Effects of repeated readings on reading abilities of English language learners with specific learning disabilities

This study investigated the effects of repeated readings on the reading abilities of 4, third-, fourth-, and fifth-grade English language learners (ELLs) with specific learning disabilities (SLD). A multiple baseline probe design across subjects was used to explore the effects of repeated readings on four dependent variables: reading fluency (words read correctly per minute; wpm), number of errors per minute (epm), types of errors per minute, and answer to literal comprehension questions. Data were collected and analyzed during baseline, intervention, generalization probes, and maintenance probes. Throughout the baseline and intervention phases, participants read a passage aloud and received error correction feedback. During baseline, this was followed by fluency and literal comprehension question assessments. During intervention, this was followed by two oral repeated readings of the passage. Then the fluency and literal comprehension question assessments were administered. Generalization probes followed approximately 25% of all sessions and consisted of a single reading of a new passage at the same readability level. Maintenance sessions occurred 2-, 4-, and 6-weeks after the intervention ended. The results of this study indicated that repeated readings had a positive effect on the reading abilities of ELLs with SLD. Participants read more wpm, made fewer epm, and answered more literal comprehension questions correctly. Additionally, on average, generalization scores were higher in intervention than in baseline. Maintenance scores were varied when compared to the last day of intervention, however, with the exception of the number of hesitations committed per minute maintenance scores were higher than baseline means. This study demonstrated that repeated readings improved the reading abilities of ELLs with SLD and that gains were generalized to untaught passages. Maintenance probes 2-, 4-, and 6- weeks following intervention indicated that mean reading fluency, errors per minute, and correct answers to literal comprehensive questions remained above baseline levels. Future research should investigate the use of repeated readings in ELLs with SLD at various stages of reading acquisition. Further, future investigations may examine how repeated readings can be integrated into classroom instruction and assessments.

The use of computer graphic organizers for narrative writing by elementary school students with Specific Learning Disabilities

Writing is an academic skill critical to students in today's schools as it serves as a predominant means for demonstrating knowledge during school years (Graham, 2008). However, for many students with Specific Learning Disabilities (SLD), learning to write is a challenging, complex process (Lane, Graham, Harris, & Weisenbach, 2006). Students SLD have substantial writing challenges related to the nature of their disability (Mayes & Calhoun, 2005). ^ This study investigated the effects of computer graphic organizer software on the narrative writing compositions of four, fourth- and fifth-grade, elementary-level boys with SLD. A multiple baseline design across subjects was used to explore the effects of the computer graphic organizer software on four dependent variables: total number of words, total planning time, number of common story elements, and overall organization. ^ Prior to baseline, participants were taught the fundamentals of narrative writing. Throughout baseline and intervention, participants were read a narrative writing prompt and were allowed up to 10 minutes to plan their writing, followed by 15 minutes for writing, and 5 minutes of editing. During baseline, all planning was done using paper and pencil. During intervention, planning was done on the computer using a graphic organizer developed from the software program Kidspiration 3.0 (2011). All compositions were written and editing was done using paper and pencil during baseline and intervention. ^ The results of this study indicated that to varying degrees computer graphic organizers had a positive effect on the narrative writing abilities of elementary aged students with SLD. Participants wrote more words (from 54.74 to 96.60 more), planned for longer periods of time (from 4.50 to 9.50 more minutes), and included more story elements in their compositions (from 2.00 to 5.10 more out of a possible 6). There were nominal to no improvements in overall organization across the 4 participants. ^ The results suggest that teachers of students with SLD should considering use computer graphic organizers in their narrative writing instruction, perhaps in conjunction with remedial writing strategies. Future investigations can include other types of writing genres, other stages of writing, participants with varied demographics and their use combined with remedial writing instruction. ^

The effect of active student responding in computer -assisted instruction on social -studies learning by students with learning disabilities

