Category: 3. Business

  • Valeo and LIDEO form a strategic partnership to support technological transformation in the automotive sector

    Valeo and LIDEO form a strategic partnership to support technological transformation in the automotive sector

    Valeo Group | 9 Oct, 2025
    | 4 min

    A strategic partnership and a unique training program to prepare the 140 automotive expertise firms in the LIDEO network for tomorrow’s innovations.


    Paris, France – October 8, 2025 – Valeo, a leader in mobility technologies and automotive aftermarket services, and LIDEO, a network of independent automotive experts, have signed a strategic partnership. For the first time, an independent expert network has formed a structured partnership with a global equipment manufacturer. The partnership will launch a training program for LIDEO experts via Valeo Tech Academy, sharing cutting-edge technological knowledge. With this agreement, the partners aim to anticipate sector changes and build expertise in new-generation vehicle technologies, such as electric and hybrid vehicles, and driver assistance systems (ADAS).

    Marlene Carrias-Iked, Vice President of Strategic Marketing and Digital Services at Valeo, said: “By partnering with LIDEO, we are reinforcing our commitment to sharing our technical expertise as closely as possible to the field. Valeo Tech Academy aims to make the latest technologies accessible to all players in the automotive aftermarket sector. This initiative lays the foundations for a lasting collaboration between a network of experts and a leading industrial player.”

    Bruno CARANTA, President of the LIDEO network, adds: “Thanks to this partnership with Valeo, LIDEO is continuing its pioneering role and supporting network employees with a unique and pragmatic educational approach that enables them to better understand and diagnose faults, in line with the latest technological innovations.”

    The rollout began in 2025: the first sessions, held in Amiens, Nantes, Nancy, and Paris, France, were an immediate success, with 90% satisfaction among participants. In response to this enthusiasm, new sessions are already planned in Toulon, Salon-de-Provence, and other cities.

    This partnership marks a key step in the professionalization and modernization of the industry. The training modules, which focus on major innovations—electric vehicles, ADAS systems, smart sensors—aim to enable experts in the LIDEO network to better understand and diagnose faults in a constantly evolving technological environment.

    Together, Valeo and LIDEO are affirming their shared ambition: to support the transformation of the automotive sector by focusing on expertise, innovation, and proximity to the field.

    Continue Reading

  • Valeo wins the EQUIP AUTO Paris 2025 International Automotive Innovation Award for its remanufactured dual wet clutch

    Valeo wins the EQUIP AUTO Paris 2025 International Automotive Innovation Award for its remanufactured dual wet clutch

    Valeo Group | 9 Oct, 2025
    | 6 min

    A breakthrough in sustainable transmissions: Valeo remanufactures the complex DQ250 dual wet clutch, which is fitted to more than 5 million vehicles in Europe.


    October 8, 2025 — Paris, France — Valeo has won the EQUIP AUTO Paris 2025 International Automotive Innovation Grand Prix in the “Parts, equipment and components for aftermarket” category for its remanufactured dual wet clutch (DWC) DQ250. This recognition underscores Valeo’s leading position in the field of transmissions, and its commitment to the circular economy for the aftermarket, providing reliable, affordable and OE-quality solutions that extend product lifetimes. The DQ250 will be available across Europe at the end of November 2025.

    Amaury Desombre, Valeo Group Reman-Repair Director & Valeo Service OES Marketing Director, said: “We are very honored to receive this award, which recognizes our deep commitment to remanufacturing. Today, we already remanufacture one million products every year, and our ambition is to double this to two million by 2030—expanding our portfolio beyond traditional parts to include electronics and high-voltage components. Above all, our priority is to make OE-quality products affordable and accessible, proving that circular economy and business performance can go hand in hand by keeping repair a viable option for every vehicle, whatever its age or complexity.”

    A rigorous industrial process

    The dual wet clutch (DWC) DQ250 is Valeo’s latest innovation in transmission parts remanufacturing. As a multi-speed automatic transmission that uses two separate wet clutches, the conception of this DWC is precise and complex. To give this product a second life, Valeo has leveraged its extensive expertise in remanufacturing to implement a rigorous industrial process. After dismantling and cleaning the used parts, each component is carefully analyzed and checked according to strict specifications. Components that do not meet the criteria are repaired or replaced with new ones. The clutch is then assembled and individually tested at the end of the line, to ensure performance equivalent to that of a new part.

    Remanufacturing: Good to better preserve the resources

    Remanufacturing is key for Valeo in the aftermarket, and integrated into the “I Care 4 the Planet” program initiated by the Group to progressively reduce the environmental impact of the automotive sector.

