Site Classification Research Articles

Seismic behavior analysis of long-span cable-stayed bridge under bi-directional near-fault ground motions

In this paper, the seismic behaviors of a long-span cable-stayed bridge subjected to bi-directional near-fault ground motions are analyzed. The cable-stayed bridge with a main span of 432 m is selected as the research object and appropriately modeled using the OpenSees software. Ten sets of historical near-fault and far-field ground motions associated with the same earthquake event and site class are utilized as input excitations. Nonlinear time-history analyses are conducted to explore three key aspects: the influence of ground motion directionality, the effectiveness of the percentage rule and simplified Square-Root-of-Sum-of-Squares (SRSS) rule, and the main influential factors. The findings reveal that near-fault ground motions induce larger seismic responses compared to far-field ground motions. Moreover, the effects of ground motion directionality are more pronounced in near-fault scenarios than in far-field events. The percentage rule and simplified SRSS rule demonstrate minor significance in predicting the critical seismic responses. The bi-directional peak ground velocity (PGV) of seismic motions in the principal directions of the cable-stayed bridge may emerge as the primary factor influencing the seismic responses, making it a suitable intensity measure for bi-directional seismic fragility assessment.

Signal-based fault location method using time and frequency domain

This research introduces an innovative approach to fault detection in high-voltage alternating current (HVAC) systems by integrating temporal and frequency domain characteristics of signals. It utilizes Traveling Wave (TW) detection and analysis, focusing on a precise window of just 100 microseconds surrounding the TW's arrival at the measurement point. Mathematical Morphology is applied to identify time-domain properties, while the Stationary Wavelet Transform is employed to extract frequency-domain features. Additionally, the integration of a Dynamic Mode Decomposition-based technique enhances TW detection accuracy. The efficacy of this approach is extensively assessed for fault site classification and regression tasks, demonstrating superior performance compared to utilizing time or frequency-domain features separately. The study also examines the method's resilience to noisy measurements and the sufficiency of training data. Comparative analysis against existing signal-based approaches within the IEEE 34 node system underscores its heightened accuracy. Furthermore, the proposed technique showcases minimal fault location estimate errors along the feeder length and competes favorably with slower phasor-based fault detection methods in performance. Regarding the distance of the fault, its proximity to the generator, transmission line, or load significantly influences the parameters of positive, negative, and zero sequence components. When a fault occurs, these parameters undergo distinct changes, serving as indicators of the fault's severity and location. If the fault occurs near the generator or substation, there may be alterations in the voltage and current magnitudes, affecting the sequence components accordingly. In the case of a fault in the transmission line, impedance changes can lead to variations in sequence parameters. Similarly, a fault near the load can cause disturbances in the voltage and current profiles, impacting the sequence components. Analyzing these changes in positive, negative, and zero sequence parameters during a fault provides valuable insights into the fault's severity and location, aiding in effective fault detection and mitigation strategies. Key Words – fault detection, high-voltage alternating current (HVAC) systems, Traveling Wave (TW), temporal domain, frequency domain, Mathematical Morphology, Stationary Wavelet Transform, Dynamic Mode Decomposition, fault site classification,

Estimation Model Peak Ground Acceleration at Bedrock and Surface of The Pasaman Barat Earthquake on February 25, 2022 M_w 6.1

<p>The earthquake occured on february 25, 2022 in West Pasaman, Province West Sumatera with momen magnitude M<sub>w</sub>6.1, produced strong ground motion so that many several buildings were damaged.  The peak ground  acceleration (PGA) represents its level ground acceleration in bedrock and peak surface acceleration (PGA<sub>m</sub>) describes the acceleration value on the surface which depends on the amplification factor and the type of soil classification. Information  peak ground acceleration (PGA) and peak surface acceleration (PGA<sub>m</sub>) values plays an important role in describing the level of damage due to earthquake events. The purpose this study for determine the peak ground  acceleration (PGA) and  peak surface acceleration (PGA<sub>m</sub>) for West Pasaman earthquake Mw6.1 using boore (1997) attenuation model. In this study using parameter data main earthquake and then peak ground acceleration (PGA) value calculated each grid points and  then analysis peak surface acceleration (PGA<sub>m</sub>) value is based on the effect of site class from information Vs30 USGS model on peak ground acceleration (PGA) at bedrock from SNI 1726 : 2012. The result in this study showed peak ground acceleration and  peak surface acceleration value  in due West Pasaman earthquake  ranged  between 0.066 - 0.345 g and 0.223 - 0.627 g. The areas affected by heavy damage occured  in Kajai, Rimbo Panti, Malampah and Tigo Nagari Subdistrict with peak ground acceleration and peak surface acceleration value around 0.115 - 0,345 g and 0.423 - 0.627 g respectively and was dominated with type site class moderate soil (SD) based on Vs30 data form USGS model.</p>

