Bioelectrics
Zohre Mojiri; Amir Akhavan; Ehsan Rouhani
Volume 16, Issue 3 , December 2022, , Pages 257-269
Abstract
Deep brain stimulation (DBS) is a technique to stimulate the deep areas of the brain which can be used in both invasive and non-invasive methods. In invasive DBS, the electrodes are surgically implanted inside the brain to achieve the desired depth of the stimulation. The invasive DBS approach suffers ...
Read More
Deep brain stimulation (DBS) is a technique to stimulate the deep areas of the brain which can be used in both invasive and non-invasive methods. In invasive DBS, the electrodes are surgically implanted inside the brain to achieve the desired depth of the stimulation. The invasive DBS approach suffers from intracranial bleeding. One solution is using non-invasive DBS by temporal interference (TI) method. In TI stimulation, the constructive interference of two electric fields generated by two high-frequency sinusoidal currents increases the stimulation intensity at a certain depth. The objective of this paper is to investigate quantitatively as well as qualitative analysis of TI stimulation effect on the activation of primary motor cortex area of the rat. To this end, a 4-channel stimulator is used. The experiment is conducted on one anesthetized rat. The transcranial stimulation is applied by the electrode fixed on the skull with screw and the results are evaluated qualitatively and the quantitatively in the domains of time, frequency, and space. To quantify the results, a three-axis accelerometer sensor is used to record the movement acceleration of the right hand. The results showed that, the variation of the stimulation parameters (stimulation current intensity, frequency difference and ratio of currents of the two electrodes) changed the stimulation area inside the two hemispheres of the brain and movement range of the right hand. Moreover, the relationship between the difference frequency of the stimulation of the two pairs of electrodes and the range of motion was analyzed using a three-order polynomial regression model.
Bioelectrics
Amin Mohammadian; Akram Ghorbali; Maryam Asadolah Tooyserkani; Razieh kaveh; kian Shahi
Volume 16, Issue 1 , May 2022, , Pages 33-50
Abstract
The interview analyst’s need to detect deception is a topic that has provided the conditions for providing solutions to empower them. So that, the experts and interview analysts can be assisted by automatically monitoring the subject's unsalient, unknown, or counterintuitive activities during the ...
Read More
The interview analyst’s need to detect deception is a topic that has provided the conditions for providing solutions to empower them. So that, the experts and interview analysts can be assisted by automatically monitoring the subject's unsalient, unknown, or counterintuitive activities during the interview. The aim of this study was to combine quantitative and qualitative information to help improve the detection of deception. For this purpose, in addition to using the capacity of verbal and non-verbal analysis methods, thermal imaging technology and new methods of spatiotemporal analysis of the thermal patterns have been used to detect concealed information in individuals. Then, based on the study design, the database consisting of 48 truth-tellers and liars who participated in a mock scenario was collected. Then, two qualitative methods of verbal and non-verbal information analysis, including standard criteria-based content analysis (CBCA) and behavioral analysis interview (BAI) scoring, were used to identify liars and truth-tellers. In order to complete the obtained results based on these two methods, using effective connectivity analysis method, physiological network analysis of communication between different areas of the face was performed in thermal images of individuals. As a result of combining quantitative and qualitative information, the final accuracy of individuals' diagnosis increased from an average of 73.61% to 79.17%. The investigation of the agreement analysis between methods by kappa coefficient and analysis of confusion matrix information indicated the existence of complementary information in various quantitative and qualitative methods to identify concealed information in individuals.
Bioelectrics
Elham Dehghanpur Deharab; Peyvand Ghaderyan
Volume 15, Issue 4 , March 2022, , Pages 279-287
Abstract
Parkinson's disease (PD) is one of the most common types of dementia associated with motor impairments and affected performance of motor skills such as writing. Brain imaging techniques are the common methods used to diagnose PD, which are expensive or invasive, and their accuracy depends on the experience ...
