Small Chunks Research Articles

Efficient computation of recurrence quantification analysis via microstates

Recurrence plot (RP) is a powerful tool in the study of nonlinear dynamics, being successfully applied in economics, medicine, geophysics, and astronomy. The Recurrence Quantification Analysis (RQA) consists of a methodology to compute RP quantifiers based on statistics over vertical/diagonal recurrent lines, densities, and other features of the RP. The traditional way to calculate the quantifiers computes each recurrent point individually and builds the histogram of the whole RP. Here we propose a new, statistical approach to calculate the quantifiers using the (recurrence) microstates, which are small representative chunks of the RP. The new way of statistically calculating the quantifiers converges fast and brings a computational gain. In particular, it reduces the time complexity from O(K2) to O(K), for K the size of the time-series. Moreover, we show that our results are independent of the system and series size.

A Pediatric Resident Curriculum for the Use of Health Literacy Communication Tools.

Background:Despite evidence that use of evidence-based communication tools (EBCT) with a universal precautions approach improves health outcomes, medical trainees report inadequate skills training.Objective:We developed, implemented, and evaluated a novel, interactive curriculum featuring a 30-minute, single-session didactic with video content, facilitated case-based discussions and preceptor modeling to improve use of EBCT among pediatric residents. A direct observation (DO) skills checklist was developed for preceptors to evaluate resident use of EBCT.Methods:Shortly after implementation of the curriculum, residents completed a survey assessing self-reported frequency of EBCT use both pre- and post-intervention. DOs were conducted 2 to 3 weeks after the didactic was completed and scores were compared among residents who participated in the curriculum and those who did not. A longitudinal 6-month follow-up survey was also distributed to assess changes over time.Key Results:Forty-seven of 78 (60%) of residents completed the survey and 45 of 60 (75%) of the eligible residents participated in the DO. There was significant change in self-reported use of all but one EBCT after participation in the curriculum. Residents reported sustained increased frequency of use of all communication tools except for Teach Back, Show Back, and explanation of return precautions in the 6 months following the curriculum. Notably, there was no significant difference in resident scores in the DO among residents who participated in the didactic session and those who did not.Conclusions:This novel interactive curriculum addresses ACGME (Accreditation Council for Graduate Medical Education) core competencies and fulfills a needed gap in resident curricula for health literacy-related skills training. Findings suggest a small, positive affect on frequency of self-reported use of health literacy EBCT. However, our findings demonstrate a lack of parallel improvement in resident performance during DO. Future curricula may require certain modifications, as well as reinforcement at regular intervals. [HLRP: Health Literacy Research and Practice. 2022;6(2):e121–e127.]Plain Language Summary:Use of evidence-based communication tools, such as presenting information in small chunks and avoiding complex medical terms among pediatric trainees, is limited. This study describes a new and interactive health literacy curriculum, with emphasis on preceptor modeling and DO to improve use of evidence-based communication tools among residents. After participation in the curriculum, residents report greater use of evidence-based communication tools. However, results from DO of residents did not demonstrate similar improvements.

Review Paper on LoRa based technologies for Vehicular and Tracking applications

Abstract: LoRa stands For Long Range. It is a low powered wide area network derived from chirp spread spectrum technology and encodes information through chirp pulses on to the radio waves. The range of LoRa greatly varies from few meters to approximately 100 Kilometers depending on the mode of operation. The main advantage of LoRa against Bluetooth, WiFi and ZigBee is its long range and it is well suited for transmission of small chunks of data with low bit rates. LoRa is generally operated at 915MHz, 868MHz and 433MHz which are Sub-Giga Heartz bands. These are a part of the ISM bands which are reserved for Industrial and Medical Purposes Internationally which are free of cost and do not require any kind of licensing. Vehicular communication is a form of exchanging messages between various vehicular and roadside units regarding their location, speed and much more. The LoRa technology when integrated with Vehicular Communication establishment of green corridors for Emergency vehicles by clearing the traffic and help in reaching the destination with minimal time delay. Keywords: LoRa, ISM Bands, Vehicular Communication

Conquering the LANTITE: Exploring Digital Mathematics Instruction & Test Taking Strategies using a Cognitive Multimedia Framework Based Portal