The purpose of this study was to compare the effects of three student response conditions during computer-assisted instruction on the acquisition and maintenance of social-studies facts. Two of the conditions required active student responding (ASR), whereas the other required an on-task (OT) response. Participants were five fifth-grade students, with learning disabilities enrolled in a private school. An alternating treatments design with a best treatments phase was used to compare the effects of the response procedures on three major dependent measures: same-day tests, next-day tests, and maintenance tests. ^ Each week for six weeks, participants were provided daily one-to-one instruction on sets of 21 unknown social-studies facts using a hypermedia computer program, with a new set of facts being practiced each week. Each set of 21 facts was divided randomly into three conditions: Clicking-ASR, Repeating-ASR, and Listening-OT. Hypermedia lesson began weekly with the concept introduction lesson, followed by practice and testing. Practice and testing occurred four days per week, per set. During Clicking-ASR, student practice involved the selection of a social-studies response by clicking on an item with the mouse on the hypermedia card. Repeating-ASR instruction required students to orally repeat the social-studies facts when prompted by the computer. During Listening-OT, students listened to the social-studies facts being read by the computer. During weeks seven and eight, instruction occurred with seven unknown facts using only the best treatment. ^ Test results show that all for all 5 students, the Repeating-ASR practice procedure resulted in more social-studies facts stated correctly on same-day tests, next-day tests, and one-and two-week maintenance tests. Clicking-ASR was the next most effective procedure. During the seventh and eighth week of instruction when only the best practice condition was implemented, Repeating-ASR produced higher scores than all conditions (including Repeating-ASR) during the first six weeks of the study. ^ The results lend further support to the growing body of literature that demonstrates the positive relation between ASR and student achievement. Much of the ASR literature has focused on the effects of increased ASR during teacher-led or peer-mediated instruction. This study adds a dimension to that research in that it demonstrated the importance of ASR during computer-assisted instruction and further suggests that the type of ASR used during computer-assisted instruction may influence learning. Future research is needed to investigate the effectiveness of other types of ASR during computer-assisted instruction and to identify other fundamental characteristics of an effective computer-assisted instruction. ^

Effects of Repeated Readings on Reading Abilities of English Language Learners with Specific Learning Disabilities

This study investigated the effects of repeated readings on the reading abilities of 4, third-, fourth-, and fifth-grade English language learners (ELLs) with specific learning disabilities (SLD). A multiple baseline probe design across subjects was used to explore the effects of repeated readings on four dependent variables: reading fluency (words read correctly per minute; wpm), number of errors per minute (epm), types of errors per minute, and answer to literal comprehension questions. Data were collected and analyzed during baseline, intervention, generalization probes, and maintenance probes. Throughout the baseline and intervention phases, participants read a passage aloud and received error correction feedback. During baseline, this was followed by fluency and literal comprehension question assessments. During intervention, this was followed by two oral repeated readings of the passage. Then the fluency and literal comprehension question assessments were administered. Generalization probes followed approximately 25% of all sessions and consisted of a single reading of a new passage at the same readability level. Maintenance sessions occurred 2-, 4-, and 6-weeks after the intervention ended. The results of this study indicated that repeated readings had a positive effect on the reading abilities of ELLs with SLD. Participants read more wpm, made fewer epm, and answered more literal comprehension questions correctly. Additionally, on average, generalization scores were higher in intervention than in baseline. Maintenance scores were varied when compared to the last day of intervention, however, with the exception of the number of hesitations committed per minute maintenance scores were higher than baseline means. This study demonstrated that repeated readings improved the reading abilities of ELLs with SLD and that gains were generalized to untaught passages. Maintenance probes 2-, 4-, and 6- weeks following intervention indicated that mean reading fluency, errors per minute, and correct answers to literal comprehensive questions remained above baseline levels. Future research should investigate the use of repeated readings in ELLs with SLD at various stages of reading acquisition. Further, future investigations may examine how repeated readings can be integrated into classroom instruction and assessments.

