Search results for: false testimony

Authors: Mohammad Zavid Parvez, Manoranjan Paul

Abstract:

A seizure prediction method is proposed by extracting global features using phase correlation between adjacent epochs for detecting relative changes and local features using fluctuation/deviation within an epoch for determining fine changes of different EEG signals. A classifier and a regularization technique are applied for the reduction of false alarms and improvement of the overall prediction accuracy. The experiments show that the proposed method outperforms the state-of-the-art methods and provides high prediction accuracy (i.e., 97.70%) with low false alarm using EEG signals in different brain locations from a benchmark data set.

Keywords: Epilepsy, seizure, phase correlation, fluctuation, deviation.

Procedia PDF Downloads 441

Authors: Dmitry Dikarev, Ajit Nimbalker, Alexei Davydov

Abstract:

Polar coding is a novel example of error correcting codes, which can achieve Shannon limit at block length N→∞ with log-linear complexity. Active research is being carried to adopt this theoretical concept for using in practical applications such as 5th generation wireless communication systems. Cyclic redundancy check (CRC) error detection code is broadly used in conjunction with successive cancellation list (SCL) decoding algorithm to improve finite-length polar code performance. However, there are two issues: increase of code block payload overhead by CRC bits and decrease of CRC error-detection capability. This paper proposes a method to control CRC overhead and false alarm rate of polar decoding. As shown in the computer simulations results, the proposed method provides the ability to use any set of CRC polynomials with any list size while maintaining the desired level of false alarm rate. This level of flexibility allows using polar codes in 5G New Radio standard.

Keywords: 5G New Radio, channel coding, cyclic redundancy check, list decoding, polar codes

Procedia PDF Downloads 195

Authors: I. Parkova, A. Vališevskis, A. Viļumsone

Abstract:

Nocturnal enuresis or bed-wetting is intermittent incontinence during sleep of children after age 5 that may precipitate wide range of behavioural and developmental problems. One of the non-pharmacological treatment methods is the use of a bed-wetting alarm system. In order to improve comfort conditions of nocturnal enuresis alarm system, modular moisture sensor should be replaced by a textile sensor. In this study behaviour and moisture detection speed of woven and sewn sensors were compared by analysing change in electrical resistance after solution (salt water) was dripped on sensor samples. Material of samples has different structure and yarn location, which affects solution detection rate. Sensor system circuit was designed and two sensor tests were performed: system activation test and false alarm test to determine the sensitivity of the system and activation threshold. Sewn sensor had better result in system’s activation test – faster reaction, but woven sensor had better result in system’s false alarm test – it was less sensitive to perspiration simulation. After experiments it was found that the optimum switching threshold is 3V in case of 5V input voltage, which provides protection against false alarms, for example – during intensive sweating.

Keywords: conductive yarns, moisture textile sensor, industry, material

Procedia PDF Downloads 221

Authors: Ayse Arslan

Abstract:

One of the important elements underpinning a conscious design is the degree of toxicity in communication. This study explores the mechanisms and strategies for identifying toxic content by avoiding dark patterns. Given the breadth of hate and harassment attacks, this study explores a threat model and taxonomy to assist in reasoning about strategies for detection, prevention, mitigation, and recovery. In addition to identifying some relevant techniques such as nudges, automatic detection, or human-ranking, the study suggests the use of major metrics such as the overhead and friction of solutions on platforms and users or balancing false positives (e.g., incorrectly penalizing legitimate users) against false negatives (e.g., users exposed to hate and harassment) to maintain a conscious design towards fairness.

Keywords: AI, ML, algorithms, policy, system design

Procedia PDF Downloads 95

Authors: Fernanda M. Assef, Maria Teresinha A. Steiner

Abstract:

The aim of this paper is to compare and discuss better classifier algorithm options for credit risk assessment by applying different Machine Learning techniques. Using records from a Brazilian financial institution, this study uses a database of 5,432 companies that are clients of the bank, where 2,600 clients are classified as non-defaulters, 1,551 are classified as defaulters and 1,281 are temporarily defaulters, meaning that the clients are overdue on their payments for up 180 days. For each case, a total of 15 attributes was considered for a one-against-all assessment using four different techniques: Artificial Neural Networks Multilayer Perceptron (ANN-MLP), Artificial Neural Networks Radial Basis Functions (ANN-RBF), Logistic Regression (LR) and finally Support Vector Machines (SVM). For each method, different parameters were analyzed in order to obtain different results when the best of each technique was compared. Initially the data were coded in thermometer code (numerical attributes) or dummy coding (for nominal attributes). The methods were then evaluated for each parameter and the best result of each technique was compared in terms of accuracy, false positives, false negatives, true positives and true negatives. This comparison showed that the best method, in terms of accuracy, was ANN-RBF (79.20% for non-defaulter classification, 97.74% for defaulters and 75.37% for the temporarily defaulter classification). However, the best accuracy does not always represent the best technique. For instance, on the classification of temporarily defaulters, this technique, in terms of false positives, was surpassed by SVM, which had the lowest rate (0.07%) of false positive classifications. All these intrinsic details are discussed considering the results found, and an overview of what was presented is shown in the conclusion of this study.