Read More
Parkinson's disease (PD) is one of the most common types of dementia associated with motor impairments and affected performance of motor skills such as writing. Brain imaging techniques are the common methods used to diagnose PD, which are expensive or invasive, and their accuracy depends on the experience and the skill of the physician. Therefore, the development of an automated, low cost, and reliable diagnostic system is desirable for researchers. In this study, a handwriting signal including cognitive and motor-perceptual components has been used as a non-invasive, cost effective and reliable characteristic in identifying PD-related cognitive and motor dysfunctions. For this purpose, the matching pursuit algorithm with high time-frequency resolution has been employed to decompose X-Y coordinates. It provides a sparse representation of the handwriting signals and quantifies the basic information about the local changes in the handwriting signals. The proposed method is evaluated on a database with 31 healthy samples and 29 Parkinson's samples using the support vector machine classifier and obtained results yields an average accuracy rate of 90%, sensitivity rate of 91.59% and specificity rate of 90%. Comparing different writing tasks has also demonstrated superior performance of writing an entire sentence for PD detection.
Bioelectrics
Farzaneh Manzari; Peyvand Ghaderyan
Volume 15, Issue 4 , March 2022, , Pages 313-328
Abstract
Obsessive-Compulsive Disorder (OCD) is the fourth most common mental disorder and the tenth cause of disability worldwide. This disorder can lead to cognitive impariments in attention, memory, thinking, auditory processing of words and visual cognition. Previous studies have demonstrated that OCD is ...
Read More
Obsessive-Compulsive Disorder (OCD) is the fourth most common mental disorder and the tenth cause of disability worldwide. This disorder can lead to cognitive impariments in attention, memory, thinking, auditory processing of words and visual cognition. Previous studies have demonstrated that OCD is associated with changes in connectivity between different lobes of the brain. Hence, the quantification of symmetry and connectivity between different brain regions has attracted great attention. This study has provided a new efficient approach based on analytic representation of EEG signals and statistical features to quantify the difference of intrinsic components of brain activity between brain lobes. For this purpose, phase spectra and amplitude envelopes of the analytic EEG signals have been extracted and analyzed. Furthermore, Non-Negative Least Square sparse classification method has been used for discriminating between healthy control group and OCD patients. The detection capability of the proposed method has been studied in 19 healthy subjects and 11 patients, performing simple flanker tasks. The obtained results have demonstrated the effectiveness of the combined amplitude and phase information in OCD detection with high average accuracy rate of 93.78 %. In comparison between different regions, the inter-hemispheric features and those extracted from the frontal lobe and frontal-parietal network have shown more efficiency in diagnosing the OCD. This study has also highlighted more importance of amplitude information in the OCD detection.
Bioelectrics
Sobhan Sheykhivand; Zohreh Mousavi; Tohid Yousefi Rezaii
Volume 14, Issue 3 , October 2020, , Pages 179-193
Abstract
In recent years, driver fatigue has become one of the major causes of road accidents, and many studies have been conducted to analyze driver fatigue. EEG signals are considered the most reliable method for measuring driver fatigue because of the non-invasive nature. Manual interpretation of EEG signals ...
Read More
In recent years, driver fatigue has become one of the major causes of road accidents, and many studies have been conducted to analyze driver fatigue. EEG signals are considered the most reliable method for measuring driver fatigue because of the non-invasive nature. Manual interpretation of EEG signals for detection of driver fatigue is impossible, so an automatic detection of driver fatigue from EEG signals should be provided. One of the problems regarding the automatic detection of driver fatigue is extraction and selection of discriminative features witch generally leads to computational complexity. This paper prepares a new approach to automatic classifying 2 stages of driver fatigue from 6 active regions of EEG signals. In the proposed method, directly apply the raw EEG signal to convolutional neural network-long short time memory (CNN-LSTM) network, without involving feature extraction/selection. This is a challenging process in previous literature. The proposed network architecture includes 7 convolutional layers with 3 LSTM layers followed by 2 fully connected layers. The LSTM network in a fusion with the CNN network has been used to increase stability and reduce oscillation. The simulation results of the proposed method for classifying 2 stages of driver fatigue for 6 active regions A, B, C, D, E (based single-channel) and F show the accuracy of 99.23%, 97.55%, 98.00%, 97.26%, 98.78%, 93.77% and Cohen’s Kappa coefficient of 0.98, 0.96, 0.97, 0.96, 0.98 and 0.92 respectively. Furthermore, comparing the obtained results with the previous methods reveals the performance improvement of the proposed driver fatigue detection in terms of accuracy. According to the high accuracy of the proposed single-channel (region E) method, it can be used for the design of automatic detection of driver fatigue systems with high speed and accuracy.
Bioelectrics
Sobhan Sheykhivand; Zohreh Mousavi; Tohid Yousefi Rezaii
Volume 14, Issue 3 , October 2020, , Pages 209-220
Abstract
Using a smart method to automatically detect different stages of epilepsy in medical applications, to reduce the workload of physicians in analyzing epilepsy data by visual inspection is one of the major challenges in recent years. One of the problems of automatic identification of different stages of ...