Selection of optimal intensity measures for seismic performance evaluation of underground utility tunnel and internal pipeline system

Seismic intensity measures (IMs), which are closely related to both earthquake hazards and structural responses, play a critical role in the performance-based earthquake engineering (PBEE) framework. This paper aims to investigate and define the most representative IMs for probabilistic seismic demand model (PSDM) for the longitudinal utility tunnel and internal pipeline system. Similar to the requirements by the Chinese Code for seismic design of urban rail transit structures, the utility tunnel in this study is assumed being buried in four typical engineering site classes for the analyses. Soil-tunnel-pipeline interactions are simulated using a double-beam system resting on a nonlinear foundation. Soil-tunnel interaction, tunnel-pipeline interaction and joint connections are modeled as nonlinear springs with different mechanical properties. A series of 17 pairs of outcrop ground-motion records and 27 commonly used IMs are selected in the analyses. Engineering demand parameter (EDP) is defined based on the maximum joint opening and the maximum strain of the utility tunnel and internal pipeline, respectively. The selected IMs for predicting the seismic responses of tunnel-pipeline systems are tested using different criteria, i.e., correction, efficiency, practicality, and proficiency. The final decision-making procedure employs a fuzzy multi-criteria decision method. The numerical results indicate that: (1) The velocity-related IMs are the most representative IMs based on the four criteria for structures buried in four sites of different conditions; (2) The optimal seismic IMs vary with different criteria, site classes and structure types. According to the fuzzy multi-criteria decision approach, optimal IMs for the tunnel-pipeline system are PGV, PGV, EPV and HI for site classes I – IV, respectively. The proposed optimal IMs can be utilized to construct seismic fragility curves of utility tunnel, internal pipeline and tunnel-pipeline systems in four different site classes.

Calibration of horizontal seismic design spectra of offshore earthquake ground motions by applying improved differential evolution method

Design Response Spectrum (DRS) serves as a crucial cornerstone for seismic design, encapsulating the characteristic parameters of the design spectrum. To investigate the offshore design spectrum required for seismic design of offshore structures, improved differential evolution (DE) methods are first used to determine the characteristic parameters of the horizontal design spectra of offshore ground motions. In assessing the stability and precision of the chosen improved DE methods, we scrutinize the applicability of various renowned DE methodologies in the calibration process. Our findings indicate that differential evolution with global and local neighborhoods (GLDE) exhibits superior stability and accuracy compared to other DE methods, rendering it suitable for calibrating the design spectrum to delineate optimal characteristic parameters of the DRS. Subsequently, the properties of the offshore horizontal design spectra are investigated by applying the recommended GLDE to 6756 seismic data collected from three offshore regions. The site conditions of water depth and sedimentary thickness of the ocean-bottom stations were investigated by the finely divided seismic data with classified earthquake types. The ocean-bottom stations are classified as A-D by the water depth and sedimentary thickness, and the offshore DRS for four site classes with different earthquake types are presented in this study. According to the observed offshore response spectra with different water depth groups, it is found that the water depth should be considered in the offshore design spectra mainly due to the differences between buried and unburied seafloor stations, and the spectral values with deep water layer are considerably larger than those with shallow water. Offshore DRSs are compared with onshore DRSs of seismic codes and different peak ground acceleration (PGA) groups are presented in this study.

DESIGN OF 8-STORY REINFORCED CONCRETE STRUCTURE OF WANGGUH APARTMENT PONTIANAK BUILDING WITH COMPARISON OF BEAM REVIEW

The article highlights the pivotal role of housing in Pontianak's economic growth, driven by its status as a regional hub attracting residents for employment, education, and services, leading to a significant demand for housing, including apartments. The study specifically focuses on the detailed design of the Wangguh Apartment Building, emphasizing safety and efficiency in response to urban development needs. The project exemplifies modern urban development efforts by aiming to create sustainable living environments.Additionally, the research compares beam designs in multi-story buildings to optimize structural integrity, stability, and load-bearing capacity while adhering to Indonesian National Standards (SNI). The study emphasizes the importance of seismic considerations given Pontianak's classification as a new earthquake zone, with detailed planning ensuring durability and safety against seismic forces. The process involves site classification, seismic design category determination, and structural system selection, with thorough structural modeling and analysis to meet stringent standards and ensure resilience. The study contributes valuable insights into reinforced concrete design and construction through meticulous calculations and adherence to standards, aiming to enhance future residential projects' effectiveness and sustainability in Pontianak City. 