In 2015, all Australian education ministers agreed that from 1 July 2016 the Government would initiate the Literacy and Numeracy Test for Initial Teacher Education (LANTITE), designed to verify that all prospective teachers could demonstrate the literacy and numeracy skills required in their profession. The LANTITE quickly became another hurdle for educators and could be the most influential gatekeeper ever implemented in Australian Initial Teacher Education (ITE) programs. Institutions, therefore, instigated support programs to help their students pass the LANTITE. This paper describes once such intervention which is modelled on the Cognitive Theory of Multimedia Learning and is designed for a context where students were placed at a distance and required self-learning approaches. This digital mathematics portal showed a significant improvement in students' ability to pass the LANTITE. The paper also identifies a set of guidelines for future portals, allowing students to measure their knowledge, using flexible picture and video resources, providing the ability to flexibly absorb content in small chunks, and giving students effective testing strategies in addition to content knowledge. Future work will look at how these strategies can be implemented and extended, specifically, for students who have a history of failing the test in the past.

B2-Tree: Page-Based String Indexing in Concurrent Environments

Recently proposed index structures, that combine trie-based and comparison-based search mechanisms, considerably improve retrieval throughput for in-memory database systems. However, most of these index structures allocate small memory chunks when required. This stands in contrast to block-based index structures, that are necessary for disk-accesses of beyond main-memory database systems such as Umbra. We therefore present the B2-tree. The outer structure is identical to that of an ordinary B+-tree. It still stores elements in a dense array in sorted order, enabling efficient range scan operations. However, B2-tree is composed of multiple trees, each page integrates another trie-based search tree, which is used to determine a small memory region where a sought entry may be found. An embedded tree thereby consists of decision nodes, which operate on a single byte at a time, and span nodes, which are used to store common prefixes. This architecture usually accesses fewer cache lines than a vanilla B+-tree as shown in our performance evaluation. As a result, the B2-tree answers point queries considerably faster. Concurrent access to B2-tree pages are managed by an optimistic locking protocol which results in high utilization of the available hardware resources. Our evaluation of read-write workloads attests more than competitive performance for the B2-tree compared to a traditional B+-tree.

Toward Swarm Manufacturing: Architecting a Cooperative 3D Printing System

AbstractSwarm manufacturing is a new paradigm for distributed manufacturing, where each factory uses an army of mobile manufacturing robots working together to manufacture desired products. It focuses on building factories within a local supply chain, where multiple products can be produced to meet changing customer demand from mass manufacturing to on-demand production of customized products. Cooperative 3D printing (C3DP) is a primitive form of swarm manufacturing, where multiple mobile 3D printing robots work together cooperatively to print the desired part, representing a major step toward enabling swarm manufacturing. At the core of C3DP lies the chunk-based printing strategy. This strategy splits the desired part into small chunks. The chunks are then assigned and scheduled to be printed by individual printing robots. In our previous work, we presented various hardware and software components of C3DP, such as mobile 3D printers, chunk-based slicing, scheduling, and simulation. This paper presents a fully integrated and functional C3DP platform with all necessary components and outlines how they work in unison from a system-level perspective. Specifically, the new architecture of hardware and software includes a set of new chunking strategies, a scalable scheduler for multi-robot printing, a SCARA-based printing robot, a mobile platform for robot transportation, a system of modular floor tiles, and a charging station for the mobile platform. Finally, we demonstrate the capability of the system using two case studies with successful large-scale prints.

A nearsighted force-training approach to systematically generate training data for the machine learning of large atomic structures.

A challenge of atomistic machine-learning (ML) methods is ensuring that the training data are suitable for the system being simulated, which is particularly challenging for systems with large numbers of atoms. Most atomistic ML approaches rely on the nearsightedness principle ("all chemistry is local"), using information about the position of an atom's neighbors to predict a per-atom energy. In this work, we develop a framework that exploits the nearsighted nature of ML models to systematically produce an appropriate training set for large structures. We use a per-atom uncertainty estimate to identify the most uncertain atoms and extract chunks centered around these atoms. It is crucial that these small chunks are both large enough to satisfy the ML's nearsighted principle (that is, filling the cutoff radius) and are large enough to be converged with respect to the electronic structure calculation. We present data indicating when the electronic structure calculations are converged with respect to the structure size, which fundamentally limits the accuracy of any nearsighted ML calculator. These new atomic chunks are calculated in electronic structures, and crucially, only a single force-that of the central atom-is added to the growing training set, preventing the noisy and irrelevant information from the piece's boundary from interfering with ML training. The resulting ML potentials are robust, despite requiring single-point calculations on only small reference structures and never seeing large training structures. We demonstrated our approach via structure optimization of a 260-atom structure and extended the approach to clusters with up to 1415 atoms.