Keywords: artificial neural networks (ANNs), classifier algorithms, credit risk assessment, logistic regression, machine Learning, support vector machines

Procedia PDF Downloads 76

Authors: Kasra Majbouri Yazdi, Adel Majbouri Yazdi, Saeid Khodayi, Jingyu Hou, Wanlei Zhou, Saeed Saedy

Abstract:

Fake news and false information are big challenges of all types of media, especially social media. There is a lot of false information, fake likes, views and duplicated accounts as big social networks such as Facebook and Twitter admitted. Most information appearing on social media is doubtful and in some cases misleading. They need to be detected as soon as possible to avoid a negative impact on society. The dimensions of the fake news datasets are growing rapidly, so to obtain a better result of detecting false information with less computation time and complexity, the dimensions need to be reduced. One of the best techniques of reducing data size is using feature selection method. The aim of this technique is to choose a feature subset from the original set to improve the classification performance. In this paper, a feature selection method is proposed with the integration of K-means clustering and Support Vector Machine (SVM) approaches which work in four steps. First, the similarities between all features are calculated. Then, features are divided into several clusters. Next, the final feature set is selected from all clusters, and finally, fake news is classified based on the final feature subset using the SVM method. The proposed method was evaluated by comparing its performance with other state-of-the-art methods on several specific benchmark datasets and the outcome showed a better classification of false information for our work. The detection performance was improved in two aspects. On the one hand, the detection runtime process decreased, and on the other hand, the classification accuracy increased because of the elimination of redundant features and the reduction of datasets dimensions.

Keywords: clustering, fake news detection, feature selection, machine learning, social media, support vector machine

Procedia PDF Downloads 145

Authors: Jocelyn Cohen

Abstract:

This paper identifies a powerful synchronicity of two traditions of life-story writing in the autobiographies of ritual abuse (RA) survivors, the Christian conversion narrative and the memoir of healing from childhood sexual trauma. Using methodologies from literary studies, history, and psychology, a close reading of three RA memoirs sheds light on a taboo and deeply suspect form of violence. Treatment of RA survivors and the unique role of psychotherapists, in particular, deserve far greater attention from multi-disciplinary scholars. Each story reflects salient characteristics of the Christian conversion narrative, a genre which originated in the US in the early 19th century with the serendipitous confluence of the simultaneous emergence of print culture and the basic structures of evangelicalism during the Second Great Awakening. The impulse of writing is thus to give testimony against the sin they witnessed and endured as young children during ritual violence perpetrated within the church. Importantly, RA is seen as an inherent if obscure aspect of Christian discourse itself, not in opposition to it, and not as an aberration. In RA's memoir, healing comes in part from the Christian narrative praxis of personal redemption, framed as prevailing in a war between good and evil. In other words, storytelling itself affects the healing, much as it does by means of each writer’s 'talking cure,' in the relationship with a psychotherapist who guides her through a repair of the life-story through the excavation of traumatic memories and their integration into the writer’s psyche. Integrating literary techniques into the psychotherapeutic relationship, therapists leverage the deep linguistic structures that clients possess as a resource to aid in their healing.

Keywords: memoir, psychotherapy, religion, trauma

Procedia PDF Downloads 96

Authors: Viviana Ventre, Giacomo Di Tollo, Roberta Martino

Abstract:

The portfolio selection problem includes the evaluation of many criteria that are difficult to compare directly and is characterized by uncertain elements. The portfolio selection problem can be modeled as a group decision problem in which several experts are invited to present their assessment. In this context, it is important to study and analyze the process of reaching a consensus among group members. Indeed, due to the various diversities among experts, reaching consensus is not necessarily always simple and easily achievable. Moreover, the concept of consensus is accompanied by the concept of false consensus, which is particularly interesting in the dynamics of group decision-making processes. False consensus can alter the evaluation and selection phase of the alternative and is the consequence of the decision maker's inability to recognize that his preferences are conditioned by subjective structures. The present work aims to investigate the dynamics of consensus attainment in a group decision problem in which equivalent portfolios are proposed. In particular, the study aims to analyze the impact of the subjective structure of the decision-maker during the evaluation and selection phase of the alternatives. Therefore, the experimental framework is divided into three phases. In the first phase, experts are sent to evaluate the characteristics of all portfolios individually, without peer comparison, arriving independently at the selection of the preferred portfolio. The experts' evaluations are used to obtain individual Analytical Hierarchical Processes that define the weight that each expert gives to all criteria with respect to the proposed alternatives. This step provides insight into how the decision maker's decision process develops, step by step, from goal analysis to alternative selection. The second phase includes the description of the decision maker's state through Markov chains. In fact, the individual weights obtained in the first phase can be reviewed and described as transition weights from one state to another. Thus, with the construction of the individual transition matrices, the possible next state of the expert is determined from the individual weights at the end of the first phase. Finally, the experts meet, and the process of reaching consensus is analyzed by considering the single individual state obtained at the previous stage and the false consensus bias. The work contributes to the study of the impact of subjective structures, quantified through the Analytical Hierarchical Process, and how they combine with the false consensus bias in group decision-making dynamics and the consensus reaching process in problems involving the selection of equivalent portfolios.