Read More
Using a smart method to automatically detect different stages of epilepsy in medical applications, to reduce the workload of physicians in analyzing epilepsy data by visual inspection is one of the major challenges in recent years. One of the problems of automatic identification of different stages of epilepsy is extraction of desirable features which can make the most distinction between different stages of epilepsy. The process of finding the proper features is generally time consuming. This study presents a new approach for the automatic identification of different epileptic stages. In this paper, a sparse represantion-based classification (SRC) with proposed dictionary learning is used to automatically identify the different stages of epilepsy using the EEG signal. The proposed method achieves 100% accuracy, sensitivity and specificity in 8 out of 9 scenarios. Also the proposed algorithm is resistant to Gaussian noise up to 0 decibels. The results show that using the proposed algorithm to identify different epileptic stages has a higher success rate than other similar methods.
Bioelectrics
Elias Ebrahimzadeh; Hamid Soltanian-Zadeh; Babak Nadjar Araabi; Seyed Sohrab Hashemi Fesharaki; Jafar Mehvari Habibabadi
Volume 13, Issue 2 , August 2019, , Pages 135-145
Abstract
Since electroencephalography (EEG) signal contains temporal information and fMRI carries spatial information, we can reasonably expect that a combination of the two contributes greatly to precise localization of epileptic focuses. With that in mind, we have first extracted spike patterns ...
Read More
Since electroencephalography (EEG) signal contains temporal information and fMRI carries spatial information, we can reasonably expect that a combination of the two contributes greatly to precise localization of epileptic focuses. With that in mind, we have first extracted spike patterns from outside of scanner EEG, through detecting and averaging the interictal epileptiform discharges (IED). Then, having implemented the correlation between the identified pattern and inside-scanner EEG, an automated system was developed to extract the temporal information when an epileptic seizure is triggered. We proceeded to convolve the obtained regressor with the hemodynamic response function (HRF) using the general linear model (GLM) for the purpose of localizing the epileptic focus. This study was conducted on 6 medication-resistant patients with epilepsy whose data was recorded in the National Brain Mapping Lab (NBML). The results of the proposed method are in line with the information provided in EEG for each of the 6 patients, and for the 4 patients who were candidates for brain surgery, they provided further information. The results suggest a significant improvement in localization accuracy and precision compared to existing methods in the literature.
Bioelectrics
Farzaneh Keyvanfard; Abbas Nasiraei Moghaddam
Volume 13, Issue 2 , August 2019, , Pages 147-158
Abstract
Brain as the most complex organ in the human body has been investigated from various aspects. The greatest origin of this complexity is due to the fact that, despite the fixed architecture of brain structure (physical connections), the functional connectivity is in a constantly changing state, resulting ...
Read More
Brain as the most complex organ in the human body has been investigated from various aspects. The greatest origin of this complexity is due to the fact that, despite the fixed architecture of brain structure (physical connections), the functional connectivity is in a constantly changing state, resulting to different behaviors. In many mental diseases, both brain structural and functional connectivities and their relationship are changed and cause different symptoms. Investigation of brain connectivity variations in the disease may help to better understanding of the relationship between brain structure and function. One of the most severe and debilitating brain disorders is Schizophrenia in which both brain structure and function are involved. Among all available methods, multimodal analysis of data has been recently gained great interest to provide the capability of extracting association between separate neuroimaging data. However, due to their voxel based viewpoint, relationship between brain connectivities cannot be inferred. In this study, the joint independent component analysis (jICA) has been proposed to investigate the relationship between brain functional and structural connectivity. We applied the suggested approach to combine functional and structural connectivity, in order to assess abnormalities underlying schizophrenic patients relative to healthy people. The findings suggest that the correspondence between brain function and structure is not necessarily one-to-one. The results also indicated that variations in several structural fibers, such as superior longitudinal fasciculus and inferior longitudinal fasciculus, are associated with functional changes in the temporal and frontal lobes. Besides, analyzing the nodal strength and shortest path length in the obtained subnetworks demonstrates that the functional subnetworks efficiency in parallel information transfer in schizophrenic patients is reduced. Overall, the outcomes point out the capability of the proposed method to better understanding of brain functional and structural connectivity association and its variations in brain disorders.
