Identifikasi Sinyal Elektromiografi Otot Vastus Medialis dan Erector Spinae dalam Transisi Gerakan untuk Kontrol Robot Kaki

To achieve the recognition of multi-attribute of object, I redesign the mnist dataset, change the color, size, location of the number. Meanwhile, I change the label accordingly. The deep neural network I use is the most common convolution neural network. Through test,we can conclude that we can use one neural network to recognize multi-attribute so long as the attribute difference of objects can be represented by functions. The concrete network(generation network) can generate the output which the input rarely contained from the attributes the network learned. Its generalization ability is good because the network is a continuous function. Through one more test, We can conclude that one neural network can do image recognition, speech recognition,and nature language processing and other things so long as the output node and the input node and more parameters add into the network. The network is universal so long as the network can process different inputs. I guess that the phenomenon of synaesthesia is the result of multi-input and multi-output. I guess that connection in mind can realize through the universal network and sending the output into input.

Download Full-text

Muscle activities of lower extremity and erector spinae muscles according to ankle joint position during squat exercise

Journal of Back and Musculoskeletal Rehabilitation ◽

10.3233/bmr-191807 ◽

2021 ◽

pp. 1-6

Author(s):

Ha-Rim Sung ◽

Se-Jung Oh ◽

Jun-Nam Ryu ◽

Yong-Jun Cha

Keyword(s):

Lower Extremity ◽

Ankle Joint ◽

Muscle Activity ◽

Vastus Lateralis ◽

Plantar Flexion ◽

Erector Spinae ◽

Neutral Position ◽

Vastus Medialis ◽

Joint Position ◽

Squat Exercise

OBJECTIVE: The purpose of this study was to investigate the most effective ankle joint position for squat exercise by comparing muscle activities of lower extremity and erector spinae muscles in different ankle joint positions. METHODS: Thirty-seven normal healthy adults in their 20s participated in this study. Muscle activities of dominant vastus medialis oblique, vastus lateralis, biceps femoris, and erect spinae were measured in three ankle joint positions; dorsiflexion, neutral, and plantar flexion. RESULTS: Muscle activities of the vastus medialis oblique, vastus lateralis, and erector spinae muscles were statistically different in the three ankle joint positions during squat exercise (p< 0.05). Vastus medialis oblique muscles showed higher muscle activity in ankle plantar flexion than in the dorsiflexion or neutral positions (plantar flexion > neutral position, +3.3% of maximal voluntary isometric contraction (MVIC); plantar flexion > dorsiflexion, +12.2% of MVIC, respectively). Vastus lateralis muscles showed 7.1% of MVIC greater muscle activity in the neutral position than in dorsiflexion, and erector spinae muscles showed higher muscle activity in dorsiflexion than in plantar flexion or in the neutral position (dorsiflexion > neutral position, +4.3% of MVIC; dorsiflexion > plantar flexion, +7.1% of MVIC, respectively). CONCLUSION: In squat exercises designed to strengthen the vastus medialis oblique, ankle joint plantar flexion is probably the most effective ankle training position, and the dorsiflexion position might be the most effective exercise for strengthening the erector spinae muscle.

Download Full-text

Multi-attribute Recognition,the key to Universal Neural Network

10.36227/techrxiv.12045540.v4 ◽

2021 ◽

Author(s):

Jinxin Wei

Keyword(s):

Neural Network ◽

Continuous Function ◽

Language Processing ◽

Deep Neural Network ◽

Input Node ◽

Output Node ◽

Nature Language Processing ◽

Generation Network ◽

Universal Network ◽

Attribute Recognition

To achieve the recognition of multi-attribute of object, I redesign the mnist dataset, change the color, size, location of the number. Meanwhile, I change the label accordingly. The deep neural network I use is the most common convolution neural network. Through test,we can conclude that we can use one neural network to recognize multi-attribute so long as the attribute difference of objects can be represented by functions. The concrete network(generation network) can generate the output which the input rarely contained from the attributes the network learned. Its generalization ability is good because the network is a continuous function. Through one more test, We can conclude that one neural network can do image recognition, speech recognition,and nature language processing and other things so long as the output node and the input node and more parameters add into the network. The network is universal so long as the network can process different inputs. I guess that the phenomenon of synaesthesia is the result of multi-input and multi-output. I guess that connection in mind can realize through the universal network and sending the output into input.