Learning from Text: Examining Teacher Thinking and Practice in AP Environmental Science

Thesis (Ph.D.)--University of Washington, 2016-08

Learning math through movement: physical education as another alternative

The purpose of this study was to determine the cognitive effects of applying physical recreational activities to two groups of pre-school students, related to mathematics to one of the groups and recreational games to the other.  A total of 27 subjects (13 girls and 14 boys) of 5 and a half and 6 and half years of age participated in the study.  The instrument used was a questionnaire including basic math concepts such as geometry, basic operations with concrete elements, and how to read the clock, based on the topics established by the Costa Rican Ministry of Public Education.  Once the instrument was developed, a plan of physical recreational activities related to math was prepared and applied to the experimental group (pre-school B) for one and a half months, while the other group played recreational games.  Data was analyzed using descriptive and inferential statistics.  Positive and significant effects were found in the physical recreational activity program regarding student performance in 10 of the 12 items that were applied to assess mastery of basic math concepts.  In conclusion, using physical education as another instrument to teach other disciplines represents an excellent alternative for pre-school teachers that try to satisfy the learning needs of children that will soon be attending school.  Using movement as part of guided and planned activities plays an indispensable role in children’s lives; therefore, learning academic subjects should be adapted to their needs to explore and know their environment.

Detecting social patterns within 20th century documentary photos: a deep learning based approach

The job of a historian is to understand what happened in the past, resorting in many cases to written documents as a firsthand source of information. Text, however, does not amount to the only source of knowledge. Pictorial representations, in fact, have also accompanied the main events of the historical timeline. In particular, the opportunity of visually representing circumstances has bloomed since the invention of photography, with the possibility of capturing in real-time the occurrence of a specific events. Thanks to the widespread use of digital technologies (e.g. smartphones and digital cameras), networking capabilities and consequent availability of multimedia content, the academic and industrial research communities have developed artificial intelligence (AI) paradigms with the aim of inferring, transferring and creating new layers of information from images, videos, etc. Now, while AI communities are devoting much of their attention to analyze digital images, from an historical research standpoint more interesting results may be obtained analyzing analog images representing the pre-digital era. Within the aforementioned scenario, the aim of this work is to analyze a collection of analog documentary photographs, building upon state-of-the-art deep learning techniques. In particular, the analysis carried out in this thesis aims at producing two following results: (a) produce the date of an image, and, (b) recognizing its background socio-cultural context,as defined by a group of historical-sociological researchers. Given these premises, the contribution of this work amounts to: (i) the introduction of an historical dataset including images of “Family Album” among all the twentieth century, (ii) the introduction of a new classification task regarding the identification of the socio-cultural context of an image, (iii) the exploitation of different deep learning architectures to perform the image dating and the image socio-cultural context classification.

Deep learning models for the automatic analysis of volleyball plays

Collecting and analysing data is an important element in any field of human activity and research. Even in sports, collecting and analyzing statistical data is attracting a growing interest. Some exemplar use cases are: improvement of technical/tactical aspects for team coaches, definition of game strategies based on the opposite team play or evaluation of the performance of players. Other advantages are related to taking more precise and impartial judgment in referee decisions: a wrong decision can change the outcomes of important matches. Finally, it can be useful to provide better representations and graphic effects that make the game more engaging for the audience during the match. Nowadays it is possible to delegate this type of task to automatic software systems that can use cameras or even hardware sensors to collect images or data and process them. One of the most efficient methods to collect data is to process the video images of the sporting event through mixed techniques concerning machine learning applied to computer vision. As in other domains in which computer vision can be applied, the main tasks in sports are related to object detection, player tracking, and to the pose estimation of athletes. The goal of the present thesis is to apply different models of CNNs to analyze volleyball matches. Starting from video frames of a volleyball match, we reproduce a bird's eye view of the playing court where all the players are projected, reporting also for each player the type of action she/he is performing.