Application of seismic refraction and MASW methods for investigating the Spillway Fault trace along the western side of the Aswan High Dam, Egypt

AbstractAn earthquake of local magnitude ML = 4.6 occurred on November 7, 2010, 4.5 km northwest of the Aswan High Dam on the Spillway Fault. In the Aswan metropolitan region this earthquake was felt intensely. As no surface rupture was found, the focal mechanism and the distribution of seismic activity was one of the tools used for finding fault dimensions. The composite fault-plane solutions for the observed events on the Spillway Fault showed a left lateral strike-slip faulting with normal-fault component striking NNW-SSE. Also, remote sensing techniques were applied for the detection and identification of the geomorphology and geometry of the Spillway Fault. In this research, sub-surface layers and structures are delineated utilizing near-surface seismic techniques. Furthermore, the area’s supposed path and position of the Spillway Fault are also investigated. Two active seismic techniques, Seismic Refraction and Multi-Channel Analysis of Surface Waves (MASW), are utilized for recording near-surface seismic wave data at 9 sites. The seismic refraction profiles are conducted as a 2D cross-section on the trace of the detected Spillway Fault in the study area to evaluate the maximum depth of penetration of the P-wave for fault investigation. The constructed 2D seismic and structural sections from P-wave results show that the obtained average depth of about 30 m. In addition, the estimated P-wave velocities extend from 600 m/s to over 6500 m/s. Some lateral variation in the seismic wave velocities in all layers may represent fault zones. Moreover, the 1D MASW technique is conducted to estimate the velocities of the shear wave for the upper 30 m (Vs30) to provide the site classes and soil characteristics along both sides of the detected Spillway Fault trace in the study area. The calculated Vs30 values emphasized the idea of the existence of a normal dip-slip fault trace which divides the study area into two different lithological parts. The first part is located on the eastern side and characterized by almost class B (hard rock, according to NEHRP classification), while the other part is located to the west, and shows almost class type C (denoted as dense soil and soft rock soil).

Low-severity fires in the boreal region: reproductive implications for black spruce stands in between stand-replacing fire events.

Stand-replacing crown fires are the most prevalent type of fire regime in boreal forests in North America. However, a substantial proportion of low-severity fires are found within fire perimeters. Here we aimed to investigate the effects of low-severity fires on the reproductive potential and seedling recruitment in boreal forests stands in between stand-replacing fire events. We recorded site and tree characteristics from 149 trees within twelve sites dominated by mature black spruce [Picea mariana (Mill.) B.S.P.] trees in the Northwest Territories, Canada. The presence of fire-scarred trees supported classification of sites as unburned or affected by low-severity fires in recent history. We used non-parametric tests to evaluate differences in site conditions between unburned and low-severity sites, and mixed effect models to evaluate differences in tree age, size, and reproductive traits among unburned trees and trees from low-severity sites. Results showed significantly higher density of dead black spruce trees in low-severity sites, and marginally significant higher presence of permafrost. Trees from low-severity fire sites were significantly older, exhibited significantly lower tree growth, and showed a tendency towards a higher probability of cone presence and percentage of open cones compared to trees from unburned sites. Surviving fire-scarred trees affected by more recent low-severity fires showed a tendency towards higher probability of cone presence and cone production. Density of black spruce seedlings significantly increased with recent low-severity fires. Trees in low-severity sites appeared to have escaped mortality from up to three fires, as indicated by fire scar records and their older ages. Shallow permafrost at low-severity sites may cause lower flammability, allowing areas to act as fire refugia. Low-severity surface fires temporarily enhanced the reproductive capacity of surviving trees and the density of seedlings, likely as a stress response to the fire event.

Site class based seismic magnitude prediction equations for earthquake early warning

Site class based seismic magnitude prediction equations for earthquake early warning

Principles of chromosome organization for meiotic recombination.