    Replacing a dual wet clutch is often costly—more than €600 excluding labor—on vehicles that are sometimes aged and whose owners face budget constraints. Discarding a part because of a single defective component is neither sustainable nor responsible. By reusing materials, remanufacturing helps limit resource extraction and reduce industrial waste. Today, Valeo’s remanufactured products contain on average up to 80% reused materials.

    Continue Reading

  • Valeo launches production of a remanufactured inverter for the Renault network

    Valeo launches production of a remanufactured inverter for the Renault network

    Valeo Group | 9 Oct, 2025
    | 5 min

    This milestone marks the completion of a project led by The Future is NEUTRAL and its subsidiary THE REMAKERS, to develop a competitive circular offering with low environmental impact.

    This new offering reduces the price by 30% compared to the equivalent new product and consumption of natural resources by at least 45%.


    Continue Reading

  • Aramco completes acquisition of additional stake in Petro Rabigh – Aramco

    1. Aramco completes acquisition of additional stake in Petro Rabigh  Aramco
    2. Aramco closes acquisition of 22.5% of Petro Rabigh  أرقام
    3. Aramco completes acquisition of approx 22.5% share capital of Petro Rabigh from Sumitomo  MarketScreener
    4. Petro Rabigh transfers Sumitomo marketing rights to Aramco  أرقام

    Continue Reading

  • BNP Paribas Cardif and Stellantis partner to develop the used vehicle market

    BNP Paribas Cardif and Stellantis partner to develop the used vehicle market

    Icare, a subsidiary of BNP Paribas Cardif, brings its expertise in warranty extension and automotive maintenance contracts. Stellantis’ Spoticar label, launched in 2019, offers a range of warranties and services for used vehicles, aiming to strengthen customer trust and facilitate transactions. Through this partnership, BNP Paribas and Stellantis are strengthening their collaboration, creating new opportunities for customers and dealers.

    This partnership covers an extended range of insurance products and services for the benefit of dealers and buyers of used vehicles. The agreement includes specific warranties for used cars, such as warranty extensions, maintenance contracts, and dealer guarantees. Dedicated offers for electric vehicles with battery coverage are also planned.

    Dealers and customers will also benefit from a claim reporting and management platform, as well as digital tools such as online training modules, sales support, and a unified partner portal integrating tools to prepare and resell vehicles. Technical and commercial support will also be provided on the ground to help with integration and performance monitoring.

    Continue Reading

  • Decarbonising heavy-duty road transport: State of the enabling conditions – ACEA – European Automobile Manufacturers' Association

    1. Decarbonising heavy-duty road transport: State of the enabling conditions  ACEA – European Automobile Manufacturers’ Association
    2. The EU will need up to 5,300 public megawatt chargers for electric trucks by 2030, new ICCT study shows  International Council on Clean Transportation
    3. ACEA urges urgent review of EU truck CO₂ targets  Commercial Motor
    4. Europe will lose out to China in e-trucks without EU action, warns industry  Financial Times
    5. Logistics Giants, Transport Companies, & Power Sector Call on President von der Leyen to Set Zero Emission Targets for Clean Deliveries  CleanTechnica

    Continue Reading

  • Details matter – how loan pricing affects monetary policy transmission in the euro area

    Details matter – how loan pricing affects monetary policy transmission in the euro area

    by Kārlis Vilerts, Sofia Anyfantaki, Konstantīns Beņkovskis, Sebastian Bredl, Massimo Giovannini, Florian Matthias Horky, Vanessa Kunzmann, Tibor Lalinsky, Athanasios Lampousis, Elizaveta Lukmanova, Filippos Petroulakis and Klāvs Zutis[1]

    Merely classifying loans as fixed-rate or floating-rate[2] fails to fully capture their distinct sensitivity to changes in ECB policy rates. We analysed the maturity of the relevant risk-free rates used to price new loans to see if it affected their short-term interest rate sensitivity – which it did. In countries where new loans were priced using shorter-term risk-free rates, interest rates increased more sharply during the ECB’s monetary tightening, regardless of the loan’s own maturity. This effect was not purely mechanical. Banks partly offset this rise by lowering the premia they charged. By looking beyond headline classifications, we gain a more nuanced understanding of how variations in lending practices drive cross-country differences in monetary policy pass-through.

    Beyond fixed and floating

    Although the euro area has a single currency and a common monetary policy, lending practices differ between euro area countries in several ways that shape the pass-through of monetary policy. In Vilerts et al. (2025), we study a less explored difference: the maturity of the relevant overnight interest rate swap (OIS) at the time of issuance of new loans. We use data from AnaCredit, a comprehensive euro area-wide loan-level database, covering about seven million new loans issued by banks to non-financial corporations (NFCs) in 2022-23.[3] This timeframe encompasses the series of post-pandemic rate hikes.

