An Extension of Testlet-Based Equating to the Polytomous Testlet Response Theory Model

Educational assessments tests are often constructed using testlets because of the flexibility to test various aspects of the cognitive activities and broad content sampling. However, the violation of the local item independence assumption is inevitable when tests are built using testlet items. In this study, simulations are conducted to evaluate the performance of item response theory models and testlet response theory models for both the dichotomous and polytomous items in the context of equating tests composed of testlets. We also examine the impact of testlet effect, length of testlet items, and sample size on estimating item and person parameters. The results show that more accurate performance of testlet response theory models over item response theory models was consistently observed across the studies, which supports the benefits of using the testlet response theory models in equating for tests composed of testlets. Further, results of the study indicate that when sample size is large, item response theory models performed similarly to testlet response theory models across all studies.

Distilling vector space model scores for the assessment of constructed responses with bifactor Inbuilt Rubric method and latent variables

In this paper, we highlight the importance of distilling the computational assessments of constructed responses to validate the indicators/proxies of constructs/trins using an empirical illustration in automated summary evaluation. We present the validation of the Inbuilt Rubric (IR) method that maps rubrics into vector spaces for concepts’ assessment. Specifically, we improved and validated its scores’ performance using latent variables, a common approach in psychometrics. We also validated a new hierarchical vector space, namely a bifactor IR. 205 Spanish undergraduate students produced 615 summaries of three different texts that were evaluated by human raters and different versions of the IR method using latent semantic analysis (LSA). The computational scores were validated using multiple linear regressions and different latent variable models like CFAs or SEMs. Convergent and discriminant validity was found for the IR scores using human rater scores as validity criteria. While this study was conducted in the Spanish language, the proposed scheme is language-independent and applicable to any language. We highlight four main conclusions: (1) Accurate performance can be observed in topic-detection tasks without hundreds/thousands of pre-scored samples required in supervised models. (2) Convergent/discriminant validity can be improved using measurement models for computational scores as they adjust for measurement errors. (3) Nouns embedded in fragments of instructional text can be an affordable alternative to use the IR method. (4) Hierarchical models, like the bifactor IR, can increase the validity of computational assessments evaluating general and specific knowledge in vector space models. R code is provided to apply the classic and bifactor IR method.

Automatic Approach for Detecting the Seizure Using RCCN Architecture

Seizure is one of the most common neurodegenerative illnesses in humans, and it can result in serious brain damage, strokes, and tumors. Seizures can be detected early, which can assist prevent harm and aid in the treatment of epilepsy sufferers. A seizure prediction system's goal is to correctly detect the pre-ictal brain state, which occurs before a seizure occurs. Patient-independent seizure prediction models have been recognized as a real-world solution to the seizure prediction problem, since they are designed to provide accurate performance across different patients by using the recorded dataset. Furthermore, building such models to adjust to the significant inter-subject variability in EEG data has received little attention. We present a patient-independent deep learning architectures that can train a global function using data from numerous people with its own learning strategy. On the CHB- MIT-EEG dataset, the proposed models reach state-of-the-art accuracy for seizure prediction, with 95.54 percent accuracy. While predicting seizures, the Siamese model trained on the suggested learning technique is able to understand patterns associated to patient differences in data. Our models outperform the competition in terms of patient-independent seizure prediction, and following model adaption, the same architecture may be employed as a patient-specific classifier. We show that the MFCC feature map used by our models contains predictive biomarkers associated to inter-ictal and pre-ictal brain states, and we are the first study to use model interpretation to explain classifier behaviour for the task of seizure prediction.

Spectral Temporal Information for Missing Data Reconstruction (STIMDR) of Landsat Reflectance Time Series

