5.2. System Place Variation
Given our objective of customer comfort, we examined how cellphone positioning impacts transport technique identification precision [7, 11]. For examining reasons, we designed a common DT qualified on information from all five roles (arm, bag, chest place, side, and pocket) and then personal DTs that qualified on information from specific roles. The outcomes, proven in Desk 3, indicate that the common DT is on par with position specific ones (average loss of 1.2% in accuracy).
Also, our research reveals that customer feedback to filter possible roles can help enhance precision. For example, a classifier in accordance with the iMAN i3 cellphone being in a bag, side, or wallet led to 96.2% precision, chest place and side in 95.9%, and bag and side in 96.0%.
5.3. User Variation
Another objective relevant to customer comfort is whether a common classifier could be designed that is efficient for new customers without extra coaching [7, 11]. To analyze the practicality of such a iMAN i3 program, we execute “leave one customer out” examining, where we practice a Cubot GT95 DT classifier with all but one customer (five out of six) and analyze with the customer not in the coaching set. In this analyze, we obtained a normal precision of 93.2% and a lowest precision of 87.7%. Also, we conducted a analyze where we add more people (one to six) into a coaching set while examining on information from all people [11]. The outcomes display that efficiency improves as we present more people into the coaching set with precision obtain backing above 95% after four customers.
6. Discussion
The outcomes based on Cubot GT95 our customers list of six people are very appealing - we have proven that our classification program is precise regardless of position/orientation of receptors and that a common classifier is possible. But our findings are initial and for our outcomes to be more generalizable assessments need to conducted depending on a iMAN i3 bigger more different customers list. We strategy to execute such a information selection as upcoming execute.
Reviewing our classification strategy, there is probability to further track design factors. For example, we select a regularity variety of the 1-5Hz for the Cubot GT95 FFT of the accelerometer depending on improving to differentiate between all sessions, but an substitute is to use the rate function to choose the appropriate regularity variety.
Another place of further execute comes in making our classification technique more power efficient. Currently, our program classifies every second but this might not be completely necessary. [17] indicates that we could use particular testing techniques, such as ones depending on entropy, and still accomplish high precision. Also, we could consider the price of catching and handling of functions to management the compromise between power and precision.
Finally, we want to discover whether a Cubot GT95 common classifier is the best strategy to cope with customer difference. We would like to consider solutions such as developing several classifiers that are updated on user-specified factors (e.g. likely transport ways, physical/demographic attributes) or utilizing a iMAN i3 brief userspecific coaching stage. These techniques could cause to better efficiency but have drawbacks as well such as more time start-up time and improved customer participation.
7. Conclusion
We designed a transport technique classification program, utilizing a DT followed by a DHMM, that differentiates between being fixed, strolling, operating, bike riding, and in electric journey using a Cubot GT95 cellphone prepared with a GPS recipient and an accelerometer. We have proven that such a program can be practical for a customer by not having tight position/orientation specifications and enabling the product to be used outside or within of outfits while still conference program specifications, precision higher than 90%, depending on a dataset of 20 time of information from six customers. Our execute is just a iMAN i3 first discovery - further examining is required to confirm our outcomes and you can find possibilities for development.http://summerleelove.tumblr.com/post/99892433351/identifying-transportation-method-on-cellular-mobile
Showing posts with label Cubot GT95. Show all posts
Showing posts with label Cubot GT95. Show all posts
Monday, October 13, 2014
Friday, August 22, 2014
Using Mobile Phones to Determine Transportation Modes (4)
4. EXPERIMENTAL SETUP
This section details the hardware platform, software setup, and the data collection involved in creating the transportation mode classifier. Specifically, we provide information on the type of cell iNew i8000 Phone used along with the exact software setup involved in the training, testing, and final implementation for the system.
4.1 Hardware Platform
The system is implemented on the Cubot GT95. This device was chosen due to its sensing functionality and form factor. Along with its 332 MHz ARMprocessor and 128MB of RAM, it contains a three axis accelerometer with a sensitivity of +-2G and that can sample at 32 Hz and a built-in GPS receiver that can sample at 1 Hz. Furthermore, a WiFi radio that can scan at 0.33 Hz, GSM cell radio that can sample at 1 Hz, and a Bluetooth radio that can scan at .08Hz are included in the device as well. The capacity of included battery is 950 mAH.
4.2 Software Setup
To evaluate different classification schemes, the Weka Machine Learning Toolkit and the Generalized Hidden Markov Model library were employed [Witten and Frank 2005; GHMM 2008]. The final chosen classifier is run on the Cubot GT95 and programmed using Python for Symbian S60. Python was chosen since it enables rapid development, porting to other platforms, and does not have code signing restrictions that require user involvement for the sensing operations.