    Our preliminary analysis reveals that structural factors, such as loan type, firm size or loan maturity, explain only a small portion of the lending rate differences across euro area countries. This suggests that other loan characteristics may play a more significant role.[4] In our study, we break the interest rate on individual loans down into a “relevant risk-free rate” and a “premium” – the residual compensating banks for risk. The relevant risk-free rate is that of the OIS. For fixed-rate loans the maturity of the relevant OIS is that equal to the maturity of the loan, while for floating-rate loans it is the maturity corresponding to the loan’s reference rate at origination.[5] For example, the relevant risk-free rate for a five-year fixed-rate loan is the five-year OIS rate on the issuance date. In contrast, for a five-year floating-rate loan benchmarked against a three-month EURIBOR and adjusted every three months, the relevant risk-free rate would be the three-month OIS rate. The premium is then calculated as the difference between the lending rate and the relevant risk-free rate.

    We find striking cross-country variation (Chart 1) in the maturity of the relevant risk-free rates: in countries such as Latvia and Ireland maturities are very short – around six months on average. Meanwhile in other countries, such as the Netherlands, Malta and France, they often exceed five years on average.

    Chart 1

    Cross-country heterogeneity in the maturity of the relevant risk-free rate

    (years)

    Source: Vilerts et al. (2025).

    Note: The figure shows the weighted average maturity of the relevant risk-free rate for the newly issued loans of NFCs in euro area countries, 2022-23.

    Loan characteristics key for pass-through

    These structural differences mean that monetary policy transmits with varying strength and speed across the euro area, depending on which segment of the risk-free yield curve dominates local lending. Two key questions emerge. First, to what extent can the cross-country variation in the rise of average interest rates on new loans between early 2022 and late 2023 be explained by differences in the evolution of the risk-free rates used to price NFC loans? And, second, how does the maturity of the relevant risk-free rate affect the pass-through of monetary policy rate changes to interest rates on new loans?

    “Before and after” analysis of lending rates

    To address the first question, we employ a time-difference approach to analysing changes in interest rate levels. In particular, we compare interest rates – as well as adjustments in the relevant risk-free rates and shifts in the premium – on loans issued in two periods bracketing the 2022-23 tightening cycle.[6] They are the first quarter of 2022, before the first hike in July 2022, and the fourth quarter of 2023, after the final hike in September 2023. We find that most of the rise in interest rates on new loans during the post-pandemic tightening was driven by increases in the relevant risk-free rate (Chart 2).

    Chart 2

    “Before and after” analysis of lending rates

    (conditional change between the first quarter of 2022 and the last quarter of 2023, percentage points)

    Source: Vilerts et al. (2025).

    Notes: The figure shows conditional changes in lending rates (from the first quarter of 2022 to the fourth quarter of 2023) with 95% confidence bands, breaking them down into the contributions from relevant risk-free rates and the premium.

    Three key observations emerge from the analysis. First, the pass-through of changes in the relevant risk-free rates to changes in lending rates exhibits notable cross-country variation. Some 11 countries experienced an increase in relevant risk-free rates exceeding 4 percentage points, with Latvia and Estonia experiencing the highest increases at 4.37-4.41 percentage points. In contrast, the Netherlands and Malta saw risk-free rates rise by only 2.85 percentage points. Second, the distinction between fixed and floating-rate loans does not always provide a clear explanation for the observed patterns. For the relevant risk-free rates the change was particularly pronounced in countries like Latvia and Ireland, where floating-rate loans with short fixation periods are more prevalent. Similarly, a strong contribution of relevant risk-free rates was observed in Italy, despite its higher reliance on fixed-rate loans which tend to have shorter maturities. Third, a large increase in the relevant risk-free rates does not necessarily result in the largest increase in lending rates. In several countries, the rise in relevant risk-free rates was offset by a decline in the premium, which moderated the overall increase in lending rates.

    Pass-through of monetary policy rates to lending rates

    We then turn our attention to loans issued near ECB Governing Council meetings and use a stacked time-difference regression (following Bredl, 2024)[7] instead of a simple before-and-after comparison. Specifically, we examine how the pass-through of monetary policy rate changes varies across loans priced off different maturities of relevant risk-free rates, now using the full set of actual changes in the policy rate, instrumented by high-frequency surprises (Altavilla et al. 2019). As shown in Chart 3, the pass-through from monetary policy rates to lending rates strengthens as the maturity of the relevant risk-free rates shortens.

    However, applying this approach to the components of interest rates shows that this mechanical pass-through is not the only factor at play, as we see adjustments in premia smoothing differences in pass-through across loan categories. We find that premia increased less for loans linked to shorter maturity risk-free rates, which partially offsets the differences in the aggregate pass-through to lending rates.