Rilevamento della qualità del manto stradale: un approccio sperimentale tramite Machine Learning

Il riconoscimento delle condizioni del manto stradale partendo esclusivamente dai dati raccolti dallo smartphone di un ciclista a bordo del suo mezzo è un ambito di ricerca finora poco esplorato. Per lo sviluppo di questa tesi è stata sviluppata un'apposita applicazione, che combinata a script Python permette di riconoscere differenti tipologie di asfalto. L’applicazione raccoglie i dati rilevati dai sensori di movimento integrati nello smartphone, che registra i movimenti mentre il ciclista è alla guida del suo mezzo. Lo smartphone è fissato in un apposito holder fissato sul manubrio della bicicletta e registra i dati provenienti da giroscopio, accelerometro e magnetometro. I dati sono memorizzati su file CSV, che sono elaborati fino ad ottenere un unico DataSet contenente tutti i dati raccolti con le features estratte mediante appositi script Python. A ogni record sarà assegnato un cluster deciso in base ai risultati prodotti da K-means, risultati utilizzati in seguito per allenare algoritmi Supervised. Lo scopo degli algoritmi è riconoscere la tipologia di manto stradale partendo da questi dati. Per l’allenamento, il DataSet è stato diviso in due parti: il training set dal quale gli algoritmi imparano a classificare i dati e il test set sul quale gli algoritmi applicano ciò che hanno imparato per dare in output la classificazione che ritengono idonea. Confrontando le previsioni degli algoritmi con quello che i dati effettivamente rappresentano si ottiene la misura dell’accuratezza dell’algoritmo.

A machine learning based method to detect genomic imbalances exploiting X chromosome exome reads

Whole Exome Sequencing (WES) is rapidly becoming the first-tier test in clinics, both thanks to its declining costs and the development of new platforms that help clinicians in the analysis and interpretation of SNV and InDels. However, we still know very little on how CNV detection could increase WES diagnostic yield. A plethora of exome CNV callers have been published over the years, all showing good performances towards specific CNV classes and sizes, suggesting that the combination of multiple tools is needed to obtain an overall good detection performance. Here we present TrainX, a ML-based method for calling heterozygous CNVs in WES data using EXCAVATOR2 Normalized Read Counts. We select males and females’ non pseudo-autosomal chromosome X alignments to construct our dataset and train our model, make predictions on autosomes target regions and use HMM to call CNVs. We compared TrainX against a set of CNV tools differing for the detection method (GATK4 gCNV, ExomeDepth, DECoN, CNVkit and EXCAVATOR2) and found that our algorithm outperformed them in terms of stability, as we identified both deletions and duplications with good scores (0.87 and 0.82 F1-scores respectively) and for sizes reaching the minimum resolution of 2 target regions. We also evaluated the method robustness using a set of WES and SNP array data (n=251), part of the Italian cohort of Epi25 collaborative, and were able to retrieve all clinical CNVs previously identified by the SNP array. TrainX showed good accuracy in detecting heterozygous CNVs of different sizes, making it a promising tool to use in a diagnostic setting.

Sviluppo di un’app mobile con Realtà Aumentata e Machine Learning in contesto di biodiversità

Il volume di tesi ha riguardato lo sviluppo di un'applicazione mobile che sfrutta la Realtà Aumentata e il Machine Learning nel contesto della biodiversità. Nello specifico si è realizzato un modello di AI che permetta la classificazione di immagini di fiori. Tale modello è stato poi integrato in Android, al fine della realizzazione di un'app che riesca a riconoscere specifiche specie di fiori, oltre a individuare gli insetti impollinatori attratti da essi e rappresentarli in Realtà Aumentata.

A deep learning model via thermodynamics and condensed matter physics

Deep Learning architectures give brilliant results in a large variety of fields, but a comprehensive theoretical description of their inner functioning is still lacking. In this work, we try to understand the behavior of neural networks by modelling in the frameworks of Thermodynamics and Condensed Matter Physics. We approach neural networks as in a real laboratory and we measure the frequency spectrum and the entropy of the weights of the trained model. The stochasticity of the training occupies a central role in the dynamics of the weights and makes it difficult to assimilate neural networks to simple physical systems. However, the analogy with Thermodynamics and the introduction of a well defined temperature leads us to an interesting result: if we eliminate from a CNN the "hottest" filters, the performance of the model remains the same, whereas, if we eliminate the "coldest" ones, the performance gets drastically worst. This result could be exploited in the realization of a training loop which eliminates the filters that do not contribute to loss reduction. In this way, the computational cost of the training will be lightened and more importantly this would be done by following a physical model. In any case, beside important practical applications, our analysis proves that a new and improved modeling of Deep Learning systems can pave the way to new and more efficient algorithms.