4.3 Data Collection
The data set used for training and testing of the transportation mode classifier was obtained by asking sixteen individuals, eight male and eight female between the ages of 20-45, to gather fifteen minutes of data while outside for each of the five transportation modes. The volunteers performed the activities in an urban setting with six iNew i8000 Phones attached simultaneously — positioned on the arm, waist, chest, hand, pocket, and in a bag with orientations set according to their preference. Accelerometer, GPS, WiFi, and GSM information were obtained according to the sample rates described earlier. In order to have GPS speed information available throughout the data collection, a GPS lock was obtained initially and the participants were advised to keep the keypad of the Elephone P8 Phone in the exposed position (slid open). In general, keeping the keypad in the exposed position (as instructed by the Cubot GT95 manual) enabled us to maintain a consistent GPS lock even when the Elephone P8 Phone is covered by clothing or placed inside a bag. The participants had a choice of using a back-pack, fanny-pack, or a tote (large open purse).
Instructions were given as to the duration of each activity needed and participants were advised to represent different styles with which they would perform each activity. The volunteers concentrated on one transportation mode at a time and performed all five consecutively during their data collection session. Ground truth annotations were controlled by the individuals, and post filtering was performed to eliminate ambiguous states (being stationary on a bike or in motorized transport). The total amount of data collected across all sixteen individuals was 120 hours, compromised of 1.25 hours of data per position (six) per individual (sixteen).
In addition to the collection described above, two additional data gathering efforts were performed. The second data collection involved one volunteer (who was involved in the primary collection) running the classification system while annotating transportation modes during everyday operation in typical and challenged environments. More information in regards to this data collection is provided in Section 5.4. The third data collection involved sixteen individuals annotating their full day (on average 23.2 hours with a minimum of 20.7 hours and a maximum of 26.8 hours) in terms of transportation modes and indoor/outdoor status while collecting the GSM cell tower identifier (1 Hz). The annotated days consisted of 8weekday and 8weekend periods. This dataset is used to evaluate our algorithm for turning on transportation mode classification only when an individual is outside.http://summerleelove.tumblr.com/post/95445778876/using-mobile-phones-to-determine-transportation-modes
This section details the hardware platform, software setup, and the data collection involved in creating the transportation mode classifier. Specifically, we provide information on the type of cell iNew i8000 Phone used along with the exact software setup involved in the training, testing, and final implementation for the system.
4.1 Hardware Platform
The system is implemented on the Cubot GT95. This device was chosen due to its sensing functionality and form factor. Along with its 332 MHz ARMprocessor and 128MB of RAM, it contains a three axis accelerometer with a sensitivity of +-2G and that can sample at 32 Hz and a built-in GPS receiver that can sample at 1 Hz. Furthermore, a WiFi radio that can scan at 0.33 Hz, GSM cell radio that can sample at 1 Hz, and a Bluetooth radio that can scan at .08Hz are included in the device as well. The capacity of included battery is 950 mAH.
4.2 Software Setup
To evaluate different classification schemes, the Weka Machine Learning Toolkit and the Generalized Hidden Markov Model library were employed [Witten and Frank 2005; GHMM 2008]. The final chosen classifier is run on the Cubot GT95 and programmed using Python for Symbian S60. Python was chosen since it enables rapid development, porting to other platforms, and does not have code signing restrictions that require user involvement for the sensing operations.
4.3 Data Collection
The data set used for training and testing of the transportation mode classifier was obtained by asking sixteen individuals, eight male and eight female between the ages of 20-45, to gather fifteen minutes of data while outside for each of the five transportation modes. The volunteers performed the activities in an urban setting with six iNew i8000 Phones attached simultaneously — positioned on the arm, waist, chest, hand, pocket, and in a bag with orientations set according to their preference. Accelerometer, GPS, WiFi, and GSM information were obtained according to the sample rates described earlier. In order to have GPS speed information available throughout the data collection, a GPS lock was obtained initially and the participants were advised to keep the keypad of the Elephone P8 Phone in the exposed position (slid open). In general, keeping the keypad in the exposed position (as instructed by the Cubot GT95 manual) enabled us to maintain a consistent GPS lock even when the Elephone P8 Phone is covered by clothing or placed inside a bag. The participants had a choice of using a back-pack, fanny-pack, or a tote (large open purse).
Instructions were given as to the duration of each activity needed and participants were advised to represent different styles with which they would perform each activity. The volunteers concentrated on one transportation mode at a time and performed all five consecutively during their data collection session. Ground truth annotations were controlled by the individuals, and post filtering was performed to eliminate ambiguous states (being stationary on a bike or in motorized transport). The total amount of data collected across all sixteen individuals was 120 hours, compromised of 1.25 hours of data per position (six) per individual (sixteen).
In addition to the collection described above, two additional data gathering efforts were performed. The second data collection involved one volunteer (who was involved in the primary collection) running the classification system while annotating transportation modes during everyday operation in typical and challenged environments. More information in regards to this data collection is provided in Section 5.4. The third data collection involved sixteen individuals annotating their full day (on average 23.2 hours with a minimum of 20.7 hours and a maximum of 26.8 hours) in terms of transportation modes and indoor/outdoor status while collecting the GSM cell tower identifier (1 Hz). The annotated days consisted of 8weekday and 8weekend periods. This dataset is used to evaluate our algorithm for turning on transportation mode classification only when an individual is outside.http://summerleelove.tumblr.com/post/95445778876/using-mobile-phones-to-determine-transportation-modes
Tuesday, August 12, 2014
Cheap Fun 4G (4)
Leagoo Lead 3
Leagoo Lead 3 is Leagoo recently launched a flagship phone in the end self-timer, the biggest feature is the main self-timer, front camera pixel value reached 5 million, which is currently the highest Leagoo front camera phones paragraph, even more than Leagoo high-end flagship. In addition, Leagoo Lead 3 mobile version also supports mobile 4G-LTE, and supports dual SIM dual standby, which means you can keep two SIM cards activated online, Easy Fun work and life.