In meiotic cells, chromosomes are organized as chromatin loop arrays anchored to a protein axis. This organization is essential to regulate meiotic recombination, from DNA double-strand break (DSB) formation to their repair. In mammals, it is unknown how chromatin loops are organized along the genome and how proteins participating in DSB formation are tethered to the chromosome axes. Here, we identify three categories of axis-associated genomic sites: PRDM9 binding sites, where DSBs form; binding sites of the insulator protein CTCF; and H3K4me3-enriched sites. We demonstrate that PRDM9 promotes the recruitment of MEI4 and IHO1, two proteins essential for DSB formation. In turn, IHO1 anchors DSB sites to the axis components HORMAD1 and SYCP3. We discovered that IHO1, HORMAD1, and SYCP3 are associated at the DSB ends during DSB repair. Our results highlight how interactions of proteins with specific genomic elements shape the meiotic chromosome organization for recombination.

Vertical Elastic Acceleration Response Spectra for Vrancea Intermediate-Depth Earthquakes

This study is focused on the evaluation of vertical elastic acceleration response spectra for Vrancea intermediate-depth earthquakes in Romania in the context of the ongoing update of the national seismic design code. The ground motion database employed in this research consists of about 500 ground motions recorded during moderate and large Vrancea intermediate-depth earthquakes with moment magnitudes MW ≥ 5.2. The analysis of the dataset showed that a single ground motion recording had a peak ground acceleration larger than 0.20 g. The results of the analyses showed that no significant differences between the control periods of the vertical elastic response spectra as a function of the site class could be inferred. It was also observed that the mean value of the amplification factor computed for the entire ground motion database was about 2.5, irrespective of the earthquake magnitude, site class, or level of horizontal peak ground acceleration. However, larger-magnitude earthquakes generate larger spectral amplifications in the medium- and long-period ranges. The analysis of the ground motions recorded in Bucharest area revealed a magnitude dependency of the control period for the vertical ground motion TC,v. Finally, a single spectral shape for vertical acceleration response spectra characterized by a maximum dynamic amplification factor of 2.5 and control periods TBv and TCv of 0.05 s and 0.60 s is proposed for design purposes. This aspect allows for a major update from the current version of the national seismic design code which proposes control periods of the elastic vertical response spectrum dependent on the horizontal ones. The short-period (at T = 0.2 s) and long-period (at T = 1.0 s) ratios of the vertical acceleration response spectrum to the corresponding horizontal ones are 0.50 and 0.40.

Modeling of kappa factor using multivariate adaptive regression splines: application to the western Türkiye ground motion dataset

AbstractThe recent seismic activity on Türkiye’s west coast, especially in the Aegean Sea region, shows that this region requires further attention. The region has significant seismic hazards because of its location in an active tectonic regime of North–South extension with multiple basin structures on soft soil deposits. Recently, despite being 70 km from the earthquake source, the Samos event (with a moment magnitude of 7.0 on October 30, 2020) caused significant localized damage and collapse in the Izmir city center due to a combination of basin effects and structural susceptibility. Despite this activity, research on site characterization and site response modeling, such as local velocity models and kappa estimates, remains sparse in this region. Kappa values display regional characteristics, necessitating the use of local kappa estimations from previous earthquake data in region–specific applications. Kappa estimates are multivariate and incorporate several characteristics such as magnitude and distance. In this study, we assess and predict the trend in mean kappa values using three–component strong–ground motion data from accelerometer sites with known VS30 values throughout western Türkiye. Multiple linear regression (MLR) and multivariate adaptive regression splines (MARS) were used to build the prediction models. The effects of epicentral distance Repi, magnitude Mw, and site class (VS30) were investigated, and the contributions of each parameter were examined using a large dataset containing recent seismic activity. The models were evaluated using well–known statistical accuracy criteria for kappa assessment. In all performance measures, the MARS model outperforms the MLR model across the selected sites.