Download Full-text

Kinematic and Electromyographic Activity Changes during Back Squat with Submaximal and Maximal Loading

Applied Bionics and Biomechanics ◽

10.1155/2017/9084725 ◽

2017 ◽

Vol 2017 ◽

pp. 1-8 ◽

Cited By ~ 14

Author(s):

Hasan U. Yavuz ◽

Deniz Erdag

Keyword(s):

Repeated Measures ◽

Injury Risk ◽

Vastus Lateralis ◽

Knee Extensor ◽

Gluteus Maximus ◽

Movement Pattern ◽

Erector Spinae ◽

Electromyographic Activity ◽

Vastus Medialis ◽

Significant Difference

The aim of this study was to investigate the possible kinematic and muscular activity changes with maximal loading during squat maneuver. Fourteen healthy male individuals, who were experienced at performing squats, participated in this study. Each subject performed squats with 80%, 90%, and 100% of the previously established 1 repetition maximum (1RM). Electromyographic (EMG) activities were measured for the vastus lateralis, vastus medialis, rectus femoris, semitendinosus, biceps femoris, gluteus maximus, and erector spinae by using an 8-channel dual-mode portable EMG and physiological signal data acquisition system (Myomonitor IV, Delsys Inc., Boston, MA, USA). Kinematical data were analyzed by using saSuite 2D kinematical analysis program. Data were analyzed with repeated measures analysis of variance (p<0.05). Overall muscle activities increased with increasing loads, but significant increases were seen only for vastus medialis and gluteus maximus during 90% and 100% of 1RM compared to 80% while there was no significant difference between 90% and 100% for any muscle. The movement pattern in the hip joint changed with an increase in forward lean during maximal loading. Results may suggest that maximal loading during squat may not be necessary for focusing on knee extensor improvement and may increase the lumbar injury risk.

Download Full-text

Multi-attribute Recognition,The key to universal neural network

10.36227/techrxiv.12045540.v1 ◽

2020 ◽

Author(s):

Jinxin Wei

Keyword(s):

Neural Network ◽

Continuous Function ◽

Language Processing ◽

Deep Neural Network ◽

Input Node ◽

Output Node ◽

Nature Language Processing ◽

Generation Network ◽

Universal Network ◽

Attribute Recognition

To achieve the recognition of multi-attribute of object, I redesign the mnist dataset, change the color, size, location of the number. Meanwhile, I change the label accordingly. The deep neural network I use is the most common convolution neural network. Through test,we can conclude that we can use one neural network to recognize multi-attribute so long as the attribute difference of objects can be represented by functions. The concrete network(generation network) can generate the output which the input rarely contained from the attributes the network learned. Its generalization ability is good because the network is a continuous function. Through one more test, We can conclude that one neural network can do image recognition, speech recognition,and nature language processing and other things so long as the output node and the input node and more parameters add into the network. The network is universal so long as the network can process different inputs. I guess that the phenomenon of synaesthesia is the result of multi-input and multi-output. I guess that connection in mind can realize through the universal network and sending the output into input.

Download Full-text

Multi-attribute Recognition,The key to universal neural network

10.36227/techrxiv.12045540 ◽

2020 ◽

Author(s):

Jinxin Wei

Keyword(s):

Neural Network ◽

Continuous Function ◽

Language Processing ◽

Deep Neural Network ◽

Input Node ◽

Output Node ◽

Nature Language Processing ◽

Generation Network ◽

Universal Network ◽

Attribute Recognition

To achieve the recognition of multi-attribute of object, I redesign the mnist dataset, change the color, size, location of the number. Meanwhile, I change the label accordingly. The deep neural network I use is the most common convolution neural network. Through test,we can conclude that we can use one neural network to recognize multi-attribute so long as the attribute difference of objects can be represented by functions. The concrete network(generation network) can generate the output which the input rarely contained from the attributes the network learned. Its generalization ability is good because the network is a continuous function. Through one more test, We can conclude that one neural network can do image recognition, speech recognition,and nature language processing and other things so long as the output node and the input node and more parameters add into the network. The network is universal so long as the network can process different inputs. I guess that the phenomenon of synaesthesia is the result of multi-input and multi-output. I guess that connection in mind can realize through the universal network and sending the output into input.

Download Full-text

Effect of Foot Orthoses on the Timing of Lower Limb Muscles Activity during Walking in Older Adults

Journal of Shahid Sadoughi University of Medical Sciences ◽

10.18502/ssu.v29i5.6771 ◽

2021 ◽

Author(s):

Arefeh Mokhtari MalekAbadi ◽

Amirali Jafarnezhadgero

Keyword(s):

Older Adults ◽

Lower Limb ◽

Vastus Lateralis ◽

Gluteus Medius ◽

Erector Spinae ◽

Medial Gastrocnemius ◽

Female Group ◽

Vastus Medialis ◽

Lower Limb Muscles ◽

Limb Muscles

Introduction: As a person gets older, their gait patterns change and their ability to walk decreases. Orthoses are used to relieve musculoskeletal disorders, skeletal problems, disabilities, etc. Therefore, the aim of this study was to investigate the effect of orthoses on timing of lower limb muscles in the older adults during gait. Methods: The present study was a clinical trial. 14 females (with average age of 60.50±4.40 years) and 14 males (with average age of 63.35±5.55 years) were selected with available sampling, voluntarily participated in this research. Eight electrodes were placed on the selected muscles (tibialis anterior, gastrocnemius medial, vastus medialis, vastus lateralis, biceps femoris, semitendinosus, gluteus medius, erector spinae) to record electrical activity during the gait with and without orthoses. To analyze the data SPSS software (version 16), and a repeated analysis of variance test was used. The significance levels in all tests were considered to be 0.05. Results: The main effects of orthoses and the interaction effects of orthoses and sex for the onset of selected muscles activities did not show any significant differences (P>0.05). The effect of sex for the onset of activities in medial gastrocnemius (P=0.007), vastus medialis (P=0.002), vastus lateralis (P=0.027), semitendinosus (P=0.004), gluteus medius (P=0.030), and erector spinae (P=0.039) muscles was significant, so that the onset of muscle activity in the female group was earlier than in the male group. Conclusion: Orthoses showed no improvement on onset of selected muscles activities, although significant differences were observed between the male and female groups.