Leagoo Lead 3 front with a 5.5 inches display with a resolution of 1280 * 720 pixels. In the core aspects of the aircraft equipped with a Qualcomm MSM8926 clocked at 1.2GHz quad-core processor and 1GB RAM + 8GB RAM memory combinations. Leagoo Lead 3 in the back has an 8 million-pixel rear camera, corresponding to a 5 million pixel front camera, imaging results quite satisfactory.
Leagoo Lead 3 is a good price smart phones, aircraft support 4G mobile network, regardless of where the Internet can easily enjoy Chaokuaigan. Also, the machine at the same level of smart phone also has a very good performance, in which the possession of his position.
Cubot GT95
As for telecom users series, Cubot blue ripples with a better price by the public consumers, before the launch of the GT95 has a good reputation, and this coincides with the FDD licensing, Cubot launched a 4G version of the GT95, hardware among such as CPU, RAM and ROM has changed, and add NFC functionality.
Cubot GT95 4G and JIAYU F1 appearance before the release is not much difference, even can be said is exactly the same. The fuselage is still a level of 5-inch 720p screen, while the rear with a 800-megapixel rear camera, did not reach 13 million pixels, but the actual camera performance is sufficient to meet the daily needs. To support the 4G network, the Cubot GT95 4G replaced the CPU 1.2GHz Qualcomm Snapdragon MSM8926 clocked quad-core processors, the number of parameters and core processor clocked lower than before a lot of memory areas remain intact using 2GB RAM + 16GB ROM combination. Also based on the latest version equipped MIfavor UI Android 4.4.2 system, flattening the System icon makes the whole interface looks very simple.
Cubot GT95 4G in fact, not a high cost of goods, coupled with the price 1599 yuan this hardware configuration is not so eye-catching. But having said that, for now this era of excess hardware, hardware configuration and not imagined so important, for the average consumer, good design and excellent quality to win more praise. I believe the next version Cubot GT95 4G can win by virtue of its advantages user's heart.http://summerleelove.tumblr.com/post/94518327201/cheap-fun-4g-3
Leagoo Lead 3 is Leagoo recently launched a flagship phone in the end self-timer, the biggest feature is the main self-timer, front camera pixel value reached 5 million, which is currently the highest Leagoo front camera phones paragraph, even more than Leagoo high-end flagship. In addition, Leagoo Lead 3 mobile version also supports mobile 4G-LTE, and supports dual SIM dual standby, which means you can keep two SIM cards activated online, Easy Fun work and life.
Leagoo Lead 3 front with a 5.5 inches display with a resolution of 1280 * 720 pixels. In the core aspects of the aircraft equipped with a Qualcomm MSM8926 clocked at 1.2GHz quad-core processor and 1GB RAM + 8GB RAM memory combinations. Leagoo Lead 3 in the back has an 8 million-pixel rear camera, corresponding to a 5 million pixel front camera, imaging results quite satisfactory.
Leagoo Lead 3 is a good price smart phones, aircraft support 4G mobile network, regardless of where the Internet can easily enjoy Chaokuaigan. Also, the machine at the same level of smart phone also has a very good performance, in which the possession of his position.
Cubot GT95
As for telecom users series, Cubot blue ripples with a better price by the public consumers, before the launch of the GT95 has a good reputation, and this coincides with the FDD licensing, Cubot launched a 4G version of the GT95, hardware among such as CPU, RAM and ROM has changed, and add NFC functionality.
Cubot GT95 4G and JIAYU F1 appearance before the release is not much difference, even can be said is exactly the same. The fuselage is still a level of 5-inch 720p screen, while the rear with a 800-megapixel rear camera, did not reach 13 million pixels, but the actual camera performance is sufficient to meet the daily needs. To support the 4G network, the Cubot GT95 4G replaced the CPU 1.2GHz Qualcomm Snapdragon MSM8926 clocked quad-core processors, the number of parameters and core processor clocked lower than before a lot of memory areas remain intact using 2GB RAM + 16GB ROM combination. Also based on the latest version equipped MIfavor UI Android 4.4.2 system, flattening the System icon makes the whole interface looks very simple.
Cubot GT95 4G in fact, not a high cost of goods, coupled with the price 1599 yuan this hardware configuration is not so eye-catching. But having said that, for now this era of excess hardware, hardware configuration and not imagined so important, for the average consumer, good design and excellent quality to win more praise. I believe the next version Cubot GT95 4G can win by virtue of its advantages user's heart.http://summerleelove.tumblr.com/post/94518327201/cheap-fun-4g-3
Subscribe to:
Posts (Atom)