    Chart 3

    Stronger pass-through at shorter maturities

    Source: Vilerts et al. (2025).

    Notes: The figure shows the effect of a 1 percentage point increase in the deposit facility rate on lending rates for loans issued within the 6 weeks before or the 7-12 weeks after an ECB Governing Council meeting relative to loans for which the relevant risk-free rates have maturities over five years.

    There are several possible explanations for this pattern. On the lender side, repricing of loans can at times outpace the pass-through to funding costs, improving net interest income and creating scope to lower premia on new loans – especially for those priced off short-term reference rates. On the borrower side, tighter policy can alter the composition of lending and firms may substitute borrowing across maturities and rate types. Overall, the evidence points to systematic smoothing effects: premia adjustments dampen differences in loan rate changes. This suggests that the variation reflects pricing within the bank rather than shifts in the banks doing the lending.

    Loan pricing design matters for monetary policy

    Our results point to several important implications for monetary policy. First, loan pricing design matters for monetary policy transmission. Markets where lending is tied to shorter maturities exhibit stronger and faster transmission. Second, loan premia also adjust independently of exogenous factors. When short-term rates move sharply, banks reprice loan premia over the relevant risk-free rate in ways that smooth differences across loans priced off different maturities. Recognising this interaction helps explain cross-country differences during tightening episodes and anticipate how the composition and pricing of new credit respond to policy.

    References

    Altavilla, C., Brugnolini, L., Gürkaynak, R.S., Motto, R. and Ragusa, G. (2019), “Measuring euro area monetary policy”, Journal of Monetary Economics, Vol. 108, Issue C, pp. 162-179.

    Bredl, S. (2024), Regional loan market structure, bank lending rates and monetary transmission.

    Vilerts, K., Anyfantaki, S., Beņkovskis, K., Bredl, S., Giovannini, M., Horky, F.M., Kunzmann, V., Lalinsky, T., Lampousis, A., Lukmanova, E., Petroulakis, F. and Zutis, K. (2025), “Details Matter: Loan Pricing and Transmission of Monetary Policy in the Euro Area”, Working Papers, No 3078, ECB.

    Continue Reading

  • Differentiating post-stroke patients from healthy individuals via vision-based skeleton-optical fusion | Journal of NeuroEngineering and Rehabilitation

    Differentiating post-stroke patients from healthy individuals via vision-based skeleton-optical fusion | Journal of NeuroEngineering and Rehabilitation

  • Benjamin EJ, Virani SS, Callaway CW, Chamberlain AM, Chang AR, Cheng S, Chiuve SE, Cushman M, Delling FN, Deo R, et al. Heart disease and stroke statistics-2018 update: a report from the american heart association. Circulation. 2018;137(12):67–492.

    Article 

    Google Scholar 

  • Levy DE, Van Uitert RL. Delayed postischemic hypoperfusion: a potentially damaging consequence of stroke. Neurology. 1979;29(9_part_1):1245–1245.

  • Pound P, Gompertz P, Ebrahim S. Illness in the context of older age: the case of stroke. Sociology of health & illness. 1998;20(4):489–506.

    Article 

    Google Scholar 

  • Dobkin BH. Strategies for stroke rehabilitation. The Lancet Neurology. 2004;3(9):528–36.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Topham LK, Khan W, Al-Jumeily D, Hussain A. Human body pose estimation for gait identification: A comprehensive survey of datasets and models. ACM Computing Surveys. 2022;55(6):1–42.

    Article 

    Google Scholar 

  • Cao Z, Simon T, Wei S-E, Sheikh Y. Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017;7291–7299.

  • Fang H-S, Li J, Tang H, Xu C, Zhu H, Xiu Y, Li Y-L, Lu C. Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time. IEEE Transaction Pattern Analysis and Machine Intelligence. 2022;45(6):7157–73.

    Article 

    Google Scholar 

  • Nadeem A, Jalal A, Kim K. Automatic human posture estimation for sport activity recognition with robust body parts detection and entropy markov model. Multimedia Tools and Applications. 2021;80:21465–98.

    Article 

    Google Scholar 

  • Lee K, Lee I, Lee S. Propagating lstm: 3d pose estimation based on joint interdependency. In: Proceedings of the European Conference on Computer Vision (ECCV), 2018;119–135.

  • Topham LK, Khan W, Al-Jumeily D, Waraich A, Hussain AJ. Gait identification using limb joint movement and deep machine learning. IEEE Access. 2022;10:100113–27.

    Article 

    Google Scholar 

  • Lonini L, Moon Y, Embry K, Cotton RJ, McKenzie K, Jenz S, Jayaraman A. Video-based pose estimation for gait analysis in stroke survivors during clinical assessments: a proof-of-concept study. Digital Biomarkers. 2022;6(1):9–18.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Washabaugh EP, Shanmugam TA, Ranganathan R, Krishnan C. Comparing the accuracy of open-source pose estimation methods for measuring gait kinematics. Gait & posture. 2022;97:188–95.