Keywords: analytical hierarchical process, consensus building, false consensus effect, markov chains, portfolio selection problem

Procedia PDF Downloads 68

Authors: Modupe Beatrice Adeyinka

Abstract:

French, as a foreign language in Nigeria, is pronounced to be the second official language and a compulsory subject in the primary school level; hence, colleges of education across the nation are saddled with the responsibility of training teachers for the subject. However, it has been observed that this policy has not been fully implemented, for French teachers in training, do face many challenges, of which translation is chief. In a bid to investigate the major cause of the perceived translation problem, this study examined French translation problems of pre-service teachers in selected colleges of education in the southwest, Nigeria. This study adopted a descriptive survey research design. The simple random sampling technique was used to select four colleges of education in the southwest, where 100 French students were randomly selected by selecting 25 from each school. The pre-service teachers’ French translation problems’ questionnaire (PTFTPQ) was used as an instrument while four research questions were answered and three null hypotheses were tested. Among others, the findings revealed that students do have problems with false friends, though mainly with its interpretation when attempting French-English translation and vice versa; majority of the students make use of French dictionary as a way out and found the material very useful for their understanding of false friends. Teachers were, therefore, urged to attend in-service training where they would be exposed to new and emerging strategies, approaches and methodologies of French language teaching that will make students overcome the challenge of translation in learning French.

Keywords: false friends, French language, pre-service teachers, source language, target language, translation

Procedia PDF Downloads 121

Authors: K. Khanafer

Abstract:

The aim of this investigation was to validate the fluid-structure interaction (FSI) model of type B aortic dissection with our experimental results from a bench-top-model. Another objective was to study the relationship between the size of a septectomy that increases the outflow of the false lumen and its effect on the values of the differential of pressure between true lumen and false lumen. FSI analysis based on Galerkin’s formulation was used in this investigation to study flow pattern and hemodynamics within a flexible type B aortic dissection model using boundary conditions from our experimental data. The numerical results of our model were verified against the experimental data for various tear size and location. Thus, CFD tools have a potential role in evaluating different scenarios and aortic dissection configurations.

Keywords: aortic dissection, fluid-structure interaction, in vitro model, numerical

Procedia PDF Downloads 246

Authors: Olivia A. Kjorlien, Maryam Asghari, Farshid Alizadeh-Shabdiz

Abstract:

The goal of this paper is to investigate the impact of mosaic augmentation on the performance of object detection solutions. To carry out the study, YOLOv4 and YOLOv4-Tiny models have been selected, which are popular, advanced object detection models. These models are also representatives of two classes of complex and simple models. The study also has been carried out on two categories of objects, simple and complex. For this study, YOLOv4 and YOLOv4 Tiny are trained with and without mosaic augmentation for two sets of objects. While mosaic augmentation improves the performance of simple object detection, it deteriorates the performance of complex object detection, specifically having the largest negative impact on the false positive rate in a complex object detection case.

Keywords: accuracy, false positives, mosaic augmentation, object detection, YOLOV4, YOLOV4-Tiny

Procedia PDF Downloads 78

Authors: Wahab Ali, Oyebade K. Oyedotun, Adnan Khashman

Abstract:

Breast cancer remains a threat to the woman’s world in view of survival rates, it early diagnosis and mortality statistics. So far, research has shown that many survivors of breast cancer cases are in the ones with early diagnosis. Breast cancer is usually categorized into stages which indicates its severity and corresponding survival rates for patients. Investigations show that the farther into the stages before diagnosis the lesser the chance of survival; hence the early diagnosis of breast cancer becomes imperative, and consequently the application of novel technologies to achieving this. Over the year, mammograms have used in the diagnosis of breast cancer, but the inconclusive deductions made from such scans lead to either false negative cases where cancer patients may be left untreated or false positive where unnecessary biopsies are carried out. This paper presents the application of artificial neural networks in the prediction of severity of breast tumour (whether benign or malignant) using mammography reports and other factors that are related to breast cancer.

