Real-time traffic sign detection and recognition using Raspberry Pi

Nowadays, the number of road accident in Malaysia is increasing expeditiously. One of the ways to reduce the number of road accident is through the development of the advanced driving assistance system (ADAS) by professional engineers. Several ADAS system has been proposed by taking into consideration the delay tolerance and the accuracy of the system itself. In this work, a traffic sign recognition system has been developed to increase the safety of the road users by installing the system inside the car for driver’s awareness. TensorFlow algorithm has been considered in this work for object recognition through machine learning due to its high accuracy. The algorithm is embedded in the Raspberry Pi 3 for processing and analysis to detect the traffic sign from the real-time video recording from Raspberry Pi camera NoIR. This work aims to study the accuracy, delay and reliability of the developed system using a Raspberry Pi 3 processor considering several scenarios related to the state of the environment and the condition of the traffic signs. A real-time testbed implementation has been conducted considering twenty different traffic signs and the results show that the system has more than 90% accuracy and is reliable with an acceptable delay.

A Pragmatic Approach to the Management of Severe Awake Bruxism in an Adolescent with Cerebral Palsy and Global Developmental Delay

Cerebral palsy is a neurological and motor condition characterised by muscle balance and posture impairments. Bruxism and malocclusion were frequently observed in patients with cerebral palsy, in contrast to other oral anomalies. The report outlines how severe awake bruxism is managed in a 16-year-old Korean boy who has nonverbal spastic cerebral palsy and global developmental delay. The treatment protocol involved the fabrication of soft occlusal splints of three and four millimetres in thickness, followed by the placement of stainless-steel crowns on all first permanent molars whilst video recording and a bruxism diary was kept. Fixed restorations demonstrate increased endurance in withstanding bruxism force in persons who are dependent on their caretaker.

Confronting Deep-Learning and Biodiversity Challenges for Automatic Video-Monitoring of Marine Ecosystems

With the availability of low-cost and efficient digital cameras, ecologists can now survey the world’s biodiversity through image sensors, especially in the previously rather inaccessible marine realm. However, the data rapidly accumulates, and ecologists face a data processing bottleneck. While computer vision has long been used as a tool to speed up image processing, it is only since the breakthrough of deep learning (DL) algorithms that the revolution in the automatic assessment of biodiversity by video recording can be considered. However, current applications of DL models to biodiversity monitoring do not consider some universal rules of biodiversity, especially rules on the distribution of species abundance, species rarity and ecosystem openness. Yet, these rules imply three issues for deep learning applications: the imbalance of long-tail datasets biases the training of DL models; scarce data greatly lessens the performances of DL models for classes with few data. Finally, the open-world issue implies that objects that are absent from the training dataset are incorrectly classified in the application dataset. Promising solutions to these issues are discussed, including data augmentation, data generation, cross-entropy modification, few-shot learning and open set recognition. At a time when biodiversity faces the immense challenges of climate change and the Anthropocene defaunation, stronger collaboration between computer scientists and ecologists is urgently needed to unlock the automatic monitoring of biodiversity.

Pedagogical Strategies for the learning of medicine students

With the epidemiological contingency, the learning processes were modified by teaching with virtualization. The teaching staff implemented pedagogical strategies structuring methodologies, interaction dynamics, fulfilling the objectives set out in the educational curriculum. Objective: To implement pedagogical strategies involved in virtualization during the learning process in medical students. Methodology: A descriptive, observational study with a qualitative approach over a period of 8 months. The sample was 225 students from the 5th semester of the Surgeon Degree. Results: It was shown that group activities, synchronous online conferences have 68% approval, dynamics such as discussion forums have 85% approval. Video recording has 45%, essays 25%, and mind maps 30%. Conclusion: Implementing educational strategies allows assessing efficiency and effectiveness promoting learning for the development of professional intellect.

Contactless facial video recording with deep learning models for the detection of atrial fibrillation

Atrial fibrillation (AF) is often asymptomatic and paroxysmal. Screening and monitoring are needed especially for people at high risk. This study sought to use camera-based remote photoplethysmography (rPPG) with a deep convolutional neural network (DCNN) learning model for AF detection. All participants were classified into groups of AF, normal sinus rhythm (NSR) and other abnormality based on 12-lead ECG. They then underwent facial video recording for 10 min with rPPG signals extracted and segmented into 30-s clips as inputs of the training of DCNN models. Using voting algorithm, the participant would be predicted as AF if > 50% of their rPPG segments were determined as AF rhythm by the model. Of the 453 participants (mean age, 69.3 ± 13.0 years, women, 46%), a total of 7320 segments (1969 AF, 1604 NSR & 3747others) were analyzed by DCNN models. The accuracy rate of rPPG with deep learning model for discriminating AF from NSR and other abnormalities was 90.0% and 97.1% in 30-s and 10-min recording, respectively. This contactless, camera-based rPPG technique with a deep-learning model achieved significantly high accuracy to discriminate AF from non-AF and may enable a feasible way for a large-scale screening or monitoring in the future.