    Article 

    Google Scholar 

  • Shi L, Zhang Y, Cheng J, Lu H. Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019;7912–7921.

  • Lamontagne A, Fung J, McFadyen BJ, Faubert J. Modulation of walking speed by changing optic flow in persons with stroke. Journal of Neuro Engineering and Rehabilitation. 2007;4:1–8.

    Article 

    Google Scholar 

  • De Keersmaecker E, Van Bladel A, Zaccardi S, Lefeber N, Rodriguez-Guerrero C, Kerckhofs E, Jansen B, Swinnen E. Virtual reality-enhanced walking in people post-stroke: effect of optic flow speed and level of immersion on the gait biomechanics. Journal of Neuro Engineering Rehabilitation. 2023;20(1):124.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Ren J, Reyes N, Barczak A, Scogings C, Liu M. An investigation of skeleton-based optical flow-guided features for 3d action recognition using a multi-stream cnn model. In: 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), 2018;199–203.

  • Alfarano A, Maiano L, Papa L, Amerini I. Estimating optical flow: A comprehensive review of the state of the art. Computer Vision and Image Understanding, 2024;104160.

  • Li J, Wang Q. Multi-modal bioelectrical signal fusion analysis based on different acquisition devices and scene settings: Overview, challenges, and novel orientation. Information Fusion. 2022;79:229–47.

    Article 

    Google Scholar 

  • Ranjan R, Ahmedt-Aristizabal D, Armin MA, Kim J. Computer vision for clinical gait analysis: A gait abnormality video dataset. arXiv preprint arXiv:2407.04190 2024.

  • Li H-T, Han S-L, Pan M-C. Lower-limb motion classification for hemiparetic patients through imu and emg signal processing. In: 2016 International Conference on Biomedical Engineering (BME-HUST), 2016;113–118.

  • Celik Y, Stuart S, Woo WL, Sejdic E, Godfrey A. Multi-modal gait: A wearable, algorithm and data fusion approach for clinical and free-living assessment. Information Fusion. 2022;78:57–70.

    Article 

    Google Scholar 

  • He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016;770–778.

  • Shi X, Chen Z, Wang H, Yeung D-Y, Wong W-K, Woo W-c. Convolutional lstm network: A machine learning approach for precipitation nowcasting. Advances in neural information processing systems 2015;28.

  • Cotton RJ. Kinematic tracking of rehabilitation patients with markerless pose estimation fused with wearable inertial sensors. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), 2020;508–514.

  • Bazarevsky V, Grishchenko I, Raveendran K, Zhu T, Zhang F, Grundmann M. Blazepose: On-device real-time body pose tracking. arXiv preprint arXiv:2006.10204 2020.

  • Sun D, Roth S, Black MJ. Secrets of optical flow estimation and their principles. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010;2432–2439.

  • Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision. In: IJCAI’81: 7th International Joint Conference on Artificial Intelligence, 1981;2:674–679.

  • Grimm F, Kraugmann J, Naros G, Gharabaghi A. Clinical validation of kinematic assessments of post-stroke upper limb movements with a multi-joint arm exoskeleton. Journal of Neuro Engineering and Rehabilitation. 2021;18(1):92.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Huang X, Liao O, Jiang S, Li J, Ma X. Kinematic analysis in post-stroke patients with moderate to severe upper limb paresis and non-disabled controls. Clinical Biomechanics. 2024;113:106206.

    Article 

    Google Scholar 

  • He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, 2016;630–645.

  • Rahman K, Shair E, Abdullah A, Lee T, Nazm N. Deep learning classification of gait disorders in neurodegenerative diseases among older adults using resnet-50. International Journal of Advanced Computer Science & Applications 2024;15(11).

  • Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 2014.

  • Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015;1–9.

  • Ikechukwu AV, Murali S, Deepu R, Shivamurthy R. Resnet-50 vs vgg-19 vs training from scratch: A comparative analysis of the segmentation and classification of pneumonia from chest x-ray images. Global Transitions Proceedings. 2021;2(2):375–81.

    Article 

    Google Scholar 

  • Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I. Attention is all you need. Advances in neural information processing systems 2017;30.

  • Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735–80.

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Cicirelli G, Impedovo D, Dentamaro V, Marani R, Pirlo G, D’Orazio TR. Human gait analysis in neurodegenerative diseases: A review. IEEE Journal of Biomedical Health Informatics. 2021;26(1):229–42.

    Article 

    Google Scholar 

  • Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al. An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 2020.