Bioelectrics
Zahra Sadat Hosseini; Seyed Mohammad Reza Hashemi Golpayegani
Volume 13, Issue 1 , April 2019, , Pages 69-84
Abstract
The esophageal carcinoma is the eight most predominate malignancy in the world and the sixth deadliest cancer. 80% of esophageal cancers occur in squamous cells. In Iran, this type of cancer is more prevalent in Golestan province. Before the onset of this type of cancer, histological precursor lesions ...
Read More
The esophageal carcinoma is the eight most predominate malignancy in the world and the sixth deadliest cancer. 80% of esophageal cancers occur in squamous cells. In Iran, this type of cancer is more prevalent in Golestan province. Before the onset of this type of cancer, histological precursor lesions emerge in the epithelial tissue of esophageal mucosa that their progression and penetration into the underlying layers of epithelium lead to cancer. This disease starts from a pre-clinical phase in most patients. In most cases, the disease progresses to the same clinical stage in the absence of appropriate therapeutic interventions. In the literature of this cancer, there is no model for the progression of these lesions (dysplasia) at the mesoscopic level. In this study, by using microscopic images of normal and low-grade dysplasia biopsy samples, we proposed a dynamical model based on the globally coupled logistic maps. The model was designed and its parameters were set based on the assumptions of the esophageal epithelium structure, functionality and using the information about the fractal geometry of this tissue. The model performance was evaluated by computation the pattern of Lyapunov exponent variations across the epithelium thickness. In this model, the decreasing trend of this index for normal tissue had a reasonable accuracy and sensitivity to diagnose it from the low-grade dysplasia. Besides, the model results show that it can be a direct relationship between the structural complexity of this biological system and its timeliness uncertainty.
Bioelectrics
Fatemeh Parastesh; Sajad Jafari; Hamed Azarnoush
Volume 13, Issue 1 , April 2019, , Pages 85-93
Abstract
Spiral wave is a particular spatiotemporal pattern, observed in a wide range of complex systems such as neuronal network. Appearance of these waves is related to the network structure as well as the dynamics of its blocks. In this paper, we propose a new modified Hindmarsh-Rose neuron model. The proposed ...
Read More
Spiral wave is a particular spatiotemporal pattern, observed in a wide range of complex systems such as neuronal network. Appearance of these waves is related to the network structure as well as the dynamics of its blocks. In this paper, we propose a new modified Hindmarsh-Rose neuron model. The proposed model uses a hyperbolic memductance function as the monotonically differentiable magnetic flux. An external electromagnetic excitation is also considered in the model. Firstly, we study the dynamics of the proposed neuron model through bifurcation diagram and Lyapunov spectrum, in two cases of no excitation and periodic excitation. The bifurcation diagram shows the property of antimonotonicity, which has not been observed in the previous models. Then a square network is constructed and we investigate the spatiotemporal pattrens. By varying the parameters values, spiral waves are observed in specific ranges. The formation of these waves depends on the interaction of all parameters simultaneously.
Bioelectrics
Amir Soleymankhani; Vahid Shalchyan
Volume 12, Issue 2 , September 2018, , Pages 85-96
Abstract
The extracellular recording from the brain's single neurons is known as a popular method in neuroscience and neuro-rehabilitation engineering. These recordings include the activity of all neurons around the electrode, for better use of which, spike sorting methods should be utilized to obtain the activity ...
Read More
The extracellular recording from the brain's single neurons is known as a popular method in neuroscience and neuro-rehabilitation engineering. These recordings include the activity of all neurons around the electrode, for better use of which, spike sorting methods should be utilized to obtain the activity of single neurons. Based on the structural properties of the neuron, such as its dendritic tree, and the distance and direction of it relative to the electrode, it can be claimed that the form of its spike waveform is unique and constant. However, spike sorting under low signal-to-noise ratio (SNR) conditions is always accompanied with challenges. A spike sorting algorithm usually consists of three sections including the spike detection, feature extraction, and classification. In this paper, a method based on optimization of continuous wavelet coefficients is presented which is effective in low SNR values. In the proposed method, after the calculation of the parameterized wavelet coefficients, using the Euclidean distance and the area under the receiver operator characteristic curve, the best parameters were chosen to increase the separation of the features, so that a suitable scale was first found with the Euclidean distance criterion and then the translation parameter was obtained with the second criterion. In this research k-means algorithm was used for the clustering as a simple but efficient method. For evaluation, three simulated data sets were made in 9 different SNRs with a modeled background noise. The obtained results from simulated data showed that the optimization of parameters in continuous wavelet transform using the proposed algorithm could effectively improve the spike sorting performance compared to principal component analysis method.