From Requirements to Source Code: Evolution of Behavioral Programs

Automatically generating executable code has a long history of arguably modest success, mostly limited to the generation of small programs of up to 200 lines of code, and genetic improvement of existing code. We present the use of genetic programming (GP) in conjunction with context-oriented behavioral programming (COBP), the latter being a programming paradigm with unique characteristics that facilitate automatic coding. COBP models a program as a set of behavioral threads (b-threads), each aligned to a single behavior or requirement of the system. To evolve behavioral programs we design viable and effective genetic operators, a genetic representation, and evaluation methods. The simplicity of the COBP paradigm, its straightforward syntax, the ability to use verification and formal-method techniques to validate program correctness, and a program comprising small independent chunks all allow us to effectively generate behavioral programs using GP. To demonstrate our approach we evolve complete programs from scratch of a highly competent O player for the game of tic-tac-toe. The evolved programs are well structured, consisting of multiple, explainable modules that specify the different behavioral aspects of the program and are similar to our handcrafted program. To validate the correctness of our individuals, we utilize the mathematical characteristics of COBP to analyze program behavior under all possible execution paths. Our analysis of an evolved program proved that it plays as expected more than 99% of the times.

A novel real-time modal analysis method for operational time-varying structural systems based on short-time extension of multivariate VMD

Engineering structures often exhibit time-varying characteristics due to environmental erosion or working conditions during their service life. Therefore, time-varying modal identification plays a crucial role in assessing the health condition of them. However, only the response is measurable, making the identification challenging. Recently, variational mode decomposition (VMD) based methods have been reported on output-only modal identification (OMI) of time-varying structures. Nevertheless, these methods cannot obtain time-varying mode shapes and identify overlapped or wideband modes. This paper develops a short-time method based on multivariate VMD (MVMD) to address these problems. Firstly, long-time non-stationary vibration signals are divided into small chunks, where modes show narrowband characteristics. Then, MVMD is employed on these short-time data chunks to extract multivariate modes. Finally, the instantaneous frequencies are recovered from the center frequencies, and the mode shapes are solved from the extracted multivariate modes. A series of numerical and experimental examples demonstrate that the short-time MVMD (STMVMD) has good noise-robustness, overlapped mode decomposition ability, and mode-tracking ability of time-varying structures.

Covert, Low-Delay, Coded Message Passing in Mobile (IoT) Networks

We introduce a gossip-like protocol for covert message passing between Alice and Bob as they move in an area watched over by a warden Willie. The area hosts a multitude of Internet of (Battlefield) Things (Io <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\beta \text{T}$ </tex-math></inline-formula> ) objects. Alice and Bob perform random walks on a random regular graph. The Io <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\beta \text{T}$ </tex-math></inline-formula> objects reside on the vertices of this graph, and some can serve as relays between Alice and Bob. The protocol starts with Alice splitting her message into small chunks, which she can covertly deposit to the relays she encounters. The protocol ends with Bob collecting the chunks. Alice may encode her data before the dissemination. Willie can either perform random walks as Alice and Bob do or conduct uniform surveillance of the area. In either case, he can only observe one relay at a time. We evaluate the system performance by the covertness probability and the message passing delay. In our protocol, Alice splits her message to increase the covertness probability and adds (coded) redundancy to reduce the transmission delay. The performance metrics depend on the graph, communications delay, and code parameters. We show that, in most scenarios, it is impossible to find the design parameters that simultaneously maximize the covertness probability and minimize the message delay.

State of Health Estimation of LiFePO4 Batteries for Battery Management燬ystems

When considering the mechanism of the batteries, the capacity reduction at storage (when not in use) and cycling (during use) and increase of internal resistance is because of degradation in the chemical composition inside the batteries. To optimize battery usage, a battery management system (BMS) is used to estimate possible aging effects while different load profiles are requested from the grid. This is specifically seen in a case when the vehicle is connected to the net (online through BMS). During this process, the BMS chooses the optimized load profiles based on the least aging effects on the battery pack. The major focus of this paper is to design an algorithm/model for lithium iron phosphate (LiFePO4) batteries. The model of the batteries is based on the accelerated aging test data (data from the beginning of life till the end of life). The objective is to develop an algorithm based on the actual battery trend during the whole life of the battery. By the analysis of the test data, the complete trend of the battery aging and the factors on which the aging is depending on is identified, the aging model can then be recalibrated to avoid any differences in the production process during cell manufacturing. The validation of the model was carried out at the end by utilizing different driving profiles at different C-rates and different ambient temperatures. A Linear and non-linear model-based approach is used based on statistical data. The parameterization was carried out by dividing the data into small chunks and estimating the parameters for the individual chunks. Self-adaptive characteristic map using a lookup table was also used. The non-linear model was chosen as the best candidate among all other approaches for longer validation of 8-month data with real driving data set.