Digital Video Tampering Detection and Localization: Review, Representations, Challenges and Algorithm

Digital videos are now low-cost, easy to capture and easy to share on social media due to the common feature of video recording in smart phones and digital devices. However, with the advancement of video editing tools, videos can be tampered (forged) easily for propaganda or to gain illegal advantages—ultimately, the authenticity of videos shared on social media cannot be taken for granted. Over the years, significant research has been devoted to developing new techniques for detecting different types of video tampering. In this paper, we offer a detailed review of existing passive video tampering detection techniques in a systematic way. The answers to research questions prepared for this study are also elaborated. The state-of-the-art research work is analyzed extensively, highlighting the pros and cons and commonly used datasets. Limitations of existing video forensic algorithms are discussed, and we conclude with research challenges and future directions.

Foot-to-Foot Contact Among Initial Goal-Directed Movements Supports the Prognostic Value of Fidgety Movements in HIE-Cooled Infants

Background: Few studies conducted to date have observed general movements in infants affected by hypoxic–ischemic encephalopathy (HIE) who underwent therapeutic hypothermia. We investigated whether foot-to-foot contact (FF) could support the predictive value of fidgety movements (FMs) in infants affected by HIE and treated with brain cooling.Methods: Spontaneous motility was video recorded for 3–5 min at 12 weeks post-term age in 58 full-term newborn infants affected by perinatal asphyxia who were cooled due to moderate to severe HIE. FF and FMs were blindly scored by three independent observers. At 24 months, each patient underwent a neurological examination by Amiel-Tison and Grenier.Results: At 24 months, 47 infants had developed typically at neurological examination, eight had developed mild motor impairment, and three developed cerebral palsy (CP). At 12 weeks, 34 (58.6%) infants had shown normal FMs, four of whom developed mild motor impairment. Twenty-four infants (41.4%) exhibited abnormal or no FMs, four of whom developed mild motor impairment and three developed CP. FF was present in 20 infants (34.5%), two of whom developed mild motor impairment. FF was absent in 38 infants (65.5%), six of whom developed mild motor impairment and three developed CP. Both FMs and FF, considered separately, were 100% sensitive for predicting CP at 24 months, but only 61 and 36%, respectively, were specific. Summing the two patterns together, the specificity increases to 73%, considering only CP as an abnormal outcome, and increases to 74% when considering CP plus mild motor impairment. Unexpectedly, fidgety movements were absent in 24 infants with typical motor outcomes, 17 of whom showed a typical motor outcome.Conclusions: FF is already part of motor repertoire at 12 weeks and allows a comparison of spontaneous non-voluntary movements (FMs) to pre-voluntary movements (FF). FF supports FMs for both sensitivity and specificity. A second video recording at 16–18 weeks, when pedipulation is present in healthy infants, is suggested: it may better define the presence or absence of goal-directed motility.

SYNTACTICAL ERROR ANALYSIS OF EFL LEARNER IN CONVERSATION CLASS AT ENGLISH LITERATURE STUDY PROGRAM/ANALISIS KESALAHAN SINTAKSIS PEMBELAJAR BAHASA INGGRIS SEBAGAI BAHASA ASING PADA KELAS PERCAKAPAN DI PROGRAM STUDI SASTRA INGGRIS

