| 1. |
- Alsolai, Hadeel, et al.
(författare)
-
A Systematic Review of Literature on Automated Sleep Scoring
- 2022
-
Ingår i: IEEE Access. - : Institute of Electrical and Electronics Engineers (IEEE). - 2169-3536. ; 10, s. 79419-79443
-
Forskningsöversikt (refereegranskat)abstract
- Sleep is a period of rest that is essential for functional learning ability, mental health, and even the performance of normal activities. Insomnia, sleep apnea, and restless legs are all examples of sleep-related issues that are growing more widespread. When appropriately analyzed, the recording of bio-electric signals, such as the Electroencephalogram, can tell how well we sleep. Improved analyses are possible due to recent improvements in machine learning and feature extraction, and they are commonly referred to as automatic sleep analysis to distinguish them from sleep data analysis by a human sleep expert. This study outlines a Systematic Literature Review and the results it provided to assess the present state-of-the-art in automatic analysis of sleep data. A search string was organized according to the PICO (Population, Intervention, Comparison, and Outcome) strategy in order to determine what machine learning and feature extraction approaches are used to generate an Automatic Sleep Scoring System. The American Academy of Sleep Medicine and Rechtschaffen & Kales are the two main scoring standards used in contemporary research, according to the report. Other types of sensors, such as Electrooculography, are employed in addition to Electroencephalography to automatically score sleep. Furthermore, the existing research on parameter tuning for machine learning models that was examined proved to be incomplete. Based on our findings, different sleep scoring standards, as well as numerous feature extraction and machine learning algorithms with parameter tuning, have a high potential for developing a reliable and robust automatic sleep scoring system for supporting physicians. In the context of the sleep scoring problem, there are evident gaps that need to be investigated in terms of automatic feature engineering techniques and parameter tuning in machine learning algorithms.
|
|
| 2. |
- Alsolai, Hadeel, et al.
(författare)
-
Employing a Long-Short-Term Memory Neural Network to Improve Automatic Sleep Stage Classification of Pharmaco-EEG Profiles
- 2022
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 12:10
-
Tidskriftsartikel (refereegranskat)abstract
- An increasing problem in today's society is the spiraling number of people suffering from various sleep disorders. The research results presented in this paper support the use of a novel method that employs techniques from the classification of sleep disorders for more accurate scoring. Applying this novel method will assist researchers with better analyzing subject profiles for recommending prescriptions or to alleviate sleep disorders. In biomedical research, the use of animal models is required to experimentally test the safety and efficacy of a drug in the pre-clinical stage. We have developed a novel LSTM Recurrent Neural Network to process Pharmaco-EEG Profiles of rats to automatically score their sleep-wake stages. The results indicate improvements over the current methods; for the case of combined channels, the model accuracy improved by 1% and 3% in binary or multiclass classifications, respectively, to accuracies of 93% and 82%. In the case of using a single channel, binary and multiclass LSTM models for identifying rodent sleep stages using single or multiple electrode positions for binary or multiclass problems have not been evaluated in prior literature. The results reveal that single or combined channels, and binary or multiclass classification tasks, can be applied in the automatic sleep scoring of rodents.
|
|
| 3. |
- Iqbal, Syed Muhammad Zeeshan, et al.
(författare)
-
A Parallel DFS Algorithm for Train Re-scheduling During Traffic Disturbances — Early Results
- 2011
-
Konferensbidrag (refereegranskat)abstract
- Railways are an important part of the infrastructure in most countries. As the railway networks become more and more saturated, even small traffic disturbances can propagate and have severe consequences. In this paper, the train re-scheduling problem is studied in order to minimize the final delay for all trains in the scenarios. We propose a parallel algorithm based on a depth-first search branch-and-bound strategy. The parallel algorithm is compared to a sequential algorithm in terms of the quality of the solution and the number of nodes evaluated, as well as to optimal solutions found by Cplex, using 20 disturbance scenarios. Our parallel algorithm significantly improves the solution for 5 out of 20 disturbance scenarios, as compared to the sequential algorithm.
|
|
| 4. |
- Iqbal, Syed Muhammad Zeeshan, et al.
(författare)
-
A parallel heuristic for fast train dispatching during railway traffic disturbances : Early results
- 2012
-
Konferensbidrag (refereegranskat)abstract
- Railways are an important part of the infrastructure in most countries. As the railway networks become more and more saturated, even small traffic disturbances can propagate and have severe consequences. Therefore, efficient re-scheduling support for the traffic managers is needed. In this paper, the train real-time re-scheduling problem is studied in order to minimize the total delay, subject to a set of safety and operational constraints. We propose a parallel greedy algorithm based on a depth-first branch-and-bound search strategy. A number of comprehensive numerical experiments are conducted to compare the parallel implementation to the sequential implementation of the same algorithm in terms of the quality of the solution and the number of nodes evaluated. The comparison is based on 20 disturbance scenarios from three different types of disturbances. Our results show that the parallel algorithm; (i) efficiently covers a larger portion of the search space by exchanging information about improvements, and (ii) finds better solutions for more complicated disturbances such as infrastructure problems. Our results show that the parallel implementation significantly improves the solution for 5 out of 20 disturbance scenarios, as compared to the sequential algorithm.
|
|
| 5. |
- Iqbal, Syed Muhammad Zeeshan, et al.
