首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Ain Shams University Researchers Describe New Findings in Artificial Intelligenc e (Interactive Augmented Reality System for Learning Phonetics Using Artificial Intelligence)

    48-49页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ar tificial intelligence. According to news originating from Cairo, Egypt, by NewsR x editors, the research stated, "The increasing adoption of language learning ap ps that utilize Augmented Reality (AR) and Artificial Intelligence (AI) for spee ch recognition has sparked interest in the potential benefits for phonetics educ ation. However, currently available AR apps only focus on teaching letter names and vocabulary, lacking the potential for a more immersive learning experience." Financial supporters for this research include School of Computer Science And El ectronic Engineering, University of Essex, Through The Open Access Fund. Our news journalists obtained a quote from the research from Ain Shams Universit y: "To address this limitation, this paper introduces an interactive AR system t hat integrates AI speech recognition with AR to provide an engaging and interact ive learning experience. To showcase the capabilities of the proposed system, we have created a prototype for the Arabic Phonetic Atlas textbook. This prototype enhances reading the /s/ sound page in the Atlas by incorporating a 3D animated model of the speech organs onto the existing 2D image. The dynamic animation of the 3D model reflects the sound description provided in the Atlas. The system a lso offers real-time user pronunciation feedback through a customized AI phoneme recognition system. A comprehensive user study was conducted to evaluate the us ability and learning impact of the proposed system, involving 83 adult participa nts aged between 18-40. The assessment approach involved the use of both direct and indirect observations, as well as various surveys to gather both numerical a nd qualitative information."
      原文链接:
    • NETL
    • NSTL

    Research Results from Laval University Update Knowledge of Machine Learning (Spe ctro-temporal acoustical markers differentiate speech from song across cultures)

    49-49页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on artificial intelligence is now available. According to news reporting out of Laval University by NewsRx editors, research stated, "Humans produce two forms of cognitively complex voca lizations: speech and song." Our news reporters obtained a quote from the research from Laval University: "It is debated whether these differ based primarily on culturally specific, learned features, or if acoustical features can reliably distinguish them. We study the spectro-temporal modulation patterns of vocalizations produced by 369 people li ving in 21 urban, rural, and small-scale societies across six continents. Specif ic ranges of spectral and temporal modulations, overlapping within categories an d across societies, significantly differentiate speech from song. Machine-learni ng classification shows that this effect is cross-culturally robust, vocalizatio ns being reliably classified solely from their spectro-temporal features across all 21 societies. Listeners unfamiliar with the cultures classify these vocaliza tions using similar spectro-temporal cues as the machine learning algorithm."
      原文链接:
    • NETL
    • NSTL

    Federal University of Uberlandia Reports Findings in Machine Learning (Explorato ry analysis of new craniometric measures for the investigation of biological sex using open-access statistical and machine-learning tools on a cone-beam compute d ...)

    50-51页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting from Uberlandia, Brazil, by N ewsRx journalists, research stated, "Investigation of the biological sex of huma n remains is a crucial aspect of physical anthropology. However, due to varying states of skeletal preservation, multiple approaches and structures of interest need to be explored." The news correspondents obtained a quote from the research from the Federal Univ ersity of Uberlandia, "This research aims to investigate the potential use of di stances between bifrontal breadth (FMB), infraorbital foramina distance (IOD), n asal breadth (NLB), inter-canine width (ICD), and distance between mental forami na (MFD) for combined sex prediction through traditional statistical methods and through open-access machine-learning tools. Ethical approval was obtained from the ethics committee, and out of 100 cone beam computed tomography (CBCT) scans, 54 individuals were selected with all the points visible. Ten extra exams were chosen to test the predictors developed from the learning sample. Descriptive an alysis of measurements, standard deviation, and standard error were obtained. T- student and Mann- Whitney tests were utilized to assess the sex differences withi n the variables. A logistic regression equation was developed and tested for the investigation of the biological sex as well as decision trees, random forest, a nd artificial neural networks machine-learning models. The results indicate a st rong correlation between the measurements and the sex of individuals. When combi ned, the measurements were able to predict sex using a regression formula or mac hine learning based models which can be exported and added to software or webpag es. Considering the methods, the estimations showed an accuracy rate superior to 80% for males and 82% for females. All skulls in th e test sample were accurately predicted by both statistical and machine-learning models."
      原文链接:
    • NETL
    • NSTL