Keywords: breast cancer, intelligent classification, neural networks, mammography

Procedia PDF Downloads 461

Authors: S. Benchelha, H. Chennaoui, M. Hakdaoui, L. Baidder, H. Mansouri, H. Ejjaaouani, T. Benchelha

Abstract:

Northern Morocco is characterized by relatively young mountains experiencing a very important dynamic compared to other areas of Morocco. The dynamics associated with the formation of the Rif chain (Alpine tectonics), is accompanied by instabilities essentially related to tectonic movements. The realization of important infrastructures (Roads, Highways,...) represents a triggering factor and favoring landslides. This paper is part of the establishment of landslides susceptibility map and concerns the mapping of unstable areas in the province of Taounate. The landslide was identified using the components of the false color (FCC) of images Landsat OLI: i) the first independent component (IC1), ii) The main component (PC), iii) Normalized difference index (NDI). This mapping for landslides class is validated by in-situ surveys.

Keywords: landslides, False Color Composite (FCC), Independent Component Analysis (ICA), Principal Component Analysis (PCA), Normalized Difference Index (NDI), Normalized Difference Mid Red Index (NDMIDR)

Procedia PDF Downloads 262

Authors: Ho Jeong Jin, Chang Won Seo, Choon Sik Cho, Bong Yong Choi, Kwang Kyun Na, Sang Rok Lee

Abstract:

In this paper, a radar signal processing technique using the LFM-FSK (Linear Frequency Modulation-Frequency Shift Keying) is proposed for reducing the false alarm rate based on the compressive sensing. The LFM-FSK method combines FMCW (Frequency Modulation Continuous Wave) signal with FSK (Frequency Shift Keying). This shows an advantage which can suppress the ghost phenomenon without the complicated CFAR (Constant False Alarm Rate) algorithm. Moreover, the parametric sparse algorithm applying the compressive sensing that restores signals efficiently with respect to the incomplete data samples is also integrated, leading to reducing the burden of ADC in the receiver of radars. 24 GHz FMCW signal is applied and tested in the real environment with FSK modulated data for verifying the proposed algorithm along with the compressive sensing.

Keywords: compressive sensing, LFM-FSK radar, radar signal processing, sparse algorithm

Procedia PDF Downloads 444

Authors: Amjad Al Shammari, Ashraf Ibrahim, Laila Seada

Abstract:

Background and Objectives: Incidence of thyroid carcinoma has been increasing world-wide. In the present study, we evaluated diagnostic accuracy of Fine needle aspiration (FNA) and its efficiency in early detecting neoplastic lesions of thyroid gland over a 3-year period. Methods: Data have been retrieved from pathology files in King Khalid Hospital. For each patient, age, gender, FNA, site & size of nodule and final histopathologic diagnosis were recorded. Results: Study included 490 cases where 419 of them were female and 71 male. Male to female ratio was 1:6. Mean age was 43 years for males and 38 for females. Cases with confirmed histopathology were 131. In 101/131 (77.1%), concordance was found between FNA and histology. In 30/131 (22.9%), there was discrepancy in diagnosis. Total malignant cases were 43, out of which 14 (32.5%) were true positive and 29 (67.44%) were false negative. No false positive cases could be found in our series. Conclusion: FNA could diagnose benign nodules in all cases, however, in malignant cases, ultrasound findings have to be taken into consideration to avoid missing of a microcarcinoma in the contralateral lobe.

Keywords: FNA, hail, histopathology, thyroid

Procedia PDF Downloads 303

Authors: C. C. Okafor

Abstract:

The effect of different varieties of plantain (Horn, false horn and French) and fibre types (soy bean residue, cassava sievette and rice bran) on functional and organoleptic properties of plantain-based flour was assessed. Horn, false horn french were processed by washing, peeling with knife, slicing into 3mm thickness and steam blanched at 80℃ for 5minutes, oven dried at 65℃ for 48 hours and milled into flours with attrition mill, sieved with 60 mesh sieve, separately. Fibre sources were processed, milled and fractionated into 60, 40 & 20 mesh sizes. Both flours were blended as 80:20, 70:30 and 60:40. Results obtained indicated that water absorption capacity is highest (2.68) in French plantain variety irrespective of the fibre type used. And in all variety tested the swelling capacity is highest (2.93) when the plantain flour is blended with soy residue (SR) and lowest (1.25) when blended with rice brain (RB). The results show that there is significant variety and fibre type interaction effect at (P < : 0.05). Again the results showed that texture mold ability and overall acceptability were best (7.00) when soy residue was used where as addition of rice bran into plantain flour resulted in fufu with poor texture. This trend was observed in all the verities of plantain tested and in all of the particle size of flour. Using cassava serviette also yield fufu similar to that produced with soy residue in all the parameter tested (mold ability, texture and overall acceptability. Generally, plantain flours from french and false horn yielded better quality fufu in terms of texture mold ability, overall acceptability, irrespective of the fibre type used.