Tecniche di deep learning per il monitoraggio del processo nell’industria dello pneumatico

Il seguente elaborato affronta l'implementazione di un algoritmo che affronta un problema di controllo di processo in ambito industriale utilizzando algoritmi di object detection. Infatti, il progetto concordato con il professore Di Stefano si è svolto in collaborazione con l’azienda Pirelli, nell’ambito della produzione di pneumatici. Lo scopo dell'algoritmo implementato è di verificare il preciso orientamento di elementi grafici della copertura, utilizzati dalle case automobilistiche per equipaggiare correttamente le vetture. In particolare, si devono individuare delle scritte sul battistrada della copertura e identificarne la posizione rispetto ad altri elementi fissati su di essa. La tesi affronta questo task in due parti distinte: la prima consiste nel training di algoritmi di deep learning per il riconoscimento degli elementi grafici e del battistrada, la seconda è un decisore che opera a valle del primo sistema utilizzando gli output delle reti allenate.

Metodologie di Corrispondenza Stereo Basate su Deep Learning per Superfici Altamente Riflettenti e Trasparenti: Dataset e Architettura

Nell’ambito della Stereo Vision, settore della Computer Vision, partendo da coppie di immagini RGB, si cerca di ricostruire la profondità della scena. La maggior parte degli algoritmi utilizzati per questo compito ipotizzano che tutte le superfici presenti nella scena siano lambertiane. Quando sono presenti superfici non lambertiane (riflettenti o trasparenti), gli algoritmi stereo esistenti sbagliano la predizione della profondità. Per risolvere questo problema, durante l’esperienza di tirocinio, si è realizzato un dataset contenente oggetti trasparenti e riflettenti che sono la base per l’allenamento della rete. Agli oggetti presenti nelle scene sono associate annotazioni 3D usate per allenare la rete. Invece, nel seguente lavoro di tesi, utilizzando l’algoritmo RAFT-Stereo [1], rete allo stato dell’arte per la stereo vision, si analizza come la rete modifica le sue prestazioni (predizione della disparità) se al suo interno viene inserito un modulo per la segmentazione semantica degli oggetti. Si introduce questo layer aggiuntivo perché, trovare la corrispondenza tra due punti appartenenti a superfici lambertiane, risulta essere molto complesso per una normale rete. Si vuole utilizzare l’informazione semantica per riconoscere questi tipi di superfici e così migliorarne la disparità. È stata scelta questa architettura neurale in quanto, durante l’esperienza di tirocinio riguardante la creazione del dataset Booster [2], è risultata la migliore su questo dataset. L’obiettivo ultimo di questo lavoro è vedere se il riconoscimento di superfici non lambertiane, da parte del modulo semantico, influenza la predizione della disparità migliorandola. Nell’ambito della stereo vision, gli elementi riflettenti e trasparenti risultano estremamente complessi da analizzare, ma restano tuttora oggetto di studio dati gli svariati settori di applicazione come la guida autonoma e la robotica.

Spectral methods in geometric deep learning

Questa tesi propone una panoramica sul funzionamento interno delle architetture alla base del deep learning e in particolare del geometric deep learning. Iniziando a discutere dalla storia degli algoritmi di intelligenza artificiale, vengono introdotti i principali costituenti di questi. In seguito vengono approfonditi alcuni elementi della teoria dei grafi, in particolare il concetto di laplaciano discreto e il suo ruolo nello studio del fenomeno di diffusione sui grafi. Infine vengono presentati alcuni algoritmi utilizzati nell'ambito del geometric deep learning su grafi per la classificazione di nodi. I concetti discussi vengono poi applicati nella realizzazione di un'architettura in grado di classficiare i nodi del dataset Zachary Karate Club.