    Universidad de San Andres Reports Findings in Frontotemporal Dementia (Automated free speech analysis reveals distinct markers of Alzheimer's and frontotemporal dementia)

    51-52页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Neurodegenerative Dise ases and Conditions - Frontotemporal Dementia is the subject of a report. Accord ing to news reporting out of Buenos Aires, Argentina, by NewsRx editors, researc h stated, "Dementia can disrupt how people experience and describe events as wel l as their own role in them. Alzheimer's disease (AD) compromises the processing of entities expressed by nouns, while behavioral variant frontotemporal dementi a (bvFTD) entails a depersonalized perspective with increased third-person refer ences."
      原文链接:
    • NETL
    • NSTL

    Shengjing Hospital of China Medical University Reports Findings in Neoplasms (De velopment and Validation of a Novel Machine Learning Model to Predict the Surviv al of Patients with Gastrointestinal Neuroendocrine Neoplasms)

    52-53页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Neoplasms is the subje ct of a report. According to news reporting out of Shenyang, People's Republic o f China, by NewsRx editors, research stated, "Well-calibrated models for persona lized prognostication of patients with gastrointestinal neuroendocrine neoplasms (GINENs) are limited. This study aimed to develop and validate a machine-learni ng model to predict the survival of patients with GINENs." Our news journalists obtained a quote from the research from the Shengjing Hospi tal of China Medical University, "Oblique random survival forest (ORSF) model, C ox proportional hazard risk model, Cox model with least absolute shrinkage and s election operator penalization, CoxBoost, Survival Gradient Boosting Machine, Ex treme Gradient Boosting survival regression, DeepHit, DeepSurv, DNNSurv, logisti c-hazard model, and PC-hazard model were compared. We further tuned hyperparamet ers and selected variables for the best-performing ORSF. Then, the final ORSF mo del was validated. A total of 43,444 patients with GINENs were included. The med ian (interquartile range) survival time was 53 (19-102) months. The ORSF model p erformed best, in which age, histology, M stage, tumor size, primary tumor site, sex, tumor number, surgery, lymph nodes removed, N stage, race, and grade were ranked as important variables. However, chemotherapy and radiotherapy were not n ecessary for the ORSF model. The ORSF model had an overall C index of 0.86 (95% confidence interval, 0.85-0.87). The area under the receiver operation curves at 1, 3, 5, and 10 years were 0.91, 0.89, 0.87, and 0.80, respectively. The decisi on curve analysis showed superior clinical usefulness of the ORSF model than the American Joint Committee on Cancer Stage. A nomogram and an online tool were gi ven."
      原文链接:
    • NETL
    • NSTL

    Istanbul University-Cerrahpasa Reports Findings in Artificial Intelligence [Artificial intelligence in retinal screening using OCT images: A review of the l ast decade (2013-2023)]