Bioelectrics
Sobhan Sheykhivand; Tohid Yousefi Rezaii; Zohreh Mousavi; Saeed Meshgini
Volume 11, Issue 4 , February 2018, , Pages 313-325
Abstract
Using an intelligent method to automatically detect sleep patterns in medical applications is one of the most important challenges in recent years to reduce the workload of physicians in analyzing sleep data through visual inspection. In this paper, a single-channel EEG-based algorithm is used to automatically ...
Read More
Using an intelligent method to automatically detect sleep patterns in medical applications is one of the most important challenges in recent years to reduce the workload of physicians in analyzing sleep data through visual inspection. In this paper, a single-channel EEG-based algorithm is used to automatically identify sleep stages using discrete wavelet transform and a hybrid model of simulated annealing and neural network. The signal is decomposed using a discrete wavelet transform into seven levels and statistical properties of each level is calculated. To optimize and reduce the dimensions of feature vectors, hybrid model of simulated annealing algorithm and multi-layered neural network are used. Then ANOVA test is applied to validate the selected features. Finally the classification is performed on the validated features by a perceptron neural network with a hidden layer, which provides an average of 90% classification ccuracy for 2 to 6-class classification of different steps of sleep EEG. Suggesting that the proposed method has higher degree of success in classifying sleep stages compared to the existing methods.
Bioelectrics
Samira Abbasi
Volume 11, Issue 2 , June 2017, , Pages 127-135
Abstract
Neural function depends on the received synapses and the intrinsic properties of the neuron. However, synaptic integration and intrinsic responses can largely depend on the synaptic inputs. In this respect, deep cerebellar nuclei (DCN) neurons which receive inhibitory synapses from Purkinje cells (PCs) ...
Read More
Neural function depends on the received synapses and the intrinsic properties of the neuron. However, synaptic integration and intrinsic responses can largely depend on the synaptic inputs. In this respect, deep cerebellar nuclei (DCN) neurons which receive inhibitory synapses from Purkinje cells (PCs) are of interest. Transmission of behavior from PC to DCN in awake animal and how this information is coded by the deep cerebellar nuclei remain unknown. To investigate this issue, simultaneous recordings from about 50 Purkinje cells converged to each DCN is required, which is impossible in experiments. Therefore, it is required to use modeling techniques. In this study, to explore the effect of Purkinje cells inputs on the power spectral of DCN output, the transmission of behavioral information from the Purkinje cell to the DCN, and behavior coding by the DCN, artificial spike trains (ASTs) of the Purkinje cell were generated, and behavioral modulation (respiration) was added to them, then, ASTs were applied to the DCN model. Power spectral density analysis of the DCN firing in response to the synaptic inputs from Purkinje cells was made and the frequency bands of the DCN output were analyzed. Results showed that the behavioral modulation frequency is reflected in the DCN spectrum and a peak is visible at low-frequencies at the power spectral of the DCN output in response to the behavioral modulation received from Purkinje cells. On the other hand, the previous study has shown that DCN performs frequency coding in response to the behavioral modulation received from Purkinje cells. Results of the present study coud confirm the frequency coding by the DCN. In addition, a high-frequency peak was observed, which coud be due to the tonic firing of the DCN.
Bioelectrics
Seyed Hojat Sabzpoushan; Tina Ghodsi Asnaashari; Fateme Pourhasanzade
Volume 11, Issue 1 , May 2017, , Pages 41-49
Abstract
Cancer is one of the most important causes of mortality in human society; therefore, scientists are always looking for new ways to cope with the disease. Understanding more about the dynamics of cancerous tumors in body can help researches. Therefore, making simple models for tumor growth is important. ...