Influence of local versus national datasets on seismic loss estimates: A case study for residential buildings in the metropolitan area of Montreal, Canada

Assessing seismic losses requires information on ground shaking levels, a comprehensive inventory of elements at risk and their asset values to evaluate repair/reconstruction costs. The uncertainties associated with these parameters are often significant and the available data are often incomplete. This study aims to assess the value and utility of detailed data in refining seismic risk estimates. Over several years, detailed site conditions and residential exposure datasets were compiled for Greater Montreal. These models were used to estimate building damage and associated losses for various seismic scenarios. Recently, Natural Resources Canada developed a national exposure model to provide a National Earthquake Risk Profile using data derived from existing sources such as topographic maps and census data. This paper compares seismic loss projections for residential buildings using the local dataset as a baseline with those from the national model using OpenQuake and the latest Seismic Hazard Model. The local site model is based on in situ data and site measurements, while the global, proxy-based model relies on USGS correlations between slope topography and site classification. Results show that the global model overestimates seismic hazards, resulting in 30% higher residential losses than the local model. Absolute losses are increased by a factor of 3.6–5.6 depending on the building classification when using the national exposure model compared to the local inventory while relative losses are increased by a factor of 1.1–1.5. These results emphasize the need to develop detailed seismic risk assessment databases for accurate risk assessments, and for selecting appropriate risk reduction measures.

Challenging Classifications? Interpreting a “Difficult” Enclosure at Inchnadamph in Northwestern Scotland

ABSTRACT This paper explores some challenges of archaeological interpretation and classification through an enclosure at Inchnadamph in Sutherland, northwestern Scotland, a site that has proven difficult to interpret. Despite a small number of archaeological interventions, including topographic and geophysical survey and excavation, the site remains enigmatic. We discuss the different interpretations suggested for the site in turn, concluding that the enclosure does not fit readily into existing classification schemes. This raises issues surrounding the use of classification systems, prior assumptions, and the need for critical thinking in interpretation. These are universal issues, applicable beyond the Scottish example chosen, and this paper highlights concerns and difficulties encountered by all who deal with the classification of sites and monuments. Ultimately, this challenges some of our preconceptions and sheds light on the limits of our knowledge, as well as the limits of our classification systems.

Earthworms as soil health indicators in no-tillage agroecosystems

No-tillage (NT) and no-tillage systems (NTS) are widely used conservation agriculture practices in Brazil, and in the state of Paraná, nearly 80% of annual crops are cultivated using these methods. Compared with NT, NTS sites permanently include: minimum soil disturbance, soil cover (straw and living vegetation) and crop rotation and diversification with cover crops. These practices often increase earthworm populations, that can be used to indicate soil health. Herein, we review soil health classification of NT sites, and the species found in Paraná state. We compiled information from 130 sites with NT or NTS, located in 29 counties, of which 93 had biomass and 91 had species richness data, aiming to compare NT with NTS sites, and the effect of the age of these practices on earthworm populations. Overall, 29 earthworm species were recorded, of which 17 were native, including many new to science. Mean abundance and biomass in NT + NTS were 104 ind m−2 and 2.5 g m−2, respectively, and richness 2.5 species per site. Abundance was significantly higher in NT than NTS in the initial phase of adoption, and both abundance and biomass decreased with increasing age of NT. Earthworm abundance and species richness were positively correlated with clayey soils and phosphorus content, while higher biomass was associated with soil carbon content and pH. A new classification system was proposed, with the categories poor (<50 ind. m−2, 1 species), moderate (≥50 to <100 ind m−2, 2 species), good (≥100 to <150 ind m−2, 3 species), very good (≥150 to 200 ind m−2, 4 species) and excellent (≥200 ind m−2, ≥5 species) soil health, using earthworm abundance and species richness, respectively. Most of the sites sampled showed poor or moderate soil health, with few displaying very good or excellent health, indicating the need for improved management practices, in order to promote earthworm populations and their potential benefits to soil fertility and plant production.

Seismic site classification based on H/V spectral ratio from strong ground motion records: the urban areas of Bursa province

Seismic site classification based on H/V spectral ratio from strong ground motion records: the urban areas of Bursa province

Classification of likely functional class for ligand binding sites identified from fragment screening

Fragment screening is used to identify binding sites and leads in drug discovery, but it is often unclear which binding sites are functionally important. Here, data from 37 experiments, and 1309 protein structures binding to 1601 ligands were analysed. A method to group ligands by binding sites is introduced and sites clustered according to profiles of relative solvent accessibility. This identified 293 unique ligand binding sites, grouped into four clusters (C1-4). C1 includes larger, buried, conserved, and population missense-depleted sites, enriched in known functional sites. C4 comprises smaller, accessible, divergent, missense-enriched sites, depleted in functional sites. A site in C1 is 28 times more likely to be functional than one in C4. Seventeen sites, which to the best of our knowledge are novel, in 13 proteins are identified as likely to be functionally important with examples from human tenascin and 5-aminolevulinate synthase highlighted. A multi-layer perceptron, and K-nearest neighbours model are presented to predict cluster labels for ligand binding sites with an accuracy of 96% and 100%, respectively, so allowing functional classification of sites for proteins not in this set. Our findings will be of interest to those studying protein-ligand interactions and developing new drugs or function modulators.

