutual learning  

摘要： Person Re-identification (ReID) aims to retrieve the pedestrian with the same identity across different views. Existing studies mainly focus on improving accuracy, while ignoring their efficiency. Recently, several hash based methods have been proposed. Despite their improvement in efficiency, there still exists an unacceptable gap in accuracy between these methods and real-valued ones. Besides, few attempts have been made to simultaneously explicitly reduce redundancy and improve discrimination of hash codes, especially for short ones. Integrating Mutual learning may be a possible solution to reach this goal. However, it fails to utilize the complementary effect of teacher and student models. Additionally, it will degrade the performance of teacher models by treating two models equally. To address these issues, we propose a salience-guided iterative asymmetric mutual hashing (SIAMH) to achieve high-quality hash code generation and fast feature extraction. Specifically, a salience-guided self-distillation branch (SSB) is proposed to enable SIAMH to generate hash codes based on salience regions, thus explicitly reducing the redundancy between codes. Moreover, a novel iterative asymmetric mutual training strategy (IAMT) is proposed to alleviate drawbacks of common mutual learning, which can continuously refine the discriminative regions for SSB and extract regularized dark knowledge for two models as well. Extensive experiment results on five widely used datasets demonstrate the superiority of the proposed method in efficiency and accuracy when compared with existing state-of-the-art hashing and real-valued approaches. The code is released at https://***/Vill-Lab/SIAMH.

ISBN: (纸本)9783885797081

摘要： ~~

关键词： Classification methods   concept classification   deep learning   link prediction   ontology extension  

摘要： In information technology, an ontology is a knowledge structure consisting of terminologies (topics), their definitions, and relational information within one or multiple domains. This semantically represented information can be used for downstream tasks, such as document classification and recommendation systems. However, as big data prevails, manually extending existing ontologies with up-to-date information becomes challenging due to the tedious and time-consuming process and the expensive cost of expert manual labor. To alleviate this problem, this paper aims to achieve a fully automatic ontology extension. We propose a novel "Direct'' approach for extending an existing Computer Science Ontology (CSO). This approach consists of two steps: initially extending the CSO with new topics and using this extended graph to obtain the new topic's node embeddings as inputs for training classifiers. However, this initial extension still contains numerous noisy links;therefore, the classifier simultaneously acts as a noisy-link filter and a link predictor. We experiment with various traditional machine learning and recent deep learning models and then compare them under our Direct approach framework. We propose two evaluation procedures to decide the best-performing model: a novel Wikipedia-based F1(w) score and a total number of resulting links. Further meta-evaluation employing four experts confirmed the reliability of our proposed approach and evaluation procedures. We found that the Direct approach's Gaussian Naive Bayes model produces the most valid and reliable links;therefore, we use it to further extend the CSO with hundreds of new CS topics and links.

关键词： Signal processing algorithms   Complexity theory   Parallel processing   Target tracking   Monte Carlo methods   Computer science   Kalman filters   Parallel   distributed particle filters   resampling   performance analysis   state size   system complexity  

摘要： Particle filters have been widely used in various fields due to their advantages in dealing with non-linear and/or non-Gaussian systems. A large number of particles are needed to guarantee the convergence of particle filters for the state estimation, especially for large-scale complex systems. Therefore, parallel/distributed particle filters were adopted to improve the performance, in which different paradigms of resampling were proposed, including the centralized resampling, the decentralized resampling, and the hybrid resampling. To ease their adoptions, we analyze time consumptions and speedup factors of parallel/distributed particle filters with various resampling algorithms, state sizes, system complexities, numbers of processing units, and model dimensions in this study. The experimental results indicate that the decentralized resampling achieves the highest speedup factors due to the local transfer of particles, the centralized resampling always has the lowest speedup factors because of the global transfer of particles, and the hybrid resampling attains the speedup factors between. Moreover, we define the complexity-state ratio, as the ratio between the system complexity and the system state size to study how it impacts the speedup factor. The experiments show that the higher complexity-state ratio results in the increase of the speedup factors. This is one of the earliest attempts to analyze and compare the performance of parallel/distributed particle filters with different resampling algorithms. The analysis can provide potential solutions for further performance improvements and guide the appropriate selection of the resampling algorithm for parallel/distributed particle filters.