Read More
Cancer is one of the most important causes of mortality in human society; therefore, scientists are always looking for new ways to cope with the disease. Understanding more about the dynamics of cancerous tumors in body can help researches. Therefore, making simple models for tumor growth is important. Various models have been proposed for the dynamics of cancer cell growth in the body. In some models, the interaction of different types of cells in the cancerous system is mentioned. The cells in the cancerous system include tumor, healthy, and the immune system cells. Generally, the previous models based on these three cell populations couldn’t simulate chaotic behaviors, while the biology of cancer has confirmed chaos in the system. In this paper, a model of three variables is presented and it’s shown that for some values of parameters the system can simulate chaotic behaviors. Model parameters are defined based on biological relationships, each of which plays a particular role in the dynamics of the system. To analyze the role of the parameters, a specific interval is assigned to each parameter, and by plotting the bifurcation diagram, behavioral changes of the system is observed. The results show that some of the parameters have less role in the system's behavior, and by adjusting some of them, free tumor system can be provided. Also, by setting other parameters, the system can lead to a malignant tumor. The parameters of the immune system equation have the least effect on the system’s dynamics. Regarding this finding, it can be said that applying a therapeutic approach that changes the parameters of the immune system will play a minor role in treatment. While applying therapies that change the parameters of healthy cells has the greatest effect on treatment.
Bioelectrics
Marzieh Alirezaei Alavijeh; Ali Maleki
Volume 10, Issue 2 , August 2016, , Pages 187-196
Abstract
Brain-computer interface system based on Steady-state visual evoked potentials is taken into consideration due to advantages such as simplicity of installation and use of the system, enough accurate and acceptable Information transfer rate. In addition to these benefits, short processing time is also ...
Read More
Brain-computer interface system based on Steady-state visual evoked potentials is taken into consideration due to advantages such as simplicity of installation and use of the system, enough accurate and acceptable Information transfer rate. In addition to these benefits, short processing time is also an important criterion to have a system that is applicable in real life and have the ability to use online. In this paper, a method based on standard CCA have been present for recognition of stimulus frequency. The proposed method is performed in two stages, offline and online. In the offline stage, the standard CCA is applied to the SSVEP and sin-cos reference signals. After that, template signals are constructed using weights that generate maximum correlation. In online stage, cross correlation between test signal and each template signals are calculated and the stimulus frequency is recognized. The greater accuracy of frequency recognition and less calculation time at the same time are shown by stimulation result.
Bioelectrics
Hamid Heydari Nejad; Hadi Delavari
Volume 9, Issue 4 , February 2015, , Pages 327-339
Abstract
The patients with Type 1 diabetes need strict blood glucose level control because the body’s production and use of insulin are impaired and hence this increases the blood glucose level. In this paper, a fractional order sliding mode control and an adaptive fractional order sliding mode control ...
Read More
The patients with Type 1 diabetes need strict blood glucose level control because the body’s production and use of insulin are impaired and hence this increases the blood glucose level. In this paper, a fractional order sliding mode control and an adaptive fractional order sliding mode control are proposed to regulate the blood glucose in the presence of the parameter variations and meal disturbance. The Bergman minimal model is used to design the proposed controllers. The proposed controllers are appropriate for making the insulin delivery pumps in closed loop control of diabetes. The proposed controllers attenuate the effect of chattering. The fractional adaptive sliding mode control makes the controller immune to disturbance and uncertainties and the fractional calculus provides robustness performance. Finally the results are compared with some other methods such as backstepping sliding mode control and fractional order sliding mode control methods. Simulation results show that the proposed controllers are able to reject both uncertainties and disturbance with a chattering free control law.
Bioelectrics
Saeid Shakeri
Volume 9, Issue 4 , February 2015, , Pages 399-410
Abstract
Falls are one of the main reasons to injury, especially in the elderly people. These injuries can be reduced by quick and accurate response or reaction, but this is not possible often in elderly people because they usually live alone and after injury caused the falling, cannot call for help. This paper ...
Read More
Falls are one of the main reasons to injury, especially in the elderly people. These injuries can be reduced by quick and accurate response or reaction, but this is not possible often in elderly people because they usually live alone and after injury caused the falling, cannot call for help. This paper presents a fall detection system to do twomajor tasks properly and quickly; firstly, it shoulddetect fall from other daily activities andsecondly, transmit falling person’s necessary information to help. This system is implemented on Android-based smartphone and it used tri-axial accelerometer and microphone to fall detection. Everydayinteraction with the smartphone makes our system more familiarto the user. The accelerometer is used to record variations of acceleration in three directions.Thissystem isimproved with detecting the noise caused the falling, by analyzing environmental sounds. After fall detection, a warning text message that contains information about time and location of the falling will besent to the caregivers. A comprehensive evaluation with 18 volunteers shows that the proposed system has sensitivity of 96% and specificity of 77% for different types of fall in quiet and noisy environments.
