Advanced Materials Research Vols. 403-408

Abstract: It is of great significance that objective evaluation of speech quality in language self-learning. Aimed at the objective evaluation process of speech quality the thesis presented to build HMM model based speech feature MFCC of human auditory model, and to use different indicators to achieve the evaluation of phoneme, word and sentence. Effective solution was proposed for such issues as the initial model to select more sequence of observations to train HMM as well as data underflow encountered during practical application of HMM algorithm. According to some speech experts, the evaluation results achieved by speech quality evaluation system were objective.

Abstract: A model of pollutant diffusion in the liquid is modified and validated based on experiments using image processing technology in the paper. By using the knowledge of field theory, the variation rule of diffusion and gray parameters was analyzed after the instantaneous images which had been pretreated. The pollutant diffusion model was validated in the research. The experimental results have shown that it is effective to investigate liquid pollutant concentration diffusion using digital image processing technology.

Abstract: In this paper, we designed a prototype of powered above-knee prosthesis. Compared with other prototypes available in the literature, our designed prosthetic leg employs a redundant actuator concept to overcome the challenge faced by the single-motor transmission systems. The redundant actuator also enables the prosthesis to be partially functional when the prosthesis loses power. Finally, in order to provide optimal control parameters for designed above-knee prosthesis to perform a smooth level-ground walking task, an inverse dynamic model based on Kane’s method is constructed.

Abstract: The aim of this paper is to design a Sensing socksfor Diabetic patients and alert the patients in case of anyphysical parameter extremity and to detect tissue damagebecause of heat, pressure and humidity. This will alert thepatient if anyone the parameter exceeds the permissible time /quantity limit. Data acquisition system using LabVIEW isdesigned to create a database for storing the information from the sensor. Diabetic neuropathy is a lack of feeling accompanied by tingling, burning, pain, or numbness in the legs and feet due to nerve damage. Loss of sensation in the lower limb and feet contributes to the risk of developing foot ulcers. When the nerve disease causes a complete loss of sensation in the feet, patients may not be aware of injuries to the feet, and fail to properly protect them. To avoid foot ulcers, sores and to alert the patients from skin injuries We have designed a socks which can be worn by the patient and it helps in monitoring the patient continuously and provides alert to the patient if there is any risks in increase heat, pressure and humidity, so that tissue damage can be avoided.

Abstract: The algorithm generated is based on designing matrices in such a way that score matrix contains the maximum scores for alignment of the DNA sequences and the aligned sequences are generated by trace matrix generated based on the score matrix. The score matrix is initialized by using Smith – Waterman algorithm and the scores used for filling up the score matrix are calculated using Needleman –Wunsch algorithm.

Abstract: Preprocessing is an operation with images at the lowest level of abstraction. Many preprocessing steps are used in the generation of images for a better quality. Skeletons are important shape descriptors in object representation and recognition. The present paper investigated how different skeletons (thinning and skeletonization) are going to be affected on various preprocessing methods. The experimental results on different images indicate good comparison of variation of skeletons on different methods of preprocessed steps.

Abstract: CIS (Continuous Interleaved Sampling) strategy in which electrodes stimulus is determined based on extracted information from amplitude of different bands of input signal, is a basis in processing methods in cochlear implant systems. In this paper besides implementing this strategy, methods for improving sample reduction and computational efficiency are also presented. In this case adaptive method according to processing parameters and an input signal has been suggested that due to the use of fewer samples to synthesize the signal is better than the other methods and is significantly efficient.

Abstract: MicroRNAs (miRNA) are single-stranded RNA molecules of about 21–23 nucleotides in length. MicroRNAs(miRNAs) constitute a large family of non coding RNAs that function to regulate gene expression. Till today wet lab experiments have been used to classify the miRNA of plants and animals. The wet lab techniques are highly expensive, labour intensive and time consuming. Thus there arises a need for computational approach for classification of plants and animal miRNA. These computational approaches are fast and economical as compared to wet lab techniques. In this paper an attempt has been made for the classification of Drosophila and its subclasses.The overall prediction accuracy of SVM modules based on mono nucleotide composition was 83.12% respectively. The accuracy of all the modules was evaluated using a 10-fold cross-validation technique.

Abstract: Robots are becoming more interactive and assisting to human beings day by day. They are serving humanity in the fields of industry, defense and medicine. Exoskeletons are also devices that reside in category of wearable robotics. An exoskeleton is an external structural mechanism with joints and links corresponding to those of the human body. With applications in rehabilitation medicine and virtual reality simulation, exoskeletons offer benefits for both disabled and healthy populations. Exoskeletons can be used as a capability magnifier or assisting device. This paper presents a proposed design for smart active exoskeleton for lower limbs. This proposed exoskeleton design not only assist a person but also tries to improve its GAIT. The twin wearable legs are powered by Actuators, all controlled by a microprocessor. The simulation results of the control mechanism shows its smart capabilities. In addition, the processor based control produces a more natural muscle like activity and as such can be considered a soft and bio-mimetic actuation system. This capacity to “replicate” the function of natural muscle and inherent safety is extremely important when working in close proximity to humans. The integration of the components sections and testing of the performance will also be considered to show how the structure and actuators can be combined to produce the various systems needed for a highly flexible/low weight clinically viable rehabilitation exoskeleton.

Abstract: The existing prosthetic upper limb design and control is divided into two broad categories. One is the myoelectric prosthesis where electromechanical active joints actuate the arm segments and is directly activated by acquiring Electromyogram (EMG) signals from the amputee which is sensed by myoelectric electrodes. Acquiring of the EMG signals is a tedious process as it involves adequate amplification and proper filtering. Also isolation of noise from EMG signals poses difficulty. The other category falls under intelligent prosthetic hand where neural networks (NN) are involved. It requires adequate training for NN operation that leads to the complexity in implementing electronic circuits. The major disadvantage of the above mentioned technologies is lack of proprioceptive feedback from the amputee. The drawbacks of the existing technologies motivates us to design a prototype with proprioceptive feedback to control the Above Elbow (AE) prosthesis with a permanent magnet implanted at the distal end of the residual humerus of the amputee. The proprioception remains intact to the residual limb skeletal structure. In this work, the proposed approach involves in processing the magnetic field variation due to residual arm bone movement which is sensed by magnetic field sensors. The embedded controller controls the movements of the prosthetic hand by processing the signals received from the sensors to assist the AE amputee.