  • Yang S, Zhang J-T, Novak AC, Brouwer B, Li Q. Estimation of spatio-temporal parameters for post-stroke hemiparetic gait using inertial sensors. Gait & posture. 2013;37(3):354–8.

    Article 

    Google Scholar 

  • Scheffer C, Cloete T. Inertial motion capture in conjunction with an artificial neural network can differentiate the gait patterns of hemiparetic stroke patients compared with able-bodied counterparts. Computer Methods Biomechanics and Biomedical Engineering. 2012;15(3):285–94.

    Article 
    CAS 
    PubMed 

    Google Scholar 

  • Repnik E, Puh U, Goljar N, Munih M, Mihelj M. Using inertial measurement units and electromyography to quantify movement during action research arm test execution. Sensors. 2018;18(9):2767.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Li Y, Zhang X, Gong Y, Cheng Y, Gao X, Chen X. Motor function evaluation of hemiplegic upper-extremities using data fusion from wearable inertial and surface emg sensors. Sensors. 2017;17(3):582.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B. Support vector machines. IEEE Intelligent Systems and their applications. 1998;13(4):18–28.

    Article 

    Google Scholar 

  • Eichler N, Hel-Or H, Shimshoni I, Itah D, Gross B, Raz S. 3d motion capture system for assessing patient motion during fugl-meyer stroke rehabilitation testing. IET Comput Vision. 2018;12(7):963–75.

    Article 

    Google Scholar 

  • Zhou C, Feng D, Chen S, Ban N, Pan J. Portable vision-based gait assessment for post-stroke rehabilitation using an attention-based lightweight cnn. Expert Systems with Application. 2024;238:122074.

    Article 

    Google Scholar 

  • Palermo M, Lopes JM, André J, Matias AC, Cerqueira J, Santos CP. A multi-camera and multimodal dataset for posture and gait analysis. Scientific data. 2022;9(1):603.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Mroz S, Baddour N, McGuirk C, Juneau P, Tu A, Cheung K, Lemaire E. Comparing the quality of human pose estimation with blazepose or openpose. In: 2021 4th International Conference on Bio-Engineering for Smart Technologies (BioSMART), 2021;1–4.

  • Jun K, Lee K, Lee S, Lee H, Kim MS. Hybrid deep neural network framework combining skeleton and gait features for pathological gait recognition. Bioengineering. 2023;10(10):1133.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Khokhlova M, Migniot C, Morozov A, Sushkova O, Dipanda A. Normal and pathological gait classification lstm model. Artifical Intelligence in Medicine . 2019;94:54–66.

    Article 
    PubMed 

    Google Scholar 

  • Benson LC, Räisänen AM, Clermont CA, Ferber R. Is this the real life, or is this just laboratory? a scoping review of imu-based running gait analysis. Sensors. 2022;22(5):1722.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Kim H, Kim Y-H, Kim S-J, Choi M-T. Pathological gait clustering in post-stroke patients using motion capture data. Gait & Posture. 2022;94:210–6.

    Article 

    Google Scholar 

  • Mengüç Y, Park Y-L, Pei H, Vogt D, Aubin PM, Winchell E, Fluke L, Stirling L, Wood RJ, Walsh CJ. Wearable soft sensing suit for human gait measurement. The International Journal of Robotics Research. 2014;33(14):1748–64.

    Article 

    Google Scholar 

  • Nakano N, Sakura T, Ueda K, Omura L, Kimura A, Iino Y, Fukashiro S, Yoshioka S. Evaluation of 3d markerless motion capture accuracy using openpose with multiple video cameras. Frontiers in sports and active living. 2020;2:50.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Topham LK, Khan W, Al-Jumeily D, Waraich A, Hussain AJ. A diverse and multi-modal gait dataset of indoor and outdoor walks acquired using multiple cameras and sensors. Scientific data. 2023;10(1):320.

    Article 
    PubMed 
    PubMed Central 

    Google Scholar 

  • Ranjan R, Ahmedt-Aristizabal D, Armin MA, Kim J. Computer vision for clinical gait analysis: A gait abnormality video dataset. IEEE Access. 2025;13:45321–39.

    Article 

    Google Scholar 

  • Nguyen T-N, Meunier J. Walking gait dataset: point clouds, skeletons and silhouettes. DIRO, University of Montreal, Tech. Rep 2018;1379.

  • Burnfield M. Gait analysis: normal and pathological function. Journal of Sports Science and Medicine. 2010;9(2):353.

    Google Scholar 

  • Hanlon M, Anderson R. Real-time gait event detection using wearable sensors. Gait & posture. 2009;30(4):523–7.

    Article 

    Google Scholar 

  • Rowe E, Beauchamp MK, Wilson JA. Age and sex differences in normative gait patterns. Gait & posture. 2021;88:109–15.

