Behavior provides important insights into neuronal processes. For example, analysis of reaching movements can give a reliable indication of the degree of impairment in neurological disorders such as stroke, Parkinson disease, or Huntington disease. The analysis of such movement abnormalities is notoriously difficult and requires a trained evaluator. Here, we show that a deep neural network is able to score behavioral impairments with expert accuracy in rodent models of stroke. The same network was also trained to successfully score movements in a variety of other behavioral tasks. The neural network also uncovered novel movement alterations related to stroke, which had higher predictive power of stroke volume than the movement components defined by human experts. Moreover, when the regression network was trained only on categorical information (control = 0; stroke = 1), it generated predictions with intermediate values between 0 and 1 that matched the human expert scores of stroke severity. The network thus offers a new data-driven approach to automatically derive ratings of motor impairments. Altogether, this network can provide a reliable neurological assessment and can assist the design of behavioral indices to diagnose and monitor neurological disorders.

Surface electromyogram (SEMG) is a common method of measurement of muscle activity. It is noninvasive and is measured with minimal risk to the subject. The analysis of SEMG signal depends on a number of factors, such as amplitude as well as time- and frequency-domain properties. In the present investigation, the study of SEMG signals at different below elbow muscles for four operations of the hand wrist/grip-like opening (op)/closing (cl)/down (d)/up (u) was carried out. Myoelectric signals were extracted by using a single-channel SEMG amplifier consisting of a differential amplifier, noninverting amplifier, and interface module. Matlab softscope was used to acquire the SEMG signal from the hardware. After acquiring the data from six selected locations, interpretations were made for the estimation of parameters of the SEMG using the Matlab-filter algorithm and the fast Fourier transform technique. An interpretation of wrist/grip operations using principal component analysis (PCA) was carried out. PCA was used to identify the best SEMG signal capturing system out of two-channel, three-channel, and four-channel systems. Two acupressure points (on wrist) were also selected for the analysis with other points on the arm. SEMG signal's study at different locations, including pressure points, will be a very helpful tool for the researchers in understanding the behavior of SEMG for the development of the prosthetic hand.

This paper proposes a classification‐based knee angle prediction from myoelectric signals. Surface electromyographic signals were recorded from four muscles in the lower limb while performing the task of standing up from a chair and sitting down on the chair. Knee angle was measured using a goniometer and quantised into five levels/classes. The surface electromyographic signals were segmented using overlapped windowing. Fifteen features per muscle were extracted and fed to the classifier. The classifier predicts the class of the knee angle at a particular instant This study examines the performance of linear discriminant analysis, Naive Bayes, k‐nearest neighbour, and support vector machine classifiers. The support vector machine classifier with a quadratic kernel performed best, with a classification accuracy of 92.2 ± 2.2%, a sensitivity of 90.19 ± 3.06%, a specificity of 98.11 ± 0.63%, and 89.38 ± 3.0% precision.

In the process of improvement of prosthetic devices, there have been efforts to develop satisfactorily working artificial hands but still lots of work is to be done to meet the accuracy and requirements of the human hand movement. The EMG signal has been most promising signal in development of artificial limbs. The present review paper gives the historical developments in three main sections. First part describes the EMG signal properties. Second part deals with the mathematical models developed till now for EMG signal analysis. In the third part different design approaches have been reviewed for artificial hand. First approach discussed here is on the body-powered terminal devices which are controlled by the user's pull on the control cable to open the hand or hook and for the grip strength. Other being myoelectric controls type, an externally-powered system which uses electrical impulses, generated by contraction of the amputees own remaining muscles to operate a motor in a mechanical hand, hook or elbow. This paper presents a brief overview of above mentioned issues with regard to artificial hands.

No abstract

Liver cirrhosis is considered as one of the most common diseases in healthcare. The widely accepted technology for the diagnosis of liver cirrhosis is via ultrasound imaging. This paper presents a technique for detecting the cirrhosis of liver through ultrasound images. The region of interest has been selected from these ultrasound images and endorsed from a radiologist. The identification of liver cirrhosis is finally detected through modified local binary pattern and OTSU methods. Experimental results from the proposed method demonstrated its feasibility and applicability for high performance cirrhotic liver identification.

Cirrhosis is a liver disease that is considered to be among the most common diseases in healthcare. Due to its noninvasive nature, ultrasound (US) imaging is a widely accepted technology for the diagnosis of this disease. This research work proposed a method for discriminating the cirrhotic liver from normal liver through US images. The liver US images were obtained from the radiologist. The radiologist also specified the region of interest (ROI) from these images, and then the proposed method was applied to it. Two parameters were extracted from the US images through differences in intensity of neighboring pixels. Then, these parameters can be used to train a classifier by which cirrhotic region of test patient can be detected. A 2-D array was created by the difference in intensity of the neighboring pixels. From this array, two parameters were calculated. The decision was taken by checking these parameters. The validation of the proposed tool was done on 80 images of cirrhotic and 30 images of normal liver, and classification accuracy of 98.18% was achieved. The result was also verified by the radiologist. The results verified its possibility and applicability for high-performance cirrhotic liver discrimination.

No abstract