(författare)
-
Multi-Strategy Based Train Re-Scheduling During Railway Traffic Disturbances
- 2013
-
Konferensbidrag (refereegranskat)abstract
- Disruptions and delays in railway traffic networks due to different types of disturbances is a frequent problem in many countries. When disruptions occur, the train traffic dispatchers may need to re-schedule the traffic and this is often a very demanding and complicated task. To support the train traffic dispatchers, we propose to use a parallelized multi-strategy based greedy algorithm. This paper presents three different parallelization approaches: (i) Single Strategy with a Partitioned List (i.e. the parallel processes originate from different starting points), (ii) Multiple Strategies with a Non-Partitioned List, and (iii) Multiple Strategies with a Partitioned List. We present an evaluation for a busy part of the Swedish railway network based on performance metrics such as the sum of all train delays at their final destinations and the number of delayed trains. The results show that parallelization helps to improve the solution quality. The parallel approach (iii) that combines all re-scheduling strategies with a partitioned list performs best among the three parallel approaches when minimizing the total final delay. The main conclusion is that the multi-strategy based parallel approach significantly improves the solution for 11 out of 20 disturbance scenarios, as compared to the sequential re-scheduling algorithm. The approach also provides an increased stability since it always delivers a feasible solution in short time.
|
|
| 6. |
- Iqbal, Syed Muhammad Zeeshan, et al.
(författare)
-
ParMiBench : An Open-Source Benchmark for Embedded Multiprocessor Systems
- 2010
-
Ingår i: IEEE Computer Architecture Letters. - : IEEE. - 1556-6056. ; 9:2, s. 45-48
-
Tidskriftsartikel (refereegranskat)abstract
- Multicore processors are the main computing platform in laptops, desktop, and servers today, and are making their way into the embedded systems market also. Using benchmarks is a common approach to evaluate the performance of a system. However, benchmarks for embedded systems have so far been either targeted for a uni-processor environment, e.g., MiBench, or have been commercial, e.g., MultiBench by EEMBC. In this paper, we propose and implement an open source benchmark, ParMiBench, targeted for multiprocessor-based embedded systems. ParMiBench consists of parallel implementations of seven compute intensive algorithms from the uni-processor benchmark suite MiBench. The applications are selected from four domains: Automation and Industry Control, Network, Office, and Security.
|
|
| 7. |
- Qureshi, Shahnawaz, et al.
(författare)
-
Evaluation of Classifiers for Emotion Detection while Performing Physical and Visual Tasks : Tower of Hanoi and IAPS
- 2018
-
Ingår i: Intelligent Systems and Applications. IntelliSys 2018. - Cham : Springer. - 9783030010539 - 9783030010546 ; , s. 347-363
-
Konferensbidrag (refereegranskat)abstract
- With the advancement in robot technology, smart human-robot interaction is of increasing importance for allowing the more excellent use of robots integrated into human environments and activities. If a robot can identify emotions and intentions of a human interacting with it, interactions with humans can potentially become more natural and effective. However, mechanisms of perception and empathy used by humans to achieve this understanding may not be suitable or adequate for use within robots. Electroencephalography (EEG) can be used for recording signals revealing emotions and motivations from a human brain. This study aimed to evaluate different machine learning techniques to classify EEG data associated with specific affective/emotional states. For experimental purposes, we used visual (IAPS) and physical (Tower of Hanoi) tasks to record human emotional states in the form of EEG data. The obtained EEG data processed, formatted and evaluated using various machine learning techniques to find out which method can most accurately classify EEG data according to associated affective/emotional states. The experiment confirms the choice of a method for improving the accuracy of results. According to the results, Support Vector Machine was the first, and Regression Tree was the second best method for classifying EEG data associated with specific affective/emotional states with accuracies up to 70.00% and 60.00%, respectively. In both tasks, SVM was better in performance than RT.
|
|
| 8. |
- Zeeshan Iqbal, Syed Muhammad, et al.
(författare)
-
A Comparative Evaluation of Re-scheduling Strategies for Train Dispatching during Disturbances
- 2012
-
Konferensbidrag (refereegranskat)abstract
- Railway traffic disturbances occur and train dispatchers make re-scheduling decisions in order to reduce the delays. In order to support the dispatchers, good rescheduling strategies are required that could reduce the delays. We propose and evaluate re-scheduling strategies based on: (i) earliest start time, (ii) earliest track release time, (iii) smallest buffer time, and (iv) shortest section runtime. A comparative evaluation is done for a busy part of the Swedish railway network. Our results indicate that strategies based on earliest start time and earliest track release time have the best average performance.
|
|