Keywords: functional, organoleptic, particle size, sieve mesh, variety

Procedia PDF Downloads 375

Authors: Abdolreza Esmaeilzadeh, Mehri Mirzaei

Abstract:

Objective: Rheumatic disease is a chronic disease that causes pain, stiffness, swelling and limited motion and function of many joints. RA is the most common form of autoimmune arthritis, affecting more than 1.3 million Americans. Of these, about 75% are women. Materials and Methods: This study was formed due to the misconception about ANA test, which is frequently performed with methods based upon solid phase as ELISA. This experiment was conducted on 430 patients, with clinical symptoms that are likely affected with rheumatic diseases, simultaneously by means of ANA and FANA. Results: 36 cases (8.37%) of patients, despite positive ANA, have demonstrated negative results via Indirect Immunofluorescence Assay (IIFA), (false positive). 116 cases (27%) have demonstrated negative ANA results, by means of the ELISA technique, although they had positive IIFA results. Conclusion: Other advantages of IIFA are antibody titration and specific pattern detection that have the capability of distinguishing positive dsDNA results. According to the restrictions and false negative cases, in patients, IIFA test is highly recommended for these disease's diagnosis.

Keywords: autoimmune disease, IIFA, EIA, rheumatic disease

Procedia PDF Downloads 475

Authors: Bryony Pound

Abstract:

This study investigated how views of green or urban space affect learning performance. It provides evidence of the value of visual access to greenspace in work and learning environments, and builds on the extensive research into the cognitive and learning-related benefits of access to green and natural spaces, particularly in learning environments. It demonstrates that benefits of visual access to natural spaces whilst learning can produce statistically significant faster responses than those facing urban views after only 5 minutes. The primary hypothesis of this research was that a greenspace view would improve short-term learning. Participants were randomly assigned to either a view of parkland or of urban buildings from the same room. They completed a psychological test of two stages. The first stage consisted of a presentation of words from eight different categories (four manmade and four natural). Following this a 2.5 minute break was given; participants were not prompted to look out of the window, but all were observed doing so. The second stage of the test involved a word recognition/false memory test of three types. Type 1 was presented words from each category; Type 2 was non-presented words from those same categories; and Type 3 was non-presented words from different categories. Participants were asked to respond with whether they thought they had seen the words before or not. Accuracy of responses and reaction times were recorded. The key finding was that reaction times for Type 2 words (highest difficulty) were significantly different between urban and green view conditions. Those with an urban view had slower reaction times for these words, so a view of greenspace resulted in better information retrieval for word and false memory recognition. Importantly, this difference was found after only 5 minutes of exposure to either view, during winter, and with a sample size of only 26. Greenspace views improve performance in a learning task. This provides a case for better visual access to greenspace in work and learning environments.

Keywords: benefits, greenspace, learning, restoration

Procedia PDF Downloads 104

Authors: Saugata Bose, Ritambhra Korpal

Abstract:

The internet has increased the copy-paste scenarios amongst students as well as amongst researchers leading to different levels of plagiarized documents. For this reason, much of research is focused on for detecting plagiarism automatically. In this paper, an initiative is discussed where Natural Language Processing (NLP) techniques as well as supervised machine learning algorithms have been combined to detect plagiarized texts. Here, the major emphasis is on to construct a framework which detects external plagiarism from monolingual texts successfully. For successfully detecting the plagiarism, n-gram frequency comparison approach has been implemented to construct the model framework. The framework is based on 120 characteristics which have been extracted during pre-processing the documents using NLP approach. Afterwards, filter metrics has been applied to select most relevant characteristics and then supervised classification learning algorithm has been used to classify the documents in four levels of plagiarism. Confusion matrix was built to estimate the false positives and false negatives. Our plagiarism framework achieved a very high the accuracy score.