The learner’s syntactical error analyses have long been interested in the second and foreign language researchers. This study aimed at investigating the syntactical error types, the form of error, and the frequencies of these errors that occurred in the sixth-semester student presentation on the conversation class at the English Literature Study Program in Universitas Teknokrat Indonesia. To achieve the objectives, the data were collected from the learner’s transcribed speech. The sampling of non-probability was used to select the classroom and participant’s characteristics. These data were collected by video recording, non- participant observation techniques, and documents. To classify the learner’s syntactical errors, Politzer Ramirez’s (1973) syntactical errors taxonomy was adopted. Further, the qualitative method was applied in this study. Based on the result of the analysis, there were 64 syntactical errors uttered by the learner. The results of the analysis were then categorized into three forms: phrases, clauses, and sentences. The results of this study showed that the learner often made the syntactical error in the form of sentences. That was 32 errors (50%). Furthermore, the study found that the amount of confusion was the most commonly uttered as the type of error (26,56%). The learner often got confused to make the right use between the number and the subject mentioned. Thus, the findings indicated that even though the learner considered as the best; yet the learner still possibly made some errors. Therefore, lecturers or instructors should raise the students’ syntactical error awareness. So that it could improve the student’ speaking skills in their level of English.Keywords: error analysis, syntactical error, conversation class, speaking skillsAbstrakAnalisis kesalahan sintaksis siswa telah lama menjadi hal yang menarik bagi peneliti bahasa kedua dan asing. Penelitian ini bertujuan untuk menyelidiki jenis kesalahan sintaksis, bentuk kesalahan, dan frekuensi kesalahan tersebut pada presentasi siswa semester enam pada kelas percakapan di Program Studi Sastra Inggris, Universitas Teknokrat Indonesia. Untuk mencapai tujuannya, data dikumpulkan dari presentasi siswa yang telah ditranskripsikan. Sampling non-probabilitas diterapkan untuk memilih karakteristik kelas dan partisipan. Data tersebut dikumpulkan dengan menggunakan teknik perekaman video, pengamatan non-partisipan, dan dokumen. Untuk mengklasifikasikan kesalahan sintaksis mahasiswa, taksonomi kesalahan sintaksis Politzer dan Ramirez (1973) diadopsi. Lebih lanjut, metode kualitatif diterapkan dalam penelitian ini. Berdasarkan hasil analisis, terdapat 64 kesalahan sintaksis yang ditemukan pada presentasi siswa. Hasil analisis kemudian dikategorikan dalam tiga bentuk, yakni frase, klausa, dan kalimat. Hasil penelitian ini menunjukkan bahwa siswa sering membuat kesalahan sintaksis dalam bentuk kalimat, yakni 32 kesalahan (50%). Lebih jauh, penelitian ini menemukan bahwa ‘number of confusion’ merupakan jenis kesalahan yang sering diujarkan, yakni 26,56%. Pembelajar sering mengalami kebingungan dalam menggunakan antara nomor dan subjek yang disebutkan. Dengan demikian, temuan menunjukkan bahwa meskipun mahasiswa dianggap yang terbaik masih membuat beberapa kesalahan. Oleh karena itu, dosen atau instruktur harus meningkatkan kesadaran kesalahan sintaksis mahasiswa sehingga hal ini dapat meningkatkan keterampilan berbicara siswa di tingkat bahasa Inggris mereka.Kata kunci: analisis kesalahan, kesalahan sintaksis, kelas percakapan, keterampilan berbicara

In vitro study of cataract extraction by bursts of microsecond 1.54-mm laser pulses

Laser extraction of a model porcine eye cataract has been performed for the first time in an in vitro experiment using a 1.54-μm Yb,Er : glass laser generating bursts of microsecond pulses. We used effective pulse repetition rates from 36 to 75 Hz and average laser output powers from 3.9 to 5.25 W. The results demonstrate for the first time that, at an effective pulse repetition rate of 45 Hz, burst repetition rate of 15 Hz, three microsecond pulses per burst, and a burst energy from 260 to 265 mJ, the laser step duration in cataract extraction is 130 plusmn; 10 s, which is comparable to the ultrasonic phacoemulsification and laser extraction time in the case of a Nd : YAG laser emitting at 1.44 μm. Acoustometry and high speed video recording of hydroacoustic processes accompanying interaction of water with 1.54-μm radiation from the Yb, Er : glass laser generating bursts of microsecond pulses have made it possible for the first time to detect overlap of hydroacoustic processes at the pulse spacing in bursts reduced to under 700 μs. In the case of overlap of hydroacoustic processes, despite the increase in average power and effective pulse repetition rate, acoustic wave generation is ineffective because pulses propagate through bubbles formed in the water. Laser cataract extraction is shown to be most effective at a lower average power, lower effective pulse repetition rate, and burst pulse spacing of 850 ± 10 μs.

Evidence of learning walks related to scorpion home burrow navigation

The Navigation by Chemotextural Familiarity Hypothesis (NCFH) suggests that scorpions use their midventral pectines to gather chemical and textural information near their burrows and use this information as they subsequently return home. For NCFH to be viable, animals must somehow acquire home-directed ″tastes″ of the substrate, such as through path integration (PI) and/or learning walks. We conducted laboratory behavioral trials using desert grassland scorpions (Paruroctonus utahensis). Animals reliably formed burrows in small mounds of sand we provided in the middle of circular, sand lined behavioral arenas. We processed overnight infrared video recordings with a MATLAB script that tracked animal movements at 1-2 s intervals. In all, we analyzed the movements of 23 animals, representing nearly 1500 hours of video recording. We found that once animals established their home burrows, they immediately made one to several short, looping excursions away from and back to their burrows before walking greater distances. We also observed similar excursions when animals made burrows in level sand in the middle of the arena (i.e., no mound provided). These putative learning walks, together with recently reported PI in scorpions, may provide the crucial home-directed information requisite for NCFH.