    Article 

    Google Scholar 

  • Dosovitskiy A, Fischer P, Ilg E, Hausser P, Hazirbas C, Golkov V, Van Der Smagt P, Cremers D, Brox T. Flownet: Learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, 2015;2758–2766.

  • Sun D, Yang X, Liu M-Y, Kautz J. Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018;8934–8943.

  • Teed Z, Deng J. Raft: Recurrent all-pairs field transforms for optical flow. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part II 16, 2020;402–419. Springer

Continue Reading

  • Visually-impaired woman had to cross Yeovil Pen Mill tracks alone

    Visually-impaired woman had to cross Yeovil Pen Mill tracks alone

    Ruth BradleyPolitics reporter, BBC Somerset, Yeovil

    BBC A woman wearing glasses holding a white cane standing outside a yellow stone train station buildingBBC

    Kath Vickery has started a petition calling for better assistance arrangements at her local station

    A severely visually-impaired woman said she crossed railway tracks alone to catch a train, after station staff she had booked to help her did not turn up.

    Kath Vickery has now started a petition to improve assistance arrangements after feeling “too anxious” to use her local station – Yeovil Pen Mill in Somerset – following the “really scary experience”.

    Great Western Railway (GWR) apologised and said it was exploring how to “deliver more robust staffing”.

    Figures show 10 out of 62 stations (16%) across the West of England have either no step-free access or issues with at least one platform. The Department for Transport said improving accessibility is “at the centre” of its decision-making.

    Ms Vickery uses a cane and needs assistance when navigating railway stations. She said the incident happened in August 2024 – although she only started her petition recently after other more minor incidents.

    Yeovil Pen Mill has a stepped footbridge to get to one of its platforms, but staff are able to help people across the tracks using a private level crossing reached by a ramp, if needed.

    “When I got there I was a bit stuck because the ticket office was shut and that’s usually where I find staff,” she said.

    “I didn’t feel comfortable going across the bridge on my own. I walked down to the track crossing in the hope someone would help.

    “I rang the passenger assist call centre, I had a 13-minute conversation with them – they accidentally cut me off transferring me to someone – in the end I managed to attract the attention of someone at the station who told me I could cross, so then I had to run across the track crossing and up the platform to get my train.

    “It was a really scary experience for me and obviously not great for safety, and still really affects me now.”

    The view from a bridge looking down onto a railway station with tracks running either side of two platforms and a covered bridge crossing between them

    Ms Vickery said she had to cross the tracks on her own when her booked assistance was not available

    Passenger assistance can be booked in advance for rail journeys – by phone, online or using an app – and is confirmed with the passenger

    When assistance has been booked, if staff are then unable to fulfil that, the passenger is meant to be informed and GWR said it offers alternatives including a free taxi to the nearest accessible station.

    Staff are meant to be available at Yeovil Pen Mill from 07:20 to 18:25 on weekdays, other than a lunch break, with shorter hours at weekends.

    Ms Vickery used to use the station every week or two to get to medical appointments and ad hoc self-employed work in Bristol and Weymouth.

    She said she has recently had to turn down work in Weymouth as she felt unable to rely on the assistance she would receive at Yeovil Pen Mill.

    Ms Vickery said losing the option of using the railway station long-term would be a “disaster” for her, with the only alternative to Bristol being a three-hour bus journey.

    “It’s not like I’ve got the choice between driving and catching a train – the choices I have are very, very limited and that’s why making sure the station is staffed its scheduled hours is so very important to me,” she said.

    She said she had two cancellations of assistance in the last year in addition to the experience in August 2024 when she was not informed the station would be unstaffed.

    “I think it’s really important that disabled people have equal opportunity to use services and that includes train stations – and in order to use the train station I need there to be staff there,” Ms Vickery said.

    A spokesperson for GWR said: “We recognise that staffing gaps during holiday periods have impacted advertised opening hours at Yeovil Pen Mill, and we apologise for any inconvenience this causes passengers like Kath who rely on staff assistance.

    “While our dedicated team works hard to maintain coverage, we know that we need to increase the staff relief pool to consistently staff all stations during peak leave periods, and we’re exploring opportunities to deliver more robust staffing.”

    A map showing which stations in Bristol, Somerset and Wiltshire have no step-free access to all platforms. They are Freshford, Avoncliff, St Andrews Road, Parsons Street, Lawrence Hill, Nailsea and Backwell, Castle Cary, Bruton, Yeovil Pen Mill, Yeovil Junction

    Source: National Rail

    According to the disabled-led campaign group Transport for All a quarter (25%) of UK train stations have step-free access with 11% of stations staffed at all times.