Parallel anomaly detection algorithm for cybersecurity on the highspeed train control system.

With the rapid development of the high-speed train industry, the high-speed train control system has now been exposed to a complicated network environment full of dangers. This paper provides a speculative parallel data detection algorithm to rapidly detect the potential threats and ensure data transmission security in the railway network. At first, the structure of the high-speed train control data received by the railway control center was analyzed and divided tentatively into small chunks to eliminate the inside dependencies. Then the traditional threat detection algorithm based on deterministic finite automaton was reformed by the speculative parallel optimization so that the inline relationship's influences that affected the data detection order could be avoided. At last, the speculative parallel detection algorithm would inspect the divided data chunks on a distributed platform. With the help of both the speculative parallel technique and the distributed platform, the detection deficiency for train control data was improved significantly. The results showed that the proposed algorithm exhibited better performance and scalability when compared with the traditional, non-parallel detection method, and massive train control data could be inspected and processed promptly. Now it has been proved by practical use that the proposed algorithm was stable and reliable. Our local train control center was able to quickly detect the anomaly and make a fast response during the train control data transmission by adopting the proposed algorithm.

LSDStrategy: A Lightweight Software-Driven Strategy for Addressing Big Data Variety of Multimedia Streaming

Many devices, users, and applications stream an irregular amount of varied data every second. This rapid generation of data continues at an enormous rate, constructing the big data that increase the need for solutions, despite resource constraints, to analyze and manipulate data. Current methods allocate cloud resources according to the characteristics of the data. Resource allocation requires a comprehensive view of the workload requirements. However, the data characteristics in big data streams are uncertain due to the random nature of data generation. Choosing and allocating the right resources to this stream is challenging. With the variety of big data streams, the stochastic nature of the stream led to unpredictable requirements and specifications. The critical issue is forecasting the workload to avoid the over-provisioning and under-provisioning of resources. Such forecasting needs an adequate dataset to describe the history logs of the incoming workload. A fast release for such a dataset provides a high chance of deploying forecasting at the right time. This paper addresses this issue with a novel strategy named LSDStrategy that analyzes the received multimedia stream based on its binary content using machine learning techniques with artificial and real datasets. LSDStrategy utilizes an evaluating voting technique to select the optimum classifier to trade off accuracy and prediction time as metrics. Multi-classifiers that have been built and tested include Decision Tree (DT), K-Nearest Neighbor (K-NN), and Random Forest (RF) over multi-content-based features. Experiments evaluated the performance of the adopted models and the selected features. According to experimental analysis, the DT approach provides a consistent performance for both artificial and real-world datasets for 85% and 81.3%, respectively. We deploy and evaluate the LSDStrategy efficiency on a regular specification server through a set of experiments using a synthetic stream. The experiments prove the LSDStrategy agility and adaptivity in identifying the multimedia-based workload type utilizing small chunks of load.

Using patient feedback to adapt intervention materials based on acceptance and commitment therapy for people receiving renal dialysis