The number of Landsat time-series applications has grown substantially because of its approximately 50-year history and relatively high spatial resolution for observing long term changes in the Earth’s surface. However, missing observations (i.e., gaps) caused by clouds and cloud shadows, orbit and sensing geometry, and sensor issues have broadly limited the development of Landsat time-series applications. Due to the large area and temporal and spatial irregularity of time-series gaps, it is difficult to find an efficient and highly precise method to fill them. The Missing Observation Prediction based on Spectral-Temporal Metrics (MOPSTM) method has been proposed and delivered good performance in filling large-area gaps of single-date Landsat images. However, it can be less practical for a time series longer than one year due to the lack of mechanics that exclude dissimilar data in time series (e.g., different phenology or changes in land cover). To solve this problem, this study proposes a new gap-filling method, Spectral Temporal Information for Missing Data Reconstruction (STIMDR), and examines its performance in Landsat reflectance time series. Two groups of experiments, including 2000 × 2000 pixel Landsat single-date images and Landsat time series acquired from four sites (Kenya, Finland, Germany, and China), were performed to test the new method. We simulated artificial gaps to evaluate predicted pixel values with real observations. Quantitative and qualitative evaluations of gap-filled images through comparisons with other state-of-the-art methods confirmed the more robust and accurate performance of the proposed method. In addition, the proposed method was also able to fill gaps contaminated by extreme cloud cover for a period (e.g., winter in high-latitude areas). A down-stream task of random forest supervised classification through both gap-filled simulated datasets and the original valid datasets verified that STIMDR-generated products are relevant to the user community for land cover applications.

An optimized PSO-ANN model for improved prediction of water treatment desalination plant performance

An accurate prediction of the performance of water treatment desalination plants could directly improve the global socio-economic balance. In this regard, many researchers have been engaged in the various artificial intelligence applied soft computing techniques to predict actual process outcomes. Inspired by the significance of such techniques, an optimized Particle Swarm Optimization based Artificial Neural Network (PSO-ANN) technique has been proposed herewith to predict an accurate performance of the reverse osmosis (RO) based water treatment desalination plants. Literature suggests that the improvements of the soft computing models depend on their modeling parameters. Therefore, we have included an extended list of nine modeling parameters with a systematic indepth investigation to explore their optimal values. Finally, the model's simulations results (R2 = 99.1%, Error = 0.006) were found superior than the existing ANN models (R2 = 98.8%, Error = 0.060), with the same experimental datasets. Additionally, the simulation results recommend that among many parameters considered, the number of hidden layer nodes (n), swarm sizes (SS), and the weight of inertia (ω) play a major role in the model optimization. This study for a more accurate prediction of the plant's performance shall pave the way for the process design and control engineers to improve the plant efficiency further.

Motivation reduces positive and negative emotional distractions

<p>Attention is biased toward emotional stimuli, which are often important for our biologically-determined goals of survival and reproduction. But to succeed in our daily tasks we must sometimes ignore emotional stimuli that are not relevant to current goals. In four experiments, I examine the extent to which we can ignore emotional stimuli if we are motivated to do so. I draw on the Dual Mechanisms of Control (DMC) framework which proposes that we use two modes of control to deal with distraction: reactive control, which shifts attention back to a task after distraction has occurred; and proactive control, which allows us to anticipate and control distraction before it occurs. In non-emotional contexts, task motivation encourages use of more effective, but more effortful, proactive control to ignore emotionally-neutral distractions. But, little is known about how we can control our attention to ignore highly distracting emotional stimuli. In all experiments, participants completed a simple visual task while attempting to ignore task-irrelevant negative (mutilation scenes), positive (erotic scenes), and neutral images (scenes of people). Distraction was indexed by slowing on distractor trials relative to a scrambled distractor, or no distractor, baseline. To manipulate motivation, half the participants completed the task with no performance-contingent reward; the other half completed the task with the opportunity to earn points and/or money for fast and accurate performance. In Experiment 1 the images were presented centrally, so attention must be shifted from the distractor location to complete the task. Reward reduced distraction by both positive and negative emotional images. Experiment 2 replicated Experiment 1, and measured pupil dilation to index the timecourse of cognitive effort. The aim of Experiment 2 was to determine whether motivation elicits a shift to proactive control to reduce emotional distraction, as it does in non-emotional contexts. Again, reward reduced positive and negative distraction. Pupil findings indicated that reward dynamically enhanced proactive control prior to stimulus-onset, facilitating rapid disengagement from distractors, regardless of their expected emotional value. In contrast, a sustained proactive strategy was used across blocks in which emotional distractors were expected, relative to blocks in which neutral distractors were expected. In the final two experiments, the distractors were presented peripherally and so must capture attention away from the central targets to impair performance. In Experiment 3, and in Experiment 4 – in which the points did not represent money – reward reduced attentional capture by positive and negative emotional distractors. Together, findings show that motivation can enhance control of positive and negative distractions that appear both centrally, and peripherally. Findings extend the DMC framework to an emotional context; motivation elicits a shift to proactive control, even when distractors are high arousal emotional stimuli. Further, in three out of four experiments, reward reduced emotional to a greater extent than neutral distraction, consistent with reward altering the outcome of goal-driven attentional competition between the targets and distractors. Understanding the complex interactions between motivation, emotion, and cognitive control will help to elucidate how we successfully navigate the world to achieve our goals.</p>