Pseudo-Velocity Response Spectrum to Velocity Response Spectrum Conversion Model

ABSTRACT Velocity response spectrum (SV) plays a critical role in the seismic design of structures equipped with velocity-dependent dampers. Often, the SV is approximated using the pseudo-velocity response spectrum (PSV), because of the lack of information on the SV in seismic codes. As indicated in the existing literature, the error of this approximation is significant for short and long periods, and therefore, researchers have started to develop PSV to SV conversion models for obtaining SV more accurately. Recent studies discovered that the relationship between the PSV and SV is affected not only by structural parameters, but also by magnitude, distance, and site class. However, models for converting PSV to SV including magnitude, distance, and site class as input parameters have not been developed. To this end, a PSV to SV conversion model including magnitude, distance, and site class is proposed in this study based on a large number of real ground motion records (16,660 horizontal acceleration time histories) selected from the Japan Strong Motion Network. Furthermore, since the magnitude and distance are not specified in the seismic design, a response-spectrum-shape factor, s, is discussed to reflect the influences of magnitude and distance. Accordingly, an SV/PSV model incorporating s is established. The proposed models show better accuracy than the existing models for cases with different magnitudes, distances, and site classes.

Site classification methodology using support vector machine: A study

The site effect is a crucial factor when analyzing seismic risk and establishing ground motion attenuation relationships. A number of countries have introduced building site classification into earthquake-resistant design codes to account for local site effects on ground motion. However, most of the site classification indicators rely on drilling data, which is often expensive and requires considerable manpower. As a result, the less detailed drilling data may lead to an undetermined site category of numerous stations. In this study, a Support Vector Machine (SVM) algorithm-based site classification model was trained to address this issue using strong ground motion data and site data from KiK-net and K-net. The classification model used the average HVSR curve of the labeled site and the combined inputs including frequency, peak, “prominence” and “sharpness” extracted from the curve. The SVM classification model has an accuracy of 76.12% on the test set, with recall rates of 82.69%, 75%, and 63.64% for sites I, II, and III, respectively. The precision rates are 75.44%, 73.77%, and 87.50%, respectively, with F1 scores of 78.90%, 74.38%, and 73.68%. For sites without significant peaks in the HVSR curve, the HVSR curve value was used as the characteristic parameter (input), and the SVM-based site classification model was also trained. The accuracy of class I and II is 75.86%. The results of this study show higher recall and accuracy rates than those obtained using the spectral ratio curve matching method (Wen et al., 2015) and GRNN method (Ji et al., 2021), indicating a better classification performance. Finally, the generalization ability of the model was verified using some basic stations in Xinjiang deployed by the “National Seismic Intensity Rapid Reporting and Early Warning Project”. The SVM-based site classification model that employs strong motion data can provide more reliable classification results for sites without detailed borehole information, and the site classification results can serve as a reference for probing ground motion attenuation relationships, ground motion simulation, and seismic fortification considering the site effect.

Breathing site classification via joint mel frequency cepstral coefficients and gammatone frequency cepstral coefficients approach

The patients with the nasopharyngeal cancer are required to breath through their mouth after performing the surgery. Hence, it is required to perform the breathing site classification and employs the classification results to indicate whether the patients breath correctly or not. Nevertheless, there is currently no such a medical aided tool in the market. To address this issue, this paper extracts both the mel frequency cepstral coefficients (MFCCs) based features and the gammatone frequency cepstral coefficients (GFCCs) based features as well as employs the random forest as the classifier for performing the breathing site classification. The data lasted for a few minutes acquired from 10 volunteers are employed to demonstrate the effectiveness of our proposed method. The computer numerical simulation results show that the average accuracy, the average specificity and the average sensitivity yielded by our proposed method are 95.30±2.00%, 93.27±3.87% and 97.15±1.87%, respectively. Although this paper proposes a method based on the fusion of two types of the acoustic features for classifying different breathing sites, the computer numerical simulation results show that our proposed method outperforms the common respiration or speech processing based methods. Besides, our proposed method is also compared to a series of relevant methods. It is found that our proposed method achieves the highest classification results at the majority signal to noise ratios among the state of the arts methods.