    Of Somerset’s 10 national rail stations, four (40%) do not have step-free access to all platforms, which can be used independently of station staff, according to information listed on the National Rail website.

    For example, Castle Cary station, on the Paddington mainline, has a stepped footbridge to the westbound platform meaning passengers need staff available to help them across the tracks.

    Across the West of England, 10 out of 62 stations (16%) have either no step-free access, like Avoncliff and Freshford in Wiltshire, or issues with at least one platform.

    Nailsea and Backwell station, which has steps to one platform and a very steep slope to the other, was due to have had ramps installed at both platforms more than 10 years ago but £1m funding was withdrawn in 2014 after a deadline to start the work was missed.

    A railway station with two platforms and steps leading to one of the platforms. A sign reads Yeovil Pen Mill. There are benches and planters on one of the platforms

    There is a stepped footbridge leading to one of the platforms at Yeovil Pen Mill

    A spokesperson for the Department for Transport said it was “taking action to make rail travel easier and more reliable for disabled passengers”.

    They added this included investing more than £10m to upgrade the Passenger Assist scheme, publishing a rail accessibility roadmap and improving information about the facilities available to provide support to passengers at stations.

    Continue Reading

  • Mitsubishi Shipbuilding Holds Christening and Launch Ceremony in Shimonoseki for Large Car Ferry HAMANASU– Second of Two Large Car Ferries Ordered by Shinnihonkai Ferry and Japan Railway Construction, Transport and Technology Agency —

    Mitsubishi Shipbuilding Holds Christening and Launch Ceremony in Shimonoseki for Large Car Ferry HAMANASU– Second of Two Large Car Ferries Ordered by Shinnihonkai Ferry and Japan Railway Construction, Transport and Technology Agency —

    Christening and Launch Ceremony of HAMANASU

    Tokyo, October 9, 2025 – Mitsubishi Shipbuilding Co., Ltd., a part of Mitsubishi Heavy Industries (MHI) Group, held a christening and launch ceremony on October 9 for the second of two large car ferries ordered by Shinnihonkai Ferry Co., Ltd. and Japan Railway Construction, Transport and Technology Agency (JRTT). The ceremony took place at the Enoura Plant of MHI’s Shimonoseki Shipyard & Machinery Works in Yamaguchi Prefecture. The new ferry will serve on a shipping route between the cities of Otaru in Hokkaido and Maizuru in Kyoto Prefecture.

    At the ceremony, Shinnihonkai Ferry President Yasuo Iritani christened the new ferry “HAMANASU,” the Japanese word for a species of native shrub rose. The ceremonial rope cut was performed by Nozomi Kobayashi, ship travel ambassador for the Japan Passengerboat Association. The ship’s handover is scheduled for June 2026 following completion of outfitting work and sea trials. The HAMANASU is the tenth ferry built by Mitsubishi Shipbuilding for Shinnihonkai Ferry.

    The HAMANASU utilizes the latest energy-saving vessel design, including being one of the second ferries in Japan to incorporate a buttock-flow stern hull(Note1) and a ducktail,(Note2) along with a KATANA BOW. Propulsion resistance is suppressed by an energy-saving roll-damping system combining an anti-rolling tank(Note3) and fin stabilizers,(Note4) providing energy savings of 5% compared to conventional ships.

    The christening and launch ceremony for the first ship ordered by Shinnihonkai Ferry and JRTT, named KEYAKI, was held in April 2025, with handover scheduled for November.

    Japan is currently undergoing a modal shift to sea transport to mitigate environmental impacts by reducing CO2 emissions, and to compensate for truck driver shortages arising from workstyle reforms. This shift has brought utilization of ferry transport into sharp relief. Going forward, Mitsubishi Shipbuilding will continue to contribute to the active use of sea transport and environmental protection, resolving diverse issues together with its business partners through construction of ferries that provide stable sea transport together with outstanding energy and environmental performance.

    • 1A hull design that reduces water resistance by optimizing the shape of the stern.
    • 2A hull form with the stern protruding like a duck’s tail.
    • 3An anti-rolling tank contains water that shifts laterally within a ship’s beam. When a vessel rolls, the tank water moves in the direction opposite to the rolling, countering the rolling effect.
    • 4Fin stabilizers are another device that reduces ship rolling. Attached to both sides of the hull, these movable fins generate lifting power in the water in the direction opposite to the rolling.

    ■ Main Specifications of the HAMANASU

    Ship type Passenger-carrying car ferry
    LOA Approx. 199m
    Beam Approx. 25.5m
    Gross tonnage Approx. 14,300t
    Service speed Approx. 28.3 knots
    Passenger capacity 286
    Loading capacity Approx. 150 trucks and 30 passenger cars

    Continue Reading