BackgroundTheory-based intervention materials must be carefully adapted to meet the needs of users with specific physical conditions. Acceptance and Commitment Therapy (ACT) has been adapted successfully for cancer, chronic pain, diabetes, irritable bowel syndrome, multiple sclerosis, and a range of other conditions, but not so far for people receiving renal haemodialysis. This paper presents findings from a study to adapt ACT-based intervention materials specifically for renal dialysis.MethodsDraft written materials consisting of four stories depicting fictitious individuals who used ACT-related techniques to help overcome different challenges and difficulties related to dialysis were adapted using a systematic patient consultation process. The participants were 18 people aged 19–80 years, with chronic kidney disease and receiving renal dialysis. Individual, semi-structured interviews were conducted to elicit participants’ views about how the content of the draft materials should be adapted to make them more realistic and relevant for people receiving renal dialysis and about how the materials should be presented and delivered to people receiving renal dialysis. The interview transcripts were analysed using a qualitative adaptation of the Delphi method in which themes are used as a framework for translating feedback into proposals for modifications.ResultsThe analysis of patient feedback supported the use of patient stories but suggested they should be presented by video and narrated by real dialysis patients. They also indicated specific adaptations to make the stories more credible and realistic. Participant feedback was translated into proposals for change that were considered along with clinical, ethical and theoretical factors. The outcome was a design for a video-based intervention that separated the stories about individuals from the explanations of the specific ACT techniques and provided greater structure, with material organised into smaller chunks. This intervention is adapted specifically for people receiving renal dialysis while retaining the distinctive theoretical principles of ACT.ConclusionsThe study shows the value of consulting patients in the development of intervention materials and illustrates a process for integrating patient feedback with theoretical, clinical and practical considerations in intervention design.

Joint speaker diarization and speech recognition based on region proposal networks

Speaker diarization, the process of partitioning an input audio stream into homogeneous segments according to the speaker identity, is an important task for speech processing. The standard clustering-based diarization pipeline (1) segments the whole utterance into small chunks, (2) extracts speaker embedding for each chunk, and (3) groups the chunks into clusters, where each cluster represents one speaker. It has two major disadvantages: first, it contains several individually optimized modules in the pipeline, and second, it cannot handle overlapping speech. To address these issues, we proposed region proposal network-based speaker diarization (RPNSD) (Huang et al., 2020). In this paper, we perform a detailed study of the RPNSD system, and make two important contributions. First, we report its diarization performance on additional datasets and empirically investigate the impact of different system settings. Second, we integrate an automatic speech recognition (ASR) component into the RPNSD system and propose a new framework called RPN-JOINT that simultaneously performs diarization and ASR. Our experiments reveal that (1) the RPNSD system can consistently achieve diarization results that are competitive with state-of-the-art methods, and (2) the RPN-JOINT system offers several advantages over the conventional cascade of diarization and ASR systems.

Improving the Performance of Block-based DRAM Caches Via Tag-Data Decoupling

In-package DRAM-based Last-Level-Caches (LLCs) that cache data in small chunks (i.e., blocks) are promising for improving system performance due to their efficient main memory bandwidth utilization. However, in these high-capacity DRAM caches, managing metadata (i.e., tags) at low cost is challenging. Storing the tags in SRAM has the advantage of quick tag access but is impractical due to a large area overhead. Storing the tags in DRAM reduces the area overhead but incurs tag serialization latency for an associative LLC design, which is inevitable for achieving high cache hit rate. To address the area and latency overhead problem, we propose a block-based DRAM LLC design that decouples tag and data into two regions in DRAM. Our design stores the tags in a latency-optimized DRAM region as the tags are accessed more often than the data. In contrast, we optimize the data region for area efficiency and map spatially-adjacent cache blocks to the same DRAM row to exploit spatial locality. Our design mitigates the tag serialization latency of existing associative DRAM LLCs via selective in-DRAM tag comparison, which overlaps the latency of tag and data accesses. This efficiently enables LLC bypassing via a novel DRAM Absence Table (DAT) that not only provides fast LLC miss detection but also reduces in-package bandwidth requirements. Our evaluation using SPEC2006 benchmarks shows that our tag-data decoupled LLC improves system performance by 11.7 percent compared to a state-of-the-art direct-mapped LLC design and by 7.2 percent compared to an existing associative LLC design.

Cache blocking strategies applied to flux reconstruction

On modern hardware architectures, the performance of Flux Reconstruction (FR) methods can be limited by memory bandwidth. In a typical implementation, these methods are implemented as a chain of distinct kernels. Often, a dataset which has just been written in the main memory by a kernel is read back immediately by the next kernel. One way to avoid such a redundant expenditure of memory bandwidth is kernel fusion. However, on a practical level kernel fusion requires that the source for all kernels be available, thus preventing calls to certain third-party library functions. Moreover, it can add substantial complexity to a codebase. An alternative to full kernel fusion is cache blocking. But for this to be effective, CPU cache has to be meaningfully big. Historically, size of L1 and L2 caches prevented cache blocking for high-order CFD applications. However in recent years, size of L2 cache has grown from around 0.25 MiB to 1.25 MiB, and made it possible to apply cache blocking for high-order CFD codes. In this approach, kernels remain distinct, and are executed one after another on small chunks of data that can fit in the cache, as opposed to on full datasets. These chunks of data stay in the cache and whenever a kernel requests access to data that is already in the cache, memory bandwidth is conserved. In this study, a data structure that facilitates cache blocking is considered, and a range of kernel grouping configurations for an FR based Euler solver are examined. A theoretical study is conducted for hexahedral elements with no anti-aliasing at p=3 and p=4 in order to determine the predicted performance of a few kernel grouping configurations. Then, these candidates are implemented in the PyFR solver and the performance gains in practice are compared with the theoretical estimates that range between 2.05x and 2.50x. An inviscid Taylor-Green Vortex test case is used as a benchmark, and the most performant configuration leads to a speedup of approximately 2.81x in practice.