Keywords: lexical matching, shallow NLP, supervised machine learning algorithm, word n-gram

Procedia PDF Downloads 328

Authors: Jean Berger, Mohamed Barkaoui

Abstract:

Discrete search path planning in time-constrained uncertain environment relying upon imperfect sensors is known to be hard, and current problem-solving techniques proposed so far to compute near real-time efficient path plans are mainly bounded to provide a few move solutions. A new information-theoretic –based open-loop decision model explicitly incorporating false alarm sensor readings, to solve a single agent military logistics search-and-delivery path planning problem with anticipated feedback is presented. The decision model consists in minimizing expected entropy considering anticipated possible observation outcomes over a given time horizon. The model captures uncertainty associated with observation events for all possible scenarios. Entropy represents a measure of uncertainty about the searched target location. Feedback information resulting from possible sensor observations outcomes along the projected path plan is exploited to update anticipated unit target occupancy beliefs. For the first time, a compact belief update formulation is generalized to explicitly include false positive observation events that may occur during plan execution. A novel genetic algorithm is then proposed to efficiently solve search path planning, providing near-optimal solutions for practical realistic problem instances. Given the run-time performance of the algorithm, natural extension to a closed-loop environment to progressively integrate real visit outcomes on a rolling time horizon can be easily envisioned. Computational results show the value of the approach in comparison to alternate heuristics.

Keywords: search path planning, false alarm, search-and-delivery, entropy, genetic algorithm

Procedia PDF Downloads 333

Authors: Dylan Elliott, Katya Pertsova

Abstract:

Preposition errors are some of the most common errors created by L2 speakers. In addition, improving error correction and detection methods remains an open issue in the realm of Natural Language Processing (NLP). This research investigates whether the bidirectional encoder representations from the transformers model (BERT) have the potential to correct preposition errors accurately enough to be useful in error correction software. This research finds that BERT performs strongly when the scope of its error correction is limited to preposition choice. The researchers used an open-source BERT model and over three hundred thousand edited sentences from Wikipedia, tagged for part of speech, where only a preposition edit had occurred. To test BERT’s ability to detect errors, a technique known as multi-level masking was used to generate suggestions based on sentence context for every prepositional environment in the test data. These suggestions were compared with the original errors in the data and their known corrections to evaluate BERT’s performance. The suggestions were further analyzed to determine if BERT more often agreed with the judgements of the Wikipedia editors. Both the untrained and fined-tuned models were compared. Finetuning led to a greater rate of error-detection which significantly improved recall, but lowered precision due to an increase in false positives or falsely flagged errors. However, in most cases, these false positives were not errors in preposition usage but merely cases where more than one preposition was possible. Furthermore, when BERT correctly identified an error, the model largely agreed with the Wikipedia editors, suggesting that BERT’s ability to detect misused prepositions is better than previously believed. To evaluate to what extent BERT’s false positives were grammatical suggestions, we plan to do a further crowd-sourcing study to test the grammaticality of BERT’s suggested sentence corrections against native speakers’ judgments.

Keywords: BERT, grammatical error correction, preposition error detection, prepositions

Procedia PDF Downloads 116

Authors: Camilla Elphick, Graham Hole, Samuel Hutton, Graham Pike

Abstract:

Pupil size has been found to change irrespective of luminosity, suggesting that it can be used to make inferences about cognitive processes, such as cognitive load. To see whether identifying a target requires a different cognitive load to rejecting distractors, the effect of viewing a target (compared with viewing distractors) on pupil size was investigated using a sequential video lineup procedure with two lineup sessions. Forty one participants were chosen randomly via the university. Pupil sizes were recorded when viewing pre target distractors and post target distractors and compared to pupil size when viewing the target. Overall, pupil size was significantly larger when viewing the target compared with viewing distractors. In the first session, pupil size changes were significantly different between participants who identified the target (Hits) and those who did not. Specifically, the pupil size of Hits reduced significantly after viewing the target (by 26%), suggesting that cognitive load reduced following identification. The pupil sizes of Misses (who made no identification) and False Alarms (who misidentified a distractor) did not reduce, suggesting that the cognitive load remained high in participants who failed to make the correct identification. In the second session, pupil sizes were smaller overall, suggesting that cognitive load was smaller in this session, and there was no significant difference between Hits, Misses and False Alarms. Furthermore, while the frequency of Hits increased, so did False Alarms. These two findings suggest that the benefits of including a second session remain uncertain, as the second session neither provided greater accuracy nor a reliable way to measure it. It is concluded that pupil size is a measure of face recognition strength in the first session of a target present lineup procedure. However, it is still not known whether cognitive load is an adequate explanation for this, or whether cognitive engagement might describe the effect more appropriately. If cognitive load and cognitive engagement can be teased apart with further investigation, this would have positive implications for understanding eyewitness identification. Nevertheless, this research has the potential to provide a tool for improving the reliability of lineup procedures.