    53-54页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report. According to news reporting out of Istanbul, Turke y, by NewsRx editors, research stated, "Optical coherence tomography (OCT) has u shered in a transformative era in the domain of ophthalmology, offering non-inva sive imaging with high resolution for ocular disease detection. OCT, which is fr equently used in diagnosing fundamental ocular pathologies, such as glaucoma and age-related macular degeneration (AMD), plays an important role in the widespre ad adoption of this technology." Our news journalists obtained a quote from the research from Istanbul University -Cerrahpasa, "Apart from glaucoma and AMD, we will also investigate pertinent pa thologies, such as epiretinal membrane (ERM), macular hole (MH), macular dystrop hy (MD), vitreomacular traction (VMT), diabetic maculopathy (DMP), cystoid macul ar edema (CME), central serous chorioretinopathy (CSC), diabetic macular edema ( DME), diabetic retinopathy (DR), drusen, glaucomatous optic neuropathy (GON), ne ovascular AMD (nAMD), myopia macular degeneration (MMD) and choroidal neovascula rization (CNV) diseases. This comprehensive review examines the role that OCT-de rived images play in detecting, characterizing, and monitoring eye diseases. The 2020 PRISMA guideline was used to structure a systematic review of research on various eye conditions using machine learning (ML) or deep learning (DL) techniq ues. A thorough search across IEEE, PubMed, Web of Science, and Scopus databases yielded 1787 publications, of which 1136 remained after removing duplicates. Su bsequent exclusion of conference papers, review papers, and non-open-access arti cles reduced the selection to 511 articles. Further scrutiny led to the exclusio n of 435 more articles due to lower-quality indexing or irrelevance, resulting i n 76 journal articles for the review. During our investigation, we found that a major challenge for ML-based decision support is the abundance of features and t he determination of their significance. In contrast, DL-based decision support i s characterized by a plug-and-play nature rather than relying on a trial-and-err or approach. Furthermore, we observed that pre-trained networks are practical an d especially useful when working on complex images such as OCT. Consequently, pr e-trained deep networks were frequently utilized for classification tasks. Curre ntly, medical decision support aims to reduce the workload of ophthalmologists a nd retina specialists during routine tasks."
      原文链接:
    • NETL
    • NSTL

    Reports on Machine Learning Findings from Symbiosis International University Pro vide New Insights (Advanced Channel Coding Schemes for B5g/6g Networks: State-of -the-art Analysis, Research Challenges and Future Directions)

    54-55页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ma chine Learning. According to news reporting out of Maharashtra, India, by NewsRx editors, research stated, "As a consequence of continuing demand for additional capacity and higher quality data transmission, channel coding as a key componen t of a digital communication network has progressed from a classical single pair , point-to-point information theoretic application to a class of coding techniqu es with diverse parameters. The heterogeneous requirements of B5G/6G networks te chnology have made flexibility of code parameters the main desired feature while designing channel codes."
      原文链接:
    • NETL
    • NSTL

    New Robotics Study Results Reported from University of Zagreb (Diver-robot Commu nication Dataset for Underwater Hand Gesture Recognition)

    55-56页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ro botics. According to news reporting originating from Zagreb, Croatia, by NewsRx correspondents, research stated, "In this paper, we present a dataset of diving gesture images used for human-robot interaction underwater. By offering this ope n access dataset, the paper aims at investigating the potential of using visual detection of diving gestures from an autonomous underwater vehicle (AUV) as a fo rm of communication with a human diver." Financial support for this research came from Office of Naval Research. Our news editors obtained a quote from the research from the University of Zagre b, "In addition to the image recording, the same dataset was recorded using a sm art gesture recognition glove. The glove uses dielectric elastomer sensors and o n -board processing to determine the selected gesture and transmit the command a ssociated with the gesture to the AUV via acoustics. Although this method can be used under different visibility conditions and even without line of sight, it i ntroduces a communication delay required for the acoustic transmission of the ge sture command. To compare efficiency, the glove was equipped with visual markers proposed in a gesture -based language called CADDIAN and recorded with an under water camera in parallel to the glove's onboard recognition process. The dataset contains over 30,000 underwater frames of nearly 900 individual gestures annota ted in corresponding snippet folders. The dataset was recorded in a balanced rat io with five different divers in sea and five different divers in pool condition s, with gestures recorded at 1, 2 and 3 metres from the camera. The glove gestur e recognition statistics are reported in terms of average diver reaction time, a verage time taken to perform a gesture, recognition success rate, transmission t imes and more."
      原文链接:
    • NETL
    • NSTL

    New Findings from Tongji University in the Area of Robotics Described (Contrast, Imitate, Adapt: Learning Robotic Skills From Raw Human Videos)