A genetic risk score using human chromosomal-scale length variation can predict schizophrenia

Studies indicate that schizophrenia has a genetic component, however it cannot be isolated to a single gene. We aimed to determine how well one could predict that a person will develop schizophrenia based on their germ line genetics. We compared 1129 people from the UK Biobank dataset who had a diagnosis of schizophrenia to an equal number of age matched people drawn from the general UK Biobank population. For each person, we constructed a profile consisting of numbers. Each number characterized the length of segments of chromosomes. We tested several machine learning algorithms to determine which was most effective in predicting schizophrenia and if any improvement in prediction occurs by breaking the chromosomes into smaller chunks. We found that the stacked ensemble, performed best with an area under the receiver operating characteristic curve (AUC) of 0.545 (95% CI 0.539–0.550). We noted an increase in the AUC by breaking the chromosomes into smaller chunks for analysis. Using SHAP values, we identified the X chromosome as the most important contributor to the predictive model. We conclude that germ line chromosomal scale length variation data could provide an effective genetic risk score for schizophrenia which performs better than chance.

Baby-led weaning: Health professionals 'knowledge and attitudes and parents' experiences from Spain. A mixed methods approach.

Baby-led weaning or self-regulated small chunk feeding by the baby has emerged as an alternative to the traditional method of complementary feeding. Parents and healthcare professionals often differ in the benefits and drawbacks about it. The research aims were to describe the knowledge of health professionals about complementary feeding and baby-led weaning (BLW) method and the attitudes towards its recommendation, and to explore the knowledge, experiences and attitudes of parents who have used this method to feed their children. A mixed methods research was carried out. A questionnaire was completed by 38 health professionals and 10 interviews were conducted with participating mothers. A total of 52.6% of health professionals recommended initiating complementary feeding at 6months of age, a guideline followed by the mothers who used BLW. Some 86.8% of the professionals knew the BLW method and 76.3% knew its benefits, but the mothers consulted mainly informal sources of information sources to learn about and implement it. The health professionals stated that it facilitated family transition, enabled the infant to adapt better to flavours and textures, promoted chewing and the development of fine motor skills, improved growth and might also be a protective factor against obesity. The mothers noted that the method was natural, encouraged infant autonomy and promoted healthy eating habits. The health professionals expressed varied opinions concerning the risks entailed in the method. The main conclusions are that the majority of health professionals participating in the study know the BLW method, its benefits; however, they do not recommend it in all cases. Mothers listen to the advice of professionals but continue to rely on other informal sources of information.

Board-Level Functional Fault Identification Using Streaming Data

High integration densities and design complexity of printed-circuit boards make board-level functional fault identification extremely difficult. Machine learning provides an opportunity to identify functional faults with high accuracy and thereby reduce repair cost. However, the large volume of manufacturing data comes in a streaming format and exhibits time-dependent concept drift in a production environment. These drawbacks limit the effectiveness of traditional machine-learning algorithms. We propose a diagnosis workflow that utilizes online learning to train classifiers incrementally with a small chunk of data at each step. These online-learning algorithms adapt to concept drift quickly with carefully designed update rules. A hybrid algorithm is also proposed to handle the scenario that data for varying numbers of boards are collected at different times. This hybrid algorithm concurrently implements two basic models. For each data chunk, this algorithm chooses the better model with high probability. The experimental results using two boards in high-volume production show that, with the help of online learning and the proposed hybrid algorithm, the F1-score for diagnosis based on binary classifiers can be improved from 57.3% to 81.0%. The top-3 accuracy for diagnosis based on multiclass classifiers can be improved from 78.3% to 91.4%.