Keywords: cognitive load, eyewitness identification, face recognition, pupillometry

Procedia PDF Downloads 371

Authors: Marzieh Karimihaghighi, Carlos Castillo

Abstract:

This work studies how Machine Learning (ML) may be used to increase the effectiveness of a criminal recidivism risk assessment tool, RisCanvi. The two key dimensions of this analysis are predictive accuracy and algorithmic fairness. ML-based prediction models obtained in this study are more accurate at predicting criminal recidivism than the manually-created formula used in RisCanvi, achieving an AUC of 0.76 and 0.73 in predicting violent and general recidivism respectively. However, the improvements are small, and it is noticed that algorithmic discrimination can easily be introduced between groups such as national vs foreigner, or young vs old. It is described how effectiveness and algorithmic fairness objectives can be balanced, applying a method in which a single error disparity in terms of generalized false positive rate is minimized, while calibration is maintained across groups. Obtained results show that this bias mitigation procedure can substantially reduce generalized false positive rate disparities across multiple groups. Based on these results, it is proposed that ML-based criminal recidivism risk prediction should not be introduced without applying algorithmic bias mitigation procedures.

Keywords: algorithmic fairness, criminal risk assessment, equalized odds, recidivism

Procedia PDF Downloads 124

Authors: Marwa Qaraqe, Muhammad Ismail, Erchin Serpedin

Abstract:

This paper presents a novel architecture for a patient-specific epileptic seizure onset detector using scalp electroencephalography (EEG). The proposed architecture is based on the decision fusion calculated from energy and neural synchronization related features. Specifically, one level of the detector calculates the condition number (CN) of an EEG matrix to evaluate the amount of neural synchronization present within the EEG channels. On a parallel level, the detector evaluates the energy contained in four EEG frequency subbands. The information is then fed into two independent (parallel) classification units based on support vector machines to determine the onset of a seizure event. The decisions from the two classifiers are then combined together according to two fusion techniques to determine a global decision. Experimental results demonstrate that the detector based on the AND fusion technique outperforms existing detectors with a sensitivity of 100%, detection latency of 3 seconds, while it achieves a 2:76 false alarm rate per hour. The OR fusion technique achieves a sensitivity of 100%, and significantly improves delay latency (0:17 seconds), yet it achieves 12 false alarms per hour.

Keywords: epilepsy, EEG, seizure onset, electroencephalography, neuron, detection

Procedia PDF Downloads 447

Authors: Gautam Sharda

Abstract:

The concept of right speech is the third stage of the noble eightfold path as prescribed by the Buddha and followed by millions of practicing Buddhists. The Buddha lays a lot of importance on the notion of right speech (Samma Vacca). In the Angutara Nikaya, the Buddha mentioned what constitutes right speech, which is basically four kinds of abstentions; namely abstaining from false speech, abstaining from slanderous speech, abstaining from harsh or hateful speech and abstaining from idle chatter. The Buddha gives reasons in support of his view as to why abstaining from these four kinds of speeches is favourable not only for maintaining the peace and equanimity within an individual but also within a society. It is a known fact that when we say something harsh or slanderous to others, it eventually affects our individual peace of mind too. We also know about the many examples of hate speeches which have led to senseless cases of violence and which are well documented within our country and the world. Also, indulging in false speech is not a healthy sign for individuals within a group as this kind of a social group which is based on falsities and lies cannot really survive for long and will eventually lead to chaos. Buddha also told us to refrain from idle chatter or gossip as generally we have seen that idle chatter or gossip does more harm than any good to the individual and the society. Hence, if most of us actually inculcate this third stage (namely, right speech) of the noble eightfold path of the Buddha in our daily life, it would be highly beneficial both for the individual and for the harmony of the society.

Keywords: Buddhism, speech, individual, society

Procedia PDF Downloads 229

Authors: Noor Azwa Azreen Binti Abd. Aziz, Muhamad Zaim Bin Mohd Rozi

Abstract:

Moving towards the 4th Industrial Revolution, artificial intelligence (AI) is now more popular than ever. This subject is gaining significance every day and is continually expanding, often merging with other fields. Instead of merely being passive observers, there are benefits to understanding modern technology by delving into its inner workings. However, in a world teeming with digital information, the impact of AI on the spread of disinformation has garnered significant attention. The dissemination of inaccurate or misleading information is referred to as misinformation, posing a serious threat to democratic society, public debate, and individual decision-making. This article delves deep into the connection between AI and the dissemination of false information, exploring its potential, risks, and ethical issues as AI technology advances. The rise of AI has ushered in a new era in the dissemination of misinformation as AI-driven technologies are increasingly responsible for curating, recommending, and amplifying information on online platforms. While AI holds the potential to enhance the detection and mitigation of misinformation through natural language processing and machine learning, it also raises concerns about the amplification and propagation of false information. AI-powered deepfake technology, for instance, can generate hyper-realistic videos and audio recordings, making it increasingly challenging to discern fact from fiction.