Motivation reduces positive and negative emotional distractions

<p>Attention is biased toward emotional stimuli, which are often important for our biologically-determined goals of survival and reproduction. But to succeed in our daily tasks we must sometimes ignore emotional stimuli that are not relevant to current goals. In four experiments, I examine the extent to which we can ignore emotional stimuli if we are motivated to do so. I draw on the Dual Mechanisms of Control (DMC) framework which proposes that we use two modes of control to deal with distraction: reactive control, which shifts attention back to a task after distraction has occurred; and proactive control, which allows us to anticipate and control distraction before it occurs. In non-emotional contexts, task motivation encourages use of more effective, but more effortful, proactive control to ignore emotionally-neutral distractions. But, little is known about how we can control our attention to ignore highly distracting emotional stimuli. In all experiments, participants completed a simple visual task while attempting to ignore task-irrelevant negative (mutilation scenes), positive (erotic scenes), and neutral images (scenes of people). Distraction was indexed by slowing on distractor trials relative to a scrambled distractor, or no distractor, baseline. To manipulate motivation, half the participants completed the task with no performance-contingent reward; the other half completed the task with the opportunity to earn points and/or money for fast and accurate performance. In Experiment 1 the images were presented centrally, so attention must be shifted from the distractor location to complete the task. Reward reduced distraction by both positive and negative emotional images. Experiment 2 replicated Experiment 1, and measured pupil dilation to index the timecourse of cognitive effort. The aim of Experiment 2 was to determine whether motivation elicits a shift to proactive control to reduce emotional distraction, as it does in non-emotional contexts. Again, reward reduced positive and negative distraction. Pupil findings indicated that reward dynamically enhanced proactive control prior to stimulus-onset, facilitating rapid disengagement from distractors, regardless of their expected emotional value. In contrast, a sustained proactive strategy was used across blocks in which emotional distractors were expected, relative to blocks in which neutral distractors were expected. In the final two experiments, the distractors were presented peripherally and so must capture attention away from the central targets to impair performance. In Experiment 3, and in Experiment 4 – in which the points did not represent money – reward reduced attentional capture by positive and negative emotional distractors. Together, findings show that motivation can enhance control of positive and negative distractions that appear both centrally, and peripherally. Findings extend the DMC framework to an emotional context; motivation elicits a shift to proactive control, even when distractors are high arousal emotional stimuli. Further, in three out of four experiments, reward reduced emotional to a greater extent than neutral distraction, consistent with reward altering the outcome of goal-driven attentional competition between the targets and distractors. Understanding the complex interactions between motivation, emotion, and cognitive control will help to elucidate how we successfully navigate the world to achieve our goals.</p>

Implementation of feature extraction and deep learning-based ensemble classifier for interference mitigation in radar signals

In automotive vehicles, radar is the one of the component for autonomous driving, used for target detection and long-range sensing. Whereas interference exists in signals, noise increases and it effects severely while detecting target objects. For these reasons, various interference mitigation techniques are implemented in this paper. By using these mitigation techniques interference and noise are reduced and original signals are reconstructed. In this paper, we proposed a method to mitigate interference in signal using deep learning. The proposed method provides the best and accurate performance in relate to the various interference conditions and gives better accuracy compared with other existing methods.

Development of the Electroencephalograph-based Brain Computer Interface System

A practical BCI-based application design contains a variety of design stages are needed to be considered. The design challenges are majorly present in 3 major stages: brain signal acquisition, signal processing unit, and signal classification. Combinations of different approaches have to be employed to achieve the functional and accurate performance of the overall design. Those design choices, algorithms, and methodologies that are meant to solve design challenges presented in the previously mentioned three stages have become a hot subject of a number of studies. This paper aims at providing a thorough overview of existing methodologies for BCI-based application design, comparing their principles and performance and recommending suitable design choices that would yield an objective result for the application.

Identifying common and novel cell types in single-cell RNA-sequencing data using FR-Match

Reference cell type atlases powered by single cell transcriptomic profiling technologies have become available to study cellular diversity at a granular level. We present FR-Match for matching query datasets to reference atlases with robust and accurate performance for identifying novel cell types and non-optimally clustered cell types in the query data. This approach shows excellent performance for cross-platform, cross-sample type, cross-tissue region, and cross-data modality cell type matching.