AimsTo compare the gait of unicompartmental knee arthroplasty (UKA) and total knee arthroplasty (TKA) patients with healthy controls, using a machine-learning approach.Patients and Methods145 participants (121 healthy controls, 12 patients with cruciate-retaining TKA, and 12 with mobile-bearing medial UKA) were recruited. The TKA and UKA patients were a minimum of 12 months post-operative, and matched for pattern and severity of arthrosis, age, and body mass index. Participants walked on an instrumented treadmill until their maximum walking speed was reached. Temporospatial gait parameters, and vertical ground reaction force data, were captured at each speed. Oxford knee scores (OKS) were also collected. An ensemble of trees algorithm was used to analyse the data: 27 gait variables were used to train classification trees for each speed, with a binary output prediction of whether these variables were derived from a UKA or TKA patient. Healthy control gait data was then tested by the decision trees at each speed and a final classification (UKA or TKA) reached for each subject in a majority voting manner over all gait cycles and speeds. Top walking speed was also recorded.Results92% of the healthy controls were classified by the decision tree as a UKA, 5% as a TKA, and 3% were unclassified. There was no significant difference in OKS between the UKA and TKA patients (p = 0.077). Top walking speed in TKA patients (1.6 m/s; 1.3 to 2.1) was significantly lower than that of both the UKA group (2.2 m/s; 1.8 to 2.7) and healthy controls (2.2 m/s; 1.5 to 2.7; p < 0.001). ConclusionUKA results in a more physiological gait compared with TKA, and a higher top walking speed. This difference in function was not detected by the OKS.Cite this article: Bone Joint J 2016;98-B(10 Suppl B):16–21.

This survey focuses on two challenging speech processing topics, namely: speaker segmentation and speaker clustering. Speaker segmentation aims at finding speaker change points in an audio stream, whereas speaker clustering aims at grouping speech segments based on speaker characteristics. Model-based, metric-based, and hybrid speaker segmentation algorithms are reviewed. Concerning speaker clustering, deterministic and probabilistic algorithms are examined. A comparative assessment of the reviewed algorithms is undertaken, the algorithm advantages and disadvantages are indicated, insight to the algorithms is offered, and deductions as well as recommendations are given. Rich transcription and movie analysis are candidate applications that benefit from combined speaker segmentation and clustering.

Highlights• An algorithmic method that detects knee osteoarthritis.• Machine learning, specifically random forests, is applied on ground reaction forces.• Discriminating parameters of knee osteoarthritis are automatically detected.• Parameters have a clinical interpretation and are in line with medical literature.• The proposed approach is subject-independent.

An algorithm for automatic speaker segmentation based on the Bayesian Information Criterion (BIC) is presented. BIC tests are not performed for every window shift (e.g. every milliseconds), as previously, but when a speaker change is most probable to occur. This is done by estimating the next probable change point thanks to a model of utterance durations. It is found that the inverse Gaussian fits best the distribution of utterance durations. As a result, less BIC tests are needed, making the proposed system less computationally demanding in time and memory, and considerably more efficient with respect to missed speaker change points. A feature selection algorithm based on branch and bound search strategy is applied in order to identify the most efficient features for speaker segmentation. Furthermore, a new theoretical formulation of BIC is derived by applying centering and simultaneous diagonalization. This formulation is considerably more computationally efficient than the standard BIC, when the covariance matrices are estimated by other estimators than the usual maximum likelihood ones. Two commonly used pairs of figures of merit are employed and their relationship is established. Computational efficiency is achieved through the speaker utterance modeling, whereas robustness is achieved by feature selection and application of BIC tests at appropriately selected time instants. Experimental results indicate that the proposed modifications yield a superior performance compared to existing approaches.