Keywords: artificial intelligence, digital information, disinformation, ethical issues, misinformation

Procedia PDF Downloads 51

Authors: Ting-Yu Hsu, Shyu-Yu Wu, Shieh-Kung Huang, Hung-Wei Chiang, Kung-Chun Lu, Pei-Yang Lin, Kuo-Liang Wen

Abstract:

Regional earthquake early warning (EEW) systems are not suitable for Taiwan, as most destructive seismic hazards arise due to in-land earthquakes. These likely cause the lead-time provided by regional EEW systems before a destructive earthquake wave arrives to become null. On the other hand, an on-site EEW system can provide more lead-time at a region closer to an epicenter, since only seismic information of the target site is required. Instead of leveraging the information of several stations, the on-site system extracts some P-wave features from the first few seconds of vertical ground acceleration of a single station and performs a prediction of the oncoming earthquake intensity at the same station according to these features. Since seismometers could be triggered by non-earthquake events such as a passing of a truck or other human activities, to reduce the likelihood of false alarms, a seismometer was installed at three different locations on the same site and the performance of the EEW system for these three sensor locations were discussed. The results show that the location on the ground of the first floor of a school building maybe a good choice, since the false alarms could be reduced and the cost for installation and maintenance is the lowest.

Keywords: earthquake early warning, on-site, seismometer location, support vector machine

Procedia PDF Downloads 218

Authors: Nantakrit Yodpijit, Teppakorn Sittiwanchai

Abstract:

The number of older adults is rising rapidly. The world’s population becomes aging. Falls is one of common and major health problems in the elderly. Falls may lead to acute and chronic injuries and deaths. The fall-prone individuals are at greater risk for decreased quality of life, lowered productivity and poverty, social problems, and additional health problems. A number of studies on falls prevention using fall detection system have been conducted. Many available technologies for fall detection system are laboratory-based and can incur substantial costs for falls prevention. The utilization of alternative technologies can potentially reduce costs. This paper presents the new design and development of a wearable-based fall detection system using an Accelerometer and Gyroscope as motion sensors for the detection of body orientation and movement. Algorithms are developed to differentiate between Activities of Daily Living (ADL) and falls by comparing Threshold-based values with Artificial Neural Networks (ANN). Results indicate the possibility of using the new threshold-based method with neural network algorithm to reduce the number of false positive (false alarm) and improve the accuracy of fall detection system.

Keywords: aging, algorithm, artificial neural networks (ANN), fall detection system, motion sensorsthreshold

Procedia PDF Downloads 468

Authors: Lamis Naddaf, Yuval Tabach

Abstract:

In this research, we identified the missense genetic variants that have the potential to enhance resistance against cancer. Such field has not been widely explored, as researchers tend to investigate mutations that cause diseases, in response to the suffering of patients, rather than those mutations that protect from them. In conjunction with the genomic revolution, and the advances in genetic engineering and synthetic biology, identifying the protective variants will increase the power of genotype-phenotype predictions and can have significant implications on improved risk estimation, diagnostics, prognosis and even for personalized therapy and drug discovery. To approach our goal, we systematically investigated the sites of the coding genomes and picked up the alleles that showed a correlation with the species’ cancer resistance. We predicted 250 protecting variants (PVs) with a 0.01 false discovery rate and more than 20 thousand PVs with a 0.25 false discovery rate. Cancer resistance in Mammals and reptiles was significantly predicted by the number of PVs a species has. Moreover, Genes enriched with the protecting variants are enriched in pathways relevant to tumor suppression like pathways of Hedgehog signaling and silencing, which its improper activation is associated with the most common form of cancer malignancy. We also showed that the PVs are more abundant in healthy people compared to cancer patients within different human races.

Keywords: comparative genomics, machine learning, cancer resistance, cancer-protecting alleles

Procedia PDF Downloads 70

Authors: Htay Htay Yi, Zin May Aye

Abstract:

Network security is role of the ICT environment because malicious users are continually growing that realm of education, business, and then related with ICT. The network security contravention is typically described and examined centrally based on a security event management system. The firewalls, Intrusion Detection System (IDS), and Intrusion Prevention System are becoming essential to monitor or prevent of potential violations, incidents attack, and imminent threats. In this system, the firewall rules are set only for where the system policies are needed. Dataset deployed in this system are derived from the testbed environment. The traffic as in DoS and PortScan traffics are applied in the testbed with firewall and IDS implementation. The network traffics are classified as normal or attacks in the existing testbed environment based on six machine learning classification methods applied in the system. It is required to be tested to get datasets and applied for DoS and PortScan. The dataset is based on CICIDS2017 and some features have been added. This system tested 26 features from the applied dataset. The system is to reduce false positive rates and to improve accuracy in the implemented testbed design. The system also proves good performance by selecting important features and comparing existing a dataset by machine learning classifiers.

Keywords: false negative rate, intrusion detection system, machine learning methods, performance

Procedia PDF Downloads 96