Download Full-text

Improvement of Mason Rule for Solving the Complicated Block Diagram

Recent Advances in Electrical & Electronic Engineering (Formerly Recent Patents on Electrical & Electronic Engineering) ◽

10.2174/2352096512666190329233555 ◽

2019 ◽

Vol 12 (6) ◽

pp. 543-553

Author(s):

Wen-M. Jiang ◽

Chung C. Chen ◽

Yen T. Chen ◽

Li J. Cao

Keyword(s):

Control System ◽

Transfer Function ◽

Block Diagram ◽

Circuit Theory ◽

System Matrix ◽

Input Node ◽

Output Node ◽

Matrix Operations ◽

Simple Matrix ◽

Traditional Approaches

Background: This study first efficiently applies the previous result Chen Electrical Unifying Approach (CEUA) utilized in the basic circuit theory to construct the control system matrix equation of the complicated block diagram. Methods: Based on the simple matrix operations proposed in this study, we can easily derive the transfer function without using the traditional Mason rule and the reduced techniques of the block diagram. We have successfully proposed a unifying approach to improve the disadvantages of the Mason rule, in which all loops must be found out and only the transfer function between the input node and the output node is evaluated, and the shortcoming of the reduced techniques for the block diagram is that the calculating process is too complex to be accepted. Results: The salient features of the proposed method are that the transfer function of the complicated block diagram can be easily obtained without using traditional Mason rule and the transfer function of any two nodes is immediately derived within only one calculation. Conclusion: We compared some demonstrated examples with some traditional approaches. Moreover, to demonstrate the practical applicability, the study has investigated one practical example.

Download Full-text

Multi-attribute Recognition,the key to Universal Neural Network

10.36227/techrxiv.12045540.v3 ◽

2021 ◽

Author(s):

Jinxin Wei

Keyword(s):

Neural Network ◽

Continuous Function ◽

Language Processing ◽

Deep Neural Network ◽

Input Node ◽

Output Node ◽

Nature Language Processing ◽

Generation Network ◽

Universal Network ◽

Attribute Recognition

To achieve the recognition of multi-attribute of object, I redesign the mnist dataset, change the color, size, location of the number. Meanwhile, I change the label accordingly. The deep neural network I use is the most common convolution neural network. Through test,we can conclude that we can use one neural network to recognize multi-attribute so long as the attribute difference of objects can be represented by functions. The concrete network(generation network) can generate the output which the input rarely contained from the attributes the network learned. Its generalization ability is good because the network is a continuous function. Through one more test, We can conclude that one neural network can do image recognition, speech recognition,and nature language processing and other things so long as the output node and the input node and more parameters add into the network. The network is universal so long as the network can process different inputs. I guess that the phenomenon of synaesthesia is the result of multi-input and multi-output. I guess that connection in mind can realize through the universal network and sending the output into input.

Download Full-text

The Piezo-resistive MC Sensor is a Fast and Accurate Sensor for the Measurement of Mechanical Muscle Activity

Sensors ◽

10.3390/s19092108 ◽

2019 ◽

Vol 19 (9) ◽

pp. 2108 ◽

Cited By ~ 2

Author(s):

Andrej Meglič ◽

Mojca Uršič ◽

Aleš Škorjanc ◽

Srđan Đorđević ◽

Gregor Belušič

Keyword(s):

Muscle Activity ◽

Skeletal Muscles ◽

Time Course ◽

Vastus Lateralis ◽

Initial Pressure ◽

Rectus Femoris ◽

Signal Amplitude ◽

Biceps Femoris ◽

Erector Spinae ◽

Vastus Medialis

A piezo-resistive muscle contraction (MC) sensor was used to assess the contractile properties of seven human skeletal muscles (vastus medialis, rectus femoris, vastus lateralis, gastrocnemius medialis, biceps femoris, erector spinae) during electrically stimulated isometric contraction. The sensor was affixed to the skin directly above the muscle centre. The length of the adjustable sensor tip (3, 4.5 and 6 mm) determined the depth of the tip in the tissue and thus the initial pressure on the skin, fatty and muscle tissue. The depth of the tip increased the signal amplitude and slightly sped up the time course of the signal by shortening the delay time. The MC sensor readings were compared to tensiomyographic (TMG) measurements. The signals obtained by MC only partially matched the TMG measurements, largely due to the faster response time of the MC sensor.

Download Full-text