    56-57页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ro botics. According to news reporting out of Shanghai, People's Republic of China, by NewsRx editors, research stated, "Learning robotic skills from raw human vid eos remains a non-trivial challenge. Previous works tackled this problem by leve raging behavior cloning or learning reward functions from videos." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from Tongji University, "Despite their remarkable performances, they may introduce several issues, such as the necessity for robot actions, requirements for consistent viewpoints and s imilar layouts between human and robot videos, as well as low sample efficiency. To this end, our key insight is to learn task priors by contrasting videos and to learn action priors through imitating trajectories from videos, and to utiliz e the task priors to guide trajectories to adapt to novel scenarios. We propose a three-stage skill learning framework denoted as Contrast-Imitate-Adapt (CIA). An interaction-aware alignment transformer is proposed to learn task priors by t emporally aligning video pairs. Then a trajectory generation model is used to le arn action priors. To adapt to novel scenarios different from human videos, the Inversion-Interaction method is designed to initialize coarse trajectories and r efine them by limited interaction. In addition, CIA introduces an optimization m ethod based on semantic directions of trajectories for interaction security and sample efficiency. The alignment distances computed by IAAformer are used as the rewards. We evaluate CIA in six real-world everyday tasks, and empirically demo nstrate that CIA significantly outperforms previous state-of-the-art works in te rms of task success rate and generalization to diverse novel scenarios layouts a nd object instances. Note to Practitioners-This work aims to study robot skill l earning from raw human videos. Compared with teleoperation or kinesthetic teachi ng in the laboratory, such learning method can flexibly utilize large-scale huma n videos available on the Internet, thereby improving the robot's ability to gen eralize to various complex scenarios. Previous works on learning from videos usu ally have some issues, including requirements for robot actions, consistent view points, similar layouts and low sample efficiency. To alleviate these issues, we propose a three-stage skill learning framework CIA. Temporal alignment is utili zed to learn task priors through our proposed transformer-based model and self-s upervised loss functions. A trajectory generation model is trained to learn the action priors. To further adapt to diverse scenarios, we propose a two-stage pol icy improvement method by initialization and interaction. An optimization method is introduced to ensure safe interaction and sample efficiency, where the optim ization objective is guided by the learned task priors."
      原文链接:
    • NETL
    • NSTL

    First Affiliated Hospital of Chongqing Medical University Reports Findings in Bi oinformatics (Mechanistic study of pre-eclampsia and macrophage-associated molec ular networks: bioinformatics insights from multiple datasets)

    57-58页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Biotechnology - Bioinf ormatics is the subject of a report. According to news reporting out of Chongqin g, People's Republic of China, by NewsRx editors, research stated, "Pre-eclampsi a is a pregnancy-related disorder characterized by hypertension and proteinuria, severely affecting the health and quality of life of patients. However, the mol ecular mechanism of macrophages in pre-eclampsia is not well understood." Our news journalists obtained a quote from the research from the First Affiliate d Hospital of Chongqing Medical University, "In this study, the key biomarkers d uring the development of pre-eclampsia were identified using bioinformatics anal ysis. The GSE75010 and GSE74341 datasets from the GEO database were obtained and merged for differential analysis. A weighted gene co-expression network analysi s (WGCNA) was constructed based on macrophage content, and machine learning meth ods were employed to identify key genes. Immunoinfiltration analysis completed b y the CIBERSORT method, R package 'ClusterProfiler' to explore functional enrich ment of these intersection genes, and potential drug predictions were conducted using the CMap database. Lastly, independent analysis of protein levels, localiz ation, and quantitative analysis was performed on placental tissues collected fr om both preeclampsia patients and healthy control groups. We identified 70 diffe rentially expressed NETs genes and found 367 macrophagerelated genes through WG CNA analysis. Machine learning identified three key genes: FNBP1L, NMUR1, and PP 14571. These three key genes were significantly associated with immune cell cont ent and enriched in multiple signaling pathways. Specifically, these genes were upregulated in PE patients. These findings establish the expression patterns of three key genes associated with M2 macrophage infiltration, providing potential targets for understanding the pathogenesis and treatment of PE. Additionally, CM ap results suggested four potential drugs, including Ttnpb, Doxorubicin, Tyrphos tin AG 825, and Tanespimycin, which may have the potential to reverse pre-eclamp sia. Studying the expression levels of three key genes in pre-eclampsia provides valuable insights into the prevention and treatment of this condition. We propo se that these genes play a crucial role in regulating the maternal-fetal immune microenvironment in PE patients, and the pathways associated with these genes of fer potential avenues for exploring the molecular mechanisms underlying preeclam psia and identifying therapeutic targets."
      原文链接:
    • NETL
    • NSTL