摘要： Tutoring is in high demand in Computer Science Education. In-person tutoring is usually very effective and desired but may not always be available due to lack of resources. Due to the fast-growing development of Artificial Intelligence (AI), online tutoring is now feasible and becomes a promising option in Computer Science (CS) education. AI has become a boon to modern life, as it is improving in sectors such as healthcare, banking, online shopping, education, chatbots, and cybersecurity. Chatbots have quickly become a new trend in recent decades. They make life easier for customers by answering questions, serving as a personal assistant for simple tasks such as scheduling meetings, adding events to the calendar, making calls, assisting with payment processes and so on. The primary goal is to enhance the customer experience and achieve high levels of customer satisfaction. To enable intelligent tutoring in CS education, we designed and implemented an AI-based chatbot to clarify various specific questions related to Computer Science courses at California State University Sacramento (Sac State). Students can ask as many questions as they want and receive answers to those questions immediately. Students will be able to enhance their communication and increase productivity. This application also will help the instructors or Teaching Assistants (TAs) to add, edit, or delete the bot's questions and answers through the user experience. The bot is implemented via Neural networks for Natural Language Processing (NLP) using text analytics. It is able to learn from the conversation and respond efficiently.

关键词： Complexity theory   Cognition   Dynamical systems   Predictive models   Complex systems   Prediction algorithms   Emergent phenomena   Adaptation   biodiversity   cognition   cognitive load   complexity   emergence  

摘要： Cognitive research has found people are sometimes adept and sometimes inept at handling complexity. Complexity is a key concept in much of cognitive science, yet the field has scarcely incorporated any of the work in complexity theory. Complexity theory may generally be too abstract to easily apply to human cognition studies. Here, the problem is addressed by considering complexity through constructing a model of epistemic emergence, Cognitive-Habitat Strategy-Ecosystem, (CHSE) to act as an overarching framework into which different conceptions of complexity and cognition can be integrated, describing how they will interact to affect cognition in complex systems. This model provides value both at the micro level, by generating specific predictions, and at the macro level, through hypothesizing interactions between other cognitive theories such as cognitive load and adaptation from failure. We detail the model's assumptions, functionality, and possible ways to measure variables.

关键词： Search problems   Heuristic algorithms   Benchmark testing   Optimization   Computer science   Additives   Tuners   Partial Max-SAT   adaptive parameter tuning   variable depth search   stochastic local search   Max-SAT evaluation  

摘要： The Partial Max-SAT (PMSAT) problem is an optimization variant of the well-known Propositional Boolean Satisfiability (SAT) problem. It holds an important place in theory and practice, because a huge number of real-world problems, such as timetabling, planning, routing, bioinformatics, fault diagnosis, etc., could be encoded into it. Stochastic local search (SLS) methods can solve many real-world problems that often involve large-scale instances at reasonable computation costs while delivering good-quality solutions. In this work, we propose a novel SLS algorithm called adaptive variable depth SLS for PMSAT problem solving based on a dynamic local search framework. Our algorithm exploits two algorithmic components of an SLS method: parameter tuning and neighborhood search. Our first contribution is the design of an adaptive parameter tuner that searches for the best parameter setting for each instance by considering its features. The second contribution is a variable depth neighborhood search (VDS) algorithm adopted for PMSAT problem, which our empirical evaluation proves is a more efficient w.r.t. single neighborhood search. We conducted our experiments on the PMSAT benchmarks from MaxSAT Evaluation 2014 to 2019, including more than 3600 instances which have been encoded from a broad range of domains such as verification, optimization, graph theory, automated-reasoning, pseudo Boolean, etc. Our experimental evaluation results show that AVD-SLS solver, which is implemented based on our algorithm, outperforms state-of-the-art PMSAT SLS solvers in most benchmark classes, including random, crafted, and industrial instances. Furthermore, AVD-SLS reports remarkably better results on weighted benchmark, and shows competitive results with several well-known hybrid PMSAT solvers.